Videre

linedance-app/venv/lib/python3.12/site-packages/sklearn/neighbors/__init__.py

@@ -0,0 +1,49 @@
+"""The k-nearest neighbors algorithms."""
+
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
+from sklearn.neighbors._ball_tree import BallTree
+from sklearn.neighbors._base import (
+    VALID_METRICS,
+    VALID_METRICS_SPARSE,
+    sort_graph_by_row_values,
+)
+from sklearn.neighbors._classification import (
+    KNeighborsClassifier,
+    RadiusNeighborsClassifier,
+)
+from sklearn.neighbors._graph import (
+    KNeighborsTransformer,
+    RadiusNeighborsTransformer,
+    kneighbors_graph,
+    radius_neighbors_graph,
+)
+from sklearn.neighbors._kd_tree import KDTree
+from sklearn.neighbors._kde import KernelDensity
+from sklearn.neighbors._lof import LocalOutlierFactor
+from sklearn.neighbors._nca import NeighborhoodComponentsAnalysis
+from sklearn.neighbors._nearest_centroid import NearestCentroid
+from sklearn.neighbors._regression import KNeighborsRegressor, RadiusNeighborsRegressor
+from sklearn.neighbors._unsupervised import NearestNeighbors
+
+__all__ = [
+    "VALID_METRICS",
+    "VALID_METRICS_SPARSE",
+    "BallTree",
+    "KDTree",
+    "KNeighborsClassifier",
+    "KNeighborsRegressor",
+    "KNeighborsTransformer",
+    "KernelDensity",
+    "LocalOutlierFactor",
+    "NearestCentroid",
+    "NearestNeighbors",
+    "NeighborhoodComponentsAnalysis",
+    "RadiusNeighborsClassifier",
+    "RadiusNeighborsRegressor",
+    "RadiusNeighborsTransformer",
+    "kneighbors_graph",
+    "radius_neighbors_graph",
+    "sort_graph_by_row_values",
+]

linedance-app/venv/lib/python3.12/site-packages/sklearn/neighbors/_ball_tree.pyx.tp

@@ -0,0 +1,284 @@
+{{py:
+
+# Generated file: _ball_tree.pyx
+
+implementation_specific_values = [
+    # The values are arranged as follows:
+    #
+    #       name_suffix, INPUT_DTYPE_t, INPUT_DTYPE
+    #
+    ('64', 'float64_t', 'np.float64'),
+    ('32', 'float32_t', 'np.float32')
+]
+
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
+}}
+
+
+__all__ = ['BallTree', 'BallTree64', 'BallTree32']
+
+{{for name_suffix, INPUT_DTYPE_t, INPUT_DTYPE in implementation_specific_values}}
+
+DOC_DICT{{name_suffix}} = {
+    'BinaryTree': 'BallTree{{name_suffix}}',
+    'binary_tree': 'ball_tree{{name_suffix}}',
+}
+
+VALID_METRICS{{name_suffix}} = [
+    'BrayCurtisDistance{{name_suffix}}',
+    'CanberraDistance{{name_suffix}}',
+    'ChebyshevDistance{{name_suffix}}',
+    'DiceDistance{{name_suffix}}',
+    'EuclideanDistance{{name_suffix}}',
+    'HammingDistance{{name_suffix}}',
+    'HaversineDistance{{name_suffix}}',
+    'JaccardDistance{{name_suffix}}',
+    'MahalanobisDistance{{name_suffix}}',
+    'ManhattanDistance{{name_suffix}}',
+    'MinkowskiDistance{{name_suffix}}',
+    'PyFuncDistance{{name_suffix}}',
+    'RogersTanimotoDistance{{name_suffix}}',
+    'RussellRaoDistance{{name_suffix}}',
+    'SEuclideanDistance{{name_suffix}}',
+    'SokalMichenerDistance{{name_suffix}}',
+    'SokalSneathDistance{{name_suffix}}',
+    'WMinkowskiDistance{{name_suffix}}',
+]
+
+{{endfor}}
+
+include "_binary_tree.pxi"
+
+{{for name_suffix, INPUT_DTYPE_t, INPUT_DTYPE in implementation_specific_values}}
+
+# Inherit BallTree{{name_suffix}} from BinaryTree{{name_suffix}}
+cdef class BallTree{{name_suffix}}(BinaryTree{{name_suffix}}):
+    __doc__ = CLASS_DOC.format(**DOC_DICT{{name_suffix}})
+    pass
+
+{{endfor}}
+
+
+#----------------------------------------------------------------------
+# The functions below specialized the Binary Tree as a Ball Tree
+#
+#   Note that these functions use the concept of "reduced distance".
+#   The reduced distance, defined for some metrics, is a quantity which
+#   is more efficient to compute than the distance, but preserves the
+#   relative rankings of the true distance.  For example, the reduced
+#   distance for the Euclidean metric is the squared-euclidean distance.
+#   For some metrics, the reduced distance is simply the distance.
+
+{{for name_suffix, INPUT_DTYPE_t, INPUT_DTYPE in implementation_specific_values}}
+
+cdef int allocate_data{{name_suffix}}(
+    BinaryTree{{name_suffix}} tree,
+    intp_t n_nodes,
+    intp_t n_features,
+) except -1:
+    """Allocate arrays needed for the KD Tree"""
+    tree.node_bounds = np.zeros((1, n_nodes, n_features), dtype={{INPUT_DTYPE}})
+    return 0
+
+
+cdef int init_node{{name_suffix}}(
+    BinaryTree{{name_suffix}} tree,
+    NodeData_t[::1] node_data,
+    intp_t i_node,
+    intp_t idx_start,
+    intp_t idx_end,
+) except -1:
+    """Initialize the node for the dataset stored in tree.data"""
+    cdef intp_t n_features = tree.data.shape[1]
+    cdef intp_t n_points = idx_end - idx_start
+
+    cdef intp_t i, j
+    cdef float64_t radius
+    cdef const {{INPUT_DTYPE_t}} *this_pt
+
+    cdef const intp_t* idx_array = &tree.idx_array[0]
+    cdef const {{INPUT_DTYPE_t}}* data = &tree.data[0, 0]
+    cdef {{INPUT_DTYPE_t}}* centroid = &tree.node_bounds[0, i_node, 0]
+
+    cdef bint with_sample_weight = tree.sample_weight is not None
+    cdef const {{INPUT_DTYPE_t}}* sample_weight
+    cdef float64_t sum_weight_node
+    if with_sample_weight:
+        sample_weight = &tree.sample_weight[0]
+
+    # determine Node centroid
+    for j in range(n_features):
+        centroid[j] = 0
+
+    if with_sample_weight:
+        sum_weight_node = 0
+        for i in range(idx_start, idx_end):
+            sum_weight_node += sample_weight[idx_array[i]]
+            this_pt = data + n_features * idx_array[i]
+            for j from 0 <= j < n_features:
+                centroid[j] += this_pt[j] * sample_weight[idx_array[i]]
+
+        for j in range(n_features):
+            centroid[j] /= sum_weight_node
+    else:
+        for i in range(idx_start, idx_end):
+            this_pt = data + n_features * idx_array[i]
+            for j from 0 <= j < n_features:
+                centroid[j] += this_pt[j]
+
+        for j in range(n_features):
+            centroid[j] /= n_points
+
+    # determine Node radius
+    radius = 0
+    for i in range(idx_start, idx_end):
+        radius = fmax(radius,
+                      tree.rdist(centroid,
+                                 data + n_features * idx_array[i],
+                                 n_features))
+
+    node_data[i_node].radius = tree.dist_metric._rdist_to_dist(radius)
+    node_data[i_node].idx_start = idx_start
+    node_data[i_node].idx_end = idx_end
+    return 0
+
+
+cdef inline float64_t min_dist{{name_suffix}}(
+    BinaryTree{{name_suffix}} tree,
+    intp_t i_node,
+    const {{INPUT_DTYPE_t}}* pt,
+) except -1 nogil:
+    """Compute the minimum distance between a point and a node"""
+    cdef float64_t dist_pt = tree.dist(pt, &tree.node_bounds[0, i_node, 0],
+                                     tree.data.shape[1])
+    return fmax(0, dist_pt - tree.node_data[i_node].radius)
+
+
+cdef inline float64_t max_dist{{name_suffix}}(
+    BinaryTree{{name_suffix}} tree,
+    intp_t i_node,
+    const {{INPUT_DTYPE_t}}* pt,
+) except -1:
+    """Compute the maximum distance between a point and a node"""
+    cdef float64_t dist_pt = tree.dist(pt, &tree.node_bounds[0, i_node, 0],
+                                     tree.data.shape[1])
+    return dist_pt + tree.node_data[i_node].radius
+
+
+cdef inline int min_max_dist{{name_suffix}}(
+    BinaryTree{{name_suffix}} tree,
+    intp_t i_node,
+    const {{INPUT_DTYPE_t}}* pt,
+    float64_t* min_dist,
+    float64_t* max_dist,
+) except -1 nogil:
+    """Compute the minimum and maximum distance between a point and a node"""
+    cdef float64_t dist_pt = tree.dist(pt, &tree.node_bounds[0, i_node, 0],
+                                     tree.data.shape[1])
+    cdef float64_t rad = tree.node_data[i_node].radius
+    min_dist[0] = fmax(0, dist_pt - rad)
+    max_dist[0] = dist_pt + rad
+    return 0
+
+
+cdef inline float64_t min_rdist{{name_suffix}}(
+    BinaryTree{{name_suffix}} tree,
+    intp_t i_node,
+    const {{INPUT_DTYPE_t}}* pt,
+) except -1 nogil:
+    """Compute the minimum reduced-distance between a point and a node"""
+    if tree.euclidean:
+        return euclidean_dist_to_rdist{{name_suffix}}(
+            min_dist{{name_suffix}}(tree, i_node, pt)
+        )
+    else:
+        return tree.dist_metric._dist_to_rdist(
+            min_dist{{name_suffix}}(tree, i_node, pt)
+        )
+
+
+cdef inline float64_t max_rdist{{name_suffix}}(
+    BinaryTree{{name_suffix}} tree,
+    intp_t i_node,
+    const {{INPUT_DTYPE_t}}* pt,
+) except -1:
+    """Compute the maximum reduced-distance between a point and a node"""
+    if tree.euclidean:
+        return euclidean_dist_to_rdist{{name_suffix}}(
+            max_dist{{name_suffix}}(tree, i_node, pt)
+        )
+    else:
+        return tree.dist_metric._dist_to_rdist(
+            max_dist{{name_suffix}}(tree, i_node, pt)
+        )
+
+
+cdef inline float64_t min_dist_dual{{name_suffix}}(
+    BinaryTree{{name_suffix}} tree1,
+    intp_t i_node1,
+    BinaryTree{{name_suffix}} tree2,
+    intp_t i_node2,
+) except -1:
+    """compute the minimum distance between two nodes"""
+    cdef float64_t dist_pt = tree1.dist(&tree2.node_bounds[0, i_node2, 0],
+                                      &tree1.node_bounds[0, i_node1, 0],
+                                      tree1.data.shape[1])
+    return fmax(0, (dist_pt - tree1.node_data[i_node1].radius
+                    - tree2.node_data[i_node2].radius))
+
+
+cdef inline float64_t max_dist_dual{{name_suffix}}(
+    BinaryTree{{name_suffix}} tree1,
+    intp_t i_node1,
+    BinaryTree{{name_suffix}} tree2,
+    intp_t i_node2,
+) except -1:
+    """compute the maximum distance between two nodes"""
+    cdef float64_t dist_pt = tree1.dist(&tree2.node_bounds[0, i_node2, 0],
+                                      &tree1.node_bounds[0, i_node1, 0],
+                                      tree1.data.shape[1])
+    return (dist_pt + tree1.node_data[i_node1].radius
+            + tree2.node_data[i_node2].radius)
+
+
+cdef inline float64_t min_rdist_dual{{name_suffix}}(
+    BinaryTree{{name_suffix}} tree1,
+    intp_t i_node1,
+    BinaryTree{{name_suffix}} tree2,
+    intp_t i_node2,
+) except -1:
+    """compute the minimum reduced distance between two nodes"""
+    if tree1.euclidean:
+        return euclidean_dist_to_rdist{{name_suffix}}(
+            min_dist_dual{{name_suffix}}(tree1, i_node1, tree2, i_node2)
+        )
+    else:
+        return tree1.dist_metric._dist_to_rdist(
+            min_dist_dual{{name_suffix}}(tree1, i_node1, tree2, i_node2)
+        )
+
+
+cdef inline float64_t max_rdist_dual{{name_suffix}}(
+    BinaryTree{{name_suffix}} tree1,
+    intp_t i_node1,
+    BinaryTree{{name_suffix}} tree2,
+    intp_t i_node2,
+) except -1:
+    """compute the maximum reduced distance between two nodes"""
+    if tree1.euclidean:
+        return euclidean_dist_to_rdist{{name_suffix}}(
+            max_dist_dual{{name_suffix}}(tree1, i_node1, tree2, i_node2)
+        )
+    else:
+        return tree1.dist_metric._dist_to_rdist(
+            max_dist_dual{{name_suffix}}(tree1, i_node1, tree2, i_node2)
+        )
+
+{{endfor}}
+
+
+class BallTree(BallTree64):
+    __doc__ = CLASS_DOC.format(BinaryTree="BallTree")
+    pass

linedance-app/venv/lib/python3.12/site-packages/sklearn/neighbors/_classification.py

@@ -0,0 +1,923 @@
+"""Nearest Neighbor Classification"""
+
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
+import warnings
+from numbers import Integral
+
+import numpy as np
+
+from sklearn.base import ClassifierMixin, _fit_context
+from sklearn.metrics._pairwise_distances_reduction import (
+    ArgKminClassMode,
+    RadiusNeighborsClassMode,
+)
+from sklearn.neighbors._base import (
+    KNeighborsMixin,
+    NeighborsBase,
+    RadiusNeighborsMixin,
+    _check_precomputed,
+    _get_weights,
+)
+from sklearn.utils._param_validation import StrOptions
+from sklearn.utils.arrayfuncs import _all_with_any_reduction_axis_1
+from sklearn.utils.extmath import weighted_mode
+from sklearn.utils.fixes import _mode
+from sklearn.utils.validation import (
+    _is_arraylike,
+    _num_samples,
+    check_is_fitted,
+    validate_data,
+)
+
+
+def _adjusted_metric(metric, metric_kwargs, p=None):
+    metric_kwargs = metric_kwargs or {}
+    if metric == "minkowski":
+        metric_kwargs["p"] = p
+        if p == 2:
+            metric = "euclidean"
+    return metric, metric_kwargs
+
+
+class KNeighborsClassifier(KNeighborsMixin, ClassifierMixin, NeighborsBase):
+    """Classifier implementing the k-nearest neighbors vote.
+
+    Read more in the :ref:`User Guide <classification>`.
+
+    Parameters
+    ----------
+    n_neighbors : int, default=5
+        Number of neighbors to use by default for :meth:`kneighbors` queries.
+
+    weights : {'uniform', 'distance'}, callable or None, default='uniform'
+        Weight function used in prediction.  Possible values:
+
+        - 'uniform' : uniform weights.  All points in each neighborhood
+          are weighted equally.
+        - 'distance' : weight points by the inverse of their distance.
+          in this case, closer neighbors of a query point will have a
+          greater influence than neighbors which are further away.
+        - [callable] : a user-defined function which accepts an
+          array of distances, and returns an array of the same shape
+          containing the weights.
+
+        Refer to the example entitled
+        :ref:`sphx_glr_auto_examples_neighbors_plot_classification.py`
+        showing the impact of the `weights` parameter on the decision
+        boundary.
+
+    algorithm : {'auto', 'ball_tree', 'kd_tree', 'brute'}, default='auto'
+        Algorithm used to compute the nearest neighbors:
+
+        - 'ball_tree' will use :class:`BallTree`
+        - 'kd_tree' will use :class:`KDTree`
+        - 'brute' will use a brute-force search.
+        - 'auto' will attempt to decide the most appropriate algorithm
+          based on the values passed to :meth:`fit` method.
+
+        Note: fitting on sparse input will override the setting of
+        this parameter, using brute force.
+
+    leaf_size : int, default=30
+        Leaf size passed to BallTree or KDTree.  This can affect the
+        speed of the construction and query, as well as the memory
+        required to store the tree.  The optimal value depends on the
+        nature of the problem.
+
+    p : float, default=2
+        Power parameter for the Minkowski metric. When p = 1, this is equivalent
+        to using manhattan_distance (l1), and euclidean_distance (l2) for p = 2.
+        For arbitrary p, minkowski_distance (l_p) is used. This parameter is expected
+        to be positive.
+
+    metric : str or callable, default='minkowski'
+        Metric to use for distance computation. Default is "minkowski", which
+        results in the standard Euclidean distance when p = 2. See the
+        documentation of `scipy.spatial.distance
+        <https://docs.scipy.org/doc/scipy/reference/spatial.distance.html>`_ and
+        the metrics listed in
+        :class:`~sklearn.metrics.pairwise.distance_metrics` for valid metric
+        values.
+
+        If metric is "precomputed", X is assumed to be a distance matrix and
+        must be square during fit. X may be a :term:`sparse graph`, in which
+        case only "nonzero" elements may be considered neighbors.
+
+        If metric is a callable function, it takes two arrays representing 1D
+        vectors as inputs and must return one value indicating the distance
+        between those vectors. This works for Scipy's metrics, but is less
+        efficient than passing the metric name as a string.
+
+    metric_params : dict, default=None
+        Additional keyword arguments for the metric function.
+
+    n_jobs : int, default=None
+        The number of parallel jobs to run for neighbors search.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See :term:`Glossary <n_jobs>`
+        for more details.
+        Doesn't affect :meth:`fit` method.
+
+    Attributes
+    ----------
+    classes_ : array of shape (n_classes,)
+        Class labels known to the classifier
+
+    effective_metric_ : str or callble
+        The distance metric used. It will be same as the `metric` parameter
+        or a synonym of it, e.g. 'euclidean' if the `metric` parameter set to
+        'minkowski' and `p` parameter set to 2.
+
+    effective_metric_params_ : dict
+        Additional keyword arguments for the metric function. For most metrics
+        will be same with `metric_params` parameter, but may also contain the
+        `p` parameter value if the `effective_metric_` attribute is set to
+        'minkowski'.
+
+    n_features_in_ : int
+        Number of features seen during :term:`fit`.
+
+        .. versionadded:: 0.24
+
+    feature_names_in_ : ndarray of shape (`n_features_in_`,)
+        Names of features seen during :term:`fit`. Defined only when `X`
+        has feature names that are all strings.
+
+        .. versionadded:: 1.0
+
+    n_samples_fit_ : int
+        Number of samples in the fitted data.
+
+    outputs_2d_ : bool
+        False when `y`'s shape is (n_samples, ) or (n_samples, 1) during fit
+        otherwise True.
+
+    See Also
+    --------
+    RadiusNeighborsClassifier: Classifier based on neighbors within a fixed radius.
+    KNeighborsRegressor: Regression based on k-nearest neighbors.
+    RadiusNeighborsRegressor: Regression based on neighbors within a fixed radius.
+    NearestNeighbors: Unsupervised learner for implementing neighbor searches.
+
+    Notes
+    -----
+    See :ref:`Nearest Neighbors <neighbors>` in the online documentation
+    for a discussion of the choice of ``algorithm`` and ``leaf_size``.
+
+    .. warning::
+
+       Regarding the Nearest Neighbors algorithms, if it is found that two
+       neighbors, neighbor `k+1` and `k`, have identical distances
+       but different labels, the results will depend on the ordering of the
+       training data.
+
+    https://en.wikipedia.org/wiki/K-nearest_neighbor_algorithm
+
+    Examples
+    --------
+    >>> X = [[0], [1], [2], [3]]
+    >>> y = [0, 0, 1, 1]
+    >>> from sklearn.neighbors import KNeighborsClassifier
+    >>> neigh = KNeighborsClassifier(n_neighbors=3)
+    >>> neigh.fit(X, y)
+    KNeighborsClassifier(...)
+    >>> print(neigh.predict([[1.1]]))
+    [0]
+    >>> print(neigh.predict_proba([[0.9]]))
+    [[0.666 0.333]]
+    """
+
+    _parameter_constraints: dict = {**NeighborsBase._parameter_constraints}
+    _parameter_constraints.pop("radius")
+    _parameter_constraints.update(
+        {"weights": [StrOptions({"uniform", "distance"}), callable, None]}
+    )
+
+    def __init__(
+        self,
+        n_neighbors=5,
+        *,
+        weights="uniform",
+        algorithm="auto",
+        leaf_size=30,
+        p=2,
+        metric="minkowski",
+        metric_params=None,
+        n_jobs=None,
+    ):
+        super().__init__(
+            n_neighbors=n_neighbors,
+            algorithm=algorithm,
+            leaf_size=leaf_size,
+            metric=metric,
+            p=p,
+            metric_params=metric_params,
+            n_jobs=n_jobs,
+        )
+        self.weights = weights
+
+    @_fit_context(
+        # KNeighborsClassifier.metric is not validated yet
+        prefer_skip_nested_validation=False
+    )
+    def fit(self, X, y):
+        """Fit the k-nearest neighbors classifier from the training dataset.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features) or \
+                (n_samples, n_samples) if metric='precomputed'
+            Training data.
+
+        y : {array-like, sparse matrix} of shape (n_samples,) or \
+                (n_samples, n_outputs)
+            Target values.
+
+        Returns
+        -------
+        self : KNeighborsClassifier
+            The fitted k-nearest neighbors classifier.
+        """
+        return self._fit(X, y)
+
+    def predict(self, X):
+        """Predict the class labels for the provided data.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_queries, n_features), \
+                or (n_queries, n_indexed) if metric == 'precomputed', or None
+            Test samples. If `None`, predictions for all indexed points are
+            returned; in this case, points are not considered their own
+            neighbors.
+
+        Returns
+        -------
+        y : ndarray of shape (n_queries,) or (n_queries, n_outputs)
+            Class labels for each data sample.
+        """
+        check_is_fitted(self, "_fit_method")
+        if self.weights == "uniform":
+            if self._fit_method == "brute" and ArgKminClassMode.is_usable_for(
+                X, self._fit_X, self.metric
+            ):
+                probabilities = self.predict_proba(X)
+                if self.outputs_2d_:
+                    return np.stack(
+                        [
+                            self.classes_[idx][np.argmax(probas, axis=1)]
+                            for idx, probas in enumerate(probabilities)
+                        ],
+                        axis=1,
+                    )
+                return self.classes_[np.argmax(probabilities, axis=1)]
+            # In that case, we do not need the distances to perform
+            # the weighting so we do not compute them.
+            neigh_ind = self.kneighbors(X, return_distance=False)
+            neigh_dist = None
+        else:
+            neigh_dist, neigh_ind = self.kneighbors(X)
+
+        classes_ = self.classes_
+        _y = self._y
+        if not self.outputs_2d_:
+            _y = self._y.reshape((-1, 1))
+            classes_ = [self.classes_]
+
+        n_outputs = len(classes_)
+        n_queries = _num_samples(self._fit_X if X is None else X)
+        weights = _get_weights(neigh_dist, self.weights)
+        if weights is not None and _all_with_any_reduction_axis_1(weights, value=0):
+            raise ValueError(
+                "All neighbors of some sample is getting zero weights. "
+                "Please modify 'weights' to avoid this case if you are "
+                "using a user-defined function."
+            )
+
+        y_pred = np.empty((n_queries, n_outputs), dtype=classes_[0].dtype)
+        for k, classes_k in enumerate(classes_):
+            if weights is None:
+                mode, _ = _mode(_y[neigh_ind, k], axis=1)
+            else:
+                mode, _ = weighted_mode(_y[neigh_ind, k], weights, axis=1)
+
+            mode = np.asarray(mode.ravel(), dtype=np.intp)
+            y_pred[:, k] = classes_k.take(mode)
+
+        if not self.outputs_2d_:
+            y_pred = y_pred.ravel()
+
+        return y_pred
+
+    def predict_proba(self, X):
+        """Return probability estimates for the test data X.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_queries, n_features), \
+                or (n_queries, n_indexed) if metric == 'precomputed', or None
+            Test samples. If `None`, predictions for all indexed points are
+            returned; in this case, points are not considered their own
+            neighbors.
+
+        Returns
+        -------
+        p : ndarray of shape (n_queries, n_classes), or a list of n_outputs \
+                of such arrays if n_outputs > 1.
+            The class probabilities of the input samples. Classes are ordered
+            by lexicographic order.
+        """
+        check_is_fitted(self, "_fit_method")
+        if self.weights == "uniform":
+            # TODO: systematize this mapping of metric for
+            # PairwiseDistancesReductions.
+            metric, metric_kwargs = _adjusted_metric(
+                metric=self.metric, metric_kwargs=self.metric_params, p=self.p
+            )
+            if (
+                self._fit_method == "brute"
+                and ArgKminClassMode.is_usable_for(X, self._fit_X, metric)
+                # TODO: Implement efficient multi-output solution
+                and not self.outputs_2d_
+            ):
+                if self.metric == "precomputed":
+                    X = _check_precomputed(X)
+                else:
+                    X = validate_data(
+                        self, X, accept_sparse="csr", reset=False, order="C"
+                    )
+
+                probabilities = ArgKminClassMode.compute(
+                    X,
+                    self._fit_X,
+                    k=self.n_neighbors,
+                    weights=self.weights,
+                    Y_labels=self._y,
+                    unique_Y_labels=self.classes_,
+                    metric=metric,
+                    metric_kwargs=metric_kwargs,
+                    # `strategy="parallel_on_X"` has in practice be shown
+                    # to be more efficient than `strategy="parallel_on_Y``
+                    # on many combination of datasets.
+                    # Hence, we choose to enforce it here.
+                    # For more information, see:
+                    # https://github.com/scikit-learn/scikit-learn/pull/24076#issuecomment-1445258342
+                    # TODO: adapt the heuristic for `strategy="auto"` for
+                    # `ArgKminClassMode` and use `strategy="auto"`.
+                    strategy="parallel_on_X",
+                )
+                return probabilities
+
+            # In that case, we do not need the distances to perform
+            # the weighting so we do not compute them.
+            neigh_ind = self.kneighbors(X, return_distance=False)
+            neigh_dist = None
+        else:
+            neigh_dist, neigh_ind = self.kneighbors(X)
+
+        classes_ = self.classes_
+        _y = self._y
+        if not self.outputs_2d_:
+            _y = self._y.reshape((-1, 1))
+            classes_ = [self.classes_]
+
+        n_queries = _num_samples(self._fit_X if X is None else X)
+
+        weights = _get_weights(neigh_dist, self.weights)
+        if weights is None:
+            weights = np.ones_like(neigh_ind)
+        elif _all_with_any_reduction_axis_1(weights, value=0):
+            raise ValueError(
+                "All neighbors of some sample is getting zero weights. "
+                "Please modify 'weights' to avoid this case if you are "
+                "using a user-defined function."
+            )
+
+        all_rows = np.arange(n_queries)
+        probabilities = []
+        for k, classes_k in enumerate(classes_):
+            pred_labels = _y[:, k][neigh_ind]
+            proba_k = np.zeros((n_queries, classes_k.size))
+
+            # a simple ':' index doesn't work right
+            for i, idx in enumerate(pred_labels.T):  # loop is O(n_neighbors)
+                proba_k[all_rows, idx] += weights[:, i]
+
+            # normalize 'votes' into real [0,1] probabilities
+            normalizer = proba_k.sum(axis=1)[:, np.newaxis]
+            proba_k /= normalizer
+
+            probabilities.append(proba_k)
+
+        if not self.outputs_2d_:
+            probabilities = probabilities[0]
+
+        return probabilities
+
+    # This function is defined here only to modify the parent docstring
+    # and add information about X=None
+    def score(self, X, y, sample_weight=None):
+        """
+        Return the mean accuracy on the given test data and labels.
+
+        In multi-label classification, this is the subset accuracy
+        which is a harsh metric since you require for each sample that
+        each label set be correctly predicted.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features), or None
+            Test samples. If `None`, predictions for all indexed points are
+            used; in this case, points are not considered their own
+            neighbors. This means that `knn.fit(X, y).score(None, y)`
+            implicitly performs a leave-one-out cross-validation procedure
+            and is equivalent to `cross_val_score(knn, X, y, cv=LeaveOneOut())`
+            but typically much faster.
+
+        y : array-like of shape (n_samples,) or (n_samples, n_outputs)
+            True labels for `X`.
+
+        sample_weight : array-like of shape (n_samples,), default=None
+            Sample weights.
+
+        Returns
+        -------
+        score : float
+            Mean accuracy of ``self.predict(X)`` w.r.t. `y`.
+        """
+        return super().score(X, y, sample_weight)
+
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.classifier_tags.multi_label = True
+        tags.input_tags.pairwise = self.metric == "precomputed"
+        return tags
+
+
+class RadiusNeighborsClassifier(RadiusNeighborsMixin, ClassifierMixin, NeighborsBase):
+    """Classifier implementing a vote among neighbors within a given radius.
+
+    Read more in the :ref:`User Guide <classification>`.
+
+    Parameters
+    ----------
+    radius : float, default=1.0
+        Range of parameter space to use by default for :meth:`radius_neighbors`
+        queries.
+
+    weights : {'uniform', 'distance'}, callable or None, default='uniform'
+        Weight function used in prediction.  Possible values:
+
+        - 'uniform' : uniform weights.  All points in each neighborhood
+          are weighted equally.
+        - 'distance' : weight points by the inverse of their distance.
+          in this case, closer neighbors of a query point will have a
+          greater influence than neighbors which are further away.
+        - [callable] : a user-defined function which accepts an
+          array of distances, and returns an array of the same shape
+          containing the weights.
+
+        Uniform weights are used by default.
+
+    algorithm : {'auto', 'ball_tree', 'kd_tree', 'brute'}, default='auto'
+        Algorithm used to compute the nearest neighbors:
+
+        - 'ball_tree' will use :class:`BallTree`
+        - 'kd_tree' will use :class:`KDTree`
+        - 'brute' will use a brute-force search.
+        - 'auto' will attempt to decide the most appropriate algorithm
+          based on the values passed to :meth:`fit` method.
+
+        Note: fitting on sparse input will override the setting of
+        this parameter, using brute force.
+
+    leaf_size : int, default=30
+        Leaf size passed to BallTree or KDTree.  This can affect the
+        speed of the construction and query, as well as the memory
+        required to store the tree.  The optimal value depends on the
+        nature of the problem.
+
+    p : float, default=2
+        Power parameter for the Minkowski metric. When p = 1, this is
+        equivalent to using manhattan_distance (l1), and euclidean_distance
+        (l2) for p = 2. For arbitrary p, minkowski_distance (l_p) is used.
+        This parameter is expected to be positive.
+
+    metric : str or callable, default='minkowski'
+        Metric to use for distance computation. Default is "minkowski", which
+        results in the standard Euclidean distance when p = 2. See the
+        documentation of `scipy.spatial.distance
+        <https://docs.scipy.org/doc/scipy/reference/spatial.distance.html>`_ and
+        the metrics listed in
+        :class:`~sklearn.metrics.pairwise.distance_metrics` for valid metric
+        values.
+
+        If metric is "precomputed", X is assumed to be a distance matrix and
+        must be square during fit. X may be a :term:`sparse graph`, in which
+        case only "nonzero" elements may be considered neighbors.
+
+        If metric is a callable function, it takes two arrays representing 1D
+        vectors as inputs and must return one value indicating the distance
+        between those vectors. This works for Scipy's metrics, but is less
+        efficient than passing the metric name as a string.
+
+    outlier_label : {manual label, 'most_frequent'}, default=None
+        Label for outlier samples (samples with no neighbors in given radius).
+
+        - manual label: str or int label (should be the same type as y)
+          or list of manual labels if multi-output is used.
+        - 'most_frequent' : assign the most frequent label of y to outliers.
+        - None : when any outlier is detected, ValueError will be raised.
+
+        The outlier label should be selected from among the unique 'Y' labels.
+        If it is specified with a different value a warning will be raised and
+        all class probabilities of outliers will be assigned to be 0.
+
+    metric_params : dict, default=None
+        Additional keyword arguments for the metric function.
+
+    n_jobs : int, default=None
+        The number of parallel jobs to run for neighbors search.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See :term:`Glossary <n_jobs>`
+        for more details.
+
+    Attributes
+    ----------
+    classes_ : ndarray of shape (n_classes,)
+        Class labels known to the classifier.
+
+    effective_metric_ : str or callable
+        The distance metric used. It will be same as the `metric` parameter
+        or a synonym of it, e.g. 'euclidean' if the `metric` parameter set to
+        'minkowski' and `p` parameter set to 2.
+
+    effective_metric_params_ : dict
+        Additional keyword arguments for the metric function. For most metrics
+        will be same with `metric_params` parameter, but may also contain the
+        `p` parameter value if the `effective_metric_` attribute is set to
+        'minkowski'.
+
+    n_features_in_ : int
+        Number of features seen during :term:`fit`.
+
+        .. versionadded:: 0.24
+
+    feature_names_in_ : ndarray of shape (`n_features_in_`,)
+        Names of features seen during :term:`fit`. Defined only when `X`
+        has feature names that are all strings.
+
+        .. versionadded:: 1.0
+
+    n_samples_fit_ : int
+        Number of samples in the fitted data.
+
+    outlier_label_ : int or array-like of shape (n_class,)
+        Label which is given for outlier samples (samples with no neighbors
+        on given radius).
+
+    outputs_2d_ : bool
+        False when `y`'s shape is (n_samples, ) or (n_samples, 1) during fit
+        otherwise True.
+
+    See Also
+    --------
+    KNeighborsClassifier : Classifier implementing the k-nearest neighbors
+        vote.
+    RadiusNeighborsRegressor : Regression based on neighbors within a
+        fixed radius.
+    KNeighborsRegressor : Regression based on k-nearest neighbors.
+    NearestNeighbors : Unsupervised learner for implementing neighbor
+        searches.
+
+    Notes
+    -----
+    See :ref:`Nearest Neighbors <neighbors>` in the online documentation
+    for a discussion of the choice of ``algorithm`` and ``leaf_size``.
+
+    https://en.wikipedia.org/wiki/K-nearest_neighbor_algorithm
+
+    Examples
+    --------
+    >>> X = [[0], [1], [2], [3]]
+    >>> y = [0, 0, 1, 1]
+    >>> from sklearn.neighbors import RadiusNeighborsClassifier
+    >>> neigh = RadiusNeighborsClassifier(radius=1.0)
+    >>> neigh.fit(X, y)
+    RadiusNeighborsClassifier(...)
+    >>> print(neigh.predict([[1.5]]))
+    [0]
+    >>> print(neigh.predict_proba([[1.0]]))
+    [[0.66666667 0.33333333]]
+    """
+
+    _parameter_constraints: dict = {
+        **NeighborsBase._parameter_constraints,
+        "weights": [StrOptions({"uniform", "distance"}), callable, None],
+        "outlier_label": [Integral, str, "array-like", None],
+    }
+    _parameter_constraints.pop("n_neighbors")
+
+    def __init__(
+        self,
+        radius=1.0,
+        *,
+        weights="uniform",
+        algorithm="auto",
+        leaf_size=30,
+        p=2,
+        metric="minkowski",
+        outlier_label=None,
+        metric_params=None,
+        n_jobs=None,
+    ):
+        super().__init__(
+            radius=radius,
+            algorithm=algorithm,
+            leaf_size=leaf_size,
+            metric=metric,
+            p=p,
+            metric_params=metric_params,
+            n_jobs=n_jobs,
+        )
+        self.weights = weights
+        self.outlier_label = outlier_label
+
+    @_fit_context(
+        # RadiusNeighborsClassifier.metric is not validated yet
+        prefer_skip_nested_validation=False
+    )
+    def fit(self, X, y):
+        """Fit the radius neighbors classifier from the training dataset.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features) or \
+                (n_samples, n_samples) if metric='precomputed'
+            Training data.
+
+        y : {array-like, sparse matrix} of shape (n_samples,) or \
+                (n_samples, n_outputs)
+            Target values.
+
+        Returns
+        -------
+        self : RadiusNeighborsClassifier
+            The fitted radius neighbors classifier.
+        """
+        self._fit(X, y)
+
+        classes_ = self.classes_
+        _y = self._y
+        if not self.outputs_2d_:
+            _y = self._y.reshape((-1, 1))
+            classes_ = [self.classes_]
+
+        if self.outlier_label is None:
+            outlier_label_ = None
+
+        elif self.outlier_label == "most_frequent":
+            outlier_label_ = []
+            # iterate over multi-output, get the most frequent label for each
+            # output.
+            for k, classes_k in enumerate(classes_):
+                label_count = np.bincount(_y[:, k])
+                outlier_label_.append(classes_k[label_count.argmax()])
+
+        else:
+            if _is_arraylike(self.outlier_label) and not isinstance(
+                self.outlier_label, str
+            ):
+                if len(self.outlier_label) != len(classes_):
+                    raise ValueError(
+                        "The length of outlier_label: {} is "
+                        "inconsistent with the output "
+                        "length: {}".format(self.outlier_label, len(classes_))
+                    )
+                outlier_label_ = self.outlier_label
+            else:
+                outlier_label_ = [self.outlier_label] * len(classes_)
+
+            for classes, label in zip(classes_, outlier_label_):
+                if _is_arraylike(label) and not isinstance(label, str):
+                    # ensure the outlier label for each output is a scalar.
+                    raise TypeError(
+                        "The outlier_label of classes {} is "
+                        "supposed to be a scalar, got "
+                        "{}.".format(classes, label)
+                    )
+                if np.append(classes, label).dtype != classes.dtype:
+                    # ensure the dtype of outlier label is consistent with y.
+                    raise TypeError(
+                        "The dtype of outlier_label {} is "
+                        "inconsistent with classes {} in "
+                        "y.".format(label, classes)
+                    )
+
+        self.outlier_label_ = outlier_label_
+
+        return self
+
+    def predict(self, X):
+        """Predict the class labels for the provided data.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_queries, n_features), \
+                or (n_queries, n_indexed) if metric == 'precomputed', or None
+            Test samples. If `None`, predictions for all indexed points are
+            returned; in this case, points are not considered their own
+            neighbors.
+
+        Returns
+        -------
+        y : ndarray of shape (n_queries,) or (n_queries, n_outputs)
+            Class labels for each data sample.
+        """
+
+        probs = self.predict_proba(X)
+        classes_ = self.classes_
+
+        if not self.outputs_2d_:
+            probs = [probs]
+            classes_ = [self.classes_]
+
+        n_outputs = len(classes_)
+        n_queries = probs[0].shape[0]
+        y_pred = np.empty((n_queries, n_outputs), dtype=classes_[0].dtype)
+
+        for k, prob in enumerate(probs):
+            # iterate over multi-output, assign labels based on probabilities
+            # of each output.
+            max_prob_index = prob.argmax(axis=1)
+            y_pred[:, k] = classes_[k].take(max_prob_index)
+
+            outlier_zero_probs = (prob == 0).all(axis=1)
+            if outlier_zero_probs.any():
+                zero_prob_index = np.flatnonzero(outlier_zero_probs)
+                y_pred[zero_prob_index, k] = self.outlier_label_[k]
+
+        if not self.outputs_2d_:
+            y_pred = y_pred.ravel()
+
+        return y_pred
+
+    def predict_proba(self, X):
+        """Return probability estimates for the test data X.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_queries, n_features), \
+                or (n_queries, n_indexed) if metric == 'precomputed', or None
+            Test samples. If `None`, predictions for all indexed points are
+            returned; in this case, points are not considered their own
+            neighbors.
+
+        Returns
+        -------
+        p : ndarray of shape (n_queries, n_classes), or a list of \
+                n_outputs of such arrays if n_outputs > 1.
+            The class probabilities of the input samples. Classes are ordered
+            by lexicographic order.
+        """
+        check_is_fitted(self, "_fit_method")
+        n_queries = _num_samples(self._fit_X if X is None else X)
+
+        metric, metric_kwargs = _adjusted_metric(
+            metric=self.metric, metric_kwargs=self.metric_params, p=self.p
+        )
+
+        if (
+            self.weights == "uniform"
+            and self._fit_method == "brute"
+            and not self.outputs_2d_
+            and RadiusNeighborsClassMode.is_usable_for(X, self._fit_X, metric)
+        ):
+            probabilities = RadiusNeighborsClassMode.compute(
+                X=X,
+                Y=self._fit_X,
+                radius=self.radius,
+                weights=self.weights,
+                Y_labels=self._y,
+                unique_Y_labels=self.classes_,
+                outlier_label=self.outlier_label,
+                metric=metric,
+                metric_kwargs=metric_kwargs,
+                strategy="parallel_on_X",
+                # `strategy="parallel_on_X"` has in practice be shown
+                # to be more efficient than `strategy="parallel_on_Y``
+                # on many combination of datasets.
+                # Hence, we choose to enforce it here.
+                # For more information, see:
+                # https://github.com/scikit-learn/scikit-learn/pull/26828/files#r1282398471
+            )
+            return probabilities
+
+        neigh_dist, neigh_ind = self.radius_neighbors(X)
+        outlier_mask = np.zeros(n_queries, dtype=bool)
+        outlier_mask[:] = [len(nind) == 0 for nind in neigh_ind]
+        outliers = np.flatnonzero(outlier_mask)
+        inliers = np.flatnonzero(~outlier_mask)
+
+        classes_ = self.classes_
+        _y = self._y
+        if not self.outputs_2d_:
+            _y = self._y.reshape((-1, 1))
+            classes_ = [self.classes_]
+
+        if self.outlier_label_ is None and outliers.size > 0:
+            raise ValueError(
+                "No neighbors found for test samples %r, "
+                "you can try using larger radius, "
+                "giving a label for outliers, "
+                "or considering removing them from your dataset." % outliers
+            )
+
+        weights = _get_weights(neigh_dist, self.weights)
+        if weights is not None:
+            weights = weights[inliers]
+
+        probabilities = []
+        # iterate over multi-output, measure probabilities of the k-th output.
+        for k, classes_k in enumerate(classes_):
+            pred_labels = np.zeros(len(neigh_ind), dtype=object)
+            pred_labels[:] = [_y[ind, k] for ind in neigh_ind]
+
+            proba_k = np.zeros((n_queries, classes_k.size))
+            proba_inl = np.zeros((len(inliers), classes_k.size))
+
+            # samples have different size of neighbors within the same radius
+            if weights is None:
+                for i, idx in enumerate(pred_labels[inliers]):
+                    proba_inl[i, :] = np.bincount(idx, minlength=classes_k.size)
+            else:
+                for i, idx in enumerate(pred_labels[inliers]):
+                    proba_inl[i, :] = np.bincount(
+                        idx, weights[i], minlength=classes_k.size
+                    )
+            proba_k[inliers, :] = proba_inl
+
+            if outliers.size > 0:
+                _outlier_label = self.outlier_label_[k]
+                label_index = np.flatnonzero(classes_k == _outlier_label)
+                if label_index.size == 1:
+                    proba_k[outliers, label_index[0]] = 1.0
+                else:
+                    warnings.warn(
+                        "Outlier label {} is not in training "
+                        "classes. All class probabilities of "
+                        "outliers will be assigned with 0."
+                        "".format(self.outlier_label_[k])
+                    )
+
+            # normalize 'votes' into real [0,1] probabilities
+            normalizer = proba_k.sum(axis=1)[:, np.newaxis]
+            normalizer[normalizer == 0.0] = 1.0
+            proba_k /= normalizer
+
+            probabilities.append(proba_k)
+
+        if not self.outputs_2d_:
+            probabilities = probabilities[0]
+
+        return probabilities
+
+    # This function is defined here only to modify the parent docstring
+    # and add information about X=None
+    def score(self, X, y, sample_weight=None):
+        """
+        Return the mean accuracy on the given test data and labels.
+
+        In multi-label classification, this is the subset accuracy
+        which is a harsh metric since you require for each sample that
+        each label set be correctly predicted.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features), or None
+            Test samples. If `None`, predictions for all indexed points are
+            used; in this case, points are not considered their own
+            neighbors. This means that `knn.fit(X, y).score(None, y)`
+            implicitly performs a leave-one-out cross-validation procedure
+            and is equivalent to `cross_val_score(knn, X, y, cv=LeaveOneOut())`
+            but typically much faster.
+
+        y : array-like of shape (n_samples,) or (n_samples, n_outputs)
+            True labels for `X`.
+
+        sample_weight : array-like of shape (n_samples,), default=None
+            Sample weights.
+
+        Returns
+        -------
+        score : float
+            Mean accuracy of ``self.predict(X)`` w.r.t. `y`.
+        """
+        return super().score(X, y, sample_weight)
+
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.classifier_tags.multi_label = True
+        return tags

linedance-app/venv/lib/python3.12/site-packages/sklearn/neighbors/_graph.py

@@ -0,0 +1,709 @@
+"""Nearest Neighbors graph functions"""
+
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
+import itertools
+
+from sklearn.base import ClassNamePrefixFeaturesOutMixin, TransformerMixin, _fit_context
+from sklearn.neighbors._base import (
+    VALID_METRICS,
+    KNeighborsMixin,
+    NeighborsBase,
+    RadiusNeighborsMixin,
+)
+from sklearn.neighbors._unsupervised import NearestNeighbors
+from sklearn.utils._param_validation import (
+    Integral,
+    Interval,
+    Real,
+    StrOptions,
+    validate_params,
+)
+from sklearn.utils.validation import check_is_fitted
+
+
+def _check_params(X, metric, p, metric_params):
+    """Check the validity of the input parameters"""
+    params = zip(["metric", "p", "metric_params"], [metric, p, metric_params])
+    est_params = X.get_params()
+    for param_name, func_param in params:
+        if func_param != est_params[param_name]:
+            raise ValueError(
+                "Got %s for %s, while the estimator has %s for the same parameter."
+                % (func_param, param_name, est_params[param_name])
+            )
+
+
+def _query_include_self(X, include_self, mode):
+    """Return the query based on include_self param"""
+    if include_self == "auto":
+        include_self = mode == "connectivity"
+
+    # it does not include each sample as its own neighbors
+    if not include_self:
+        X = None
+
+    return X
+
+
+@validate_params(
+    {
+        "X": ["array-like", "sparse matrix", KNeighborsMixin],
+        "n_neighbors": [Interval(Integral, 1, None, closed="left")],
+        "mode": [StrOptions({"connectivity", "distance"})],
+        "metric": [StrOptions(set(itertools.chain(*VALID_METRICS.values()))), callable],
+        "p": [Interval(Real, 0, None, closed="right"), None],
+        "metric_params": [dict, None],
+        "include_self": ["boolean", StrOptions({"auto"})],
+        "n_jobs": [Integral, None],
+    },
+    prefer_skip_nested_validation=False,  # metric is not validated yet
+)
+def kneighbors_graph(
+    X,
+    n_neighbors,
+    *,
+    mode="connectivity",
+    metric="minkowski",
+    p=2,
+    metric_params=None,
+    include_self=False,
+    n_jobs=None,
+):
+    """Compute the (weighted) graph of k-Neighbors for points in X.
+
+    Read more in the :ref:`User Guide <unsupervised_neighbors>`.
+
+    Parameters
+    ----------
+    X : {array-like, sparse matrix} of shape (n_samples, n_features)
+        Sample data.
+
+    n_neighbors : int
+        Number of neighbors for each sample.
+
+    mode : {'connectivity', 'distance'}, default='connectivity'
+        Type of returned matrix: 'connectivity' will return the connectivity
+        matrix with ones and zeros, and 'distance' will return the distances
+        between neighbors according to the given metric.
+
+    metric : str, default='minkowski'
+        Metric to use for distance computation. Default is "minkowski", which
+        results in the standard Euclidean distance when p = 2. See the
+        documentation of `scipy.spatial.distance
+        <https://docs.scipy.org/doc/scipy/reference/spatial.distance.html>`_ and
+        the metrics listed in
+        :class:`~sklearn.metrics.pairwise.distance_metrics` for valid metric
+        values.
+
+    p : float, default=2
+        Power parameter for the Minkowski metric. When p = 1, this is equivalent
+        to using manhattan_distance (l1), and euclidean_distance (l2) for p = 2.
+        For arbitrary p, minkowski_distance (l_p) is used. This parameter is expected
+        to be positive.
+
+    metric_params : dict, default=None
+        Additional keyword arguments for the metric function.
+
+    include_self : bool or 'auto', default=False
+        Whether or not to mark each sample as the first nearest neighbor to
+        itself. If 'auto', then True is used for mode='connectivity' and False
+        for mode='distance'.
+
+    n_jobs : int, default=None
+        The number of parallel jobs to run for neighbors search.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See :term:`Glossary <n_jobs>`
+        for more details.
+
+    Returns
+    -------
+    A : sparse matrix of shape (n_samples, n_samples)
+        Graph where A[i, j] is assigned the weight of edge that
+        connects i to j. The matrix is of CSR format.
+
+    See Also
+    --------
+    radius_neighbors_graph: Compute the (weighted) graph of Neighbors for points in X.
+
+    Examples
+    --------
+    >>> X = [[0], [3], [1]]
+    >>> from sklearn.neighbors import kneighbors_graph
+    >>> A = kneighbors_graph(X, 2, mode='connectivity', include_self=True)
+    >>> A.toarray()
+    array([[1., 0., 1.],
+           [0., 1., 1.],
+           [1., 0., 1.]])
+    """
+    if not isinstance(X, KNeighborsMixin):
+        X = NearestNeighbors(
+            n_neighbors=n_neighbors,
+            metric=metric,
+            p=p,
+            metric_params=metric_params,
+            n_jobs=n_jobs,
+        ).fit(X)
+    else:
+        _check_params(X, metric, p, metric_params)
+
+    query = _query_include_self(X._fit_X, include_self, mode)
+    return X.kneighbors_graph(X=query, n_neighbors=n_neighbors, mode=mode)
+
+
+@validate_params(
+    {
+        "X": ["array-like", "sparse matrix", RadiusNeighborsMixin],
+        "radius": [Interval(Real, 0, None, closed="both")],
+        "mode": [StrOptions({"connectivity", "distance"})],
+        "metric": [StrOptions(set(itertools.chain(*VALID_METRICS.values()))), callable],
+        "p": [Interval(Real, 0, None, closed="right"), None],
+        "metric_params": [dict, None],
+        "include_self": ["boolean", StrOptions({"auto"})],
+        "n_jobs": [Integral, None],
+    },
+    prefer_skip_nested_validation=False,  # metric is not validated yet
+)
+def radius_neighbors_graph(
+    X,
+    radius,
+    *,
+    mode="connectivity",
+    metric="minkowski",
+    p=2,
+    metric_params=None,
+    include_self=False,
+    n_jobs=None,
+):
+    """Compute the (weighted) graph of Neighbors for points in X.
+
+    Neighborhoods are restricted the points at a distance lower than
+    radius.
+
+    Read more in the :ref:`User Guide <unsupervised_neighbors>`.
+
+    Parameters
+    ----------
+    X : {array-like, sparse matrix} of shape (n_samples, n_features)
+        Sample data.
+
+    radius : float
+        Radius of neighborhoods.
+
+    mode : {'connectivity', 'distance'}, default='connectivity'
+        Type of returned matrix: 'connectivity' will return the connectivity
+        matrix with ones and zeros, and 'distance' will return the distances
+        between neighbors according to the given metric.
+
+    metric : str, default='minkowski'
+        Metric to use for distance computation. Default is "minkowski", which
+        results in the standard Euclidean distance when p = 2. See the
+        documentation of `scipy.spatial.distance
+        <https://docs.scipy.org/doc/scipy/reference/spatial.distance.html>`_ and
+        the metrics listed in
+        :class:`~sklearn.metrics.pairwise.distance_metrics` for valid metric
+        values.
+
+    p : float, default=2
+        Power parameter for the Minkowski metric. When p = 1, this is
+        equivalent to using manhattan_distance (l1), and euclidean_distance
+        (l2) for p = 2. For arbitrary p, minkowski_distance (l_p) is used.
+
+    metric_params : dict, default=None
+        Additional keyword arguments for the metric function.
+
+    include_self : bool or 'auto', default=False
+        Whether or not to mark each sample as the first nearest neighbor to
+        itself. If 'auto', then True is used for mode='connectivity' and False
+        for mode='distance'.
+
+    n_jobs : int, default=None
+        The number of parallel jobs to run for neighbors search.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See :term:`Glossary <n_jobs>`
+        for more details.
+
+    Returns
+    -------
+    A : sparse matrix of shape (n_samples, n_samples)
+        Graph where A[i, j] is assigned the weight of edge that connects
+        i to j. The matrix is of CSR format.
+
+    See Also
+    --------
+    kneighbors_graph: Compute the weighted graph of k-neighbors for points in X.
+
+    Examples
+    --------
+    >>> X = [[0], [3], [1]]
+    >>> from sklearn.neighbors import radius_neighbors_graph
+    >>> A = radius_neighbors_graph(X, 1.5, mode='connectivity',
+    ...                            include_self=True)
+    >>> A.toarray()
+    array([[1., 0., 1.],
+           [0., 1., 0.],
+           [1., 0., 1.]])
+    """
+    if not isinstance(X, RadiusNeighborsMixin):
+        X = NearestNeighbors(
+            radius=radius,
+            metric=metric,
+            p=p,
+            metric_params=metric_params,
+            n_jobs=n_jobs,
+        ).fit(X)
+    else:
+        _check_params(X, metric, p, metric_params)
+
+    query = _query_include_self(X._fit_X, include_self, mode)
+    return X.radius_neighbors_graph(query, radius, mode)
+
+
+class KNeighborsTransformer(
+    ClassNamePrefixFeaturesOutMixin, KNeighborsMixin, TransformerMixin, NeighborsBase
+):
+    """Transform X into a (weighted) graph of k nearest neighbors.
+
+    The transformed data is a sparse graph as returned by kneighbors_graph.
+
+    Read more in the :ref:`User Guide <neighbors_transformer>`.
+
+    .. versionadded:: 0.22
+
+    Parameters
+    ----------
+    mode : {'distance', 'connectivity'}, default='distance'
+        Type of returned matrix: 'connectivity' will return the connectivity
+        matrix with ones and zeros, and 'distance' will return the distances
+        between neighbors according to the given metric.
+
+    n_neighbors : int, default=5
+        Number of neighbors for each sample in the transformed sparse graph.
+        For compatibility reasons, as each sample is considered as its own
+        neighbor, one extra neighbor will be computed when mode == 'distance'.
+        In this case, the sparse graph contains (n_neighbors + 1) neighbors.
+
+    algorithm : {'auto', 'ball_tree', 'kd_tree', 'brute'}, default='auto'
+        Algorithm used to compute the nearest neighbors:
+
+        - 'ball_tree' will use :class:`BallTree`
+        - 'kd_tree' will use :class:`KDTree`
+        - 'brute' will use a brute-force search.
+        - 'auto' will attempt to decide the most appropriate algorithm
+          based on the values passed to :meth:`fit` method.
+
+        Note: fitting on sparse input will override the setting of
+        this parameter, using brute force.
+
+    leaf_size : int, default=30
+        Leaf size passed to BallTree or KDTree.  This can affect the
+        speed of the construction and query, as well as the memory
+        required to store the tree.  The optimal value depends on the
+        nature of the problem.
+
+    metric : str or callable, default='minkowski'
+        Metric to use for distance computation. Default is "minkowski", which
+        results in the standard Euclidean distance when p = 2. See the
+        documentation of `scipy.spatial.distance
+        <https://docs.scipy.org/doc/scipy/reference/spatial.distance.html>`_ and
+        the metrics listed in
+        :class:`~sklearn.metrics.pairwise.distance_metrics` for valid metric
+        values.
+
+        If metric is a callable function, it takes two arrays representing 1D
+        vectors as inputs and must return one value indicating the distance
+        between those vectors. This works for Scipy's metrics, but is less
+        efficient than passing the metric name as a string.
+
+        Distance matrices are not supported.
+
+    p : float, default=2
+        Parameter for the Minkowski metric from
+        sklearn.metrics.pairwise.pairwise_distances. When p = 1, this is
+        equivalent to using manhattan_distance (l1), and euclidean_distance
+        (l2) for p = 2. For arbitrary p, minkowski_distance (l_p) is used.
+        This parameter is expected to be positive.
+
+    metric_params : dict, default=None
+        Additional keyword arguments for the metric function.
+
+    n_jobs : int, default=None
+        The number of parallel jobs to run for neighbors search.
+        If ``-1``, then the number of jobs is set to the number of CPU cores.
+
+    Attributes
+    ----------
+    effective_metric_ : str or callable
+        The distance metric used. It will be same as the `metric` parameter
+        or a synonym of it, e.g. 'euclidean' if the `metric` parameter set to
+        'minkowski' and `p` parameter set to 2.
+
+    effective_metric_params_ : dict
+        Additional keyword arguments for the metric function. For most metrics
+        will be same with `metric_params` parameter, but may also contain the
+        `p` parameter value if the `effective_metric_` attribute is set to
+        'minkowski'.
+
+    n_features_in_ : int
+        Number of features seen during :term:`fit`.
+
+        .. versionadded:: 0.24
+
+    feature_names_in_ : ndarray of shape (`n_features_in_`,)
+        Names of features seen during :term:`fit`. Defined only when `X`
+        has feature names that are all strings.
+
+        .. versionadded:: 1.0
+
+    n_samples_fit_ : int
+        Number of samples in the fitted data.
+
+    See Also
+    --------
+    kneighbors_graph : Compute the weighted graph of k-neighbors for
+        points in X.
+    RadiusNeighborsTransformer : Transform X into a weighted graph of
+        neighbors nearer than a radius.
+
+    Notes
+    -----
+    For an example of using :class:`~sklearn.neighbors.KNeighborsTransformer`
+    in combination with :class:`~sklearn.manifold.TSNE` see
+    :ref:`sphx_glr_auto_examples_neighbors_approximate_nearest_neighbors.py`.
+
+    Examples
+    --------
+    >>> from sklearn.datasets import load_wine
+    >>> from sklearn.neighbors import KNeighborsTransformer
+    >>> X, _ = load_wine(return_X_y=True)
+    >>> X.shape
+    (178, 13)
+    >>> transformer = KNeighborsTransformer(n_neighbors=5, mode='distance')
+    >>> X_dist_graph = transformer.fit_transform(X)
+    >>> X_dist_graph.shape
+    (178, 178)
+    """
+
+    _parameter_constraints: dict = {
+        **NeighborsBase._parameter_constraints,
+        "mode": [StrOptions({"distance", "connectivity"})],
+    }
+    _parameter_constraints.pop("radius")
+
+    def __init__(
+        self,
+        *,
+        mode="distance",
+        n_neighbors=5,
+        algorithm="auto",
+        leaf_size=30,
+        metric="minkowski",
+        p=2,
+        metric_params=None,
+        n_jobs=None,
+    ):
+        super().__init__(
+            n_neighbors=n_neighbors,
+            radius=None,
+            algorithm=algorithm,
+            leaf_size=leaf_size,
+            metric=metric,
+            p=p,
+            metric_params=metric_params,
+            n_jobs=n_jobs,
+        )
+        self.mode = mode
+
+    @_fit_context(
+        # KNeighborsTransformer.metric is not validated yet
+        prefer_skip_nested_validation=False
+    )
+    def fit(self, X, y=None):
+        """Fit the k-nearest neighbors transformer from the training dataset.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features) or \
+                (n_samples, n_samples) if metric='precomputed'
+            Training data.
+        y : Ignored
+            Not used, present for API consistency by convention.
+
+        Returns
+        -------
+        self : KNeighborsTransformer
+            The fitted k-nearest neighbors transformer.
+        """
+        self._fit(X)
+        self._n_features_out = self.n_samples_fit_
+        return self
+
+    def transform(self, X):
+        """Compute the (weighted) graph of Neighbors for points in X.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples_transform, n_features)
+            Sample data.
+
+        Returns
+        -------
+        Xt : sparse matrix of shape (n_samples_transform, n_samples_fit)
+            Xt[i, j] is assigned the weight of edge that connects i to j.
+            Only the neighbors have an explicit value.
+            The diagonal is always explicit.
+            The matrix is of CSR format.
+        """
+        check_is_fitted(self)
+        add_one = self.mode == "distance"
+        return self.kneighbors_graph(
+            X, mode=self.mode, n_neighbors=self.n_neighbors + add_one
+        )
+
+    def fit_transform(self, X, y=None):
+        """Fit to data, then transform it.
+
+        Fits transformer to X and y with optional parameters fit_params
+        and returns a transformed version of X.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training set.
+
+        y : Ignored
+            Not used, present for API consistency by convention.
+
+        Returns
+        -------
+        Xt : sparse matrix of shape (n_samples, n_samples)
+            Xt[i, j] is assigned the weight of edge that connects i to j.
+            Only the neighbors have an explicit value.
+            The diagonal is always explicit.
+            The matrix is of CSR format.
+        """
+        return self.fit(X).transform(X)
+
+
+class RadiusNeighborsTransformer(
+    ClassNamePrefixFeaturesOutMixin,
+    RadiusNeighborsMixin,
+    TransformerMixin,
+    NeighborsBase,
+):
+    """Transform X into a (weighted) graph of neighbors nearer than a radius.
+
+    The transformed data is a sparse graph as returned by
+    `radius_neighbors_graph`.
+
+    Read more in the :ref:`User Guide <neighbors_transformer>`.
+
+    .. versionadded:: 0.22
+
+    Parameters
+    ----------
+    mode : {'distance', 'connectivity'}, default='distance'
+        Type of returned matrix: 'connectivity' will return the connectivity
+        matrix with ones and zeros, and 'distance' will return the distances
+        between neighbors according to the given metric.
+
+    radius : float, default=1.0
+        Radius of neighborhood in the transformed sparse graph.
+
+    algorithm : {'auto', 'ball_tree', 'kd_tree', 'brute'}, default='auto'
+        Algorithm used to compute the nearest neighbors:
+
+        - 'ball_tree' will use :class:`BallTree`
+        - 'kd_tree' will use :class:`KDTree`
+        - 'brute' will use a brute-force search.
+        - 'auto' will attempt to decide the most appropriate algorithm
+          based on the values passed to :meth:`fit` method.
+
+        Note: fitting on sparse input will override the setting of
+        this parameter, using brute force.
+
+    leaf_size : int, default=30
+        Leaf size passed to BallTree or KDTree.  This can affect the
+        speed of the construction and query, as well as the memory
+        required to store the tree.  The optimal value depends on the
+        nature of the problem.
+
+    metric : str or callable, default='minkowski'
+        Metric to use for distance computation. Default is "minkowski", which
+        results in the standard Euclidean distance when p = 2. See the
+        documentation of `scipy.spatial.distance
+        <https://docs.scipy.org/doc/scipy/reference/spatial.distance.html>`_ and
+        the metrics listed in
+        :class:`~sklearn.metrics.pairwise.distance_metrics` for valid metric
+        values.
+
+        If metric is a callable function, it takes two arrays representing 1D
+        vectors as inputs and must return one value indicating the distance
+        between those vectors. This works for Scipy's metrics, but is less
+        efficient than passing the metric name as a string.
+
+        Distance matrices are not supported.
+
+    p : float, default=2
+        Parameter for the Minkowski metric from
+        sklearn.metrics.pairwise.pairwise_distances. When p = 1, this is
+        equivalent to using manhattan_distance (l1), and euclidean_distance
+        (l2) for p = 2. For arbitrary p, minkowski_distance (l_p) is used.
+        This parameter is expected to be positive.
+
+    metric_params : dict, default=None
+        Additional keyword arguments for the metric function.
+
+    n_jobs : int, default=None
+        The number of parallel jobs to run for neighbors search.
+        If ``-1``, then the number of jobs is set to the number of CPU cores.
+
+    Attributes
+    ----------
+    effective_metric_ : str or callable
+        The distance metric used. It will be same as the `metric` parameter
+        or a synonym of it, e.g. 'euclidean' if the `metric` parameter set to
+        'minkowski' and `p` parameter set to 2.
+
+    effective_metric_params_ : dict
+        Additional keyword arguments for the metric function. For most metrics
+        will be same with `metric_params` parameter, but may also contain the
+        `p` parameter value if the `effective_metric_` attribute is set to
+        'minkowski'.
+
+    n_features_in_ : int
+        Number of features seen during :term:`fit`.
+
+        .. versionadded:: 0.24
+
+    feature_names_in_ : ndarray of shape (`n_features_in_`,)
+        Names of features seen during :term:`fit`. Defined only when `X`
+        has feature names that are all strings.
+
+        .. versionadded:: 1.0
+
+    n_samples_fit_ : int
+        Number of samples in the fitted data.
+
+    See Also
+    --------
+    kneighbors_graph : Compute the weighted graph of k-neighbors for
+        points in X.
+    KNeighborsTransformer : Transform X into a weighted graph of k
+        nearest neighbors.
+
+    Examples
+    --------
+    >>> import numpy as np
+    >>> from sklearn.datasets import load_wine
+    >>> from sklearn.cluster import DBSCAN
+    >>> from sklearn.neighbors import RadiusNeighborsTransformer
+    >>> from sklearn.pipeline import make_pipeline
+    >>> X, _ = load_wine(return_X_y=True)
+    >>> estimator = make_pipeline(
+    ...     RadiusNeighborsTransformer(radius=42.0, mode='distance'),
+    ...     DBSCAN(eps=25.0, metric='precomputed'))
+    >>> X_clustered = estimator.fit_predict(X)
+    >>> clusters, counts = np.unique(X_clustered, return_counts=True)
+    >>> print(counts)
+    [ 29  15 111  11  12]
+    """
+
+    _parameter_constraints: dict = {
+        **NeighborsBase._parameter_constraints,
+        "mode": [StrOptions({"distance", "connectivity"})],
+    }
+    _parameter_constraints.pop("n_neighbors")
+
+    def __init__(
+        self,
+        *,
+        mode="distance",
+        radius=1.0,
+        algorithm="auto",
+        leaf_size=30,
+        metric="minkowski",
+        p=2,
+        metric_params=None,
+        n_jobs=None,
+    ):
+        super().__init__(
+            n_neighbors=None,
+            radius=radius,
+            algorithm=algorithm,
+            leaf_size=leaf_size,
+            metric=metric,
+            p=p,
+            metric_params=metric_params,
+            n_jobs=n_jobs,
+        )
+        self.mode = mode
+
+    @_fit_context(
+        # RadiusNeighborsTransformer.metric is not validated yet
+        prefer_skip_nested_validation=False
+    )
+    def fit(self, X, y=None):
+        """Fit the radius neighbors transformer from the training dataset.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features) or \
+                (n_samples, n_samples) if metric='precomputed'
+            Training data.
+
+        y : Ignored
+            Not used, present for API consistency by convention.
+
+        Returns
+        -------
+        self : RadiusNeighborsTransformer
+            The fitted radius neighbors transformer.
+        """
+        self._fit(X)
+        self._n_features_out = self.n_samples_fit_
+        return self
+
+    def transform(self, X):
+        """Compute the (weighted) graph of Neighbors for points in X.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples_transform, n_features)
+            Sample data.
+
+        Returns
+        -------
+        Xt : sparse matrix of shape (n_samples_transform, n_samples_fit)
+            Xt[i, j] is assigned the weight of edge that connects i to j.
+            Only the neighbors have an explicit value.
+            The diagonal is always explicit.
+            The matrix is of CSR format.
+        """
+        check_is_fitted(self)
+        return self.radius_neighbors_graph(X, mode=self.mode, sort_results=True)
+
+    def fit_transform(self, X, y=None):
+        """Fit to data, then transform it.
+
+        Fits transformer to X and y with optional parameters fit_params
+        and returns a transformed version of X.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training set.
+
+        y : Ignored
+            Not used, present for API consistency by convention.
+
+        Returns
+        -------
+        Xt : sparse matrix of shape (n_samples, n_samples)
+            Xt[i, j] is assigned the weight of edge that connects i to j.
+            Only the neighbors have an explicit value.
+            The diagonal is always explicit.
+            The matrix is of CSR format.
+        """
+        return self.fit(X).transform(X)

linedance-app/venv/lib/python3.12/site-packages/sklearn/neighbors/_kd_tree.pyx.tp

@@ -0,0 +1,336 @@
+{{py:
+
+# Generated file: _kd_tree.pyx
+
+implementation_specific_values = [
+    # The values are arranged as follows:
+    #
+    #       name_suffix, INPUT_DTYPE_t, INPUT_DTYPE
+    #
+    ('64', 'float64_t', 'np.float64'),
+    ('32', 'float32_t', 'np.float32')
+]
+
+# By Jake Vanderplas (2013) <jakevdp@cs.washington.edu>
+# written for the scikit-learn project
+# SPDX-License-Identifier: BSD-3-Clause
+
+}}
+
+
+__all__ = ['KDTree', 'KDTree64', 'KDTree32']
+
+{{for name_suffix, INPUT_DTYPE_t, INPUT_DTYPE in implementation_specific_values}}
+
+DOC_DICT{{name_suffix}} = {
+    'BinaryTree': 'KDTree{{name_suffix}}',
+    'binary_tree': 'kd_tree{{name_suffix}}',
+}
+
+VALID_METRICS{{name_suffix}} = [
+    'EuclideanDistance{{name_suffix}}',
+    'ManhattanDistance{{name_suffix}}',
+    'ChebyshevDistance{{name_suffix}}',
+    'MinkowskiDistance{{name_suffix}}'
+]
+
+{{endfor}}
+
+include "_binary_tree.pxi"
+
+{{for name_suffix, INPUT_DTYPE_t, INPUT_DTYPE in implementation_specific_values}}
+
+# Inherit KDTree{{name_suffix}} from BinaryTree{{name_suffix}}
+cdef class KDTree{{name_suffix}}(BinaryTree{{name_suffix}}):
+    __doc__ = CLASS_DOC.format(**DOC_DICT{{name_suffix}})
+    pass
+
+{{endfor}}
+
+
+# ----------------------------------------------------------------------
+# The functions below specialized the Binary Tree as a KD Tree
+#
+#   Note that these functions use the concept of "reduced distance".
+#   The reduced distance, defined for some metrics, is a quantity which
+#   is more efficient to compute than the distance, but preserves the
+#   relative rankings of the true distance.  For example, the reduced
+#   distance for the Euclidean metric is the squared-euclidean distance.
+#   For some metrics, the reduced distance is simply the distance.
+
+{{for name_suffix, INPUT_DTYPE_t, INPUT_DTYPE in implementation_specific_values}}
+
+cdef int allocate_data{{name_suffix}}(
+    BinaryTree{{name_suffix}} tree,
+    intp_t n_nodes,
+    intp_t n_features,
+) except -1:
+    """Allocate arrays needed for the KD Tree"""
+    tree.node_bounds = np.zeros((2, n_nodes, n_features), dtype={{INPUT_DTYPE}})
+    return 0
+
+
+cdef int init_node{{name_suffix}}(
+    BinaryTree{{name_suffix}} tree,
+    NodeData_t[::1] node_data,
+    intp_t i_node,
+    intp_t idx_start,
+    intp_t idx_end,
+) except -1:
+    """Initialize the node for the dataset stored in tree.data"""
+    cdef intp_t n_features = tree.data.shape[1]
+    cdef intp_t i, j
+    cdef float64_t rad = 0
+
+    cdef {{INPUT_DTYPE_t}}* lower_bounds = &tree.node_bounds[0, i_node, 0]
+    cdef {{INPUT_DTYPE_t}}* upper_bounds = &tree.node_bounds[1, i_node, 0]
+    cdef const {{INPUT_DTYPE_t}}* data = &tree.data[0, 0]
+    cdef const intp_t* idx_array = &tree.idx_array[0]
+
+    cdef const {{INPUT_DTYPE_t}}* data_row
+
+    # determine Node bounds
+    for j in range(n_features):
+        lower_bounds[j] = INF
+        upper_bounds[j] = -INF
+
+    # Compute the actual data range.  At build time, this is slightly
+    # slower than using the previously-computed bounds of the parent node,
+    # but leads to more compact trees and thus faster queries.
+    for i in range(idx_start, idx_end):
+        data_row = data + idx_array[i] * n_features
+        for j in range(n_features):
+            lower_bounds[j] = fmin(lower_bounds[j], data_row[j])
+            upper_bounds[j] = fmax(upper_bounds[j], data_row[j])
+
+    for j in range(n_features):
+        if tree.dist_metric.p == INF:
+            rad = fmax(rad, 0.5 * (upper_bounds[j] - lower_bounds[j]))
+        else:
+            rad += pow(0.5 * abs(upper_bounds[j] - lower_bounds[j]),
+                       tree.dist_metric.p)
+
+    node_data[i_node].idx_start = idx_start
+    node_data[i_node].idx_end = idx_end
+
+    # The radius will hold the size of the circumscribed hypersphere measured
+    # with the specified metric: in querying, this is used as a measure of the
+    # size of each node when deciding which nodes to split.
+    node_data[i_node].radius = pow(rad, 1. / tree.dist_metric.p)
+    return 0
+
+
+cdef float64_t min_rdist{{name_suffix}}(
+    BinaryTree{{name_suffix}} tree,
+    intp_t i_node,
+    const {{INPUT_DTYPE_t}}* pt,
+) except -1 nogil:
+    """Compute the minimum reduced-distance between a point and a node"""
+    cdef intp_t n_features = tree.data.shape[1]
+    cdef float64_t d, d_lo, d_hi, rdist=0.0
+    cdef intp_t j
+
+    if tree.dist_metric.p == INF:
+        for j in range(n_features):
+            d_lo = tree.node_bounds[0, i_node, j] - pt[j]
+            d_hi = pt[j] - tree.node_bounds[1, i_node, j]
+            d = (d_lo + fabs(d_lo)) + (d_hi + fabs(d_hi))
+            rdist = fmax(rdist, 0.5 * d)
+    else:
+        # here we'll use the fact that x + abs(x) = 2 * max(x, 0)
+        for j in range(n_features):
+            d_lo = tree.node_bounds[0, i_node, j] - pt[j]
+            d_hi = pt[j] - tree.node_bounds[1, i_node, j]
+            d = (d_lo + fabs(d_lo)) + (d_hi + fabs(d_hi))
+            rdist += pow(0.5 * d, tree.dist_metric.p)
+
+    return rdist
+
+
+cdef float64_t min_dist{{name_suffix}}(
+    BinaryTree{{name_suffix}} tree,
+    intp_t i_node,
+    const {{INPUT_DTYPE_t}}* pt,
+) except -1:
+    """Compute the minimum distance between a point and a node"""
+    if tree.dist_metric.p == INF:
+        return min_rdist{{name_suffix}}(tree, i_node, pt)
+    else:
+        return pow(
+            min_rdist{{name_suffix}}(tree, i_node, pt),
+            1. / tree.dist_metric.p
+        )
+
+
+cdef float64_t max_rdist{{name_suffix}}(
+    BinaryTree{{name_suffix}} tree,
+    intp_t i_node,
+    const {{INPUT_DTYPE_t}}* pt,
+) except -1:
+    """Compute the maximum reduced-distance between a point and a node"""
+    cdef intp_t n_features = tree.data.shape[1]
+
+    cdef float64_t d_lo, d_hi, rdist=0.0
+    cdef intp_t j
+
+    if tree.dist_metric.p == INF:
+        for j in range(n_features):
+            rdist = fmax(rdist, fabs(pt[j] - tree.node_bounds[0, i_node, j]))
+            rdist = fmax(rdist, fabs(pt[j] - tree.node_bounds[1, i_node, j]))
+    else:
+        for j in range(n_features):
+            d_lo = fabs(pt[j] - tree.node_bounds[0, i_node, j])
+            d_hi = fabs(pt[j] - tree.node_bounds[1, i_node, j])
+            rdist += pow(fmax(d_lo, d_hi), tree.dist_metric.p)
+
+    return rdist
+
+
+cdef float64_t max_dist{{name_suffix}}(
+    BinaryTree{{name_suffix}} tree,
+    intp_t i_node,
+    const {{INPUT_DTYPE_t}}* pt,
+) except -1:
+    """Compute the maximum distance between a point and a node"""
+    if tree.dist_metric.p == INF:
+        return max_rdist{{name_suffix}}(tree, i_node, pt)
+    else:
+        return pow(
+            max_rdist{{name_suffix}}(tree, i_node, pt),
+            1. / tree.dist_metric.p
+        )
+
+
+cdef inline int min_max_dist{{name_suffix}}(
+    BinaryTree{{name_suffix}} tree,
+    intp_t i_node,
+    const {{INPUT_DTYPE_t}}* pt,
+    float64_t* min_dist,
+    float64_t* max_dist,
+) except -1 nogil:
+    """Compute the minimum and maximum distance between a point and a node"""
+    cdef intp_t n_features = tree.data.shape[1]
+
+    cdef float64_t d, d_lo, d_hi
+    cdef intp_t j
+
+    min_dist[0] = 0.0
+    max_dist[0] = 0.0
+
+    if tree.dist_metric.p == INF:
+        for j in range(n_features):
+            d_lo = tree.node_bounds[0, i_node, j] - pt[j]
+            d_hi = pt[j] - tree.node_bounds[1, i_node, j]
+            d = (d_lo + fabs(d_lo)) + (d_hi + fabs(d_hi))
+            min_dist[0] = fmax(min_dist[0], 0.5 * d)
+            max_dist[0] = fmax(max_dist[0], fabs(d_lo))
+            max_dist[0] = fmax(max_dist[0], fabs(d_hi))
+    else:
+        # as above, use the fact that x + abs(x) = 2 * max(x, 0)
+        for j in range(n_features):
+            d_lo = tree.node_bounds[0, i_node, j] - pt[j]
+            d_hi = pt[j] - tree.node_bounds[1, i_node, j]
+            d = (d_lo + fabs(d_lo)) + (d_hi + fabs(d_hi))
+            min_dist[0] += pow(0.5 * d, tree.dist_metric.p)
+            max_dist[0] += pow(fmax(fabs(d_lo), fabs(d_hi)),
+                               tree.dist_metric.p)
+
+        min_dist[0] = pow(min_dist[0], 1. / tree.dist_metric.p)
+        max_dist[0] = pow(max_dist[0], 1. / tree.dist_metric.p)
+
+    return 0
+
+
+cdef inline float64_t min_rdist_dual{{name_suffix}}(
+    BinaryTree{{name_suffix}} tree1,
+    intp_t i_node1,
+    BinaryTree{{name_suffix}} tree2,
+    intp_t i_node2,
+) except -1:
+    """Compute the minimum reduced distance between two nodes"""
+    cdef intp_t n_features = tree1.data.shape[1]
+
+    cdef float64_t d, d1, d2, rdist=0.0
+    cdef intp_t j
+
+    if tree1.dist_metric.p == INF:
+        for j in range(n_features):
+            d1 = (tree1.node_bounds[0, i_node1, j]
+                  - tree2.node_bounds[1, i_node2, j])
+            d2 = (tree2.node_bounds[0, i_node2, j]
+                  - tree1.node_bounds[1, i_node1, j])
+            d = (d1 + fabs(d1)) + (d2 + fabs(d2))
+
+            rdist = fmax(rdist, 0.5 * d)
+    else:
+        # here we'll use the fact that x + abs(x) = 2 * max(x, 0)
+        for j in range(n_features):
+            d1 = (tree1.node_bounds[0, i_node1, j]
+                  - tree2.node_bounds[1, i_node2, j])
+            d2 = (tree2.node_bounds[0, i_node2, j]
+                  - tree1.node_bounds[1, i_node1, j])
+            d = (d1 + fabs(d1)) + (d2 + fabs(d2))
+
+            rdist += pow(0.5 * d, tree1.dist_metric.p)
+
+    return rdist
+
+
+cdef inline float64_t min_dist_dual{{name_suffix}}(
+    BinaryTree{{name_suffix}} tree1,
+    intp_t i_node1,
+    BinaryTree{{name_suffix}} tree2,
+    intp_t i_node2,
+) except -1:
+    """Compute the minimum distance between two nodes"""
+    return tree1.dist_metric._rdist_to_dist(
+        min_rdist_dual{{name_suffix}}(tree1, i_node1, tree2, i_node2)
+    )
+
+
+cdef inline float64_t max_rdist_dual{{name_suffix}}(
+    BinaryTree{{name_suffix}} tree1,
+    intp_t i_node1,
+    BinaryTree{{name_suffix}} tree2,
+    intp_t i_node2,
+) except -1:
+    """Compute the maximum reduced distance between two nodes"""
+    cdef intp_t n_features = tree1.data.shape[1]
+
+    cdef float64_t d1, d2, rdist=0.0
+    cdef intp_t j
+
+    if tree1.dist_metric.p == INF:
+        for j in range(n_features):
+            rdist = fmax(rdist, fabs(tree1.node_bounds[0, i_node1, j]
+                                     - tree2.node_bounds[1, i_node2, j]))
+            rdist = fmax(rdist, fabs(tree1.node_bounds[1, i_node1, j]
+                                     - tree2.node_bounds[0, i_node2, j]))
+    else:
+        for j in range(n_features):
+            d1 = fabs(tree1.node_bounds[0, i_node1, j]
+                      - tree2.node_bounds[1, i_node2, j])
+            d2 = fabs(tree1.node_bounds[1, i_node1, j]
+                      - tree2.node_bounds[0, i_node2, j])
+            rdist += pow(fmax(d1, d2), tree1.dist_metric.p)
+
+    return rdist
+
+
+cdef inline float64_t max_dist_dual{{name_suffix}}(
+    BinaryTree{{name_suffix}} tree1,
+    intp_t i_node1,
+    BinaryTree{{name_suffix}} tree2,
+    intp_t i_node2,
+) except -1:
+    """Compute the maximum distance between two nodes"""
+    return tree1.dist_metric._rdist_to_dist(
+        max_rdist_dual{{name_suffix}}(tree1, i_node1, tree2, i_node2)
+    )
+
+{{endfor}}
+
+
+class KDTree(KDTree64):
+    __doc__ = CLASS_DOC.format(BinaryTree="KDTree")
+    pass

linedance-app/venv/lib/python3.12/site-packages/sklearn/neighbors/_kde.py

@@ -0,0 +1,363 @@
+"""
+Kernel Density Estimation
+-------------------------
+"""
+
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
+import itertools
+from numbers import Integral, Real
+
+import numpy as np
+from scipy.special import gammainc
+
+from sklearn.base import BaseEstimator, _fit_context
+from sklearn.neighbors._ball_tree import BallTree
+from sklearn.neighbors._base import VALID_METRICS
+from sklearn.neighbors._kd_tree import KDTree
+from sklearn.utils import check_random_state
+from sklearn.utils._param_validation import Interval, StrOptions
+from sklearn.utils.extmath import row_norms
+from sklearn.utils.validation import (
+    _check_sample_weight,
+    check_is_fitted,
+    validate_data,
+)
+
+VALID_KERNELS = [
+    "gaussian",
+    "tophat",
+    "epanechnikov",
+    "exponential",
+    "linear",
+    "cosine",
+]
+
+TREE_DICT = {"ball_tree": BallTree, "kd_tree": KDTree}
+
+
+# TODO: implement a brute force version for testing purposes
+# TODO: create a density estimation base class?
+class KernelDensity(BaseEstimator):
+    """Kernel Density Estimation.
+
+    Read more in the :ref:`User Guide <kernel_density>`.
+
+    Parameters
+    ----------
+    bandwidth : float or {"scott", "silverman"}, default=1.0
+        The bandwidth of the kernel. If bandwidth is a float, it defines the
+        bandwidth of the kernel. If bandwidth is a string, one of the estimation
+        methods is implemented.
+
+    algorithm : {'kd_tree', 'ball_tree', 'auto'}, default='auto'
+        The tree algorithm to use.
+
+    kernel : {'gaussian', 'tophat', 'epanechnikov', 'exponential', 'linear', \
+                 'cosine'}, default='gaussian'
+        The kernel to use.
+
+    metric : str, default='euclidean'
+        Metric to use for distance computation. See the
+        documentation of `scipy.spatial.distance
+        <https://docs.scipy.org/doc/scipy/reference/spatial.distance.html>`_ and
+        the metrics listed in
+        :class:`~sklearn.metrics.pairwise.distance_metrics` for valid metric
+        values.
+
+        Not all metrics are valid with all algorithms: refer to the
+        documentation of :class:`BallTree` and :class:`KDTree`. Note that the
+        normalization of the density output is correct only for the Euclidean
+        distance metric.
+
+    atol : float, default=0
+        The desired absolute tolerance of the result.  A larger tolerance will
+        generally lead to faster execution.
+
+    rtol : float, default=0
+        The desired relative tolerance of the result.  A larger tolerance will
+        generally lead to faster execution.
+
+    breadth_first : bool, default=True
+        If true (default), use a breadth-first approach to the problem.
+        Otherwise use a depth-first approach.
+
+    leaf_size : int, default=40
+        Specify the leaf size of the underlying tree.  See :class:`BallTree`
+        or :class:`KDTree` for details.
+
+    metric_params : dict, default=None
+        Additional parameters to be passed to the tree for use with the
+        metric.  For more information, see the documentation of
+        :class:`BallTree` or :class:`KDTree`.
+
+    Attributes
+    ----------
+    n_features_in_ : int
+        Number of features seen during :term:`fit`.
+
+        .. versionadded:: 0.24
+
+    tree_ : ``BinaryTree`` instance
+        The tree algorithm for fast generalized N-point problems.
+
+    feature_names_in_ : ndarray of shape (`n_features_in_`,)
+        Names of features seen during :term:`fit`. Defined only when `X`
+        has feature names that are all strings.
+
+    bandwidth_ : float
+        Value of the bandwidth, given directly by the bandwidth parameter or
+        estimated using the 'scott' or 'silverman' method.
+
+        .. versionadded:: 1.0
+
+    See Also
+    --------
+    sklearn.neighbors.KDTree : K-dimensional tree for fast generalized N-point
+        problems.
+    sklearn.neighbors.BallTree : Ball tree for fast generalized N-point
+        problems.
+
+    Examples
+    --------
+    Compute a gaussian kernel density estimate with a fixed bandwidth.
+
+    >>> from sklearn.neighbors import KernelDensity
+    >>> import numpy as np
+    >>> rng = np.random.RandomState(42)
+    >>> X = rng.random_sample((100, 3))
+    >>> kde = KernelDensity(kernel='gaussian', bandwidth=0.5).fit(X)
+    >>> log_density = kde.score_samples(X[:3])
+    >>> log_density
+    array([-1.52955942, -1.51462041, -1.60244657])
+    """
+
+    _parameter_constraints: dict = {
+        "bandwidth": [
+            Interval(Real, 0, None, closed="neither"),
+            StrOptions({"scott", "silverman"}),
+        ],
+        "algorithm": [StrOptions(set(TREE_DICT.keys()) | {"auto"})],
+        "kernel": [StrOptions(set(VALID_KERNELS))],
+        "metric": [
+            StrOptions(
+                set(itertools.chain(*[VALID_METRICS[alg] for alg in TREE_DICT.keys()]))
+            )
+        ],
+        "atol": [Interval(Real, 0, None, closed="left")],
+        "rtol": [Interval(Real, 0, None, closed="left")],
+        "breadth_first": ["boolean"],
+        "leaf_size": [Interval(Integral, 1, None, closed="left")],
+        "metric_params": [None, dict],
+    }
+
+    def __init__(
+        self,
+        *,
+        bandwidth=1.0,
+        algorithm="auto",
+        kernel="gaussian",
+        metric="euclidean",
+        atol=0,
+        rtol=0,
+        breadth_first=True,
+        leaf_size=40,
+        metric_params=None,
+    ):
+        self.algorithm = algorithm
+        self.bandwidth = bandwidth
+        self.kernel = kernel
+        self.metric = metric
+        self.atol = atol
+        self.rtol = rtol
+        self.breadth_first = breadth_first
+        self.leaf_size = leaf_size
+        self.metric_params = metric_params
+
+    def _choose_algorithm(self, algorithm, metric):
+        # given the algorithm string + metric string, choose the optimal
+        # algorithm to compute the result.
+        if algorithm == "auto":
+            # use KD Tree if possible
+            if metric in KDTree.valid_metrics:
+                return "kd_tree"
+            elif metric in BallTree.valid_metrics:
+                return "ball_tree"
+        else:  # kd_tree or ball_tree
+            if metric not in TREE_DICT[algorithm].valid_metrics:
+                raise ValueError(
+                    "invalid metric for {0}: '{1}'".format(TREE_DICT[algorithm], metric)
+                )
+            return algorithm
+
+    @_fit_context(
+        # KernelDensity.metric is not validated yet
+        prefer_skip_nested_validation=False
+    )
+    def fit(self, X, y=None, sample_weight=None):
+        """Fit the Kernel Density model on the data.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            List of n_features-dimensional data points.  Each row
+            corresponds to a single data point.
+
+        y : None
+            Ignored. This parameter exists only for compatibility with
+            :class:`~sklearn.pipeline.Pipeline`.
+
+        sample_weight : array-like of shape (n_samples,), default=None
+            List of sample weights attached to the data X.
+
+            .. versionadded:: 0.20
+
+        Returns
+        -------
+        self : object
+            Returns the instance itself.
+        """
+        algorithm = self._choose_algorithm(self.algorithm, self.metric)
+
+        if isinstance(self.bandwidth, str):
+            if self.bandwidth == "scott":
+                self.bandwidth_ = X.shape[0] ** (-1 / (X.shape[1] + 4))
+            elif self.bandwidth == "silverman":
+                self.bandwidth_ = (X.shape[0] * (X.shape[1] + 2) / 4) ** (
+                    -1 / (X.shape[1] + 4)
+                )
+        else:
+            self.bandwidth_ = self.bandwidth
+
+        X = validate_data(self, X, order="C", dtype=np.float64)
+
+        if sample_weight is not None:
+            sample_weight = _check_sample_weight(
+                sample_weight, X, dtype=np.float64, ensure_non_negative=True
+            )
+
+        kwargs = self.metric_params
+        if kwargs is None:
+            kwargs = {}
+        self.tree_ = TREE_DICT[algorithm](
+            X,
+            metric=self.metric,
+            leaf_size=self.leaf_size,
+            sample_weight=sample_weight,
+            **kwargs,
+        )
+        return self
+
+    def score_samples(self, X):
+        """Compute the log-likelihood of each sample under the model.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            An array of points to query.  Last dimension should match dimension
+            of training data (n_features).
+
+        Returns
+        -------
+        density : ndarray of shape (n_samples,)
+            Log-likelihood of each sample in `X`. These are normalized to be
+            probability densities, so values will be low for high-dimensional
+            data.
+        """
+        check_is_fitted(self)
+        # The returned density is normalized to the number of points.
+        # For it to be a probability, we must scale it.  For this reason
+        # we'll also scale atol.
+        X = validate_data(self, X, order="C", dtype=np.float64, reset=False)
+        if self.tree_.sample_weight is None:
+            N = self.tree_.data.shape[0]
+        else:
+            N = self.tree_.sum_weight
+        atol_N = self.atol * N
+        log_density = self.tree_.kernel_density(
+            X,
+            h=self.bandwidth_,
+            kernel=self.kernel,
+            atol=atol_N,
+            rtol=self.rtol,
+            breadth_first=self.breadth_first,
+            return_log=True,
+        )
+        log_density -= np.log(N)
+        return log_density
+
+    def score(self, X, y=None):
+        """Compute the total log-likelihood under the model.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            List of n_features-dimensional data points.  Each row
+            corresponds to a single data point.
+
+        y : None
+            Ignored. This parameter exists only for compatibility with
+            :class:`~sklearn.pipeline.Pipeline`.
+
+        Returns
+        -------
+        logprob : float
+            Total log-likelihood of the data in X. This is normalized to be a
+            probability density, so the value will be low for high-dimensional
+            data.
+        """
+        return np.sum(self.score_samples(X))
+
+    def sample(self, n_samples=1, random_state=None):
+        """Generate random samples from the model.
+
+        Currently, this is implemented only for gaussian and tophat kernels.
+
+        Parameters
+        ----------
+        n_samples : int, default=1
+            Number of samples to generate.
+
+        random_state : int, RandomState instance or None, default=None
+            Determines random number generation used to generate
+            random samples. Pass an int for reproducible results
+            across multiple function calls.
+            See :term:`Glossary <random_state>`.
+
+        Returns
+        -------
+        X : array-like of shape (n_samples, n_features)
+            List of samples.
+        """
+        check_is_fitted(self)
+        # TODO: implement sampling for other valid kernel shapes
+        if self.kernel not in ["gaussian", "tophat"]:
+            raise NotImplementedError()
+
+        data = np.asarray(self.tree_.data)
+
+        rng = check_random_state(random_state)
+        u = rng.uniform(0, 1, size=n_samples)
+        if self.tree_.sample_weight is None:
+            i = (u * data.shape[0]).astype(np.int64)
+        else:
+            cumsum_weight = np.cumsum(np.asarray(self.tree_.sample_weight))
+            sum_weight = cumsum_weight[-1]
+            i = np.searchsorted(cumsum_weight, u * sum_weight)
+        if self.kernel == "gaussian":
+            return np.atleast_2d(rng.normal(data[i], self.bandwidth_))
+
+        elif self.kernel == "tophat":
+            # we first draw points from a d-dimensional normal distribution,
+            # then use an incomplete gamma function to map them to a uniform
+            # d-dimensional tophat distribution.
+            dim = data.shape[1]
+            X = rng.normal(size=(n_samples, dim))
+            s_sq = row_norms(X, squared=True)
+            correction = (
+                gammainc(0.5 * dim, 0.5 * s_sq) ** (1.0 / dim)
+                * self.bandwidth_
+                / np.sqrt(s_sq)
+            )
+            return data[i] + X * correction[:, np.newaxis]

linedance-app/venv/lib/python3.12/site-packages/sklearn/neighbors/_lof.py

@@ -0,0 +1,521 @@
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
+import warnings
+from numbers import Real
+
+import numpy as np
+
+from sklearn.base import OutlierMixin, _fit_context
+from sklearn.neighbors._base import KNeighborsMixin, NeighborsBase
+from sklearn.utils import check_array
+from sklearn.utils._param_validation import Interval, StrOptions
+from sklearn.utils.metaestimators import available_if
+from sklearn.utils.validation import check_is_fitted
+
+__all__ = ["LocalOutlierFactor"]
+
+
+class LocalOutlierFactor(KNeighborsMixin, OutlierMixin, NeighborsBase):
+    """Unsupervised Outlier Detection using the Local Outlier Factor (LOF).
+
+    The anomaly score of each sample is called the Local Outlier Factor.
+    It measures the local deviation of the density of a given sample with respect
+    to its neighbors.
+    It is local in that the anomaly score depends on how isolated the object
+    is with respect to the surrounding neighborhood.
+    More precisely, locality is given by k-nearest neighbors, whose distance
+    is used to estimate the local density.
+    By comparing the local density of a sample to the local densities of its
+    neighbors, one can identify samples that have a substantially lower density
+    than their neighbors. These are considered outliers.
+
+    .. versionadded:: 0.19
+
+    Parameters
+    ----------
+    n_neighbors : int, default=20
+        Number of neighbors to use by default for :meth:`kneighbors` queries.
+        If n_neighbors is larger than the number of samples provided,
+        all samples will be used.
+
+    algorithm : {'auto', 'ball_tree', 'kd_tree', 'brute'}, default='auto'
+        Algorithm used to compute the nearest neighbors:
+
+        - 'ball_tree' will use :class:`BallTree`
+        - 'kd_tree' will use :class:`KDTree`
+        - 'brute' will use a brute-force search.
+        - 'auto' will attempt to decide the most appropriate algorithm
+          based on the values passed to :meth:`fit` method.
+
+        Note: fitting on sparse input will override the setting of
+        this parameter, using brute force.
+
+    leaf_size : int, default=30
+        Leaf is size passed to :class:`BallTree` or :class:`KDTree`. This can
+        affect the speed of the construction and query, as well as the memory
+        required to store the tree. The optimal value depends on the
+        nature of the problem.
+
+    metric : str or callable, default='minkowski'
+        Metric to use for distance computation. Default is "minkowski", which
+        results in the standard Euclidean distance when p = 2. See the
+        documentation of `scipy.spatial.distance
+        <https://docs.scipy.org/doc/scipy/reference/spatial.distance.html>`_ and
+        the metrics listed in
+        :class:`~sklearn.metrics.pairwise.distance_metrics` for valid metric
+        values.
+
+        If metric is "precomputed", X is assumed to be a distance matrix and
+        must be square during fit. X may be a :term:`sparse graph`, in which
+        case only "nonzero" elements may be considered neighbors.
+
+        If metric is a callable function, it takes two arrays representing 1D
+        vectors as inputs and must return one value indicating the distance
+        between those vectors. This works for Scipy's metrics, but is less
+        efficient than passing the metric name as a string.
+
+    p : float, default=2
+        Parameter for the Minkowski metric from
+        :func:`sklearn.metrics.pairwise_distances`. When p = 1, this
+        is equivalent to using manhattan_distance (l1), and euclidean_distance
+        (l2) for p = 2. For arbitrary p, minkowski_distance (l_p) is used.
+
+    metric_params : dict, default=None
+        Additional keyword arguments for the metric function.
+
+    contamination : 'auto' or float, default='auto'
+        The amount of contamination of the data set, i.e. the proportion
+        of outliers in the data set. When fitting this is used to define the
+        threshold on the scores of the samples.
+
+        - if 'auto', the threshold is determined as in the
+          original paper,
+        - if a float, the contamination should be in the range (0, 0.5].
+
+        .. versionchanged:: 0.22
+           The default value of ``contamination`` changed from 0.1
+           to ``'auto'``.
+
+    novelty : bool, default=False
+        By default, LocalOutlierFactor is only meant to be used for outlier
+        detection (novelty=False). Set novelty to True if you want to use
+        LocalOutlierFactor for novelty detection. In this case be aware that
+        you should only use predict, decision_function and score_samples
+        on new unseen data and not on the training set; and note that the
+        results obtained this way may differ from the standard LOF results.
+
+        .. versionadded:: 0.20
+
+    n_jobs : int, default=None
+        The number of parallel jobs to run for neighbors search.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See :term:`Glossary <n_jobs>`
+        for more details.
+
+    Attributes
+    ----------
+    negative_outlier_factor_ : ndarray of shape (n_samples,)
+        The opposite LOF of the training samples. The higher, the more normal.
+        Inliers tend to have a LOF score close to 1
+        (``negative_outlier_factor_`` close to -1), while outliers tend to have
+        a larger LOF score.
+
+        The local outlier factor (LOF) of a sample captures its
+        supposed 'degree of abnormality'.
+        It is the average of the ratio of the local reachability density of
+        a sample and those of its k-nearest neighbors.
+
+    n_neighbors_ : int
+        The actual number of neighbors used for :meth:`kneighbors` queries.
+
+    offset_ : float
+        Offset used to obtain binary labels from the raw scores.
+        Observations having a negative_outlier_factor smaller than `offset_`
+        are detected as abnormal.
+        The offset is set to -1.5 (inliers score around -1), except when a
+        contamination parameter different than "auto" is provided. In that
+        case, the offset is defined in such a way we obtain the expected
+        number of outliers in training.
+
+        .. versionadded:: 0.20
+
+    effective_metric_ : str
+        The effective metric used for the distance computation.
+
+    effective_metric_params_ : dict
+        The effective additional keyword arguments for the metric function.
+
+    n_features_in_ : int
+        Number of features seen during :term:`fit`.
+
+        .. versionadded:: 0.24
+
+    feature_names_in_ : ndarray of shape (`n_features_in_`,)
+        Names of features seen during :term:`fit`. Defined only when `X`
+        has feature names that are all strings.
+
+        .. versionadded:: 1.0
+
+    n_samples_fit_ : int
+        It is the number of samples in the fitted data.
+
+    See Also
+    --------
+    sklearn.svm.OneClassSVM: Unsupervised Outlier Detection using
+        Support Vector Machine.
+
+    References
+    ----------
+    .. [1] Breunig, M. M., Kriegel, H. P., Ng, R. T., & Sander, J. (2000, May).
+           `LOF: identifying density-based local outliers.
+           <https://dl.acm.org/doi/pdf/10.1145/342009.335388>`_
+           In Proceedings of the 2000 ACM SIGMOD International Conference on
+           Management of Data, pp. 93-104.
+
+    Examples
+    --------
+    >>> import numpy as np
+    >>> from sklearn.neighbors import LocalOutlierFactor
+    >>> X = [[-1.1], [0.2], [101.1], [0.3]]
+    >>> clf = LocalOutlierFactor(n_neighbors=2)
+    >>> clf.fit_predict(X)
+    array([ 1,  1, -1,  1])
+    >>> clf.negative_outlier_factor_
+    array([ -0.9821,  -1.0370, -73.3697,  -0.9821])
+    """
+
+    _parameter_constraints: dict = {
+        **NeighborsBase._parameter_constraints,
+        "contamination": [
+            StrOptions({"auto"}),
+            Interval(Real, 0, 0.5, closed="right"),
+        ],
+        "novelty": ["boolean"],
+    }
+    _parameter_constraints.pop("radius")
+
+    def __init__(
+        self,
+        n_neighbors=20,
+        *,
+        algorithm="auto",
+        leaf_size=30,
+        metric="minkowski",
+        p=2,
+        metric_params=None,
+        contamination="auto",
+        novelty=False,
+        n_jobs=None,
+    ):
+        super().__init__(
+            n_neighbors=n_neighbors,
+            algorithm=algorithm,
+            leaf_size=leaf_size,
+            metric=metric,
+            p=p,
+            metric_params=metric_params,
+            n_jobs=n_jobs,
+        )
+        self.contamination = contamination
+        self.novelty = novelty
+
+    def _check_novelty_fit_predict(self):
+        if self.novelty:
+            msg = (
+                "fit_predict is not available when novelty=True. Use "
+                "novelty=False if you want to predict on the training set."
+            )
+            raise AttributeError(msg)
+        return True
+
+    @available_if(_check_novelty_fit_predict)
+    def fit_predict(self, X, y=None):
+        """Fit the model to the training set X and return the labels.
+
+        **Not available for novelty detection (when novelty is set to True).**
+        Label is 1 for an inlier and -1 for an outlier according to the LOF
+        score and the contamination parameter.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features), default=None
+            The query sample or samples to compute the Local Outlier Factor
+            w.r.t. the training samples.
+
+        y : Ignored
+            Not used, present for API consistency by convention.
+
+        Returns
+        -------
+        is_inlier : ndarray of shape (n_samples,)
+            Returns -1 for anomalies/outliers and 1 for inliers.
+        """
+
+        # As fit_predict would be different from fit.predict, fit_predict is
+        # only available for outlier detection (novelty=False)
+
+        return self.fit(X)._predict()
+
+    @_fit_context(
+        # LocalOutlierFactor.metric is not validated yet
+        prefer_skip_nested_validation=False
+    )
+    def fit(self, X, y=None):
+        """Fit the local outlier factor detector from the training dataset.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features) or \
+                (n_samples, n_samples) if metric='precomputed'
+            Training data.
+
+        y : Ignored
+            Not used, present for API consistency by convention.
+
+        Returns
+        -------
+        self : LocalOutlierFactor
+            The fitted local outlier factor detector.
+        """
+        self._fit(X)
+
+        n_samples = self.n_samples_fit_
+        if self.n_neighbors > n_samples:
+            warnings.warn(
+                "n_neighbors (%s) is greater than the "
+                "total number of samples (%s). n_neighbors "
+                "will be set to (n_samples - 1) for estimation."
+                % (self.n_neighbors, n_samples)
+            )
+        self.n_neighbors_ = max(1, min(self.n_neighbors, n_samples - 1))
+
+        self._distances_fit_X_, _neighbors_indices_fit_X_ = self.kneighbors(
+            n_neighbors=self.n_neighbors_
+        )
+
+        if self._fit_X.dtype == np.float32:
+            self._distances_fit_X_ = self._distances_fit_X_.astype(
+                self._fit_X.dtype,
+                copy=False,
+            )
+
+        self._lrd = self._local_reachability_density(
+            self._distances_fit_X_, _neighbors_indices_fit_X_
+        )
+
+        # Compute lof score over training samples to define offset_:
+        lrd_ratios_array = (
+            self._lrd[_neighbors_indices_fit_X_] / self._lrd[:, np.newaxis]
+        )
+
+        self.negative_outlier_factor_ = -np.mean(lrd_ratios_array, axis=1)
+
+        if self.contamination == "auto":
+            # inliers score around -1 (the higher, the less abnormal).
+            self.offset_ = -1.5
+        else:
+            self.offset_ = np.percentile(
+                self.negative_outlier_factor_, 100.0 * self.contamination
+            )
+
+        # Verify if negative_outlier_factor_ values are within acceptable range.
+        # Novelty must also be false to detect outliers
+        if np.min(self.negative_outlier_factor_) < -1e7 and not self.novelty:
+            warnings.warn(
+                "Duplicate values are leading to incorrect results. "
+                "Increase the number of neighbors for more accurate results."
+            )
+
+        return self
+
+    def _check_novelty_predict(self):
+        if not self.novelty:
+            msg = (
+                "predict is not available when novelty=False, use "
+                "fit_predict if you want to predict on training data. Use "
+                "novelty=True if you want to use LOF for novelty detection "
+                "and predict on new unseen data."
+            )
+            raise AttributeError(msg)
+        return True
+
+    @available_if(_check_novelty_predict)
+    def predict(self, X=None):
+        """Predict the labels (1 inlier, -1 outlier) of X according to LOF.
+
+        **Only available for novelty detection (when novelty is set to True).**
+        This method allows to generalize prediction to *new observations* (not
+        in the training set). Note that the result of ``clf.fit(X)`` then
+        ``clf.predict(X)`` with ``novelty=True`` may differ from the result
+        obtained by ``clf.fit_predict(X)`` with ``novelty=False``.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            The query sample or samples to compute the Local Outlier Factor
+            w.r.t. the training samples.
+
+        Returns
+        -------
+        is_inlier : ndarray of shape (n_samples,)
+            Returns -1 for anomalies/outliers and +1 for inliers.
+        """
+        return self._predict(X)
+
+    def _predict(self, X=None):
+        """Predict the labels (1 inlier, -1 outlier) of X according to LOF.
+
+        If X is None, returns the same as fit_predict(X_train).
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features), default=None
+            The query sample or samples to compute the Local Outlier Factor
+            w.r.t. the training samples. If None, makes prediction on the
+            training data without considering them as their own neighbors.
+
+        Returns
+        -------
+        is_inlier : ndarray of shape (n_samples,)
+            Returns -1 for anomalies/outliers and +1 for inliers.
+        """
+        check_is_fitted(self)
+
+        if X is not None:
+            shifted_opposite_lof_scores = self.decision_function(X)
+            is_inlier = np.ones(shifted_opposite_lof_scores.shape[0], dtype=int)
+            is_inlier[shifted_opposite_lof_scores < 0] = -1
+        else:
+            is_inlier = np.ones(self.n_samples_fit_, dtype=int)
+            is_inlier[self.negative_outlier_factor_ < self.offset_] = -1
+
+        return is_inlier
+
+    def _check_novelty_decision_function(self):
+        if not self.novelty:
+            msg = (
+                "decision_function is not available when novelty=False. "
+                "Use novelty=True if you want to use LOF for novelty "
+                "detection and compute decision_function for new unseen "
+                "data. Note that the opposite LOF of the training samples "
+                "is always available by considering the "
+                "negative_outlier_factor_ attribute."
+            )
+            raise AttributeError(msg)
+        return True
+
+    @available_if(_check_novelty_decision_function)
+    def decision_function(self, X):
+        """Shifted opposite of the Local Outlier Factor of X.
+
+        Bigger is better, i.e. large values correspond to inliers.
+
+        **Only available for novelty detection (when novelty is set to True).**
+        The shift offset allows a zero threshold for being an outlier.
+        The argument X is supposed to contain *new data*: if X contains a
+        point from training, it considers the later in its own neighborhood.
+        Also, the samples in X are not considered in the neighborhood of any
+        point.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            The query sample or samples to compute the Local Outlier Factor
+            w.r.t. the training samples.
+
+        Returns
+        -------
+        shifted_opposite_lof_scores : ndarray of shape (n_samples,)
+            The shifted opposite of the Local Outlier Factor of each input
+            samples. The lower, the more abnormal. Negative scores represent
+            outliers, positive scores represent inliers.
+        """
+        return self.score_samples(X) - self.offset_
+
+    def _check_novelty_score_samples(self):
+        if not self.novelty:
+            msg = (
+                "score_samples is not available when novelty=False. The "
+                "scores of the training samples are always available "
+                "through the negative_outlier_factor_ attribute. Use "
+                "novelty=True if you want to use LOF for novelty detection "
+                "and compute score_samples for new unseen data."
+            )
+            raise AttributeError(msg)
+        return True
+
+    @available_if(_check_novelty_score_samples)
+    def score_samples(self, X):
+        """Opposite of the Local Outlier Factor of X.
+
+        It is the opposite as bigger is better, i.e. large values correspond
+        to inliers.
+
+        **Only available for novelty detection (when novelty is set to True).**
+        The argument X is supposed to contain *new data*: if X contains a
+        point from training, it considers the later in its own neighborhood.
+        Also, the samples in X are not considered in the neighborhood of any
+        point. Because of this, the scores obtained via ``score_samples`` may
+        differ from the standard LOF scores.
+        The standard LOF scores for the training data is available via the
+        ``negative_outlier_factor_`` attribute.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            The query sample or samples to compute the Local Outlier Factor
+            w.r.t. the training samples.
+
+        Returns
+        -------
+        opposite_lof_scores : ndarray of shape (n_samples,)
+            The opposite of the Local Outlier Factor of each input samples.
+            The lower, the more abnormal.
+        """
+        check_is_fitted(self)
+        X = check_array(X, accept_sparse="csr")
+
+        distances_X, neighbors_indices_X = self.kneighbors(
+            X, n_neighbors=self.n_neighbors_
+        )
+
+        if X.dtype == np.float32:
+            distances_X = distances_X.astype(X.dtype, copy=False)
+
+        X_lrd = self._local_reachability_density(
+            distances_X,
+            neighbors_indices_X,
+        )
+
+        lrd_ratios_array = self._lrd[neighbors_indices_X] / X_lrd[:, np.newaxis]
+
+        # as bigger is better:
+        return -np.mean(lrd_ratios_array, axis=1)
+
+    def _local_reachability_density(self, distances_X, neighbors_indices):
+        """The local reachability density (LRD)
+
+        The LRD of a sample is the inverse of the average reachability
+        distance of its k-nearest neighbors.
+
+        Parameters
+        ----------
+        distances_X : ndarray of shape (n_queries, self.n_neighbors)
+            Distances to the neighbors (in the training samples `self._fit_X`)
+            of each query point to compute the LRD.
+
+        neighbors_indices : ndarray of shape (n_queries, self.n_neighbors)
+            Neighbors indices (of each query point) among training samples
+            self._fit_X.
+
+        Returns
+        -------
+        local_reachability_density : ndarray of shape (n_queries,)
+            The local reachability density of each sample.
+        """
+        dist_k = self._distances_fit_X_[neighbors_indices, self.n_neighbors_ - 1]
+        reach_dist_array = np.maximum(distances_X, dist_k)
+
+        # 1e-10 to avoid `nan' when nb of duplicates > n_neighbors_:
+        return 1.0 / (np.mean(reach_dist_array, axis=1) + 1e-10)

linedance-app/venv/lib/python3.12/site-packages/sklearn/neighbors/_nca.py

@@ -0,0 +1,534 @@
+"""
+Neighborhood Component Analysis
+"""
+
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
+import sys
+import time
+from numbers import Integral, Real
+from warnings import warn
+
+import numpy as np
+from scipy.optimize import minimize
+
+from sklearn.base import (
+    BaseEstimator,
+    ClassNamePrefixFeaturesOutMixin,
+    TransformerMixin,
+    _fit_context,
+)
+from sklearn.decomposition import PCA
+from sklearn.exceptions import ConvergenceWarning
+from sklearn.metrics import pairwise_distances
+from sklearn.preprocessing import LabelEncoder
+from sklearn.utils._param_validation import Interval, StrOptions
+from sklearn.utils.extmath import softmax
+from sklearn.utils.fixes import _get_additional_lbfgs_options_dict
+from sklearn.utils.multiclass import check_classification_targets
+from sklearn.utils.random import check_random_state
+from sklearn.utils.validation import check_array, check_is_fitted, validate_data
+
+
+class NeighborhoodComponentsAnalysis(
+    ClassNamePrefixFeaturesOutMixin, TransformerMixin, BaseEstimator
+):
+    """Neighborhood Components Analysis.
+
+    Neighborhood Component Analysis (NCA) is a machine learning algorithm for
+    metric learning. It learns a linear transformation in a supervised fashion
+    to improve the classification accuracy of a stochastic nearest neighbors
+    rule in the transformed space.
+
+    Read more in the :ref:`User Guide <nca>`.
+
+    Parameters
+    ----------
+    n_components : int, default=None
+        Preferred dimensionality of the projected space.
+        If None it will be set to `n_features`.
+
+    init : {'auto', 'pca', 'lda', 'identity', 'random'} or ndarray of shape \
+            (n_features_a, n_features_b), default='auto'
+        Initialization of the linear transformation. Possible options are
+        `'auto'`, `'pca'`, `'lda'`, `'identity'`, `'random'`, and a numpy
+        array of shape `(n_features_a, n_features_b)`.
+
+        - `'auto'`
+            Depending on `n_components`, the most reasonable initialization
+            is chosen. If `n_components <= min(n_features, n_classes - 1)`
+            we use `'lda'`, as it uses labels information. If not, but
+            `n_components < min(n_features, n_samples)`, we use `'pca'`, as
+            it projects data in meaningful directions (those of higher
+            variance). Otherwise, we just use `'identity'`.
+
+        - `'pca'`
+            `n_components` principal components of the inputs passed
+            to :meth:`fit` will be used to initialize the transformation.
+            (See :class:`~sklearn.decomposition.PCA`)
+
+        - `'lda'`
+            `min(n_components, n_classes)` most discriminative
+            components of the inputs passed to :meth:`fit` will be used to
+            initialize the transformation. (If `n_components > n_classes`,
+            the rest of the components will be zero.) (See
+            :class:`~sklearn.discriminant_analysis.LinearDiscriminantAnalysis`)
+
+        - `'identity'`
+            If `n_components` is strictly smaller than the
+            dimensionality of the inputs passed to :meth:`fit`, the identity
+            matrix will be truncated to the first `n_components` rows.
+
+        - `'random'`
+            The initial transformation will be a random array of shape
+            `(n_components, n_features)`. Each value is sampled from the
+            standard normal distribution.
+
+        - numpy array
+            `n_features_b` must match the dimensionality of the inputs passed
+            to :meth:`fit` and n_features_a must be less than or equal to that.
+            If `n_components` is not `None`, `n_features_a` must match it.
+
+    warm_start : bool, default=False
+        If `True` and :meth:`fit` has been called before, the solution of the
+        previous call to :meth:`fit` is used as the initial linear
+        transformation (`n_components` and `init` will be ignored).
+
+    max_iter : int, default=50
+        Maximum number of iterations in the optimization.
+
+    tol : float, default=1e-5
+        Convergence tolerance for the optimization.
+
+    callback : callable, default=None
+        If not `None`, this function is called after every iteration of the
+        optimizer, taking as arguments the current solution (flattened
+        transformation matrix) and the number of iterations. This might be
+        useful in case one wants to examine or store the transformation
+        found after each iteration.
+
+    verbose : int, default=0
+        If 0, no progress messages will be printed.
+        If 1, progress messages will be printed to stdout.
+        If > 1, progress messages will be printed and the `disp`
+        parameter of :func:`scipy.optimize.minimize` will be set to
+        `verbose - 2`.
+
+    random_state : int or numpy.RandomState, default=None
+        A pseudo random number generator object or a seed for it if int. If
+        `init='random'`, `random_state` is used to initialize the random
+        transformation. If `init='pca'`, `random_state` is passed as an
+        argument to PCA when initializing the transformation. Pass an int
+        for reproducible results across multiple function calls.
+        See :term:`Glossary <random_state>`.
+
+    Attributes
+    ----------
+    components_ : ndarray of shape (n_components, n_features)
+        The linear transformation learned during fitting.
+
+    n_features_in_ : int
+        Number of features seen during :term:`fit`.
+
+        .. versionadded:: 0.24
+
+    n_iter_ : int
+        Counts the number of iterations performed by the optimizer.
+
+    random_state_ : numpy.RandomState
+        Pseudo random number generator object used during initialization.
+
+    feature_names_in_ : ndarray of shape (`n_features_in_`,)
+        Names of features seen during :term:`fit`. Defined only when `X`
+        has feature names that are all strings.
+
+        .. versionadded:: 1.0
+
+    See Also
+    --------
+    sklearn.discriminant_analysis.LinearDiscriminantAnalysis : Linear
+        Discriminant Analysis.
+    sklearn.decomposition.PCA : Principal component analysis (PCA).
+
+    References
+    ----------
+    .. [1] J. Goldberger, G. Hinton, S. Roweis, R. Salakhutdinov.
+           "Neighbourhood Components Analysis". Advances in Neural Information
+           Processing Systems. 17, 513-520, 2005.
+           https://www.cs.toronto.edu/~rsalakhu/papers/ncanips.pdf
+
+    .. [2] Wikipedia entry on Neighborhood Components Analysis
+           https://en.wikipedia.org/wiki/Neighbourhood_components_analysis
+
+    Examples
+    --------
+    >>> from sklearn.neighbors import NeighborhoodComponentsAnalysis
+    >>> from sklearn.neighbors import KNeighborsClassifier
+    >>> from sklearn.datasets import load_iris
+    >>> from sklearn.model_selection import train_test_split
+    >>> X, y = load_iris(return_X_y=True)
+    >>> X_train, X_test, y_train, y_test = train_test_split(X, y,
+    ... stratify=y, test_size=0.7, random_state=42)
+    >>> nca = NeighborhoodComponentsAnalysis(random_state=42)
+    >>> nca.fit(X_train, y_train)
+    NeighborhoodComponentsAnalysis(...)
+    >>> knn = KNeighborsClassifier(n_neighbors=3)
+    >>> knn.fit(X_train, y_train)
+    KNeighborsClassifier(...)
+    >>> print(knn.score(X_test, y_test))
+    0.933333...
+    >>> knn.fit(nca.transform(X_train), y_train)
+    KNeighborsClassifier(...)
+    >>> print(knn.score(nca.transform(X_test), y_test))
+    0.961904...
+    """
+
+    _parameter_constraints: dict = {
+        "n_components": [
+            Interval(Integral, 1, None, closed="left"),
+            None,
+        ],
+        "init": [
+            StrOptions({"auto", "pca", "lda", "identity", "random"}),
+            np.ndarray,
+        ],
+        "warm_start": ["boolean"],
+        "max_iter": [Interval(Integral, 1, None, closed="left")],
+        "tol": [Interval(Real, 0, None, closed="left")],
+        "callback": [callable, None],
+        "verbose": ["verbose"],
+        "random_state": ["random_state"],
+    }
+
+    def __init__(
+        self,
+        n_components=None,
+        *,
+        init="auto",
+        warm_start=False,
+        max_iter=50,
+        tol=1e-5,
+        callback=None,
+        verbose=0,
+        random_state=None,
+    ):
+        self.n_components = n_components
+        self.init = init
+        self.warm_start = warm_start
+        self.max_iter = max_iter
+        self.tol = tol
+        self.callback = callback
+        self.verbose = verbose
+        self.random_state = random_state
+
+    @_fit_context(prefer_skip_nested_validation=True)
+    def fit(self, X, y):
+        """Fit the model according to the given training data.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            The training samples.
+
+        y : array-like of shape (n_samples,)
+            The corresponding training labels.
+
+        Returns
+        -------
+        self : object
+            Fitted estimator.
+        """
+        # Validate the inputs X and y, and converts y to numerical classes.
+        X, y = validate_data(self, X, y, ensure_min_samples=2)
+        check_classification_targets(y)
+        y = LabelEncoder().fit_transform(y)
+
+        # Check the preferred dimensionality of the projected space
+        if self.n_components is not None and self.n_components > X.shape[1]:
+            raise ValueError(
+                "The preferred dimensionality of the "
+                f"projected space `n_components` ({self.n_components}) cannot "
+                "be greater than the given data "
+                f"dimensionality ({X.shape[1]})!"
+            )
+        # If warm_start is enabled, check that the inputs are consistent
+        if (
+            self.warm_start
+            and hasattr(self, "components_")
+            and self.components_.shape[1] != X.shape[1]
+        ):
+            raise ValueError(
+                f"The new inputs dimensionality ({X.shape[1]}) does not "
+                "match the input dimensionality of the "
+                f"previously learned transformation ({self.components_.shape[1]})."
+            )
+        # Check how the linear transformation should be initialized
+        init = self.init
+        if isinstance(init, np.ndarray):
+            init = check_array(init)
+            # Assert that init.shape[1] = X.shape[1]
+            if init.shape[1] != X.shape[1]:
+                raise ValueError(
+                    f"The input dimensionality ({init.shape[1]}) of the given "
+                    "linear transformation `init` must match the "
+                    f"dimensionality of the given inputs `X` ({X.shape[1]})."
+                )
+            # Assert that init.shape[0] <= init.shape[1]
+            if init.shape[0] > init.shape[1]:
+                raise ValueError(
+                    f"The output dimensionality ({init.shape[0]}) of the given "
+                    "linear transformation `init` cannot be "
+                    f"greater than its input dimensionality ({init.shape[1]})."
+                )
+            # Assert that self.n_components = init.shape[0]
+            if self.n_components is not None and self.n_components != init.shape[0]:
+                raise ValueError(
+                    "The preferred dimensionality of the "
+                    f"projected space `n_components` ({self.n_components}) does"
+                    " not match the output dimensionality of "
+                    "the given linear transformation "
+                    f"`init` ({init.shape[0]})!"
+                )
+
+        # Initialize the random generator
+        self.random_state_ = check_random_state(self.random_state)
+
+        # Measure the total training time
+        t_train = time.time()
+
+        # Compute a mask that stays fixed during optimization:
+        same_class_mask = y[:, np.newaxis] == y[np.newaxis, :]
+        # (n_samples, n_samples)
+
+        # Initialize the transformation
+        transformation = np.ravel(self._initialize(X, y, init))
+
+        # Create a dictionary of parameters to be passed to the optimizer
+        disp = self.verbose - 2 if self.verbose > 1 else -1
+        optimizer_params = {
+            "method": "L-BFGS-B",
+            "fun": self._loss_grad_lbfgs,
+            "args": (X, same_class_mask, -1.0),
+            "jac": True,
+            "x0": transformation,
+            "tol": self.tol,
+            "options": dict(
+                maxiter=self.max_iter,
+                **_get_additional_lbfgs_options_dict("disp", disp),
+            ),
+            "callback": self._callback,
+        }
+
+        # Call the optimizer
+        self.n_iter_ = 0
+        opt_result = minimize(**optimizer_params)
+
+        # Reshape the solution found by the optimizer
+        self.components_ = opt_result.x.reshape(-1, X.shape[1])
+
+        # Stop timer
+        t_train = time.time() - t_train
+        if self.verbose:
+            cls_name = self.__class__.__name__
+
+            # Warn the user if the algorithm did not converge
+            if not opt_result.success:
+                warn(
+                    "[{}] NCA did not converge: {}".format(
+                        cls_name, opt_result.message
+                    ),
+                    ConvergenceWarning,
+                )
+
+            print("[{}] Training took {:8.2f}s.".format(cls_name, t_train))
+
+        return self
+
+    def transform(self, X):
+        """Apply the learned transformation to the given data.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Data samples.
+
+        Returns
+        -------
+        X_embedded: ndarray of shape (n_samples, n_components)
+            The data samples transformed.
+
+        Raises
+        ------
+        NotFittedError
+            If :meth:`fit` has not been called before.
+        """
+
+        check_is_fitted(self)
+        X = validate_data(self, X, reset=False)
+
+        return np.dot(X, self.components_.T)
+
+    def _initialize(self, X, y, init):
+        """Initialize the transformation.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            The training samples.
+
+        y : array-like of shape (n_samples,)
+            The training labels.
+
+        init : str or ndarray of shape (n_features_a, n_features_b)
+            The validated initialization of the linear transformation.
+
+        Returns
+        -------
+        transformation : ndarray of shape (n_components, n_features)
+            The initialized linear transformation.
+
+        """
+
+        transformation = init
+        if self.warm_start and hasattr(self, "components_"):
+            transformation = self.components_
+        elif isinstance(init, np.ndarray):
+            pass
+        else:
+            n_samples, n_features = X.shape
+            n_components = self.n_components or n_features
+            if init == "auto":
+                n_classes = len(np.unique(y))
+                if n_components <= min(n_features, n_classes - 1):
+                    init = "lda"
+                elif n_components < min(n_features, n_samples):
+                    init = "pca"
+                else:
+                    init = "identity"
+            if init == "identity":
+                transformation = np.eye(n_components, X.shape[1])
+            elif init == "random":
+                transformation = self.random_state_.standard_normal(
+                    size=(n_components, X.shape[1])
+                )
+            elif init in {"pca", "lda"}:
+                init_time = time.time()
+                if init == "pca":
+                    pca = PCA(
+                        n_components=n_components, random_state=self.random_state_
+                    )
+                    if self.verbose:
+                        print("Finding principal components... ", end="")
+                        sys.stdout.flush()
+                    pca.fit(X)
+                    transformation = pca.components_
+                elif init == "lda":
+                    from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
+
+                    lda = LinearDiscriminantAnalysis(n_components=n_components)
+                    if self.verbose:
+                        print("Finding most discriminative components... ", end="")
+                        sys.stdout.flush()
+                    lda.fit(X, y)
+                    transformation = lda.scalings_.T[:n_components]
+                if self.verbose:
+                    print("done in {:5.2f}s".format(time.time() - init_time))
+        return transformation
+
+    def _callback(self, transformation):
+        """Called after each iteration of the optimizer.
+
+        Parameters
+        ----------
+        transformation : ndarray of shape (n_components * n_features,)
+            The solution computed by the optimizer in this iteration.
+        """
+        if self.callback is not None:
+            self.callback(transformation, self.n_iter_)
+
+        self.n_iter_ += 1
+
+    def _loss_grad_lbfgs(self, transformation, X, same_class_mask, sign=1.0):
+        """Compute the loss and the loss gradient w.r.t. `transformation`.
+
+        Parameters
+        ----------
+        transformation : ndarray of shape (n_components * n_features,)
+            The raveled linear transformation on which to compute loss and
+            evaluate gradient.
+
+        X : ndarray of shape (n_samples, n_features)
+            The training samples.
+
+        same_class_mask : ndarray of shape (n_samples, n_samples)
+            A mask where `mask[i, j] == 1` if `X[i]` and `X[j]` belong
+            to the same class, and `0` otherwise.
+
+        Returns
+        -------
+        loss : float
+            The loss computed for the given transformation.
+
+        gradient : ndarray of shape (n_components * n_features,)
+            The new (flattened) gradient of the loss.
+        """
+
+        if self.n_iter_ == 0:
+            self.n_iter_ += 1
+            if self.verbose:
+                header_fields = ["Iteration", "Objective Value", "Time(s)"]
+                header_fmt = "{:>10} {:>20} {:>10}"
+                header = header_fmt.format(*header_fields)
+                cls_name = self.__class__.__name__
+                print("[{}]".format(cls_name))
+                print(
+                    "[{}] {}\n[{}] {}".format(
+                        cls_name, header, cls_name, "-" * len(header)
+                    )
+                )
+
+        t_funcall = time.time()
+
+        transformation = transformation.reshape(-1, X.shape[1])
+        X_embedded = np.dot(X, transformation.T)  # (n_samples, n_components)
+
+        # Compute softmax distances
+        p_ij = pairwise_distances(X_embedded, squared=True)
+        np.fill_diagonal(p_ij, np.inf)
+        p_ij = softmax(-p_ij)  # (n_samples, n_samples)
+
+        # Compute loss
+        masked_p_ij = p_ij * same_class_mask
+        p = np.sum(masked_p_ij, axis=1, keepdims=True)  # (n_samples, 1)
+        loss = np.sum(p)
+
+        # Compute gradient of loss w.r.t. `transform`
+        weighted_p_ij = masked_p_ij - p_ij * p
+        weighted_p_ij_sym = weighted_p_ij + weighted_p_ij.T
+        np.fill_diagonal(weighted_p_ij_sym, -weighted_p_ij.sum(axis=0))
+        gradient = 2 * X_embedded.T.dot(weighted_p_ij_sym).dot(X)
+        # time complexity of the gradient: O(n_components x n_samples x (
+        # n_samples + n_features))
+
+        if self.verbose:
+            t_funcall = time.time() - t_funcall
+            values_fmt = "[{}] {:>10} {:>20.6e} {:>10.2f}"
+            print(
+                values_fmt.format(
+                    self.__class__.__name__, self.n_iter_, loss, t_funcall
+                )
+            )
+            sys.stdout.flush()
+
+        return sign * loss, sign * gradient.ravel()
+
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.target_tags.required = True
+        return tags
+
+    @property
+    def _n_features_out(self):
+        """Number of transformed output features."""
+        return self.components_.shape[0]

linedance-app/venv/lib/python3.12/site-packages/sklearn/neighbors/_nearest_centroid.py

@@ -0,0 +1,356 @@
+"""
+Nearest Centroid Classification
+"""
+
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
+import warnings
+from numbers import Real
+
+import numpy as np
+from scipy import sparse as sp
+
+from sklearn.base import BaseEstimator, ClassifierMixin, _fit_context
+from sklearn.discriminant_analysis import DiscriminantAnalysisPredictionMixin
+from sklearn.metrics.pairwise import pairwise_distances, pairwise_distances_argmin
+from sklearn.preprocessing import LabelEncoder
+from sklearn.utils import get_tags
+from sklearn.utils._available_if import available_if
+from sklearn.utils._param_validation import Interval, StrOptions
+from sklearn.utils.multiclass import check_classification_targets
+from sklearn.utils.sparsefuncs import csc_median_axis_0
+from sklearn.utils.validation import check_is_fitted, validate_data
+
+
+class NearestCentroid(
+    DiscriminantAnalysisPredictionMixin, ClassifierMixin, BaseEstimator
+):
+    """Nearest centroid classifier.
+
+    Each class is represented by its centroid, with test samples classified to
+    the class with the nearest centroid.
+
+    Read more in the :ref:`User Guide <nearest_centroid_classifier>`.
+
+    Parameters
+    ----------
+    metric : {"euclidean", "manhattan"}, default="euclidean"
+        Metric to use for distance computation.
+
+        If `metric="euclidean"`, the centroid for the samples corresponding to each
+        class is the arithmetic mean, which minimizes the sum of squared L1 distances.
+        If `metric="manhattan"`, the centroid is the feature-wise median, which
+        minimizes the sum of L1 distances.
+
+        .. versionchanged:: 1.5
+            All metrics but `"euclidean"` and `"manhattan"` were deprecated and
+            now raise an error.
+
+        .. versionchanged:: 0.19
+            `metric='precomputed'` was deprecated and now raises an error
+
+    shrink_threshold : float, default=None
+        Threshold for shrinking centroids to remove features.
+
+    priors : {"uniform", "empirical"} or array-like of shape (n_classes,), \
+        default="uniform"
+        The class prior probabilities. By default, the class proportions are
+        inferred from the training data.
+
+        .. versionadded:: 1.6
+
+    Attributes
+    ----------
+    centroids_ : array-like of shape (n_classes, n_features)
+        Centroid of each class.
+
+    classes_ : array of shape (n_classes,)
+        The unique classes labels.
+
+    n_features_in_ : int
+        Number of features seen during :term:`fit`.
+
+        .. versionadded:: 0.24
+
+    feature_names_in_ : ndarray of shape (`n_features_in_`,)
+        Names of features seen during :term:`fit`. Defined only when `X`
+        has feature names that are all strings.
+
+        .. versionadded:: 1.0
+
+    deviations_ : ndarray of shape (n_classes, n_features)
+        Deviations (or shrinkages) of the centroids of each class from the
+        overall centroid. Equal to eq. (18.4) if `shrink_threshold=None`,
+        else (18.5) p. 653 of [2]. Can be used to identify features used
+        for classification.
+
+        .. versionadded:: 1.6
+
+    within_class_std_dev_ : ndarray of shape (n_features,)
+        Pooled or within-class standard deviation of input data.
+
+        .. versionadded:: 1.6
+
+    class_prior_ : ndarray of shape (n_classes,)
+        The class prior probabilities.
+
+        .. versionadded:: 1.6
+
+    See Also
+    --------
+    KNeighborsClassifier : Nearest neighbors classifier.
+
+    Notes
+    -----
+    When used for text classification with tf-idf vectors, this classifier is
+    also known as the Rocchio classifier.
+
+    References
+    ----------
+    [1] Tibshirani, R., Hastie, T., Narasimhan, B., & Chu, G. (2002). Diagnosis of
+    multiple cancer types by shrunken centroids of gene expression. Proceedings
+    of the National Academy of Sciences of the United States of America,
+    99(10), 6567-6572. The National Academy of Sciences.
+
+    [2] Hastie, T., Tibshirani, R., Friedman, J. (2009). The Elements of Statistical
+    Learning Data Mining, Inference, and Prediction. 2nd Edition. New York, Springer.
+
+    Examples
+    --------
+    >>> from sklearn.neighbors import NearestCentroid
+    >>> import numpy as np
+    >>> X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, 1], [2, 1], [3, 2]])
+    >>> y = np.array([1, 1, 1, 2, 2, 2])
+    >>> clf = NearestCentroid()
+    >>> clf.fit(X, y)
+    NearestCentroid()
+    >>> print(clf.predict([[-0.8, -1]]))
+    [1]
+    """
+
+    _parameter_constraints: dict = {
+        "metric": [StrOptions({"manhattan", "euclidean"})],
+        "shrink_threshold": [Interval(Real, 0, None, closed="neither"), None],
+        "priors": ["array-like", StrOptions({"empirical", "uniform"})],
+    }
+
+    def __init__(
+        self,
+        metric="euclidean",
+        *,
+        shrink_threshold=None,
+        priors="uniform",
+    ):
+        self.metric = metric
+        self.shrink_threshold = shrink_threshold
+        self.priors = priors
+
+    @_fit_context(prefer_skip_nested_validation=True)
+    def fit(self, X, y):
+        """
+        Fit the NearestCentroid model according to the given training data.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            Training vector, where `n_samples` is the number of samples and
+            `n_features` is the number of features.
+            Note that centroid shrinking cannot be used with sparse matrices.
+        y : array-like of shape (n_samples,)
+            Target values.
+
+        Returns
+        -------
+        self : object
+            Fitted estimator.
+        """
+        # If X is sparse and the metric is "manhattan", store it in a csc
+        # format is easier to calculate the median.
+        if self.metric == "manhattan":
+            X, y = validate_data(self, X, y, accept_sparse=["csc"])
+        else:
+            ensure_all_finite = (
+                "allow-nan" if get_tags(self).input_tags.allow_nan else True
+            )
+            X, y = validate_data(
+                self,
+                X,
+                y,
+                ensure_all_finite=ensure_all_finite,
+                accept_sparse=["csr", "csc"],
+            )
+        is_X_sparse = sp.issparse(X)
+        check_classification_targets(y)
+
+        n_samples, n_features = X.shape
+        le = LabelEncoder()
+        y_ind = le.fit_transform(y)
+        self.classes_ = classes = le.classes_
+        n_classes = classes.size
+        if n_classes < 2:
+            raise ValueError(
+                "The number of classes has to be greater than one; got %d class"
+                % (n_classes)
+            )
+
+        if self.priors == "empirical":  # estimate priors from sample
+            _, class_counts = np.unique(y, return_inverse=True)  # non-negative ints
+            self.class_prior_ = np.bincount(class_counts) / float(len(y))
+        elif self.priors == "uniform":
+            self.class_prior_ = np.asarray([1 / n_classes] * n_classes)
+        else:
+            self.class_prior_ = np.asarray(self.priors)
+
+        if (self.class_prior_ < 0).any():
+            raise ValueError("priors must be non-negative")
+        if not np.isclose(self.class_prior_.sum(), 1.0):
+            warnings.warn(
+                "The priors do not sum to 1. Normalizing such that it sums to one.",
+                UserWarning,
+            )
+            self.class_prior_ = self.class_prior_ / self.class_prior_.sum()
+
+        # Mask mapping each class to its members.
+        self.centroids_ = np.empty((n_classes, n_features), dtype=np.float64)
+
+        # Number of clusters in each class.
+        nk = np.zeros(n_classes)
+
+        for cur_class in range(n_classes):
+            center_mask = y_ind == cur_class
+            nk[cur_class] = np.sum(center_mask)
+            if is_X_sparse:
+                center_mask = np.where(center_mask)[0]
+
+            if self.metric == "manhattan":
+                # NumPy does not calculate median of sparse matrices.
+                if not is_X_sparse:
+                    self.centroids_[cur_class] = np.median(X[center_mask], axis=0)
+                else:
+                    self.centroids_[cur_class] = csc_median_axis_0(X[center_mask])
+            else:  # metric == "euclidean"
+                self.centroids_[cur_class] = X[center_mask].mean(axis=0)
+
+        # Compute within-class std_dev with unshrunked centroids
+        variance = np.array(X - self.centroids_[y_ind], copy=False) ** 2
+        self.within_class_std_dev_ = np.array(
+            np.sqrt(variance.sum(axis=0) / (n_samples - n_classes)), copy=False
+        )
+        if any(self.within_class_std_dev_ == 0):
+            warnings.warn(
+                "self.within_class_std_dev_ has at least 1 zero standard deviation."
+                "Inputs within the same classes for at least 1 feature are identical."
+            )
+
+        err_msg = "All features have zero variance. Division by zero."
+        if is_X_sparse and np.all((X.max(axis=0) - X.min(axis=0)).toarray() == 0):
+            raise ValueError(err_msg)
+        elif not is_X_sparse and np.all(np.ptp(X, axis=0) == 0):
+            raise ValueError(err_msg)
+
+        dataset_centroid_ = X.mean(axis=0)
+        # m parameter for determining deviation
+        m = np.sqrt((1.0 / nk) - (1.0 / n_samples))
+        # Calculate deviation using the standard deviation of centroids.
+        # To deter outliers from affecting the results.
+        s = self.within_class_std_dev_ + np.median(self.within_class_std_dev_)
+        mm = m.reshape(len(m), 1)  # Reshape to allow broadcasting.
+        ms = mm * s
+        self.deviations_ = np.array(
+            (self.centroids_ - dataset_centroid_) / ms, copy=False
+        )
+        # Soft thresholding: if the deviation crosses 0 during shrinking,
+        # it becomes zero.
+        if self.shrink_threshold:
+            signs = np.sign(self.deviations_)
+            self.deviations_ = np.abs(self.deviations_) - self.shrink_threshold
+            np.clip(self.deviations_, 0, None, out=self.deviations_)
+            self.deviations_ *= signs
+            # Now adjust the centroids using the deviation
+            msd = ms * self.deviations_
+            self.centroids_ = np.array(dataset_centroid_ + msd, copy=False)
+        return self
+
+    def predict(self, X):
+        """Perform classification on an array of test vectors `X`.
+
+        The predicted class `C` for each sample in `X` is returned.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            Input data.
+
+        Returns
+        -------
+        y_pred : ndarray of shape (n_samples,)
+            The predicted classes.
+        """
+        check_is_fitted(self)
+        if np.isclose(self.class_prior_, 1 / len(self.classes_)).all():
+            # `validate_data` is called here since we are not calling `super()`
+            ensure_all_finite = (
+                "allow-nan" if get_tags(self).input_tags.allow_nan else True
+            )
+            X = validate_data(
+                self,
+                X,
+                ensure_all_finite=ensure_all_finite,
+                accept_sparse="csr",
+                reset=False,
+            )
+            return self.classes_[
+                pairwise_distances_argmin(X, self.centroids_, metric=self.metric)
+            ]
+        else:
+            return super().predict(X)
+
+    def _decision_function(self, X):
+        # return discriminant scores, see eq. (18.2) p. 652 of the ESL.
+        check_is_fitted(self, "centroids_")
+
+        X_normalized = validate_data(
+            self, X, copy=True, reset=False, accept_sparse="csr", dtype=np.float64
+        )
+
+        discriminant_score = np.empty(
+            (X_normalized.shape[0], self.classes_.size), dtype=np.float64
+        )
+
+        mask = self.within_class_std_dev_ != 0
+        X_normalized[:, mask] /= self.within_class_std_dev_[mask]
+        centroids_normalized = self.centroids_.copy()
+        centroids_normalized[:, mask] /= self.within_class_std_dev_[mask]
+
+        for class_idx in range(self.classes_.size):
+            distances = pairwise_distances(
+                X_normalized, centroids_normalized[[class_idx]], metric=self.metric
+            ).ravel()
+            distances **= 2
+            discriminant_score[:, class_idx] = np.squeeze(
+                -distances + 2.0 * np.log(self.class_prior_[class_idx])
+            )
+
+        return discriminant_score
+
+    def _check_euclidean_metric(self):
+        return self.metric == "euclidean"
+
+    decision_function = available_if(_check_euclidean_metric)(
+        DiscriminantAnalysisPredictionMixin.decision_function
+    )
+
+    predict_proba = available_if(_check_euclidean_metric)(
+        DiscriminantAnalysisPredictionMixin.predict_proba
+    )
+
+    predict_log_proba = available_if(_check_euclidean_metric)(
+        DiscriminantAnalysisPredictionMixin.predict_log_proba
+    )
+
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.input_tags.allow_nan = self.metric == "nan_euclidean"
+        tags.input_tags.sparse = True
+        return tags

linedance-app/venv/lib/python3.12/site-packages/sklearn/neighbors/_partition_nodes.pxd

@@ -0,0 +1,10 @@
+from cython cimport floating
+from sklearn.utils._typedefs cimport float64_t, intp_t
+
+cdef int partition_node_indices(
+        const floating *data,
+        intp_t *node_indices,
+        intp_t split_dim,
+        intp_t split_index,
+        intp_t n_features,
+        intp_t n_points) except -1

linedance-app/venv/lib/python3.12/site-packages/sklearn/neighbors/_partition_nodes.pyx

@@ -0,0 +1,122 @@
+# BinaryTrees rely on partial sorts to partition their nodes during their
+# initialisation.
+#
+# The C++ std library exposes nth_element, an efficient partial sort for this
+# situation which has a linear time complexity as well as the best performances.
+#
+# To use std::algorithm::nth_element, a few fixture are defined using Cython:
+# - partition_node_indices, a Cython function used in BinaryTrees, that calls
+# - partition_node_indices_inner, a C++ function that wraps nth_element and uses
+# - an IndexComparator to state how to compare KDTrees' indices
+#
+# IndexComparator has been defined so that partial sorts are stable with
+# respect to the nodes initial indices.
+#
+# See for reference:
+#  - https://en.cppreference.com/w/cpp/algorithm/nth_element.
+#  - https://github.com/scikit-learn/scikit-learn/pull/11103
+#  - https://github.com/scikit-learn/scikit-learn/pull/19473
+from cython cimport floating
+
+
+cdef extern from *:
+    """
+    #include <algorithm>
+
+    template<class D, class I>
+    class IndexComparator {
+    private:
+        const D *data;
+        I split_dim, n_features;
+    public:
+        IndexComparator(const D *data, const I &split_dim, const I &n_features):
+            data(data), split_dim(split_dim), n_features(n_features) {}
+
+        bool operator()(const I &a, const I &b) const {
+            D a_value = data[a * n_features + split_dim];
+            D b_value = data[b * n_features + split_dim];
+            return a_value == b_value ? a < b : a_value < b_value;
+        }
+    };
+
+    template<class D, class I>
+    void partition_node_indices_inner(
+        const D *data,
+        I *node_indices,
+        const I &split_dim,
+        const I &split_index,
+        const I &n_features,
+        const I &n_points) {
+        IndexComparator<D, I> index_comparator(data, split_dim, n_features);
+        std::nth_element(
+            node_indices,
+            node_indices + split_index,
+            node_indices + n_points,
+            index_comparator);
+    }
+    """
+    void partition_node_indices_inner[D, I](
+                const D *data,
+                I *node_indices,
+                I split_dim,
+                I split_index,
+                I n_features,
+                I n_points) except +
+
+
+cdef int partition_node_indices(
+        const floating *data,
+        intp_t *node_indices,
+        intp_t split_dim,
+        intp_t split_index,
+        intp_t n_features,
+        intp_t n_points) except -1:
+    """Partition points in the node into two equal-sized groups.
+
+    Upon return, the values in node_indices will be rearranged such that
+    (assuming numpy-style indexing):
+
+        data[node_indices[0:split_index], split_dim]
+          <= data[node_indices[split_index], split_dim]
+
+    and
+
+        data[node_indices[split_index], split_dim]
+          <= data[node_indices[split_index:n_points], split_dim]
+
+    The algorithm is essentially a partial in-place quicksort around a
+    set pivot.
+
+    Parameters
+    ----------
+    data : double pointer
+        Pointer to a 2D array of the training data, of shape [N, n_features].
+        N must be greater than any of the values in node_indices.
+    node_indices : int pointer
+        Pointer to a 1D array of length n_points.  This lists the indices of
+        each of the points within the current node.  This will be modified
+        in-place.
+    split_dim : int
+        the dimension on which to split.  This will usually be computed via
+        the routine ``find_node_split_dim``.
+    split_index : int
+        the index within node_indices around which to split the points.
+    n_features: int
+        the number of features (i.e columns) in the 2D array pointed by data.
+    n_points : int
+        the length of node_indices. This is also the number of points in
+        the original dataset.
+    Returns
+    -------
+    status : int
+        integer exit status.  On return, the contents of node_indices are
+        modified as noted above.
+    """
+    partition_node_indices_inner(
+        data,
+        node_indices,
+        split_dim,
+        split_index,
+        n_features,
+        n_points)
+    return 0

linedance-app/venv/lib/python3.12/site-packages/sklearn/neighbors/_quad_tree.pxd

@@ -0,0 +1,90 @@
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
+# See quad_tree.pyx for details.
+
+cimport numpy as cnp
+from sklearn.utils._typedefs cimport float32_t, intp_t
+
+# This is effectively an ifdef statement in Cython
+# It allows us to write printf debugging lines
+# and remove them at compile time
+cdef enum:
+    DEBUGFLAG = 0
+
+# XXX: Careful to not change the order of the arguments. It is important to
+# have is_leaf and max_width consecutive as it permits to avoid padding by
+# the compiler and keep the size coherent for both C and numpy data structures.
+cdef struct Cell:
+    # Base storage structure for cells in a QuadTree object
+
+    # Tree structure
+    intp_t parent                # Parent cell of this cell
+    intp_t[8] children           # Array pointing to children of this cell
+
+    # Cell description
+    intp_t cell_id               # Id of the cell in the cells array in the Tree
+    intp_t point_index           # Index of the point at this cell (only defined
+    #                            # in non empty leaf)
+    bint is_leaf                 # Does this cell have children?
+    float32_t squared_max_width  # Squared value of the maximum width w
+    intp_t depth                 # Depth of the cell in the tree
+    intp_t cumulative_size       # Number of points included in the subtree with
+    #                            # this cell as a root.
+
+    # Internal constants
+    float32_t[3] center          # Store the center for quick split of cells
+    float32_t[3] barycenter      # Keep track of the center of mass of the cell
+
+    # Cell boundaries
+    float32_t[3] min_bounds      # Inferior boundaries of this cell (inclusive)
+    float32_t[3] max_bounds      # Superior boundaries of this cell (exclusive)
+
+
+cdef class _QuadTree:
+    # The QuadTree object is a quad tree structure constructed by inserting
+    # recursively points in the tree and splitting cells in 4 so that each
+    # leaf cell contains at most one point.
+    # This structure also handle 3D data, inserted in trees with 8 children
+    # for each node.
+
+    # Parameters of the tree
+    cdef public int n_dimensions         # Number of dimensions in X
+    cdef public int verbose              # Verbosity of the output
+    cdef intp_t n_cells_per_cell         # Number of children per node. (2 ** n_dimension)
+
+    # Tree inner structure
+    cdef public intp_t max_depth         # Max depth of the tree
+    cdef public intp_t cell_count        # Counter for node IDs
+    cdef public intp_t capacity          # Capacity of tree, in terms of nodes
+    cdef public intp_t n_points          # Total number of points
+    cdef Cell* cells                     # Array of nodes
+
+    # Point insertion methods
+    cdef int insert_point(self, float32_t[3] point, intp_t point_index,
+                          intp_t cell_id=*) except -1 nogil
+    cdef intp_t _insert_point_in_new_child(self, float32_t[3] point, Cell* cell,
+                                           intp_t point_index, intp_t size=*
+                                           ) noexcept nogil
+    cdef intp_t _select_child(self, float32_t[3] point, Cell* cell) noexcept nogil
+    cdef bint _is_duplicate(self, float32_t[3] point1, float32_t[3] point2) noexcept nogil
+
+    # Create a summary of the Tree compare to a query point
+    cdef long summarize(self, float32_t[3] point, float32_t* results,
+                        float squared_theta=*, intp_t cell_id=*, long idx=*
+                        ) noexcept nogil
+
+    # Internal cell initialization methods
+    cdef void _init_cell(self, Cell* cell, intp_t parent, intp_t depth) noexcept nogil
+    cdef void _init_root(self, float32_t[3] min_bounds, float32_t[3] max_bounds
+                         ) noexcept nogil
+
+    # Private methods
+    cdef int _check_point_in_cell(self, float32_t[3] point, Cell* cell
+                                  ) except -1 nogil
+
+    # Private array manipulation to manage the ``cells`` array
+    cdef int _resize(self, intp_t capacity) except -1 nogil
+    cdef int _resize_c(self, intp_t capacity=*) except -1 nogil
+    cdef int _get_cell(self, float32_t[3] point, intp_t cell_id=*) except -1 nogil
+    cdef Cell[:] _get_cell_ndarray(self)

linedance-app/venv/lib/python3.12/site-packages/sklearn/neighbors/_quad_tree.pyx

@@ -0,0 +1,611 @@
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
+
+from cpython cimport Py_INCREF, PyObject, PyTypeObject
+
+from libc.math cimport fabsf
+from libc.stdlib cimport free
+from libc.string cimport memcpy
+from libc.stdio cimport printf
+from libc.stdint cimport SIZE_MAX
+
+from sklearn.tree._utils cimport safe_realloc
+
+import numpy as np
+cimport numpy as cnp
+cnp.import_array()
+
+cdef extern from "numpy/arrayobject.h":
+    object PyArray_NewFromDescr(PyTypeObject* subtype, cnp.dtype descr,
+                                int nd, cnp.npy_intp* dims,
+                                cnp.npy_intp* strides,
+                                void* data, int flags, object obj)
+    int PyArray_SetBaseObject(cnp.ndarray arr, PyObject* obj)
+
+# Build the corresponding numpy dtype for Cell.
+# This works by casting `dummy` to an array of Cell of length 1, which numpy
+# can construct a `dtype`-object for. See https://stackoverflow.com/q/62448946
+# for a more detailed explanation.
+cdef Cell dummy
+CELL_DTYPE = np.asarray(<Cell[:1]>(&dummy)).dtype
+
+assert CELL_DTYPE.itemsize == sizeof(Cell)
+
+cdef const float EPSILON = 1e-6
+
+
+cdef class _QuadTree:
+    """Array-based representation of a QuadTree.
+
+    This class is currently working for indexing 2D data (regular QuadTree) and
+    for indexing 3D data (OcTree). It is planned to split the 2 implementations
+    using `Cython.Tempita` to save some memory for QuadTree.
+
+    Note that this code is currently internally used only by the Barnes-Hut
+    method in `sklearn.manifold.TSNE`. It is planned to be refactored and
+    generalized in the future to be compatible with nearest neighbors API of
+    `sklearn.neighbors` with 2D and 3D data.
+    """
+    def __cinit__(self, int n_dimensions, int verbose):
+        """Constructor."""
+        # Parameters of the tree
+        self.n_dimensions = n_dimensions
+        self.verbose = verbose
+        self.n_cells_per_cell = <int> (2 ** self.n_dimensions)
+
+        # Inner structures
+        self.max_depth = 0
+        self.cell_count = 0
+        self.capacity = 0
+        self.n_points = 0
+        self.cells = NULL
+
+    def __dealloc__(self):
+        """Destructor."""
+        # Free all inner structures
+        free(self.cells)
+
+    @property
+    def cumulative_size(self):
+        cdef Cell[:] cell_mem_view = self._get_cell_ndarray()
+        return cell_mem_view.base['cumulative_size'][:self.cell_count]
+
+    @property
+    def leafs(self):
+        cdef Cell[:] cell_mem_view = self._get_cell_ndarray()
+        return cell_mem_view.base['is_leaf'][:self.cell_count]
+
+    def build_tree(self, X):
+        """Build a tree from an array of points X."""
+        cdef:
+            int i
+            float32_t[3] pt
+            float32_t[3] min_bounds, max_bounds
+
+        # validate X and prepare for query
+        # X = check_array(X, dtype=float32_t, order='C')
+        n_samples = X.shape[0]
+
+        capacity = 100
+        self._resize(capacity)
+        m = np.min(X, axis=0)
+        M = np.max(X, axis=0)
+        # Scale the maximum to get all points strictly in the tree bounding box
+        # The 3 bounds are for positive, negative and small values
+        M = np.maximum(M * (1. + 1e-3 * np.sign(M)), M + 1e-3)
+        for i in range(self.n_dimensions):
+            min_bounds[i] = m[i]
+            max_bounds[i] = M[i]
+
+            if self.verbose > 10:
+                printf("[QuadTree] bounding box axis %i : [%f, %f]\n",
+                       i, min_bounds[i], max_bounds[i])
+
+        # Create the initial node with boundaries from the dataset
+        self._init_root(min_bounds, max_bounds)
+
+        for i in range(n_samples):
+            for j in range(self.n_dimensions):
+                pt[j] = X[i, j]
+            self.insert_point(pt, i)
+
+        # Shrink the cells array to reduce memory usage
+        self._resize(capacity=self.cell_count)
+
+    cdef int insert_point(self, float32_t[3] point, intp_t point_index,
+                          intp_t cell_id=0) except -1 nogil:
+        """Insert a point in the QuadTree."""
+        cdef int ax
+        cdef intp_t selected_child
+        cdef Cell* cell = &self.cells[cell_id]
+        cdef intp_t n_point = cell.cumulative_size
+
+        if self.verbose > 10:
+            printf("[QuadTree] Inserting depth %li\n", cell.depth)
+
+        # Assert that the point is in the right range
+        if DEBUGFLAG:
+            self._check_point_in_cell(point, cell)
+
+        # If the cell is an empty leaf, insert the point in it
+        if cell.cumulative_size == 0:
+            cell.cumulative_size = 1
+            self.n_points += 1
+            for i in range(self.n_dimensions):
+                cell.barycenter[i] = point[i]
+            cell.point_index = point_index
+            if self.verbose > 10:
+                printf("[QuadTree] inserted point %li in cell %li\n",
+                       point_index, cell_id)
+            return cell_id
+
+        # If the cell is not a leaf, update cell internals and
+        # recurse in selected child
+        if not cell.is_leaf:
+            for ax in range(self.n_dimensions):
+                # barycenter update using a weighted mean
+                cell.barycenter[ax] = (
+                    n_point * cell.barycenter[ax] + point[ax]) / (n_point + 1)
+
+            # Increase the size of the subtree starting from this cell
+            cell.cumulative_size += 1
+
+            # Insert child in the correct subtree
+            selected_child = self._select_child(point, cell)
+            if self.verbose > 49:
+                printf("[QuadTree] selected child %li\n", selected_child)
+            if selected_child == -1:
+                self.n_points += 1
+                return self._insert_point_in_new_child(point, cell, point_index)
+            return self.insert_point(point, point_index, selected_child)
+
+        # Finally, if the cell is a leaf with a point already inserted,
+        # split the cell in n_cells_per_cell if the point is not a duplicate.
+        # If it is a duplicate, increase the size of the leaf and return.
+        if self._is_duplicate(point, cell.barycenter):
+            if self.verbose > 10:
+                printf("[QuadTree] found a duplicate!\n")
+            cell.cumulative_size += 1
+            self.n_points += 1
+            return cell_id
+
+        # In a leaf, the barycenter correspond to the only point included
+        # in it.
+        self._insert_point_in_new_child(cell.barycenter, cell, cell.point_index,
+                                        cell.cumulative_size)
+        return self.insert_point(point, point_index, cell_id)
+
+    # XXX: This operation is not Thread safe
+    cdef intp_t _insert_point_in_new_child(
+        self, float32_t[3] point, Cell* cell, intp_t point_index, intp_t size=1
+    ) noexcept nogil:
+        """Create a child of cell which will contain point."""
+
+        # Local variable definition
+        cdef:
+            intp_t cell_id, cell_child_id, parent_id
+            float32_t[3] save_point
+            float32_t width
+            Cell* child
+            int i
+
+        # If the maximal capacity of the Tree have been reached, double the capacity
+        # We need to save the current cell id and the current point to retrieve them
+        # in case the reallocation
+        if self.cell_count + 1 > self.capacity:
+            parent_id = cell.cell_id
+            for i in range(self.n_dimensions):
+                save_point[i] = point[i]
+            self._resize(SIZE_MAX)
+            cell = &self.cells[parent_id]
+            point = save_point
+
+        # Get an empty cell and initialize it
+        cell_id = self.cell_count
+        self.cell_count += 1
+        child = &self.cells[cell_id]
+
+        self._init_cell(child, cell.cell_id, cell.depth + 1)
+        child.cell_id = cell_id
+
+        # Set the cell as an inner cell of the Tree
+        cell.is_leaf = False
+        cell.point_index = -1
+
+        # Set the correct boundary for the cell, store the point in the cell
+        # and compute its index in the children array.
+        cell_child_id = 0
+        for i in range(self.n_dimensions):
+            cell_child_id *= 2
+            if point[i] >= cell.center[i]:
+                cell_child_id += 1
+                child.min_bounds[i] = cell.center[i]
+                child.max_bounds[i] = cell.max_bounds[i]
+            else:
+                child.min_bounds[i] = cell.min_bounds[i]
+                child.max_bounds[i] = cell.center[i]
+            child.center[i] = (child.min_bounds[i] + child.max_bounds[i]) / 2.
+            width = child.max_bounds[i] - child.min_bounds[i]
+
+            child.barycenter[i] = point[i]
+            child.squared_max_width = max(child.squared_max_width, width*width)
+
+        # Store the point info and the size to account for duplicated points
+        child.point_index = point_index
+        child.cumulative_size = size
+
+        # Store the child cell in the correct place in children
+        cell.children[cell_child_id] = child.cell_id
+
+        if DEBUGFLAG:
+            # Assert that the point is in the right range
+            self._check_point_in_cell(point, child)
+        if self.verbose > 10:
+            printf("[QuadTree] inserted point %li in new child %li\n",
+                   point_index, cell_id)
+
+        return cell_id
+
+    cdef bint _is_duplicate(self, float32_t[3] point1, float32_t[3] point2) noexcept nogil:
+        """Check if the two given points are equals."""
+        cdef int i
+        cdef bint res = True
+        for i in range(self.n_dimensions):
+            # Use EPSILON to avoid numerical error that would overgrow the tree
+            res &= fabsf(point1[i] - point2[i]) <= EPSILON
+        return res
+
+    cdef intp_t _select_child(self, float32_t[3] point, Cell* cell) noexcept nogil:
+        """Select the child of cell which contains the given query point."""
+        cdef:
+            int i
+            intp_t selected_child = 0
+
+        for i in range(self.n_dimensions):
+            # Select the correct child cell to insert the point by comparing
+            # it to the borders of the cells using precomputed center.
+            selected_child *= 2
+            if point[i] >= cell.center[i]:
+                selected_child += 1
+        return cell.children[selected_child]
+
+    cdef void _init_cell(self, Cell* cell, intp_t parent, intp_t depth) noexcept nogil:
+        """Initialize a cell structure with some constants."""
+        cell.parent = parent
+        cell.is_leaf = True
+        cell.depth = depth
+        cell.squared_max_width = 0
+        cell.cumulative_size = 0
+        for i in range(self.n_cells_per_cell):
+            cell.children[i] = SIZE_MAX
+
+    cdef void _init_root(self, float32_t[3] min_bounds, float32_t[3] max_bounds
+                         ) noexcept nogil:
+        """Initialize the root node with the given space boundaries"""
+        cdef:
+            int i
+            float32_t width
+            Cell* root = &self.cells[0]
+
+        self._init_cell(root, -1, 0)
+        for i in range(self.n_dimensions):
+            root.min_bounds[i] = min_bounds[i]
+            root.max_bounds[i] = max_bounds[i]
+            root.center[i] = (max_bounds[i] + min_bounds[i]) / 2.
+            width = max_bounds[i] - min_bounds[i]
+            root.squared_max_width = max(root.squared_max_width, width*width)
+        root.cell_id = 0
+
+        self.cell_count += 1
+
+    cdef int _check_point_in_cell(self, float32_t[3] point, Cell* cell
+                                  ) except -1 nogil:
+        """Check that the given point is in the cell boundaries."""
+
+        if self.verbose >= 50:
+            if self.n_dimensions == 3:
+                printf("[QuadTree] Checking point (%f, %f, %f) in cell %li "
+                       "([%f/%f, %f/%f, %f/%f], size %li)\n",
+                       point[0], point[1], point[2], cell.cell_id,
+                       cell.min_bounds[0], cell.max_bounds[0], cell.min_bounds[1],
+                       cell.max_bounds[1], cell.min_bounds[2], cell.max_bounds[2],
+                       cell.cumulative_size)
+            else:
+                printf("[QuadTree] Checking point (%f, %f) in cell %li "
+                       "([%f/%f, %f/%f], size %li)\n",
+                       point[0], point[1], cell.cell_id, cell.min_bounds[0],
+                       cell.max_bounds[0], cell.min_bounds[1],
+                       cell.max_bounds[1], cell.cumulative_size)
+
+        for i in range(self.n_dimensions):
+            if (cell.min_bounds[i] > point[i] or
+                    cell.max_bounds[i] <= point[i]):
+                with gil:
+                    msg = "[QuadTree] InsertionError: point out of cell "
+                    msg += "boundary.\nAxis %li: cell [%f, %f]; point %f\n"
+
+                    msg %= i, cell.min_bounds[i],  cell.max_bounds[i], point[i]
+                    raise ValueError(msg)
+
+    def _check_coherence(self):
+        """Check the coherence of the cells of the tree.
+
+        Check that the info stored in each cell is compatible with the info
+        stored in descendent and sibling cells. Raise a ValueError if this
+        fails.
+        """
+        for cell in self.cells[:self.cell_count]:
+            # Check that the barycenter of inserted point is within the cell
+            # boundaries
+            self._check_point_in_cell(cell.barycenter, &cell)
+
+            if not cell.is_leaf:
+                # Compute the number of point in children and compare with
+                # its cummulative_size.
+                n_points = 0
+                for idx in range(self.n_cells_per_cell):
+                    child_id = cell.children[idx]
+                    if child_id != -1:
+                        child = self.cells[child_id]
+                        n_points += child.cumulative_size
+                        assert child.cell_id == child_id, (
+                            "Cell id not correctly initialized.")
+                if n_points != cell.cumulative_size:
+                    raise ValueError(
+                        "Cell {} is incoherent. Size={} but found {} points "
+                        "in children. ({})"
+                        .format(cell.cell_id, cell.cumulative_size,
+                                n_points, cell.children))
+
+        # Make sure that the number of point in the tree correspond to the
+        # cumulative size in root cell.
+        if self.n_points != self.cells[0].cumulative_size:
+            raise ValueError(
+                "QuadTree is incoherent. Size={} but found {} points "
+                "in children."
+                .format(self.n_points, self.cells[0].cumulative_size))
+
+    cdef long summarize(self, float32_t[3] point, float32_t* results,
+                        float squared_theta=.5, intp_t cell_id=0, long idx=0
+                        ) noexcept nogil:
+        """Summarize the tree compared to a query point.
+
+        Input arguments
+        ---------------
+        point : array (n_dimensions)
+             query point to construct the summary.
+        cell_id : integer, optional (default: 0)
+            current cell of the tree summarized. This should be set to 0 for
+            external calls.
+        idx : integer, optional (default: 0)
+            current index in the result array. This should be set to 0 for
+            external calls
+        squared_theta: float, optional (default: .5)
+            threshold to decide whether the node is sufficiently far
+            from the query point to be a good summary. The formula is such that
+            the node is a summary if
+                node_width^2 / dist_node_point^2 < squared_theta.
+            Note that the argument should be passed as theta^2 to avoid
+            computing square roots of the distances.
+
+        Output arguments
+        ----------------
+        results : array (n_samples * (n_dimensions+2))
+            result will contain a summary of the tree information compared to
+            the query point:
+            - results[idx:idx+n_dimensions] contains the coordinate-wise
+                difference between the query point and the summary cell idx.
+                This is useful in t-SNE to compute the negative forces.
+            - result[idx+n_dimensions+1] contains the squared euclidean
+                distance to the summary cell idx.
+            - result[idx+n_dimensions+2] contains the number of point of the
+                tree contained in the summary cell idx.
+
+        Return
+        ------
+        idx : integer
+            number of elements in the results array.
+        """
+        cdef:
+            int i, idx_d = idx + self.n_dimensions
+            bint duplicate = True
+            Cell* cell = &self.cells[cell_id]
+
+        results[idx_d] = 0.
+        for i in range(self.n_dimensions):
+            results[idx + i] = point[i] - cell.barycenter[i]
+            results[idx_d] += results[idx + i] * results[idx + i]
+            duplicate &= fabsf(results[idx + i]) <= EPSILON
+
+        # Do not compute self interactions
+        if duplicate and cell.is_leaf:
+            return idx
+
+        # Check whether we can use this node as a summary
+        # It's a summary node if the angular size as measured from the point
+        # is relatively small (w.r.t. theta) or if it is a leaf node.
+        # If it can be summarized, we use the cell center of mass
+        # Otherwise, we go a higher level of resolution and into the leaves.
+        if cell.is_leaf or (
+                (cell.squared_max_width / results[idx_d]) < squared_theta):
+            results[idx_d + 1] = <float32_t> cell.cumulative_size
+            return idx + self.n_dimensions + 2
+
+        else:
+            # Recursively compute the summary in nodes
+            for c in range(self.n_cells_per_cell):
+                child_id = cell.children[c]
+                if child_id != -1:
+                    idx = self.summarize(point, results, squared_theta,
+                                         child_id, idx)
+
+        return idx
+
+    def get_cell(self, point):
+        """return the id of the cell containing the query point or raise
+        ValueError if the point is not in the tree
+        """
+        cdef float32_t[3] query_pt
+        cdef int i
+
+        assert len(point) == self.n_dimensions, (
+            "Query point should be a point in dimension {}."
+            .format(self.n_dimensions))
+
+        for i in range(self.n_dimensions):
+            query_pt[i] = point[i]
+
+        return self._get_cell(query_pt, 0)
+
+    cdef int _get_cell(self, float32_t[3] point, intp_t cell_id=0
+                       ) except -1 nogil:
+        """guts of get_cell.
+
+        Return the id of the cell containing the query point or raise ValueError
+        if the point is not in the tree"""
+        cdef:
+            intp_t selected_child
+            Cell* cell = &self.cells[cell_id]
+
+        if cell.is_leaf:
+            if self._is_duplicate(cell.barycenter, point):
+                if self.verbose > 99:
+                    printf("[QuadTree] Found point in cell: %li\n",
+                           cell.cell_id)
+                return cell_id
+            with gil:
+                raise ValueError("Query point not in the Tree.")
+
+        selected_child = self._select_child(point, cell)
+        if selected_child > 0:
+            if self.verbose > 99:
+                printf("[QuadTree] Selected_child: %li\n", selected_child)
+            return self._get_cell(point, selected_child)
+        with gil:
+            raise ValueError("Query point not in the Tree.")
+
+    # Pickling primitives
+
+    def __reduce__(self):
+        """Reduce re-implementation, for pickling."""
+        return (_QuadTree, (self.n_dimensions, self.verbose), self.__getstate__())
+
+    def __getstate__(self):
+        """Getstate re-implementation, for pickling."""
+        d = {}
+        # capacity is inferred during the __setstate__ using nodes
+        d["max_depth"] = self.max_depth
+        d["cell_count"] = self.cell_count
+        d["capacity"] = self.capacity
+        d["n_points"] = self.n_points
+        d["cells"] = self._get_cell_ndarray().base
+        return d
+
+    def __setstate__(self, d):
+        """Setstate re-implementation, for unpickling."""
+        self.max_depth = d["max_depth"]
+        self.cell_count = d["cell_count"]
+        self.capacity = d["capacity"]
+        self.n_points = d["n_points"]
+
+        if 'cells' not in d:
+            raise ValueError('You have loaded Tree version which '
+                             'cannot be imported')
+
+        cell_ndarray = d['cells']
+
+        if (cell_ndarray.ndim != 1 or
+                cell_ndarray.dtype != CELL_DTYPE or
+                not cell_ndarray.flags.c_contiguous):
+            raise ValueError('Did not recognise loaded array layout')
+
+        self.capacity = cell_ndarray.shape[0]
+        if self._resize_c(self.capacity) != 0:
+            raise MemoryError("resizing tree to %d" % self.capacity)
+
+        cdef Cell[:] cell_mem_view = cell_ndarray
+        memcpy(
+            pto=self.cells,
+            pfrom=&cell_mem_view[0],
+            size=self.capacity * sizeof(Cell),
+        )
+
+    # Array manipulation methods, to convert it to numpy or to resize
+    # self.cells array
+
+    cdef Cell[:] _get_cell_ndarray(self):
+        """Wraps nodes as a NumPy struct array.
+
+        The array keeps a reference to this Tree, which manages the underlying
+        memory. Individual fields are publicly accessible as properties of the
+        Tree.
+        """
+        cdef cnp.npy_intp shape[1]
+        shape[0] = <cnp.npy_intp> self.cell_count
+        cdef cnp.npy_intp strides[1]
+        strides[0] = sizeof(Cell)
+        cdef Cell[:] arr
+        Py_INCREF(CELL_DTYPE)
+        arr = PyArray_NewFromDescr(
+            subtype=<PyTypeObject *> np.ndarray,
+            descr=CELL_DTYPE,
+            nd=1,
+            dims=shape,
+            strides=strides,
+            data=<void*> self.cells,
+            flags=cnp.NPY_ARRAY_DEFAULT,
+            obj=None,
+        )
+        Py_INCREF(self)
+        if PyArray_SetBaseObject(arr.base, <PyObject*> self) < 0:
+            raise ValueError("Can't initialize array!")
+        return arr
+
+    cdef int _resize(self, intp_t capacity) except -1 nogil:
+        """Resize all inner arrays to `capacity`, if `capacity` == -1, then
+           double the size of the inner arrays.
+
+        Returns -1 in case of failure to allocate memory (and raise MemoryError)
+        or 0 otherwise.
+        """
+        if self._resize_c(capacity) != 0:
+            # Acquire gil only if we need to raise
+            with gil:
+                raise MemoryError()
+
+    cdef int _resize_c(self, intp_t capacity=SIZE_MAX) except -1 nogil:
+        """Guts of _resize
+
+        Returns -1 in case of failure to allocate memory (and raise MemoryError)
+        or 0 otherwise.
+        """
+        if capacity == self.capacity and self.cells != NULL:
+            return 0
+
+        if <size_t> capacity == SIZE_MAX:
+            if self.capacity == 0:
+                capacity = 9  # default initial value to min
+            else:
+                capacity = 2 * self.capacity
+
+        safe_realloc(&self.cells, capacity)
+
+        # if capacity smaller than cell_count, adjust the counter
+        if capacity < self.cell_count:
+            self.cell_count = capacity
+
+        self.capacity = capacity
+        return 0
+
+    def _py_summarize(self, float32_t[:] query_pt, float32_t[:, :] X, float angle):
+        # Used for testing summarize
+        cdef:
+            float32_t[:] summary
+            int n_samples
+
+        n_samples = X.shape[0]
+        summary = np.empty(4 * n_samples, dtype=np.float32)
+
+        idx = self.summarize(&query_pt[0], &summary[0], angle * angle)
+        return idx, summary

linedance-app/venv/lib/python3.12/site-packages/sklearn/neighbors/_regression.py

@@ -0,0 +1,518 @@
+"""Nearest Neighbor Regression."""
+
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
+import warnings
+
+import numpy as np
+
+from sklearn.base import RegressorMixin, _fit_context
+from sklearn.metrics import DistanceMetric
+from sklearn.neighbors._base import (
+    KNeighborsMixin,
+    NeighborsBase,
+    RadiusNeighborsMixin,
+    _get_weights,
+)
+from sklearn.utils._param_validation import StrOptions
+
+
+class KNeighborsRegressor(KNeighborsMixin, RegressorMixin, NeighborsBase):
+    """Regression based on k-nearest neighbors.
+
+    The target is predicted by local interpolation of the targets
+    associated of the nearest neighbors in the training set.
+
+    Read more in the :ref:`User Guide <regression>`.
+
+    .. versionadded:: 0.9
+
+    Parameters
+    ----------
+    n_neighbors : int, default=5
+        Number of neighbors to use by default for :meth:`kneighbors` queries.
+
+    weights : {'uniform', 'distance'}, callable or None, default='uniform'
+        Weight function used in prediction.  Possible values:
+
+        - 'uniform' : uniform weights.  All points in each neighborhood
+          are weighted equally.
+        - 'distance' : weight points by the inverse of their distance.
+          in this case, closer neighbors of a query point will have a
+          greater influence than neighbors which are further away.
+        - [callable] : a user-defined function which accepts an
+          array of distances, and returns an array of the same shape
+          containing the weights.
+
+        Uniform weights are used by default.
+
+        See the following example for a demonstration of the impact of
+        different weighting schemes on predictions:
+        :ref:`sphx_glr_auto_examples_neighbors_plot_regression.py`.
+
+    algorithm : {'auto', 'ball_tree', 'kd_tree', 'brute'}, default='auto'
+        Algorithm used to compute the nearest neighbors:
+
+        - 'ball_tree' will use :class:`BallTree`
+        - 'kd_tree' will use :class:`KDTree`
+        - 'brute' will use a brute-force search.
+        - 'auto' will attempt to decide the most appropriate algorithm
+          based on the values passed to :meth:`fit` method.
+
+        Note: fitting on sparse input will override the setting of
+        this parameter, using brute force.
+
+    leaf_size : int, default=30
+        Leaf size passed to BallTree or KDTree.  This can affect the
+        speed of the construction and query, as well as the memory
+        required to store the tree.  The optimal value depends on the
+        nature of the problem.
+
+    p : float, default=2
+        Power parameter for the Minkowski metric. When p = 1, this is
+        equivalent to using manhattan_distance (l1), and euclidean_distance
+        (l2) for p = 2. For arbitrary p, minkowski_distance (l_p) is used.
+
+    metric : str, DistanceMetric object or callable, default='minkowski'
+        Metric to use for distance computation. Default is "minkowski", which
+        results in the standard Euclidean distance when p = 2. See the
+        documentation of `scipy.spatial.distance
+        <https://docs.scipy.org/doc/scipy/reference/spatial.distance.html>`_ and
+        the metrics listed in
+        :class:`~sklearn.metrics.pairwise.distance_metrics` for valid metric
+        values.
+
+        If metric is "precomputed", X is assumed to be a distance matrix and
+        must be square during fit. X may be a :term:`sparse graph`, in which
+        case only "nonzero" elements may be considered neighbors.
+
+        If metric is a callable function, it takes two arrays representing 1D
+        vectors as inputs and must return one value indicating the distance
+        between those vectors. This works for Scipy's metrics, but is less
+        efficient than passing the metric name as a string.
+
+        If metric is a DistanceMetric object, it will be passed directly to
+        the underlying computation routines.
+
+    metric_params : dict, default=None
+        Additional keyword arguments for the metric function.
+
+    n_jobs : int, default=None
+        The number of parallel jobs to run for neighbors search.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See :term:`Glossary <n_jobs>`
+        for more details.
+        Doesn't affect :meth:`fit` method.
+
+    Attributes
+    ----------
+    effective_metric_ : str or callable
+        The distance metric to use. It will be same as the `metric` parameter
+        or a synonym of it, e.g. 'euclidean' if the `metric` parameter set to
+        'minkowski' and `p` parameter set to 2.
+
+    effective_metric_params_ : dict
+        Additional keyword arguments for the metric function. For most metrics
+        will be same with `metric_params` parameter, but may also contain the
+        `p` parameter value if the `effective_metric_` attribute is set to
+        'minkowski'.
+
+    n_features_in_ : int
+        Number of features seen during :term:`fit`.
+
+        .. versionadded:: 0.24
+
+    feature_names_in_ : ndarray of shape (`n_features_in_`,)
+        Names of features seen during :term:`fit`. Defined only when `X`
+        has feature names that are all strings.
+
+        .. versionadded:: 1.0
+
+    n_samples_fit_ : int
+        Number of samples in the fitted data.
+
+    See Also
+    --------
+    NearestNeighbors : Unsupervised learner for implementing neighbor searches.
+    RadiusNeighborsRegressor : Regression based on neighbors within a fixed radius.
+    KNeighborsClassifier : Classifier implementing the k-nearest neighbors vote.
+    RadiusNeighborsClassifier : Classifier implementing
+        a vote among neighbors within a given radius.
+
+    Notes
+    -----
+    See :ref:`Nearest Neighbors <neighbors>` in the online documentation
+    for a discussion of the choice of ``algorithm`` and ``leaf_size``.
+
+    .. warning::
+
+       Regarding the Nearest Neighbors algorithms, if it is found that two
+       neighbors, neighbor `k+1` and `k`, have identical distances but
+       different labels, the results will depend on the ordering of the
+       training data.
+
+    https://en.wikipedia.org/wiki/K-nearest_neighbors_algorithm
+
+    Examples
+    --------
+    >>> X = [[0], [1], [2], [3]]
+    >>> y = [0, 0, 1, 1]
+    >>> from sklearn.neighbors import KNeighborsRegressor
+    >>> neigh = KNeighborsRegressor(n_neighbors=2)
+    >>> neigh.fit(X, y)
+    KNeighborsRegressor(...)
+    >>> print(neigh.predict([[1.5]]))
+    [0.5]
+    """
+
+    _parameter_constraints: dict = {
+        **NeighborsBase._parameter_constraints,
+        "weights": [StrOptions({"uniform", "distance"}), callable, None],
+    }
+    _parameter_constraints["metric"].append(DistanceMetric)
+    _parameter_constraints.pop("radius")
+
+    def __init__(
+        self,
+        n_neighbors=5,
+        *,
+        weights="uniform",
+        algorithm="auto",
+        leaf_size=30,
+        p=2,
+        metric="minkowski",
+        metric_params=None,
+        n_jobs=None,
+    ):
+        super().__init__(
+            n_neighbors=n_neighbors,
+            algorithm=algorithm,
+            leaf_size=leaf_size,
+            metric=metric,
+            p=p,
+            metric_params=metric_params,
+            n_jobs=n_jobs,
+        )
+        self.weights = weights
+
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        # For cross-validation routines to split data correctly
+        tags.input_tags.pairwise = self.metric == "precomputed"
+        return tags
+
+    @_fit_context(
+        # KNeighborsRegressor.metric is not validated yet
+        prefer_skip_nested_validation=False
+    )
+    def fit(self, X, y):
+        """Fit the k-nearest neighbors regressor from the training dataset.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features) or \
+                (n_samples, n_samples) if metric='precomputed'
+            Training data.
+
+        y : {array-like, sparse matrix} of shape (n_samples,) or \
+                (n_samples, n_outputs)
+            Target values.
+
+        Returns
+        -------
+        self : KNeighborsRegressor
+            The fitted k-nearest neighbors regressor.
+        """
+        return self._fit(X, y)
+
+    def predict(self, X):
+        """Predict the target for the provided data.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_queries, n_features), \
+                or (n_queries, n_indexed) if metric == 'precomputed', or None
+            Test samples. If `None`, predictions for all indexed points are
+            returned; in this case, points are not considered their own
+            neighbors.
+
+        Returns
+        -------
+        y : ndarray of shape (n_queries,) or (n_queries, n_outputs), dtype=int
+            Target values.
+        """
+        if self.weights == "uniform":
+            # In that case, we do not need the distances to perform
+            # the weighting so we do not compute them.
+            neigh_ind = self.kneighbors(X, return_distance=False)
+            neigh_dist = None
+        else:
+            neigh_dist, neigh_ind = self.kneighbors(X)
+
+        weights = _get_weights(neigh_dist, self.weights)
+
+        _y = self._y
+        if _y.ndim == 1:
+            _y = _y.reshape((-1, 1))
+
+        if weights is None:
+            y_pred = np.mean(_y[neigh_ind], axis=1)
+        else:
+            y_pred = np.empty((neigh_dist.shape[0], _y.shape[1]), dtype=np.float64)
+            denom = np.sum(weights, axis=1)
+
+            for j in range(_y.shape[1]):
+                num = np.sum(_y[neigh_ind, j] * weights, axis=1)
+                y_pred[:, j] = num / denom
+
+        if self._y.ndim == 1:
+            y_pred = y_pred.ravel()
+
+        return y_pred
+
+
+class RadiusNeighborsRegressor(RadiusNeighborsMixin, RegressorMixin, NeighborsBase):
+    """Regression based on neighbors within a fixed radius.
+
+    The target is predicted by local interpolation of the targets
+    associated of the nearest neighbors in the training set.
+
+    Read more in the :ref:`User Guide <regression>`.
+
+    .. versionadded:: 0.9
+
+    Parameters
+    ----------
+    radius : float, default=1.0
+        Range of parameter space to use by default for :meth:`radius_neighbors`
+        queries.
+
+    weights : {'uniform', 'distance'}, callable or None, default='uniform'
+        Weight function used in prediction.  Possible values:
+
+        - 'uniform' : uniform weights.  All points in each neighborhood
+          are weighted equally.
+        - 'distance' : weight points by the inverse of their distance.
+          in this case, closer neighbors of a query point will have a
+          greater influence than neighbors which are further away.
+        - [callable] : a user-defined function which accepts an
+          array of distances, and returns an array of the same shape
+          containing the weights.
+
+        Uniform weights are used by default.
+
+    algorithm : {'auto', 'ball_tree', 'kd_tree', 'brute'}, default='auto'
+        Algorithm used to compute the nearest neighbors:
+
+        - 'ball_tree' will use :class:`BallTree`
+        - 'kd_tree' will use :class:`KDTree`
+        - 'brute' will use a brute-force search.
+        - 'auto' will attempt to decide the most appropriate algorithm
+          based on the values passed to :meth:`fit` method.
+
+        Note: fitting on sparse input will override the setting of
+        this parameter, using brute force.
+
+    leaf_size : int, default=30
+        Leaf size passed to BallTree or KDTree.  This can affect the
+        speed of the construction and query, as well as the memory
+        required to store the tree.  The optimal value depends on the
+        nature of the problem.
+
+    p : float, default=2
+        Power parameter for the Minkowski metric. When p = 1, this is
+        equivalent to using manhattan_distance (l1), and euclidean_distance
+        (l2) for p = 2. For arbitrary p, minkowski_distance (l_p) is used.
+
+    metric : str or callable, default='minkowski'
+        Metric to use for distance computation. Default is "minkowski", which
+        results in the standard Euclidean distance when p = 2. See the
+        documentation of `scipy.spatial.distance
+        <https://docs.scipy.org/doc/scipy/reference/spatial.distance.html>`_ and
+        the metrics listed in
+        :class:`~sklearn.metrics.pairwise.distance_metrics` for valid metric
+        values.
+
+        If metric is "precomputed", X is assumed to be a distance matrix and
+        must be square during fit. X may be a :term:`sparse graph`, in which
+        case only "nonzero" elements may be considered neighbors.
+
+        If metric is a callable function, it takes two arrays representing 1D
+        vectors as inputs and must return one value indicating the distance
+        between those vectors. This works for Scipy's metrics, but is less
+        efficient than passing the metric name as a string.
+
+    metric_params : dict, default=None
+        Additional keyword arguments for the metric function.
+
+    n_jobs : int, default=None
+        The number of parallel jobs to run for neighbors search.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See :term:`Glossary <n_jobs>`
+        for more details.
+
+    Attributes
+    ----------
+    effective_metric_ : str or callable
+        The distance metric to use. It will be same as the `metric` parameter
+        or a synonym of it, e.g. 'euclidean' if the `metric` parameter set to
+        'minkowski' and `p` parameter set to 2.
+
+    effective_metric_params_ : dict
+        Additional keyword arguments for the metric function. For most metrics
+        will be same with `metric_params` parameter, but may also contain the
+        `p` parameter value if the `effective_metric_` attribute is set to
+        'minkowski'.
+
+    n_features_in_ : int
+        Number of features seen during :term:`fit`.
+
+        .. versionadded:: 0.24
+
+    feature_names_in_ : ndarray of shape (`n_features_in_`,)
+        Names of features seen during :term:`fit`. Defined only when `X`
+        has feature names that are all strings.
+
+        .. versionadded:: 1.0
+
+    n_samples_fit_ : int
+        Number of samples in the fitted data.
+
+    See Also
+    --------
+    NearestNeighbors : Unsupervised learner for implementing neighbor searches.
+    KNeighborsRegressor : Regression based on k-nearest neighbors.
+    KNeighborsClassifier : Classifier based on the k-nearest neighbors.
+    RadiusNeighborsClassifier : Classifier based on neighbors within a given radius.
+
+    Notes
+    -----
+    See :ref:`Nearest Neighbors <neighbors>` in the online documentation
+    for a discussion of the choice of ``algorithm`` and ``leaf_size``.
+
+    https://en.wikipedia.org/wiki/K-nearest_neighbor_algorithm
+
+    Examples
+    --------
+    >>> X = [[0], [1], [2], [3]]
+    >>> y = [0, 0, 1, 1]
+    >>> from sklearn.neighbors import RadiusNeighborsRegressor
+    >>> neigh = RadiusNeighborsRegressor(radius=1.0)
+    >>> neigh.fit(X, y)
+    RadiusNeighborsRegressor(...)
+    >>> print(neigh.predict([[1.5]]))
+    [0.5]
+    """
+
+    _parameter_constraints: dict = {
+        **NeighborsBase._parameter_constraints,
+        "weights": [StrOptions({"uniform", "distance"}), callable, None],
+    }
+    _parameter_constraints.pop("n_neighbors")
+
+    def __init__(
+        self,
+        radius=1.0,
+        *,
+        weights="uniform",
+        algorithm="auto",
+        leaf_size=30,
+        p=2,
+        metric="minkowski",
+        metric_params=None,
+        n_jobs=None,
+    ):
+        super().__init__(
+            radius=radius,
+            algorithm=algorithm,
+            leaf_size=leaf_size,
+            p=p,
+            metric=metric,
+            metric_params=metric_params,
+            n_jobs=n_jobs,
+        )
+        self.weights = weights
+
+    @_fit_context(
+        # RadiusNeighborsRegressor.metric is not validated yet
+        prefer_skip_nested_validation=False
+    )
+    def fit(self, X, y):
+        """Fit the radius neighbors regressor from the training dataset.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features) or \
+                (n_samples, n_samples) if metric='precomputed'
+            Training data.
+
+        y : {array-like, sparse matrix} of shape (n_samples,) or \
+                (n_samples, n_outputs)
+            Target values.
+
+        Returns
+        -------
+        self : RadiusNeighborsRegressor
+            The fitted radius neighbors regressor.
+        """
+        return self._fit(X, y)
+
+    def predict(self, X):
+        """Predict the target for the provided data.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_queries, n_features), \
+                or (n_queries, n_indexed) if metric == 'precomputed', or None
+            Test samples. If `None`, predictions for all indexed points are
+            returned; in this case, points are not considered their own
+            neighbors.
+
+        Returns
+        -------
+        y : ndarray of shape (n_queries,) or (n_queries, n_outputs), \
+                dtype=double
+            Target values.
+        """
+        neigh_dist, neigh_ind = self.radius_neighbors(X)
+
+        weights = _get_weights(neigh_dist, self.weights)
+
+        _y = self._y
+        if _y.ndim == 1:
+            _y = _y.reshape((-1, 1))
+
+        empty_obs = np.full_like(_y[0], np.nan)
+
+        if weights is None:
+            y_pred = np.array(
+                [
+                    np.mean(_y[ind, :], axis=0) if len(ind) else empty_obs
+                    for (i, ind) in enumerate(neigh_ind)
+                ]
+            )
+
+        else:
+            y_pred = np.array(
+                [
+                    (
+                        np.average(_y[ind, :], axis=0, weights=weights[i])
+                        if len(ind)
+                        else empty_obs
+                    )
+                    for (i, ind) in enumerate(neigh_ind)
+                ]
+            )
+
+        if np.any(np.isnan(y_pred)):
+            empty_warning_msg = (
+                "One or more samples have no neighbors "
+                "within specified radius; predicting NaN."
+            )
+            warnings.warn(empty_warning_msg)
+
+        if self._y.ndim == 1:
+            y_pred = y_pred.ravel()
+
+        return y_pred

linedance-app/venv/lib/python3.12/site-packages/sklearn/neighbors/_unsupervised.py

@@ -0,0 +1,179 @@
+"""Unsupervised nearest neighbors learner"""
+
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
+from sklearn.base import _fit_context
+from sklearn.neighbors._base import KNeighborsMixin, NeighborsBase, RadiusNeighborsMixin
+
+
+class NearestNeighbors(KNeighborsMixin, RadiusNeighborsMixin, NeighborsBase):
+    """Unsupervised learner for implementing neighbor searches.
+
+    Read more in the :ref:`User Guide <unsupervised_neighbors>`.
+
+    .. versionadded:: 0.9
+
+    Parameters
+    ----------
+    n_neighbors : int, default=5
+        Number of neighbors to use by default for :meth:`kneighbors` queries.
+
+    radius : float, default=1.0
+        Range of parameter space to use by default for :meth:`radius_neighbors`
+        queries.
+
+    algorithm : {'auto', 'ball_tree', 'kd_tree', 'brute'}, default='auto'
+        Algorithm used to compute the nearest neighbors:
+
+        - 'ball_tree' will use :class:`BallTree`
+        - 'kd_tree' will use :class:`KDTree`
+        - 'brute' will use a brute-force search.
+        - 'auto' will attempt to decide the most appropriate algorithm
+          based on the values passed to :meth:`fit` method.
+
+        Note: fitting on sparse input will override the setting of
+        this parameter, using brute force.
+
+    leaf_size : int, default=30
+        Leaf size passed to BallTree or KDTree.  This can affect the
+        speed of the construction and query, as well as the memory
+        required to store the tree.  The optimal value depends on the
+        nature of the problem.
+
+    metric : str or callable, default='minkowski'
+        Metric to use for distance computation. Default is "minkowski", which
+        results in the standard Euclidean distance when p = 2. See the
+        documentation of `scipy.spatial.distance
+        <https://docs.scipy.org/doc/scipy/reference/spatial.distance.html>`_ and
+        the metrics listed in
+        :class:`~sklearn.metrics.pairwise.distance_metrics` for valid metric
+        values.
+
+        If metric is "precomputed", X is assumed to be a distance matrix and
+        must be square during fit. X may be a :term:`sparse graph`, in which
+        case only "nonzero" elements may be considered neighbors.
+
+        If metric is a callable function, it takes two arrays representing 1D
+        vectors as inputs and must return one value indicating the distance
+        between those vectors. This works for Scipy's metrics, but is less
+        efficient than passing the metric name as a string.
+
+    p : float (positive), default=2
+        Parameter for the Minkowski metric from
+        sklearn.metrics.pairwise.pairwise_distances. When p = 1, this is
+        equivalent to using manhattan_distance (l1), and euclidean_distance
+        (l2) for p = 2. For arbitrary p, minkowski_distance (l_p) is used.
+
+    metric_params : dict, default=None
+        Additional keyword arguments for the metric function.
+
+    n_jobs : int, default=None
+        The number of parallel jobs to run for neighbors search.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See :term:`Glossary <n_jobs>`
+        for more details.
+
+    Attributes
+    ----------
+    effective_metric_ : str
+        Metric used to compute distances to neighbors.
+
+    effective_metric_params_ : dict
+        Parameters for the metric used to compute distances to neighbors.
+
+    n_features_in_ : int
+        Number of features seen during :term:`fit`.
+
+        .. versionadded:: 0.24
+
+    feature_names_in_ : ndarray of shape (`n_features_in_`,)
+        Names of features seen during :term:`fit`. Defined only when `X`
+        has feature names that are all strings.
+
+        .. versionadded:: 1.0
+
+    n_samples_fit_ : int
+        Number of samples in the fitted data.
+
+    See Also
+    --------
+    KNeighborsClassifier : Classifier implementing the k-nearest neighbors
+        vote.
+    RadiusNeighborsClassifier : Classifier implementing a vote among neighbors
+        within a given radius.
+    KNeighborsRegressor : Regression based on k-nearest neighbors.
+    RadiusNeighborsRegressor : Regression based on neighbors within a fixed
+        radius.
+    BallTree : Space partitioning data structure for organizing points in a
+        multi-dimensional space, used for nearest neighbor search.
+
+    Notes
+    -----
+    See :ref:`Nearest Neighbors <neighbors>` in the online documentation
+    for a discussion of the choice of ``algorithm`` and ``leaf_size``.
+
+    https://en.wikipedia.org/wiki/K-nearest_neighbors_algorithm
+
+    Examples
+    --------
+    >>> import numpy as np
+    >>> from sklearn.neighbors import NearestNeighbors
+    >>> samples = [[0, 0, 2], [1, 0, 0], [0, 0, 1]]
+    >>> neigh = NearestNeighbors(n_neighbors=2, radius=0.4)
+    >>> neigh.fit(samples)
+    NearestNeighbors(...)
+    >>> neigh.kneighbors([[0, 0, 1.3]], 2, return_distance=False)
+    array([[2, 0]]...)
+    >>> nbrs = neigh.radius_neighbors(
+    ...    [[0, 0, 1.3]], 0.4, return_distance=False
+    ... )
+    >>> np.asarray(nbrs[0][0])
+    array(2)
+    """
+
+    def __init__(
+        self,
+        *,
+        n_neighbors=5,
+        radius=1.0,
+        algorithm="auto",
+        leaf_size=30,
+        metric="minkowski",
+        p=2,
+        metric_params=None,
+        n_jobs=None,
+    ):
+        super().__init__(
+            n_neighbors=n_neighbors,
+            radius=radius,
+            algorithm=algorithm,
+            leaf_size=leaf_size,
+            metric=metric,
+            p=p,
+            metric_params=metric_params,
+            n_jobs=n_jobs,
+        )
+
+    @_fit_context(
+        # NearestNeighbors.metric is not validated yet
+        prefer_skip_nested_validation=False
+    )
+    def fit(self, X, y=None):
+        """Fit the nearest neighbors estimator from the training dataset.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features) or \
+                (n_samples, n_samples) if metric='precomputed'
+            Training data.
+
+        y : Ignored
+            Not used, present for API consistency by convention.
+
+        Returns
+        -------
+        self : NearestNeighbors
+            The fitted nearest neighbors estimator.
+        """
+        return self._fit(X)

linedance-app/venv/lib/python3.12/site-packages/sklearn/neighbors/meson.build

@@ -0,0 +1,53 @@
+_binary_tree_pxi = custom_target(
+  '_binary_tree_pxi',
+  output: '_binary_tree.pxi',
+  input: '_binary_tree.pxi.tp',
+  command: [tempita, '@INPUT@', '-o', '@OUTDIR@'],
+)
+
+# .pyx is generated so this is needed to make Cython compilation work. The pxi
+# file is included avoid "missing dependency paths" with ninja -t missindeps
+neighbors_cython_tree = [
+  fs.copyfile('__init__.py'),
+  fs.copyfile('_partition_nodes.pxd'),
+  _binary_tree_pxi,
+]
+
+name_list = ['_ball_tree', '_kd_tree']
+
+foreach name: name_list
+  pyx = custom_target(
+    name + '_pyx',
+    output: name + '.pyx',
+    input: name + '.pyx.tp',
+    command: [tempita, '@INPUT@', '-o', '@OUTDIR@'],
+    # TODO in principle this should go in py.exension_module below. This is
+    # temporary work-around for dependency issue with .pyx.tp files. For more
+    # details, see https://github.com/mesonbuild/meson/issues/13212
+    depends: [neighbors_cython_tree, utils_cython_tree, metrics_cython_tree],
+  )
+  py.extension_module(
+    name,
+    cython_gen.process(pyx),
+    dependencies: [np_dep],
+    subdir: 'sklearn/neighbors',
+    install: true
+)
+endforeach
+
+neighbors_extension_metadata = {
+  '_partition_nodes':
+      {'sources': [cython_gen_cpp.process('_partition_nodes.pyx')],
+       'dependencies': [np_dep]},
+  '_quad_tree': {'sources': [cython_gen.process('_quad_tree.pyx')], 'dependencies': [np_dep]},
+}
+
+foreach ext_name, ext_dict : neighbors_extension_metadata
+  py.extension_module(
+    ext_name,
+    [ext_dict.get('sources'), utils_cython_tree],
+    dependencies: ext_dict.get('dependencies'),
+    subdir: 'sklearn/neighbors',
+    install: true
+  )
+endforeach

linedance-app/venv/lib/python3.12/site-packages/sklearn/neighbors/tests/test_ball_tree.py

@@ -0,0 +1,200 @@
+import itertools
+
+import numpy as np
+import pytest
+from numpy.testing import assert_allclose, assert_array_almost_equal, assert_equal
+
+from sklearn.neighbors._ball_tree import BallTree, BallTree32, BallTree64
+from sklearn.utils import check_random_state
+from sklearn.utils._testing import _convert_container
+from sklearn.utils.validation import check_array
+
+rng = np.random.RandomState(10)
+V_mahalanobis = rng.rand(3, 3)
+V_mahalanobis = np.dot(V_mahalanobis, V_mahalanobis.T)
+
+DIMENSION = 3
+
+METRICS = {
+    "euclidean": {},
+    "manhattan": {},
+    "minkowski": dict(p=3),
+    "chebyshev": {},
+}
+
+DISCRETE_METRICS = ["hamming", "canberra", "braycurtis"]
+
+BOOLEAN_METRICS = [
+    "jaccard",
+    "dice",
+    "rogerstanimoto",
+    "russellrao",
+    "sokalmichener",
+    "sokalsneath",
+]
+
+BALL_TREE_CLASSES = [
+    BallTree64,
+    BallTree32,
+]
+
+
+def brute_force_neighbors(X, Y, k, metric, **kwargs):
+    from sklearn.metrics import DistanceMetric
+
+    X, Y = check_array(X), check_array(Y)
+    D = DistanceMetric.get_metric(metric, **kwargs).pairwise(Y, X)
+    ind = np.argsort(D, axis=1)[:, :k]
+    dist = D[np.arange(Y.shape[0])[:, None], ind]
+    return dist, ind
+
+
+def test_BallTree_is_BallTree64_subclass():
+    assert issubclass(BallTree, BallTree64)
+
+
+@pytest.mark.parametrize("metric", itertools.chain(BOOLEAN_METRICS, DISCRETE_METRICS))
+@pytest.mark.parametrize("array_type", ["list", "array"])
+@pytest.mark.parametrize("BallTreeImplementation", BALL_TREE_CLASSES)
+def test_ball_tree_query_metrics(metric, array_type, BallTreeImplementation):
+    rng = check_random_state(0)
+    if metric in BOOLEAN_METRICS:
+        X = rng.random_sample((40, 10)).round(0)
+        Y = rng.random_sample((10, 10)).round(0)
+    elif metric in DISCRETE_METRICS:
+        X = (4 * rng.random_sample((40, 10))).round(0)
+        Y = (4 * rng.random_sample((10, 10))).round(0)
+    X = _convert_container(X, array_type)
+    Y = _convert_container(Y, array_type)
+
+    k = 5
+
+    bt = BallTreeImplementation(X, leaf_size=1, metric=metric)
+    dist1, ind1 = bt.query(Y, k)
+    dist2, ind2 = brute_force_neighbors(X, Y, k, metric)
+    assert_array_almost_equal(dist1, dist2)
+
+
+@pytest.mark.parametrize(
+    "BallTreeImplementation, decimal_tol", zip(BALL_TREE_CLASSES, [6, 5])
+)
+def test_query_haversine(BallTreeImplementation, decimal_tol):
+    rng = check_random_state(0)
+    X = 2 * np.pi * rng.random_sample((40, 2))
+    bt = BallTreeImplementation(X, leaf_size=1, metric="haversine")
+    dist1, ind1 = bt.query(X, k=5)
+    dist2, ind2 = brute_force_neighbors(X, X, k=5, metric="haversine")
+
+    assert_array_almost_equal(dist1, dist2, decimal=decimal_tol)
+    assert_array_almost_equal(ind1, ind2)
+
+
+@pytest.mark.parametrize("BallTreeImplementation", BALL_TREE_CLASSES)
+def test_array_object_type(BallTreeImplementation):
+    """Check that we do not accept object dtype array."""
+    X = np.array([(1, 2, 3), (2, 5), (5, 5, 1, 2)], dtype=object)
+    with pytest.raises(ValueError, match="setting an array element with a sequence"):
+        BallTreeImplementation(X)
+
+
+@pytest.mark.parametrize("BallTreeImplementation", BALL_TREE_CLASSES)
+def test_bad_pyfunc_metric(BallTreeImplementation):
+    def wrong_returned_value(x, y):
+        return "1"
+
+    def one_arg_func(x):
+        return 1.0  # pragma: no cover
+
+    X = np.ones((5, 2))
+    msg = "Custom distance function must accept two vectors and return a float."
+    with pytest.raises(TypeError, match=msg):
+        BallTreeImplementation(X, metric=wrong_returned_value)
+
+    msg = "takes 1 positional argument but 2 were given"
+    with pytest.raises(TypeError, match=msg):
+        BallTreeImplementation(X, metric=one_arg_func)
+
+
+@pytest.mark.parametrize("metric", itertools.chain(METRICS, BOOLEAN_METRICS))
+def test_ball_tree_numerical_consistency(global_random_seed, metric):
+    # Results on float64 and float32 versions of a dataset must be
+    # numerically close.
+    X_64, X_32, Y_64, Y_32 = get_dataset_for_binary_tree(
+        random_seed=global_random_seed, features=50
+    )
+
+    metric_params = METRICS.get(metric, {})
+    bt_64 = BallTree64(X_64, leaf_size=1, metric=metric, **metric_params)
+    bt_32 = BallTree32(X_32, leaf_size=1, metric=metric, **metric_params)
+
+    # Test consistency with respect to the `query` method
+    k = 5
+    dist_64, ind_64 = bt_64.query(Y_64, k=k)
+    dist_32, ind_32 = bt_32.query(Y_32, k=k)
+    assert_allclose(dist_64, dist_32, rtol=1e-5)
+    assert_equal(ind_64, ind_32)
+    assert dist_64.dtype == np.float64
+    assert dist_32.dtype == np.float32
+
+    # Test consistency with respect to the `query_radius` method
+    r = 2.38
+    ind_64 = bt_64.query_radius(Y_64, r=r)
+    ind_32 = bt_32.query_radius(Y_32, r=r)
+    for _ind64, _ind32 in zip(ind_64, ind_32):
+        assert_equal(_ind64, _ind32)
+
+    # Test consistency with respect to the `query_radius` method
+    # with return distances being true
+    ind_64, dist_64 = bt_64.query_radius(Y_64, r=r, return_distance=True)
+    ind_32, dist_32 = bt_32.query_radius(Y_32, r=r, return_distance=True)
+    for _ind64, _ind32, _dist_64, _dist_32 in zip(ind_64, ind_32, dist_64, dist_32):
+        assert_equal(_ind64, _ind32)
+        assert_allclose(_dist_64, _dist_32, rtol=1e-5)
+        assert _dist_64.dtype == np.float64
+        assert _dist_32.dtype == np.float32
+
+
+@pytest.mark.parametrize("metric", itertools.chain(METRICS, BOOLEAN_METRICS))
+def test_kernel_density_numerical_consistency(global_random_seed, metric):
+    # Test consistency with respect to the `kernel_density` method
+    X_64, X_32, Y_64, Y_32 = get_dataset_for_binary_tree(random_seed=global_random_seed)
+
+    metric_params = METRICS.get(metric, {})
+    bt_64 = BallTree64(X_64, leaf_size=1, metric=metric, **metric_params)
+    bt_32 = BallTree32(X_32, leaf_size=1, metric=metric, **metric_params)
+
+    kernel = "gaussian"
+    h = 0.1
+    density64 = bt_64.kernel_density(Y_64, h=h, kernel=kernel, breadth_first=True)
+    density32 = bt_32.kernel_density(Y_32, h=h, kernel=kernel, breadth_first=True)
+    assert_allclose(density64, density32, rtol=1e-5)
+    assert density64.dtype == np.float64
+    assert density32.dtype == np.float32
+
+
+def test_two_point_correlation_numerical_consistency(global_random_seed):
+    # Test consistency with respect to the `two_point_correlation` method
+    X_64, X_32, Y_64, Y_32 = get_dataset_for_binary_tree(random_seed=global_random_seed)
+
+    bt_64 = BallTree64(X_64, leaf_size=10)
+    bt_32 = BallTree32(X_32, leaf_size=10)
+
+    r = np.linspace(0, 1, 10)
+
+    counts_64 = bt_64.two_point_correlation(Y_64, r=r, dualtree=True)
+    counts_32 = bt_32.two_point_correlation(Y_32, r=r, dualtree=True)
+    assert_allclose(counts_64, counts_32)
+
+
+def get_dataset_for_binary_tree(random_seed, features=3):
+    rng = np.random.RandomState(random_seed)
+    _X = rng.rand(100, features)
+    _Y = rng.rand(5, features)
+
+    X_64 = _X.astype(dtype=np.float64, copy=False)
+    Y_64 = _Y.astype(dtype=np.float64, copy=False)
+
+    X_32 = _X.astype(dtype=np.float32, copy=False)
+    Y_32 = _Y.astype(dtype=np.float32, copy=False)
+
+    return X_64, X_32, Y_64, Y_32

linedance-app/venv/lib/python3.12/site-packages/sklearn/neighbors/tests/test_graph.py

@@ -0,0 +1,101 @@
+import numpy as np
+import pytest
+
+from sklearn.metrics import euclidean_distances
+from sklearn.neighbors import KNeighborsTransformer, RadiusNeighborsTransformer
+from sklearn.neighbors._base import _is_sorted_by_data
+from sklearn.utils._testing import assert_array_equal
+
+
+def test_transformer_result():
+    # Test the number of neighbors returned
+    n_neighbors = 5
+    n_samples_fit = 20
+    n_queries = 18
+    n_features = 10
+
+    rng = np.random.RandomState(42)
+    X = rng.randn(n_samples_fit, n_features)
+    X2 = rng.randn(n_queries, n_features)
+    radius = np.percentile(euclidean_distances(X), 10)
+
+    # with n_neighbors
+    for mode in ["distance", "connectivity"]:
+        add_one = mode == "distance"
+        nnt = KNeighborsTransformer(n_neighbors=n_neighbors, mode=mode)
+        Xt = nnt.fit_transform(X)
+        assert Xt.shape == (n_samples_fit, n_samples_fit)
+        assert Xt.data.shape == (n_samples_fit * (n_neighbors + add_one),)
+        assert Xt.format == "csr"
+        assert _is_sorted_by_data(Xt)
+
+        X2t = nnt.transform(X2)
+        assert X2t.shape == (n_queries, n_samples_fit)
+        assert X2t.data.shape == (n_queries * (n_neighbors + add_one),)
+        assert X2t.format == "csr"
+        assert _is_sorted_by_data(X2t)
+
+    # with radius
+    for mode in ["distance", "connectivity"]:
+        add_one = mode == "distance"
+        nnt = RadiusNeighborsTransformer(radius=radius, mode=mode)
+        Xt = nnt.fit_transform(X)
+        assert Xt.shape == (n_samples_fit, n_samples_fit)
+        assert not Xt.data.shape == (n_samples_fit * (n_neighbors + add_one),)
+        assert Xt.format == "csr"
+        assert _is_sorted_by_data(Xt)
+
+        X2t = nnt.transform(X2)
+        assert X2t.shape == (n_queries, n_samples_fit)
+        assert not X2t.data.shape == (n_queries * (n_neighbors + add_one),)
+        assert X2t.format == "csr"
+        assert _is_sorted_by_data(X2t)
+
+
+def _has_explicit_diagonal(X):
+    """Return True if the diagonal is explicitly stored"""
+    X = X.tocoo()
+    explicit = X.row[X.row == X.col]
+    return len(explicit) == X.shape[0]
+
+
+def test_explicit_diagonal():
+    # Test that the diagonal is explicitly stored in the sparse graph
+    n_neighbors = 5
+    n_samples_fit, n_samples_transform, n_features = 20, 18, 10
+    rng = np.random.RandomState(42)
+    X = rng.randn(n_samples_fit, n_features)
+    X2 = rng.randn(n_samples_transform, n_features)
+
+    nnt = KNeighborsTransformer(n_neighbors=n_neighbors)
+    Xt = nnt.fit_transform(X)
+    assert _has_explicit_diagonal(Xt)
+    assert np.all(Xt.data.reshape(n_samples_fit, n_neighbors + 1)[:, 0] == 0)
+
+    Xt = nnt.transform(X)
+    assert _has_explicit_diagonal(Xt)
+    assert np.all(Xt.data.reshape(n_samples_fit, n_neighbors + 1)[:, 0] == 0)
+
+    # Using transform on new data should not always have zero diagonal
+    X2t = nnt.transform(X2)
+    assert not _has_explicit_diagonal(X2t)
+
+
+@pytest.mark.parametrize("Klass", [KNeighborsTransformer, RadiusNeighborsTransformer])
+def test_graph_feature_names_out(Klass):
+    """Check `get_feature_names_out` for transformers defined in `_graph.py`."""
+
+    n_samples_fit = 20
+    n_features = 10
+    rng = np.random.RandomState(42)
+    X = rng.randn(n_samples_fit, n_features)
+
+    est = Klass().fit(X)
+    names_out = est.get_feature_names_out()
+
+    class_name_lower = Klass.__name__.lower()
+    expected_names_out = np.array(
+        [f"{class_name_lower}{i}" for i in range(est.n_samples_fit_)],
+        dtype=object,
+    )
+    assert_array_equal(names_out, expected_names_out)

linedance-app/venv/lib/python3.12/site-packages/sklearn/neighbors/tests/test_kd_tree.py

@@ -0,0 +1,103 @@
+import numpy as np
+import pytest
+from numpy.testing import assert_allclose, assert_equal
+
+from sklearn.neighbors._kd_tree import KDTree, KDTree32, KDTree64
+from sklearn.neighbors.tests.test_ball_tree import get_dataset_for_binary_tree
+from sklearn.utils.parallel import Parallel, delayed
+
+DIMENSION = 3
+
+METRICS = {"euclidean": {}, "manhattan": {}, "chebyshev": {}, "minkowski": dict(p=3)}
+
+KD_TREE_CLASSES = [
+    KDTree64,
+    KDTree32,
+]
+
+
+def test_KDTree_is_KDTree64_subclass():
+    assert issubclass(KDTree, KDTree64)
+
+
+@pytest.mark.parametrize("BinarySearchTree", KD_TREE_CLASSES)
+def test_array_object_type(BinarySearchTree):
+    """Check that we do not accept object dtype array."""
+    X = np.array([(1, 2, 3), (2, 5), (5, 5, 1, 2)], dtype=object)
+    with pytest.raises(ValueError, match="setting an array element with a sequence"):
+        BinarySearchTree(X)
+
+
+# TODO: remove mark once loky bug is fixed:
+# https://github.com/joblib/loky/issues/458
+@pytest.mark.thread_unsafe
+@pytest.mark.parametrize("BinarySearchTree", KD_TREE_CLASSES)
+def test_kdtree_picklable_with_joblib(BinarySearchTree):
+    """Make sure that KDTree queries work when joblib memmaps.
+
+    Non-regression test for #21685 and #21228."""
+    rng = np.random.RandomState(0)
+    X = rng.random_sample((10, 3))
+    tree = BinarySearchTree(X, leaf_size=2)
+
+    # Call Parallel with max_nbytes=1 to trigger readonly memory mapping that
+    # use to raise "ValueError: buffer source array is read-only" in a previous
+    # version of the Cython code.
+    Parallel(n_jobs=2, max_nbytes=1)(delayed(tree.query)(data) for data in 2 * [X])
+
+
+@pytest.mark.parametrize("metric", METRICS)
+def test_kd_tree_numerical_consistency(global_random_seed, metric):
+    # Results on float64 and float32 versions of a dataset must be
+    # numerically close.
+    X_64, X_32, Y_64, Y_32 = get_dataset_for_binary_tree(
+        random_seed=global_random_seed, features=50
+    )
+
+    metric_params = METRICS.get(metric, {})
+    kd_64 = KDTree64(X_64, leaf_size=2, metric=metric, **metric_params)
+    kd_32 = KDTree32(X_32, leaf_size=2, metric=metric, **metric_params)
+
+    # Test consistency with respect to the `query` method
+    k = 4
+    dist_64, ind_64 = kd_64.query(Y_64, k=k)
+    dist_32, ind_32 = kd_32.query(Y_32, k=k)
+    assert_allclose(dist_64, dist_32, rtol=1e-5)
+    assert_equal(ind_64, ind_32)
+    assert dist_64.dtype == np.float64
+    assert dist_32.dtype == np.float32
+
+    # Test consistency with respect to the `query_radius` method
+    r = 2.38
+    ind_64 = kd_64.query_radius(Y_64, r=r)
+    ind_32 = kd_32.query_radius(Y_32, r=r)
+    for _ind64, _ind32 in zip(ind_64, ind_32):
+        assert_equal(_ind64, _ind32)
+
+    # Test consistency with respect to the `query_radius` method
+    # with return distances being true
+    ind_64, dist_64 = kd_64.query_radius(Y_64, r=r, return_distance=True)
+    ind_32, dist_32 = kd_32.query_radius(Y_32, r=r, return_distance=True)
+    for _ind64, _ind32, _dist_64, _dist_32 in zip(ind_64, ind_32, dist_64, dist_32):
+        assert_equal(_ind64, _ind32)
+        assert_allclose(_dist_64, _dist_32, rtol=1e-5)
+        assert _dist_64.dtype == np.float64
+        assert _dist_32.dtype == np.float32
+
+
+@pytest.mark.parametrize("metric", METRICS)
+def test_kernel_density_numerical_consistency(global_random_seed, metric):
+    # Test consistency with respect to the `kernel_density` method
+    X_64, X_32, Y_64, Y_32 = get_dataset_for_binary_tree(random_seed=global_random_seed)
+
+    metric_params = METRICS.get(metric, {})
+    kd_64 = KDTree64(X_64, leaf_size=2, metric=metric, **metric_params)
+    kd_32 = KDTree32(X_32, leaf_size=2, metric=metric, **metric_params)
+
+    kernel = "gaussian"
+    h = 0.1
+    density64 = kd_64.kernel_density(Y_64, h=h, kernel=kernel, breadth_first=True)
+    density32 = kd_32.kernel_density(Y_32, h=h, kernel=kernel, breadth_first=True)
+    assert_allclose(density64, density32, rtol=1e-5)
+    assert density64.dtype == np.float64
+    assert density32.dtype == np.float32

linedance-app/venv/lib/python3.12/site-packages/sklearn/neighbors/tests/test_kde.py

@@ -0,0 +1,252 @@
+import joblib
+import numpy as np
+import pytest
+
+from sklearn.datasets import make_blobs
+from sklearn.exceptions import NotFittedError
+from sklearn.model_selection import GridSearchCV
+from sklearn.neighbors import KDTree, KernelDensity, NearestNeighbors
+from sklearn.neighbors._ball_tree import kernel_norm
+from sklearn.pipeline import make_pipeline
+from sklearn.preprocessing import StandardScaler
+from sklearn.utils._testing import assert_allclose
+
+
+# XXX Duplicated in test_neighbors_tree, test_kde
+def compute_kernel_slow(Y, X, kernel, h):
+    if h == "scott":
+        h = X.shape[0] ** (-1 / (X.shape[1] + 4))
+    elif h == "silverman":
+        h = (X.shape[0] * (X.shape[1] + 2) / 4) ** (-1 / (X.shape[1] + 4))
+
+    d = np.sqrt(((Y[:, None, :] - X) ** 2).sum(-1))
+    norm = kernel_norm(h, X.shape[1], kernel) / X.shape[0]
+
+    if kernel == "gaussian":
+        return norm * np.exp(-0.5 * (d * d) / (h * h)).sum(-1)
+    elif kernel == "tophat":
+        return norm * (d < h).sum(-1)
+    elif kernel == "epanechnikov":
+        return norm * ((1.0 - (d * d) / (h * h)) * (d < h)).sum(-1)
+    elif kernel == "exponential":
+        return norm * (np.exp(-d / h)).sum(-1)
+    elif kernel == "linear":
+        return norm * ((1 - d / h) * (d < h)).sum(-1)
+    elif kernel == "cosine":
+        return norm * (np.cos(0.5 * np.pi * d / h) * (d < h)).sum(-1)
+    else:
+        raise ValueError("kernel not recognized")
+
+
+def check_results(kernel, bandwidth, atol, rtol, X, Y, dens_true):
+    kde = KernelDensity(kernel=kernel, bandwidth=bandwidth, atol=atol, rtol=rtol)
+    log_dens = kde.fit(X).score_samples(Y)
+    assert_allclose(np.exp(log_dens), dens_true, atol=atol, rtol=max(1e-7, rtol))
+    assert_allclose(
+        np.exp(kde.score(Y)), np.prod(dens_true), atol=atol, rtol=max(1e-7, rtol)
+    )
+
+
+@pytest.mark.parametrize(
+    "kernel", ["gaussian", "tophat", "epanechnikov", "exponential", "linear", "cosine"]
+)
+@pytest.mark.parametrize("bandwidth", [0.01, 0.1, 1, "scott", "silverman"])
+def test_kernel_density(kernel, bandwidth):
+    n_samples, n_features = (100, 3)
+
+    rng = np.random.RandomState(0)
+    X = rng.randn(n_samples, n_features)
+    Y = rng.randn(n_samples, n_features)
+
+    dens_true = compute_kernel_slow(Y, X, kernel, bandwidth)
+
+    for rtol in [0, 1e-5]:
+        for atol in [1e-6, 1e-2]:
+            for breadth_first in (True, False):
+                check_results(kernel, bandwidth, atol, rtol, X, Y, dens_true)
+
+
+def test_kernel_density_sampling(n_samples=100, n_features=3):
+    rng = np.random.RandomState(0)
+    X = rng.randn(n_samples, n_features)
+
+    bandwidth = 0.2
+
+    for kernel in ["gaussian", "tophat"]:
+        # draw a tophat sample
+        kde = KernelDensity(bandwidth=bandwidth, kernel=kernel).fit(X)
+        samp = kde.sample(100)
+        assert X.shape == samp.shape
+
+        # check that samples are in the right range
+        nbrs = NearestNeighbors(n_neighbors=1).fit(X)
+        dist, ind = nbrs.kneighbors(X, return_distance=True)
+
+        if kernel == "tophat":
+            assert np.all(dist < bandwidth)
+        elif kernel == "gaussian":
+            # 5 standard deviations is safe for 100 samples, but there's a
+            # very small chance this test could fail.
+            assert np.all(dist < 5 * bandwidth)
+
+    # check unsupported kernels
+    for kernel in ["epanechnikov", "exponential", "linear", "cosine"]:
+        kde = KernelDensity(bandwidth=bandwidth, kernel=kernel).fit(X)
+        with pytest.raises(NotImplementedError):
+            kde.sample(100)
+
+    # non-regression test: used to return a scalar
+    X = rng.randn(4, 1)
+    kde = KernelDensity(kernel="gaussian").fit(X)
+    assert kde.sample().shape == (1, 1)
+
+
+@pytest.mark.parametrize("algorithm", ["auto", "ball_tree", "kd_tree"])
+@pytest.mark.parametrize(
+    "metric", ["euclidean", "minkowski", "manhattan", "chebyshev", "haversine"]
+)
+def test_kde_algorithm_metric_choice(algorithm, metric):
+    # Smoke test for various metrics and algorithms
+    rng = np.random.RandomState(0)
+    X = rng.randn(10, 2)  # 2 features required for haversine dist.
+    Y = rng.randn(10, 2)
+
+    kde = KernelDensity(algorithm=algorithm, metric=metric)
+
+    if algorithm == "kd_tree" and metric not in KDTree.valid_metrics:
+        with pytest.raises(ValueError, match="invalid metric"):
+            kde.fit(X)
+    else:
+        kde.fit(X)
+        y_dens = kde.score_samples(Y)
+        assert y_dens.shape == Y.shape[:1]
+
+
+def test_kde_score(n_samples=100, n_features=3):
+    pass
+    # FIXME
+    # rng = np.random.RandomState(0)
+    # X = rng.random_sample((n_samples, n_features))
+    # Y = rng.random_sample((n_samples, n_features))
+
+
+def test_kde_sample_weights_error():
+    kde = KernelDensity()
+    with pytest.raises(ValueError):
+        kde.fit(np.random.random((200, 10)), sample_weight=np.random.random((200, 10)))
+    with pytest.raises(ValueError):
+        kde.fit(np.random.random((200, 10)), sample_weight=-np.random.random(200))
+
+
+def test_kde_pipeline_gridsearch():
+    # test that kde plays nice in pipelines and grid-searches
+    X, _ = make_blobs(cluster_std=0.1, random_state=1, centers=[[0, 1], [1, 0], [0, 0]])
+    pipe1 = make_pipeline(
+        StandardScaler(with_mean=False, with_std=False),
+        KernelDensity(kernel="gaussian"),
+    )
+    params = dict(kerneldensity__bandwidth=[0.001, 0.01, 0.1, 1, 10])
+    search = GridSearchCV(pipe1, param_grid=params)
+    search.fit(X)
+    assert search.best_params_["kerneldensity__bandwidth"] == 0.1
+
+
+def test_kde_sample_weights():
+    n_samples = 400
+    size_test = 20
+    weights_neutral = np.full(n_samples, 3.0)
+    for d in [1, 2, 10]:
+        rng = np.random.RandomState(0)
+        X = rng.rand(n_samples, d)
+        weights = 1 + (10 * X.sum(axis=1)).astype(np.int8)
+        X_repetitions = np.repeat(X, weights, axis=0)
+        n_samples_test = size_test // d
+        test_points = rng.rand(n_samples_test, d)
+        for algorithm in ["auto", "ball_tree", "kd_tree"]:
+            for metric in ["euclidean", "minkowski", "manhattan", "chebyshev"]:
+                if algorithm != "kd_tree" or metric in KDTree.valid_metrics:
+                    kde = KernelDensity(algorithm=algorithm, metric=metric)
+
+                    # Test that adding a constant sample weight has no effect
+                    kde.fit(X, sample_weight=weights_neutral)
+                    scores_const_weight = kde.score_samples(test_points)
+                    sample_const_weight = kde.sample(random_state=1234)
+                    kde.fit(X)
+                    scores_no_weight = kde.score_samples(test_points)
+                    sample_no_weight = kde.sample(random_state=1234)
+                    assert_allclose(scores_const_weight, scores_no_weight)
+                    assert_allclose(sample_const_weight, sample_no_weight)
+
+                    # Test equivalence between sampling and (integer) weights
+                    kde.fit(X, sample_weight=weights)
+                    scores_weight = kde.score_samples(test_points)
+                    sample_weight = kde.sample(random_state=1234)
+                    kde.fit(X_repetitions)
+                    scores_ref_sampling = kde.score_samples(test_points)
+                    sample_ref_sampling = kde.sample(random_state=1234)
+                    assert_allclose(scores_weight, scores_ref_sampling)
+                    assert_allclose(sample_weight, sample_ref_sampling)
+
+                    # Test that sample weights has a non-trivial effect
+                    diff = np.max(np.abs(scores_no_weight - scores_weight))
+                    assert diff > 0.001
+
+                    # Test invariance with respect to arbitrary scaling
+                    scale_factor = rng.rand()
+                    kde.fit(X, sample_weight=(scale_factor * weights))
+                    scores_scaled_weight = kde.score_samples(test_points)
+                    assert_allclose(scores_scaled_weight, scores_weight)
+
+
+@pytest.mark.parametrize("sample_weight", [None, [0.1, 0.2, 0.3]])
+def test_pickling(tmpdir, sample_weight):
+    # Make sure that predictions are the same before and after pickling. Used
+    # to be a bug because sample_weights wasn't pickled and the resulting tree
+    # would miss some info.
+
+    kde = KernelDensity()
+    data = np.reshape([1.0, 2.0, 3.0], (-1, 1))
+    kde.fit(data, sample_weight=sample_weight)
+
+    X = np.reshape([1.1, 2.1], (-1, 1))
+    scores = kde.score_samples(X)
+
+    file_path = str(tmpdir.join("dump.pkl"))
+    joblib.dump(kde, file_path)
+    kde = joblib.load(file_path)
+    scores_pickled = kde.score_samples(X)
+
+    assert_allclose(scores, scores_pickled)
+
+
+@pytest.mark.parametrize("method", ["score_samples", "sample"])
+def test_check_is_fitted(method):
+    # Check that predict raises an exception in an unfitted estimator.
+    # Unfitted estimators should raise a NotFittedError.
+    rng = np.random.RandomState(0)
+    X = rng.randn(10, 2)
+    kde = KernelDensity()
+
+    with pytest.raises(NotFittedError):
+        getattr(kde, method)(X)
+
+
+@pytest.mark.parametrize("bandwidth", ["scott", "silverman", 0.1])
+def test_bandwidth(bandwidth):
+    n_samples, n_features = (100, 3)
+    rng = np.random.RandomState(0)
+    X = rng.randn(n_samples, n_features)
+    kde = KernelDensity(bandwidth=bandwidth).fit(X)
+    samp = kde.sample(100)
+    kde_sc = kde.score_samples(X)
+    assert X.shape == samp.shape
+    assert kde_sc.shape == (n_samples,)
+
+    # Test that the attribute self.bandwidth_ has the expected value
+    if bandwidth == "scott":
+        h = X.shape[0] ** (-1 / (X.shape[1] + 4))
+    elif bandwidth == "silverman":
+        h = (X.shape[0] * (X.shape[1] + 2) / 4) ** (-1 / (X.shape[1] + 4))
+    else:
+        h = bandwidth
+    assert kde.bandwidth_ == pytest.approx(h)

linedance-app/venv/lib/python3.12/site-packages/sklearn/neighbors/tests/test_lof.py

@@ -0,0 +1,394 @@
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
+import re
+from math import sqrt
+
+import numpy as np
+import pytest
+
+from sklearn import metrics, neighbors
+from sklearn.datasets import load_iris
+from sklearn.metrics import roc_auc_score
+from sklearn.utils import check_random_state
+from sklearn.utils._testing import assert_allclose, assert_array_equal
+from sklearn.utils.estimator_checks import (
+    check_outlier_corruption,
+    parametrize_with_checks,
+)
+from sklearn.utils.fixes import CSR_CONTAINERS
+
+# load the iris dataset
+# and randomly permute it
+rng = check_random_state(0)
+iris = load_iris()
+perm = rng.permutation(iris.target.size)
+iris.data = iris.data[perm]
+iris.target = iris.target[perm]
+
+
+def test_lof(global_dtype):
+    # Toy sample (the last two samples are outliers):
+    X = np.asarray(
+        [[-2, -1], [-1, -1], [-1, -2], [1, 1], [1, 2], [2, 1], [5, 3], [-4, 2]],
+        dtype=global_dtype,
+    )
+
+    # Test LocalOutlierFactor:
+    clf = neighbors.LocalOutlierFactor(n_neighbors=5)
+    score = clf.fit(X).negative_outlier_factor_
+    assert_array_equal(clf._fit_X, X)
+
+    # Assert largest outlier score is smaller than smallest inlier score:
+    assert np.min(score[:-2]) > np.max(score[-2:])
+
+    # Assert predict() works:
+    clf = neighbors.LocalOutlierFactor(contamination=0.25, n_neighbors=5).fit(X)
+    expected_predictions = 6 * [1] + 2 * [-1]
+    assert_array_equal(clf._predict(), expected_predictions)
+    assert_array_equal(clf.fit_predict(X), expected_predictions)
+
+
+def test_lof_performance(global_dtype):
+    # Generate train/test data
+    rng = check_random_state(2)
+    X = 0.3 * rng.randn(120, 2).astype(global_dtype, copy=False)
+    X_train = X[:100]
+
+    # Generate some abnormal novel observations
+    X_outliers = rng.uniform(low=-4, high=4, size=(20, 2)).astype(
+        global_dtype, copy=False
+    )
+    X_test = np.r_[X[100:], X_outliers]
+    y_test = np.array([0] * 20 + [1] * 20)
+
+    # fit the model for novelty detection
+    clf = neighbors.LocalOutlierFactor(novelty=True).fit(X_train)
+
+    # predict scores (the lower, the more normal)
+    y_pred = -clf.decision_function(X_test)
+
+    # check that roc_auc is good
+    assert roc_auc_score(y_test, y_pred) > 0.99
+
+
+def test_lof_values(global_dtype):
+    # toy samples:
+    X_train = np.asarray([[1, 1], [1, 2], [2, 1]], dtype=global_dtype)
+    clf1 = neighbors.LocalOutlierFactor(
+        n_neighbors=2, contamination=0.1, novelty=True
+    ).fit(X_train)
+    clf2 = neighbors.LocalOutlierFactor(n_neighbors=2, novelty=True).fit(X_train)
+    s_0 = 2.0 * sqrt(2.0) / (1.0 + sqrt(2.0))
+    s_1 = (1.0 + sqrt(2)) * (1.0 / (4.0 * sqrt(2.0)) + 1.0 / (2.0 + 2.0 * sqrt(2)))
+    # check predict()
+    assert_allclose(-clf1.negative_outlier_factor_, [s_0, s_1, s_1])
+    assert_allclose(-clf2.negative_outlier_factor_, [s_0, s_1, s_1])
+    # check predict(one sample not in train)
+    assert_allclose(-clf1.score_samples([[2.0, 2.0]]), [s_0])
+    assert_allclose(-clf2.score_samples([[2.0, 2.0]]), [s_0])
+    # check predict(one sample already in train)
+    assert_allclose(-clf1.score_samples([[1.0, 1.0]]), [s_1])
+    assert_allclose(-clf2.score_samples([[1.0, 1.0]]), [s_1])
+
+
+def test_lof_precomputed(global_dtype, random_state=42):
+    """Tests LOF with a distance matrix."""
+    # Note: smaller samples may result in spurious test success
+    rng = np.random.RandomState(random_state)
+    X = rng.random_sample((10, 4)).astype(global_dtype, copy=False)
+    Y = rng.random_sample((3, 4)).astype(global_dtype, copy=False)
+    DXX = metrics.pairwise_distances(X, metric="euclidean")
+    DYX = metrics.pairwise_distances(Y, X, metric="euclidean")
+    # As a feature matrix (n_samples by n_features)
+    lof_X = neighbors.LocalOutlierFactor(n_neighbors=3, novelty=True)
+    lof_X.fit(X)
+    pred_X_X = lof_X._predict()
+    pred_X_Y = lof_X.predict(Y)
+
+    # As a dense distance matrix (n_samples by n_samples)
+    lof_D = neighbors.LocalOutlierFactor(
+        n_neighbors=3, algorithm="brute", metric="precomputed", novelty=True
+    )
+    lof_D.fit(DXX)
+    pred_D_X = lof_D._predict()
+    pred_D_Y = lof_D.predict(DYX)
+
+    assert_allclose(pred_X_X, pred_D_X)
+    assert_allclose(pred_X_Y, pred_D_Y)
+
+
+def test_n_neighbors_attribute():
+    X = iris.data
+    clf = neighbors.LocalOutlierFactor(n_neighbors=500).fit(X)
+    assert clf.n_neighbors_ == X.shape[0] - 1
+
+    clf = neighbors.LocalOutlierFactor(n_neighbors=500)
+    msg = "n_neighbors will be set to (n_samples - 1)"
+    with pytest.warns(UserWarning, match=re.escape(msg)):
+        clf.fit(X)
+    assert clf.n_neighbors_ == X.shape[0] - 1
+
+
+def test_score_samples(global_dtype):
+    X_train = np.asarray([[1, 1], [1, 2], [2, 1]], dtype=global_dtype)
+    X_test = np.asarray([[2.0, 2.0]], dtype=global_dtype)
+    clf1 = neighbors.LocalOutlierFactor(
+        n_neighbors=2, contamination=0.1, novelty=True
+    ).fit(X_train)
+    clf2 = neighbors.LocalOutlierFactor(n_neighbors=2, novelty=True).fit(X_train)
+
+    clf1_scores = clf1.score_samples(X_test)
+    clf1_decisions = clf1.decision_function(X_test)
+
+    clf2_scores = clf2.score_samples(X_test)
+    clf2_decisions = clf2.decision_function(X_test)
+
+    assert_allclose(
+        clf1_scores,
+        clf1_decisions + clf1.offset_,
+    )
+    assert_allclose(
+        clf2_scores,
+        clf2_decisions + clf2.offset_,
+    )
+    assert_allclose(clf1_scores, clf2_scores)
+
+
+def test_novelty_errors():
+    X = iris.data
+
+    # check errors for novelty=False
+    clf = neighbors.LocalOutlierFactor()
+    clf.fit(X)
+    # predict, decision_function and score_samples raise ValueError
+    for method in ["predict", "decision_function", "score_samples"]:
+        outer_msg = f"'LocalOutlierFactor' has no attribute '{method}'"
+        inner_msg = "{} is not available when novelty=False".format(method)
+        with pytest.raises(AttributeError, match=outer_msg) as exec_info:
+            getattr(clf, method)
+
+        assert isinstance(exec_info.value.__cause__, AttributeError)
+        assert inner_msg in str(exec_info.value.__cause__)
+
+    # check errors for novelty=True
+    clf = neighbors.LocalOutlierFactor(novelty=True)
+
+    outer_msg = "'LocalOutlierFactor' has no attribute 'fit_predict'"
+    inner_msg = "fit_predict is not available when novelty=True"
+    with pytest.raises(AttributeError, match=outer_msg) as exec_info:
+        getattr(clf, "fit_predict")
+
+    assert isinstance(exec_info.value.__cause__, AttributeError)
+    assert inner_msg in str(exec_info.value.__cause__)
+
+
+def test_novelty_training_scores(global_dtype):
+    # check that the scores of the training samples are still accessible
+    # when novelty=True through the negative_outlier_factor_ attribute
+    X = iris.data.astype(global_dtype)
+
+    # fit with novelty=False
+    clf_1 = neighbors.LocalOutlierFactor()
+    clf_1.fit(X)
+    scores_1 = clf_1.negative_outlier_factor_
+
+    # fit with novelty=True
+    clf_2 = neighbors.LocalOutlierFactor(novelty=True)
+    clf_2.fit(X)
+    scores_2 = clf_2.negative_outlier_factor_
+
+    assert_allclose(scores_1, scores_2)
+
+
+def test_hasattr_prediction():
+    # check availability of prediction methods depending on novelty value.
+    X = [[1, 1], [1, 2], [2, 1]]
+
+    # when novelty=True
+    clf = neighbors.LocalOutlierFactor(novelty=True)
+    clf.fit(X)
+    assert hasattr(clf, "predict")
+    assert hasattr(clf, "decision_function")
+    assert hasattr(clf, "score_samples")
+    assert not hasattr(clf, "fit_predict")
+
+    # when novelty=False
+    clf = neighbors.LocalOutlierFactor(novelty=False)
+    clf.fit(X)
+    assert hasattr(clf, "fit_predict")
+    assert not hasattr(clf, "predict")
+    assert not hasattr(clf, "decision_function")
+    assert not hasattr(clf, "score_samples")
+
+
+@parametrize_with_checks([neighbors.LocalOutlierFactor(novelty=True)])
+def test_novelty_true_common_tests(estimator, check):
+    # the common tests are run for the default LOF (novelty=False).
+    # here we run these common tests for LOF when novelty=True
+    check(estimator)
+
+
+@pytest.mark.parametrize("expected_outliers", [30, 53])
+def test_predicted_outlier_number(expected_outliers):
+    # the number of predicted outliers should be equal to the number of
+    # expected outliers unless there are ties in the abnormality scores.
+    X = iris.data
+    n_samples = X.shape[0]
+    contamination = float(expected_outliers) / n_samples
+
+    clf = neighbors.LocalOutlierFactor(contamination=contamination)
+    y_pred = clf.fit_predict(X)
+
+    num_outliers = np.sum(y_pred != 1)
+    if num_outliers != expected_outliers:
+        y_dec = clf.negative_outlier_factor_
+        check_outlier_corruption(num_outliers, expected_outliers, y_dec)
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+def test_sparse(csr_container):
+    # LocalOutlierFactor must support CSR inputs
+    # TODO: compare results on dense and sparse data as proposed in:
+    # https://github.com/scikit-learn/scikit-learn/pull/23585#discussion_r968388186
+    X = csr_container(iris.data)
+
+    lof = neighbors.LocalOutlierFactor(novelty=True)
+    lof.fit(X)
+    lof.predict(X)
+    lof.score_samples(X)
+    lof.decision_function(X)
+
+    lof = neighbors.LocalOutlierFactor(novelty=False)
+    lof.fit_predict(X)
+
+
+def test_lof_error_n_neighbors_too_large():
+    """Check that we raise a proper error message when n_neighbors == n_samples.
+
+    Non-regression test for:
+    https://github.com/scikit-learn/scikit-learn/issues/17207
+    """
+    X = np.ones((7, 7))
+
+    msg = (
+        "Expected n_neighbors < n_samples_fit, but n_neighbors = 1, "
+        "n_samples_fit = 1, n_samples = 1"
+    )
+    with pytest.raises(ValueError, match=msg):
+        lof = neighbors.LocalOutlierFactor(n_neighbors=1).fit(X[:1])
+
+    lof = neighbors.LocalOutlierFactor(n_neighbors=2).fit(X[:2])
+    assert lof.n_samples_fit_ == 2
+
+    msg = (
+        "Expected n_neighbors < n_samples_fit, but n_neighbors = 2, "
+        "n_samples_fit = 2, n_samples = 2"
+    )
+    with pytest.raises(ValueError, match=msg):
+        lof.kneighbors(None, n_neighbors=2)
+
+    distances, indices = lof.kneighbors(None, n_neighbors=1)
+    assert distances.shape == (2, 1)
+    assert indices.shape == (2, 1)
+
+    msg = (
+        "Expected n_neighbors <= n_samples_fit, but n_neighbors = 3, "
+        "n_samples_fit = 2, n_samples = 7"
+    )
+    with pytest.raises(ValueError, match=msg):
+        lof.kneighbors(X, n_neighbors=3)
+
+    (
+        distances,
+        indices,
+    ) = lof.kneighbors(X, n_neighbors=2)
+    assert distances.shape == (7, 2)
+    assert indices.shape == (7, 2)
+
+
+@pytest.mark.parametrize("algorithm", ["auto", "ball_tree", "kd_tree", "brute"])
+@pytest.mark.parametrize("novelty", [True, False])
+@pytest.mark.parametrize("contamination", [0.5, "auto"])
+def test_lof_input_dtype_preservation(global_dtype, algorithm, contamination, novelty):
+    """Check that the fitted attributes are stored using the data type of X."""
+    X = iris.data.astype(global_dtype, copy=False)
+
+    iso = neighbors.LocalOutlierFactor(
+        n_neighbors=5, algorithm=algorithm, contamination=contamination, novelty=novelty
+    )
+    iso.fit(X)
+
+    assert iso.negative_outlier_factor_.dtype == global_dtype
+
+    for method in ("score_samples", "decision_function"):
+        if hasattr(iso, method):
+            y_pred = getattr(iso, method)(X)
+            assert y_pred.dtype == global_dtype
+
+
+@pytest.mark.parametrize("algorithm", ["auto", "ball_tree", "kd_tree", "brute"])
+@pytest.mark.parametrize("novelty", [True, False])
+@pytest.mark.parametrize("contamination", [0.5, "auto"])
+def test_lof_dtype_equivalence(algorithm, novelty, contamination):
+    """Check the equivalence of the results with 32 and 64 bits input."""
+
+    inliers = iris.data[:50]  # setosa iris are really distinct from others
+    outliers = iris.data[-5:]  # virginica will be considered as outliers
+    # lower the precision of the input data to check that we have an equivalence when
+    # making the computation in 32 and 64 bits.
+    X = np.concatenate([inliers, outliers], axis=0).astype(np.float32)
+
+    lof_32 = neighbors.LocalOutlierFactor(
+        algorithm=algorithm, novelty=novelty, contamination=contamination
+    )
+    X_32 = X.astype(np.float32, copy=True)
+    lof_32.fit(X_32)
+
+    lof_64 = neighbors.LocalOutlierFactor(
+        algorithm=algorithm, novelty=novelty, contamination=contamination
+    )
+    X_64 = X.astype(np.float64, copy=True)
+    lof_64.fit(X_64)
+
+    assert_allclose(lof_32.negative_outlier_factor_, lof_64.negative_outlier_factor_)
+
+    for method in ("score_samples", "decision_function", "predict", "fit_predict"):
+        if hasattr(lof_32, method):
+            y_pred_32 = getattr(lof_32, method)(X_32)
+            y_pred_64 = getattr(lof_64, method)(X_64)
+            assert_allclose(y_pred_32, y_pred_64, atol=0.0002)
+
+
+def test_lof_duplicate_samples():
+    """
+    Check that LocalOutlierFactor raises a warning when duplicate values
+    in the training data cause inaccurate results.
+
+    Non-regression test for:
+    https://github.com/scikit-learn/scikit-learn/issues/27839
+    """
+
+    rng = np.random.default_rng(0)
+
+    x = rng.permutation(
+        np.hstack(
+            [
+                [0.1] * 1000,  # constant values
+                np.linspace(0.1, 0.3, num=3000),
+                rng.random(500) * 100,  # the clear outliers
+            ]
+        )
+    )
+    X = x.reshape(-1, 1)
+
+    error_msg = (
+        "Duplicate values are leading to incorrect results. "
+        "Increase the number of neighbors for more accurate results."
+    )
+
+    lof = neighbors.LocalOutlierFactor(n_neighbors=5, contamination=0.1)
+
+    # Catch the warning
+    with pytest.warns(UserWarning, match=re.escape(error_msg)):
+        lof.fit_predict(X)

linedance-app/venv/lib/python3.12/site-packages/sklearn/neighbors/tests/test_nca.py

@@ -0,0 +1,563 @@
+"""
+Testing for Neighborhood Component Analysis module (sklearn.neighbors.nca)
+"""
+
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
+import re
+
+import numpy as np
+import pytest
+from numpy.testing import assert_array_almost_equal, assert_array_equal
+from scipy.optimize import check_grad
+
+from sklearn import clone
+from sklearn.datasets import load_iris, make_blobs, make_classification
+from sklearn.exceptions import ConvergenceWarning
+from sklearn.metrics import pairwise_distances
+from sklearn.neighbors import NeighborhoodComponentsAnalysis
+from sklearn.preprocessing import LabelEncoder
+from sklearn.utils import check_random_state
+from sklearn.utils.validation import validate_data
+
+rng = check_random_state(0)
+# Load and shuffle the iris dataset.
+iris = load_iris()
+perm = rng.permutation(iris.target.size)
+iris_data = iris.data[perm]
+iris_target = iris.target[perm]
+# Avoid having test data introducing dependencies between tests.
+iris_data.flags.writeable = False
+iris_target.flags.writeable = False
+EPS = np.finfo(float).eps
+
+
+def test_simple_example():
+    """Test on a simple example.
+
+    Puts four points in the input space where the opposite labels points are
+    next to each other. After transform the samples from the same class
+    should be next to each other.
+
+    """
+    X = np.array([[0, 0], [0, 1], [2, 0], [2, 1]])
+    y = np.array([1, 0, 1, 0])
+    nca = NeighborhoodComponentsAnalysis(
+        n_components=2, init="identity", random_state=42
+    )
+    nca.fit(X, y)
+    X_t = nca.transform(X)
+    assert_array_equal(pairwise_distances(X_t).argsort()[:, 1], np.array([2, 3, 0, 1]))
+
+
+def test_toy_example_collapse_points():
+    """Test on a toy example of three points that should collapse
+
+    We build a simple example: two points from the same class and a point from
+    a different class in the middle of them. On this simple example, the new
+    (transformed) points should all collapse into one single point. Indeed, the
+    objective is 2/(1 + exp(d/2)), with d the euclidean distance between the
+    two samples from the same class. This is maximized for d=0 (because d>=0),
+    with an objective equal to 1 (loss=-1.).
+
+    """
+    rng = np.random.RandomState(42)
+    input_dim = 5
+    two_points = rng.randn(2, input_dim)
+    X = np.vstack([two_points, two_points.mean(axis=0)[np.newaxis, :]])
+    y = [0, 0, 1]
+
+    class LossStorer:
+        def __init__(self, X, y):
+            self.loss = np.inf  # initialize the loss to very high
+            # Initialize a fake NCA and variables needed to compute the loss:
+            self.fake_nca = NeighborhoodComponentsAnalysis()
+            self.fake_nca.n_iter_ = np.inf
+            self.X, y = validate_data(self.fake_nca, X, y, ensure_min_samples=2)
+            y = LabelEncoder().fit_transform(y)
+            self.same_class_mask = y[:, np.newaxis] == y[np.newaxis, :]
+
+        def callback(self, transformation, n_iter):
+            """Stores the last value of the loss function"""
+            self.loss, _ = self.fake_nca._loss_grad_lbfgs(
+                transformation, self.X, self.same_class_mask, -1.0
+            )
+
+    loss_storer = LossStorer(X, y)
+    nca = NeighborhoodComponentsAnalysis(random_state=42, callback=loss_storer.callback)
+    X_t = nca.fit_transform(X, y)
+    print(X_t)
+    # test that points are collapsed into one point
+    assert_array_almost_equal(X_t - X_t[0], 0.0)
+    assert abs(loss_storer.loss + 1) < 1e-10
+
+
+def test_finite_differences(global_random_seed):
+    """Test gradient of loss function
+
+    Assert that the gradient is almost equal to its finite differences
+    approximation.
+    """
+    # Initialize the transformation `M`, as well as `X` and `y` and `NCA`
+    rng = np.random.RandomState(global_random_seed)
+    X, y = make_classification(random_state=global_random_seed)
+    M = rng.randn(rng.randint(1, X.shape[1] + 1), X.shape[1])
+    nca = NeighborhoodComponentsAnalysis()
+    nca.n_iter_ = 0
+    mask = y[:, np.newaxis] == y[np.newaxis, :]
+
+    def fun(M):
+        return nca._loss_grad_lbfgs(M, X, mask)[0]
+
+    def grad(M):
+        return nca._loss_grad_lbfgs(M, X, mask)[1]
+
+    # compare the gradient to a finite difference approximation
+    diff = check_grad(fun, grad, M.ravel())
+    assert diff == pytest.approx(0.0, abs=1e-4)
+
+
+def test_params_validation():
+    # Test that invalid parameters raise value error
+    X = np.arange(12).reshape(4, 3)
+    y = [1, 1, 2, 2]
+    NCA = NeighborhoodComponentsAnalysis
+    rng = np.random.RandomState(42)
+
+    init = rng.rand(5, 3)
+    msg = (
+        f"The output dimensionality ({init.shape[0]}) "
+        "of the given linear transformation `init` cannot be "
+        f"greater than its input dimensionality ({init.shape[1]})."
+    )
+    with pytest.raises(ValueError, match=re.escape(msg)):
+        NCA(init=init).fit(X, y)
+    n_components = 10
+    msg = (
+        "The preferred dimensionality of the projected space "
+        f"`n_components` ({n_components}) cannot be greater "
+        f"than the given data dimensionality ({X.shape[1]})!"
+    )
+    with pytest.raises(ValueError, match=re.escape(msg)):
+        NCA(n_components=n_components).fit(X, y)
+
+
+def test_transformation_dimensions():
+    X = np.arange(12).reshape(4, 3)
+    y = [1, 1, 2, 2]
+
+    # Fail if transformation input dimension does not match inputs dimensions
+    transformation = np.array([[1, 2], [3, 4]])
+    with pytest.raises(ValueError):
+        NeighborhoodComponentsAnalysis(init=transformation).fit(X, y)
+
+    # Fail if transformation output dimension is larger than
+    # transformation input dimension
+    transformation = np.array([[1, 2], [3, 4], [5, 6]])
+    # len(transformation) > len(transformation[0])
+    with pytest.raises(ValueError):
+        NeighborhoodComponentsAnalysis(init=transformation).fit(X, y)
+
+    # Pass otherwise
+    transformation = np.arange(9).reshape(3, 3)
+    NeighborhoodComponentsAnalysis(init=transformation).fit(X, y)
+
+
+def test_n_components():
+    rng = np.random.RandomState(42)
+    X = np.arange(12).reshape(4, 3)
+    y = [1, 1, 2, 2]
+
+    init = rng.rand(X.shape[1] - 1, 3)
+
+    # n_components = X.shape[1] != transformation.shape[0]
+    n_components = X.shape[1]
+    nca = NeighborhoodComponentsAnalysis(init=init, n_components=n_components)
+    msg = (
+        "The preferred dimensionality of the projected space "
+        f"`n_components` ({n_components}) does not match the output "
+        "dimensionality of the given linear transformation "
+        f"`init` ({init.shape[0]})!"
+    )
+    with pytest.raises(ValueError, match=re.escape(msg)):
+        nca.fit(X, y)
+
+    # n_components > X.shape[1]
+    n_components = X.shape[1] + 2
+    nca = NeighborhoodComponentsAnalysis(init=init, n_components=n_components)
+    msg = (
+        "The preferred dimensionality of the projected space "
+        f"`n_components` ({n_components}) cannot be greater than "
+        f"the given data dimensionality ({X.shape[1]})!"
+    )
+    with pytest.raises(ValueError, match=re.escape(msg)):
+        nca.fit(X, y)
+
+    # n_components < X.shape[1]
+    nca = NeighborhoodComponentsAnalysis(n_components=2, init="identity")
+    nca.fit(X, y)
+
+
+def test_init_transformation():
+    rng = np.random.RandomState(42)
+    X, y = make_blobs(n_samples=30, centers=6, n_features=5, random_state=0)
+
+    # Start learning from scratch
+    nca = NeighborhoodComponentsAnalysis(init="identity")
+    nca.fit(X, y)
+
+    # Initialize with random
+    nca_random = NeighborhoodComponentsAnalysis(init="random")
+    nca_random.fit(X, y)
+
+    # Initialize with auto
+    nca_auto = NeighborhoodComponentsAnalysis(init="auto")
+    nca_auto.fit(X, y)
+
+    # Initialize with PCA
+    nca_pca = NeighborhoodComponentsAnalysis(init="pca")
+    nca_pca.fit(X, y)
+
+    # Initialize with LDA
+    nca_lda = NeighborhoodComponentsAnalysis(init="lda")
+    nca_lda.fit(X, y)
+
+    init = rng.rand(X.shape[1], X.shape[1])
+    nca = NeighborhoodComponentsAnalysis(init=init)
+    nca.fit(X, y)
+
+    # init.shape[1] must match X.shape[1]
+    init = rng.rand(X.shape[1], X.shape[1] + 1)
+    nca = NeighborhoodComponentsAnalysis(init=init)
+    msg = (
+        f"The input dimensionality ({init.shape[1]}) of the given "
+        "linear transformation `init` must match the "
+        f"dimensionality of the given inputs `X` ({X.shape[1]})."
+    )
+    with pytest.raises(ValueError, match=re.escape(msg)):
+        nca.fit(X, y)
+
+    # init.shape[0] must be <= init.shape[1]
+    init = rng.rand(X.shape[1] + 1, X.shape[1])
+    nca = NeighborhoodComponentsAnalysis(init=init)
+    msg = (
+        f"The output dimensionality ({init.shape[0]}) of the given "
+        "linear transformation `init` cannot be "
+        f"greater than its input dimensionality ({init.shape[1]})."
+    )
+    with pytest.raises(ValueError, match=re.escape(msg)):
+        nca.fit(X, y)
+
+    # init.shape[0] must match n_components
+    init = rng.rand(X.shape[1], X.shape[1])
+    n_components = X.shape[1] - 2
+    nca = NeighborhoodComponentsAnalysis(init=init, n_components=n_components)
+    msg = (
+        "The preferred dimensionality of the "
+        f"projected space `n_components` ({n_components}) "
+        "does not match the output dimensionality of the given "
+        f"linear transformation `init` ({init.shape[0]})!"
+    )
+    with pytest.raises(ValueError, match=re.escape(msg)):
+        nca.fit(X, y)
+
+
+@pytest.mark.parametrize("n_samples", [3, 5, 7, 11])
+@pytest.mark.parametrize("n_features", [3, 5, 7, 11])
+@pytest.mark.parametrize("n_classes", [5, 7, 11])
+@pytest.mark.parametrize("n_components", [3, 5, 7, 11])
+def test_auto_init(n_samples, n_features, n_classes, n_components):
+    # Test that auto choose the init as expected with every configuration
+    # of order of n_samples, n_features, n_classes and n_components.
+    rng = np.random.RandomState(42)
+    nca_base = NeighborhoodComponentsAnalysis(
+        init="auto", n_components=n_components, max_iter=1, random_state=rng
+    )
+    if n_classes >= n_samples:
+        pass
+        # n_classes > n_samples is impossible, and n_classes == n_samples
+        # throws an error from lda but is an absurd case
+    else:
+        X = rng.randn(n_samples, n_features)
+        y = np.tile(range(n_classes), n_samples // n_classes + 1)[:n_samples]
+        if n_components > n_features:
+            # this would return a ValueError, which is already tested in
+            # test_params_validation
+            pass
+        else:
+            nca = clone(nca_base)
+            nca.fit(X, y)
+            if n_components <= min(n_classes - 1, n_features):
+                nca_other = clone(nca_base).set_params(init="lda")
+            elif n_components < min(n_features, n_samples):
+                nca_other = clone(nca_base).set_params(init="pca")
+            else:
+                nca_other = clone(nca_base).set_params(init="identity")
+            nca_other.fit(X, y)
+            assert_array_almost_equal(nca.components_, nca_other.components_)
+
+
+def test_warm_start_validation():
+    X, y = make_classification(
+        n_samples=30,
+        n_features=5,
+        n_classes=4,
+        n_redundant=0,
+        n_informative=5,
+        random_state=0,
+    )
+
+    nca = NeighborhoodComponentsAnalysis(warm_start=True, max_iter=5)
+    nca.fit(X, y)
+
+    X_less_features, y = make_classification(
+        n_samples=30,
+        n_features=4,
+        n_classes=4,
+        n_redundant=0,
+        n_informative=4,
+        random_state=0,
+    )
+    msg = (
+        f"The new inputs dimensionality ({X_less_features.shape[1]}) "
+        "does not match the input dimensionality of the previously learned "
+        f"transformation ({nca.components_.shape[1]})."
+    )
+    with pytest.raises(ValueError, match=re.escape(msg)):
+        nca.fit(X_less_features, y)
+
+
+def test_warm_start_effectiveness():
+    # A 1-iteration second fit on same data should give almost same result
+    # with warm starting, and quite different result without warm starting.
+
+    nca_warm = NeighborhoodComponentsAnalysis(warm_start=True, random_state=0)
+    nca_warm.fit(iris_data, iris_target)
+    transformation_warm = nca_warm.components_
+    nca_warm.max_iter = 1
+    nca_warm.fit(iris_data, iris_target)
+    transformation_warm_plus_one = nca_warm.components_
+
+    nca_cold = NeighborhoodComponentsAnalysis(warm_start=False, random_state=0)
+    nca_cold.fit(iris_data, iris_target)
+    transformation_cold = nca_cold.components_
+    nca_cold.max_iter = 1
+    nca_cold.fit(iris_data, iris_target)
+    transformation_cold_plus_one = nca_cold.components_
+
+    diff_warm = np.sum(np.abs(transformation_warm_plus_one - transformation_warm))
+    diff_cold = np.sum(np.abs(transformation_cold_plus_one - transformation_cold))
+    assert diff_warm < 3.0, (
+        "Transformer changed significantly after one "
+        "iteration even though it was warm-started."
+    )
+
+    assert diff_cold > diff_warm, (
+        "Cold-started transformer changed less "
+        "significantly than warm-started "
+        "transformer after one iteration."
+    )
+
+
+@pytest.mark.parametrize(
+    "init_name", ["pca", "lda", "identity", "random", "precomputed"]
+)
+def test_verbose(init_name, capsys):
+    # assert there is proper output when verbose = 1, for every initialization
+    # except auto because auto will call one of the others
+    rng = np.random.RandomState(42)
+    X, y = make_blobs(n_samples=30, centers=6, n_features=5, random_state=0)
+    regexp_init = r"... done in \ *\d+\.\d{2}s"
+    msgs = {
+        "pca": "Finding principal components" + regexp_init,
+        "lda": "Finding most discriminative components" + regexp_init,
+    }
+    if init_name == "precomputed":
+        init = rng.randn(X.shape[1], X.shape[1])
+    else:
+        init = init_name
+    nca = NeighborhoodComponentsAnalysis(verbose=1, init=init)
+    nca.fit(X, y)
+    out, _ = capsys.readouterr()
+
+    # check output
+    lines = re.split("\n+", out)
+    # if pca or lda init, an additional line is printed, so we test
+    # it and remove it to test the rest equally among initializations
+    if init_name in ["pca", "lda"]:
+        assert re.match(msgs[init_name], lines[0])
+        lines = lines[1:]
+    assert lines[0] == "[NeighborhoodComponentsAnalysis]"
+    header = "{:>10} {:>20} {:>10}".format("Iteration", "Objective Value", "Time(s)")
+    assert lines[1] == "[NeighborhoodComponentsAnalysis] {}".format(header)
+    assert lines[2] == "[NeighborhoodComponentsAnalysis] {}".format("-" * len(header))
+    for line in lines[3:-2]:
+        # The following regex will match for instance:
+        # '[NeighborhoodComponentsAnalysis]  0    6.988936e+01   0.01'
+        assert re.match(
+            r"\[NeighborhoodComponentsAnalysis\] *\d+ *\d\.\d{6}e"
+            r"[+|-]\d+\ *\d+\.\d{2}",
+            line,
+        )
+    assert re.match(
+        r"\[NeighborhoodComponentsAnalysis\] Training took\ *\d+\.\d{2}s\.",
+        lines[-2],
+    )
+    assert lines[-1] == ""
+
+
+def test_no_verbose(capsys):
+    # assert by default there is no output (verbose=0)
+    nca = NeighborhoodComponentsAnalysis()
+    nca.fit(iris_data, iris_target)
+    out, _ = capsys.readouterr()
+    # check output
+    assert out == ""
+
+
+def test_singleton_class():
+    X = iris_data.copy()
+    y = iris_target.copy()
+
+    # one singleton class
+    singleton_class = 1
+    (ind_singleton,) = np.where(y == singleton_class)
+    y[ind_singleton] = 2
+    y[ind_singleton[0]] = singleton_class
+
+    nca = NeighborhoodComponentsAnalysis(max_iter=30)
+    nca.fit(X, y)
+
+    # One non-singleton class
+    (ind_1,) = np.where(y == 1)
+    (ind_2,) = np.where(y == 2)
+    y[ind_1] = 0
+    y[ind_1[0]] = 1
+    y[ind_2] = 0
+    y[ind_2[0]] = 2
+
+    nca = NeighborhoodComponentsAnalysis(max_iter=30)
+    nca.fit(X, y)
+
+    # Only singleton classes
+    (ind_0,) = np.where(y == 0)
+    (ind_1,) = np.where(y == 1)
+    (ind_2,) = np.where(y == 2)
+    X = X[[ind_0[0], ind_1[0], ind_2[0]]]
+    y = y[[ind_0[0], ind_1[0], ind_2[0]]]
+
+    nca = NeighborhoodComponentsAnalysis(init="identity", max_iter=30)
+    nca.fit(X, y)
+    assert_array_equal(X, nca.transform(X))
+
+
+def test_one_class():
+    X = iris_data[iris_target == 0]
+    y = iris_target[iris_target == 0]
+
+    nca = NeighborhoodComponentsAnalysis(
+        max_iter=30, n_components=X.shape[1], init="identity"
+    )
+    nca.fit(X, y)
+    assert_array_equal(X, nca.transform(X))
+
+
+def test_callback(capsys):
+    max_iter = 10
+
+    def my_cb(transformation, n_iter):
+        assert transformation.shape == (iris_data.shape[1] ** 2,)
+        rem_iter = max_iter - n_iter
+        print("{} iterations remaining...".format(rem_iter))
+
+    # assert that my_cb is called
+    nca = NeighborhoodComponentsAnalysis(max_iter=max_iter, callback=my_cb, verbose=1)
+    nca.fit(iris_data, iris_target)
+    out, _ = capsys.readouterr()
+
+    # check output
+    assert "{} iterations remaining...".format(max_iter - 1) in out
+
+
+def test_expected_transformation_shape():
+    """Test that the transformation has the expected shape."""
+    X = iris_data
+    y = iris_target
+
+    class TransformationStorer:
+        def __init__(self, X, y):
+            # Initialize a fake NCA and variables needed to call the loss
+            # function:
+            self.fake_nca = NeighborhoodComponentsAnalysis()
+            self.fake_nca.n_iter_ = np.inf
+            self.X, y = validate_data(self.fake_nca, X, y, ensure_min_samples=2)
+            y = LabelEncoder().fit_transform(y)
+            self.same_class_mask = y[:, np.newaxis] == y[np.newaxis, :]
+
+        def callback(self, transformation, n_iter):
+            """Stores the last value of the transformation taken as input by
+            the optimizer"""
+            self.transformation = transformation
+
+    transformation_storer = TransformationStorer(X, y)
+    cb = transformation_storer.callback
+    nca = NeighborhoodComponentsAnalysis(max_iter=5, callback=cb)
+    nca.fit(X, y)
+    assert transformation_storer.transformation.size == X.shape[1] ** 2
+
+
+def test_convergence_warning():
+    nca = NeighborhoodComponentsAnalysis(max_iter=2, verbose=1)
+    cls_name = nca.__class__.__name__
+    msg = "[{}] NCA did not converge".format(cls_name)
+    with pytest.warns(ConvergenceWarning, match=re.escape(msg)):
+        nca.fit(iris_data, iris_target)
+
+
+@pytest.mark.parametrize(
+    "param, value",
+    [
+        ("n_components", np.int32(3)),
+        ("max_iter", np.int32(100)),
+        ("tol", np.float32(0.0001)),
+    ],
+)
+def test_parameters_valid_types(param, value):
+    # check that no error is raised when parameters have numpy integer or
+    # floating types.
+    nca = NeighborhoodComponentsAnalysis(**{param: value})
+
+    X = iris_data
+    y = iris_target
+
+    nca.fit(X, y)
+
+
+@pytest.mark.parametrize("n_components", [None, 2])
+def test_nca_feature_names_out(n_components):
+    """Check `get_feature_names_out` for `NeighborhoodComponentsAnalysis`.
+
+    Non-regression test for:
+    https://github.com/scikit-learn/scikit-learn/issues/28293
+    """
+
+    X = iris_data
+    y = iris_target
+
+    est = NeighborhoodComponentsAnalysis(n_components=n_components).fit(X, y)
+    names_out = est.get_feature_names_out()
+
+    class_name_lower = est.__class__.__name__.lower()
+
+    if n_components is not None:
+        expected_n_features = n_components
+    else:
+        expected_n_features = X.shape[1]
+
+    expected_names_out = np.array(
+        [f"{class_name_lower}{i}" for i in range(expected_n_features)],
+        dtype=object,
+    )
+
+    assert_array_equal(names_out, expected_names_out)

linedance-app/venv/lib/python3.12/site-packages/sklearn/neighbors/tests/test_nearest_centroid.py

@@ -0,0 +1,237 @@
+"""
+Testing for the nearest centroid module.
+"""
+
+import numpy as np
+import pytest
+
+from sklearn import datasets
+from sklearn.neighbors import NearestCentroid
+from sklearn.utils._testing import (
+    assert_allclose,
+    assert_array_almost_equal,
+    assert_array_equal,
+)
+from sklearn.utils.fixes import CSR_CONTAINERS
+
+# toy sample
+X = [[-2, -1], [-1, -1], [-1, -2], [1, 1], [1, 2], [2, 1]]
+y = [-1, -1, -1, 1, 1, 1]
+T = [[-1, -1], [2, 2], [3, 2]]
+true_result = [-1, 1, 1]
+true_result_prior1 = [-1, 1, 1]
+
+true_discriminant_scores = [-32, 64, 80]
+true_proba = [[1, 1.26642e-14], [1.60381e-28, 1], [1.80485e-35, 1]]
+
+
+# also load the iris dataset
+# and randomly permute it
+iris = datasets.load_iris()
+rng = np.random.RandomState(1)
+perm = rng.permutation(iris.target.size)
+iris.data = iris.data[perm]
+iris.target = iris.target[perm]
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+def test_classification_toy(csr_container):
+    # Check classification on a toy dataset, including sparse versions.
+    X_csr = csr_container(X)
+    T_csr = csr_container(T)
+
+    # Check classification on a toy dataset, including sparse versions.
+    clf = NearestCentroid()
+    clf.fit(X, y)
+    assert_array_equal(clf.predict(T), true_result)
+    assert_array_almost_equal(clf.decision_function(T), true_discriminant_scores)
+    assert_array_almost_equal(clf.predict_proba(T), true_proba)
+
+    # Test uniform priors
+    clf = NearestCentroid(priors="uniform")
+    clf.fit(X, y)
+    assert_array_equal(clf.predict(T), true_result)
+    assert_array_almost_equal(clf.decision_function(T), true_discriminant_scores)
+    assert_array_almost_equal(clf.predict_proba(T), true_proba)
+
+    clf = NearestCentroid(priors="empirical")
+    clf.fit(X, y)
+    assert_array_equal(clf.predict(T), true_result)
+    assert_array_almost_equal(clf.decision_function(T), true_discriminant_scores)
+    assert_array_almost_equal(clf.predict_proba(T), true_proba)
+
+    # Test custom priors
+    clf = NearestCentroid(priors=[0.25, 0.75])
+    clf.fit(X, y)
+    assert_array_equal(clf.predict(T), true_result_prior1)
+
+    # Same test, but with a sparse matrix to fit and test.
+    clf = NearestCentroid()
+    clf.fit(X_csr, y)
+    assert_array_equal(clf.predict(T_csr), true_result)
+
+    # Fit with sparse, test with non-sparse
+    clf = NearestCentroid()
+    clf.fit(X_csr, y)
+    assert_array_equal(clf.predict(T), true_result)
+
+    # Fit with non-sparse, test with sparse
+    clf = NearestCentroid()
+    clf.fit(X, y)
+    assert_array_equal(clf.predict(T_csr), true_result)
+
+    # Fit and predict with non-CSR sparse matrices
+    clf = NearestCentroid()
+    clf.fit(X_csr.tocoo(), y)
+    assert_array_equal(clf.predict(T_csr.tolil()), true_result)
+
+
+def test_iris():
+    # Check consistency on dataset iris.
+    for metric in ("euclidean", "manhattan"):
+        clf = NearestCentroid(metric=metric).fit(iris.data, iris.target)
+        score = np.mean(clf.predict(iris.data) == iris.target)
+        assert score > 0.9, "Failed with score = " + str(score)
+
+
+def test_iris_shrinkage():
+    # Check consistency on dataset iris, when using shrinkage.
+    for metric in ("euclidean", "manhattan"):
+        for shrink_threshold in [None, 0.1, 0.5]:
+            clf = NearestCentroid(metric=metric, shrink_threshold=shrink_threshold)
+            clf = clf.fit(iris.data, iris.target)
+            score = np.mean(clf.predict(iris.data) == iris.target)
+            assert score > 0.8, "Failed with score = " + str(score)
+
+
+def test_pickle():
+    import pickle
+
+    # classification
+    obj = NearestCentroid()
+    obj.fit(iris.data, iris.target)
+    score = obj.score(iris.data, iris.target)
+    s = pickle.dumps(obj)
+
+    obj2 = pickle.loads(s)
+    assert type(obj2) == obj.__class__
+    score2 = obj2.score(iris.data, iris.target)
+    assert_array_equal(
+        score,
+        score2,
+        "Failed to generate same score after pickling (classification).",
+    )
+
+
+def test_shrinkage_correct():
+    # Ensure that the shrinking is correct.
+    # The expected result is calculated by R (pamr),
+    # which is implemented by the author of the original paper.
+    # (One need to modify the code to output the new centroid in pamr.predict)
+
+    X = np.array([[0, 1], [1, 0], [1, 1], [2, 0], [6, 8]])
+    y = np.array([1, 1, 2, 2, 2])
+    clf = NearestCentroid(shrink_threshold=0.1)
+    clf.fit(X, y)
+    expected_result = np.array([[0.7787310, 0.8545292], [2.814179, 2.763647]])
+    np.testing.assert_array_almost_equal(clf.centroids_, expected_result)
+
+
+def test_shrinkage_threshold_decoded_y():
+    clf = NearestCentroid(shrink_threshold=0.01)
+    y_ind = np.asarray(y)
+    y_ind[y_ind == -1] = 0
+    clf.fit(X, y_ind)
+    centroid_encoded = clf.centroids_
+    clf.fit(X, y)
+    assert_array_equal(centroid_encoded, clf.centroids_)
+
+
+def test_predict_translated_data():
+    # Test that NearestCentroid gives same results on translated data
+
+    rng = np.random.RandomState(0)
+    X = rng.rand(50, 50)
+    y = rng.randint(0, 3, 50)
+    noise = rng.rand(50)
+    clf = NearestCentroid(shrink_threshold=0.1)
+    clf.fit(X, y)
+    y_init = clf.predict(X)
+    clf = NearestCentroid(shrink_threshold=0.1)
+    X_noise = X + noise
+    clf.fit(X_noise, y)
+    y_translate = clf.predict(X_noise)
+    assert_array_equal(y_init, y_translate)
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+def test_manhattan_metric(csr_container):
+    # Test the manhattan metric.
+    X_csr = csr_container(X)
+
+    clf = NearestCentroid(metric="manhattan")
+    clf.fit(X, y)
+    dense_centroid = clf.centroids_
+    clf.fit(X_csr, y)
+    assert_array_equal(clf.centroids_, dense_centroid)
+    assert_array_equal(dense_centroid, [[-1, -1], [1, 1]])
+
+
+def test_features_zero_var():
+    # Test that features with 0 variance throw error
+
+    X = np.empty((10, 2))
+    X[:, 0] = -0.13725701
+    X[:, 1] = -0.9853293
+    y = np.zeros((10))
+    y[0] = 1
+
+    clf = NearestCentroid(shrink_threshold=0.1)
+    with pytest.raises(ValueError):
+        clf.fit(X, y)
+
+
+def test_negative_priors_error():
+    """Check that we raise an error when the user-defined priors are negative."""
+    clf = NearestCentroid(priors=[-2, 4])
+    with pytest.raises(ValueError, match="priors must be non-negative"):
+        clf.fit(X, y)
+
+
+def test_warn_non_normalized_priors():
+    """Check that we raise a warning and normalize the user-defined priors when they
+    don't sum to 1.
+    """
+    priors = [2, 4]
+    clf = NearestCentroid(priors=priors)
+    with pytest.warns(
+        UserWarning,
+        match="The priors do not sum to 1. Normalizing such that it sums to one.",
+    ):
+        clf.fit(X, y)
+
+    assert_allclose(clf.class_prior_, np.asarray(priors) / np.asarray(priors).sum())
+
+
+@pytest.mark.parametrize(
+    "response_method", ["decision_function", "predict_proba", "predict_log_proba"]
+)
+def test_method_not_available_with_manhattan(response_method):
+    """Check that we raise an AttributeError with Manhattan metric when trying
+    to call a non-thresholded response method.
+    """
+    clf = NearestCentroid(metric="manhattan").fit(X, y)
+    with pytest.raises(AttributeError):
+        getattr(clf, response_method)(T)
+
+
+@pytest.mark.parametrize("array_constructor", [np.array] + CSR_CONTAINERS)
+def test_error_zero_variances(array_constructor):
+    """Check that we raise an error when the variance for all features is zero."""
+    X = np.ones((len(y), 2))
+    X[:, 1] *= 2
+    X = array_constructor(X)
+
+    clf = NearestCentroid()
+    with pytest.raises(ValueError, match="All features have zero variance"):
+        clf.fit(X, y)

linedance-app/venv/lib/python3.12/site-packages/sklearn/neighbors/tests/test_neighbors_pipeline.py

@@ -0,0 +1,256 @@
+"""
+This is testing the equivalence between some estimators with internal nearest
+neighbors computations, and the corresponding pipeline versions with
+KNeighborsTransformer or RadiusNeighborsTransformer to precompute the
+neighbors.
+"""
+
+import numpy as np
+
+from sklearn.base import clone
+from sklearn.cluster import DBSCAN, SpectralClustering
+from sklearn.cluster.tests.common import generate_clustered_data
+from sklearn.datasets import make_blobs
+from sklearn.manifold import TSNE, Isomap, SpectralEmbedding
+from sklearn.neighbors import (
+    KNeighborsRegressor,
+    KNeighborsTransformer,
+    LocalOutlierFactor,
+    RadiusNeighborsRegressor,
+    RadiusNeighborsTransformer,
+)
+from sklearn.pipeline import make_pipeline
+from sklearn.utils._testing import assert_array_almost_equal
+
+
+def test_spectral_clustering():
+    # Test chaining KNeighborsTransformer and SpectralClustering
+    n_neighbors = 5
+    X, _ = make_blobs(random_state=0)
+
+    # compare the chained version and the compact version
+    est_chain = make_pipeline(
+        KNeighborsTransformer(n_neighbors=n_neighbors, mode="connectivity"),
+        SpectralClustering(
+            n_neighbors=n_neighbors, affinity="precomputed", random_state=42
+        ),
+    )
+    est_compact = SpectralClustering(
+        n_neighbors=n_neighbors, affinity="nearest_neighbors", random_state=42
+    )
+    labels_compact = est_compact.fit_predict(X)
+    labels_chain = est_chain.fit_predict(X)
+    assert_array_almost_equal(labels_chain, labels_compact)
+
+
+def test_spectral_embedding():
+    # Test chaining KNeighborsTransformer and SpectralEmbedding
+    n_neighbors = 5
+
+    n_samples = 1000
+    centers = np.array(
+        [
+            [0.0, 5.0, 0.0, 0.0, 0.0],
+            [0.0, 0.0, 4.0, 0.0, 0.0],
+            [1.0, 0.0, 0.0, 5.0, 1.0],
+        ]
+    )
+    S, true_labels = make_blobs(
+        n_samples=n_samples, centers=centers, cluster_std=1.0, random_state=42
+    )
+
+    # compare the chained version and the compact version
+    est_chain = make_pipeline(
+        KNeighborsTransformer(n_neighbors=n_neighbors, mode="connectivity"),
+        SpectralEmbedding(
+            n_neighbors=n_neighbors, affinity="precomputed", random_state=42
+        ),
+    )
+    est_compact = SpectralEmbedding(
+        n_neighbors=n_neighbors, affinity="nearest_neighbors", random_state=42
+    )
+    St_compact = est_compact.fit_transform(S)
+    St_chain = est_chain.fit_transform(S)
+    assert_array_almost_equal(St_chain, St_compact)
+
+
+def test_dbscan():
+    # Test chaining RadiusNeighborsTransformer and DBSCAN
+    radius = 0.3
+    n_clusters = 3
+    X = generate_clustered_data(n_clusters=n_clusters)
+
+    # compare the chained version and the compact version
+    est_chain = make_pipeline(
+        RadiusNeighborsTransformer(radius=radius, mode="distance"),
+        DBSCAN(metric="precomputed", eps=radius),
+    )
+    est_compact = DBSCAN(eps=radius)
+
+    labels_chain = est_chain.fit_predict(X)
+    labels_compact = est_compact.fit_predict(X)
+    assert_array_almost_equal(labels_chain, labels_compact)
+
+
+def test_isomap():
+    # Test chaining KNeighborsTransformer and Isomap with
+    # neighbors_algorithm='precomputed'
+    algorithm = "auto"
+    n_neighbors = 10
+
+    X, _ = make_blobs(random_state=0)
+    X2, _ = make_blobs(random_state=1)
+
+    # compare the chained version and the compact version
+    est_chain = make_pipeline(
+        KNeighborsTransformer(
+            n_neighbors=n_neighbors, algorithm=algorithm, mode="distance"
+        ),
+        Isomap(n_neighbors=n_neighbors, metric="precomputed"),
+    )
+    est_compact = Isomap(n_neighbors=n_neighbors, neighbors_algorithm=algorithm)
+
+    Xt_chain = est_chain.fit_transform(X)
+    Xt_compact = est_compact.fit_transform(X)
+    assert_array_almost_equal(Xt_chain, Xt_compact)
+
+    Xt_chain = est_chain.transform(X2)
+    Xt_compact = est_compact.transform(X2)
+    assert_array_almost_equal(Xt_chain, Xt_compact)
+
+
+def test_tsne():
+    # Test chaining KNeighborsTransformer and TSNE
+    max_iter = 250
+    perplexity = 5
+    n_neighbors = int(3.0 * perplexity + 1)
+
+    rng = np.random.RandomState(0)
+    X = rng.randn(20, 2)
+
+    for metric in ["minkowski", "sqeuclidean"]:
+        # compare the chained version and the compact version
+        est_chain = make_pipeline(
+            KNeighborsTransformer(
+                n_neighbors=n_neighbors, mode="distance", metric=metric
+            ),
+            TSNE(
+                init="random",
+                metric="precomputed",
+                perplexity=perplexity,
+                method="barnes_hut",
+                random_state=42,
+                max_iter=max_iter,
+            ),
+        )
+        est_compact = TSNE(
+            init="random",
+            metric=metric,
+            perplexity=perplexity,
+            max_iter=max_iter,
+            method="barnes_hut",
+            random_state=42,
+        )
+
+        Xt_chain = est_chain.fit_transform(X)
+        Xt_compact = est_compact.fit_transform(X)
+        assert_array_almost_equal(Xt_chain, Xt_compact)
+
+
+def test_lof_novelty_false():
+    # Test chaining KNeighborsTransformer and LocalOutlierFactor
+    n_neighbors = 4
+
+    rng = np.random.RandomState(0)
+    X = rng.randn(40, 2)
+
+    # compare the chained version and the compact version
+    est_chain = make_pipeline(
+        KNeighborsTransformer(n_neighbors=n_neighbors, mode="distance"),
+        LocalOutlierFactor(
+            metric="precomputed",
+            n_neighbors=n_neighbors,
+            novelty=False,
+            contamination="auto",
+        ),
+    )
+    est_compact = LocalOutlierFactor(
+        n_neighbors=n_neighbors, novelty=False, contamination="auto"
+    )
+
+    pred_chain = est_chain.fit_predict(X)
+    pred_compact = est_compact.fit_predict(X)
+    assert_array_almost_equal(pred_chain, pred_compact)
+
+
+def test_lof_novelty_true():
+    # Test chaining KNeighborsTransformer and LocalOutlierFactor
+    n_neighbors = 4
+
+    rng = np.random.RandomState(0)
+    X1 = rng.randn(40, 2)
+    X2 = rng.randn(40, 2)
+
+    # compare the chained version and the compact version
+    est_chain = make_pipeline(
+        KNeighborsTransformer(n_neighbors=n_neighbors, mode="distance"),
+        LocalOutlierFactor(
+            metric="precomputed",
+            n_neighbors=n_neighbors,
+            novelty=True,
+            contamination="auto",
+        ),
+    )
+    est_compact = LocalOutlierFactor(
+        n_neighbors=n_neighbors, novelty=True, contamination="auto"
+    )
+
+    pred_chain = est_chain.fit(X1).predict(X2)
+    pred_compact = est_compact.fit(X1).predict(X2)
+    assert_array_almost_equal(pred_chain, pred_compact)
+
+
+def test_kneighbors_regressor():
+    # Test chaining KNeighborsTransformer and classifiers/regressors
+    rng = np.random.RandomState(0)
+    X = 2 * rng.rand(40, 5) - 1
+    X2 = 2 * rng.rand(40, 5) - 1
+    y = rng.rand(40, 1)
+
+    n_neighbors = 12
+    radius = 1.5
+    # We precompute more neighbors than necessary, to have equivalence between
+    # k-neighbors estimator after radius-neighbors transformer, and vice-versa.
+    factor = 2
+
+    k_trans = KNeighborsTransformer(n_neighbors=n_neighbors, mode="distance")
+    k_trans_factor = KNeighborsTransformer(
+        n_neighbors=int(n_neighbors * factor), mode="distance"
+    )
+
+    r_trans = RadiusNeighborsTransformer(radius=radius, mode="distance")
+    r_trans_factor = RadiusNeighborsTransformer(
+        radius=int(radius * factor), mode="distance"
+    )
+
+    k_reg = KNeighborsRegressor(n_neighbors=n_neighbors)
+    r_reg = RadiusNeighborsRegressor(radius=radius)
+
+    test_list = [
+        (k_trans, k_reg),
+        (k_trans_factor, r_reg),
+        (r_trans, r_reg),
+        (r_trans_factor, k_reg),
+    ]
+
+    for trans, reg in test_list:
+        # compare the chained version and the compact version
+        reg_compact = clone(reg)
+        reg_precomp = clone(reg)
+        reg_precomp.set_params(metric="precomputed")
+
+        reg_chain = make_pipeline(clone(trans), reg_precomp)
+
+        y_pred_chain = reg_chain.fit(X, y).predict(X2)
+        y_pred_compact = reg_compact.fit(X, y).predict(X2)
+        assert_array_almost_equal(y_pred_chain, y_pred_compact)

linedance-app/venv/lib/python3.12/site-packages/sklearn/neighbors/tests/test_neighbors_tree.py

@@ -0,0 +1,296 @@
+# SPDX-License-Identifier: BSD-3-Clause
+
+import itertools
+import pickle
+
+import numpy as np
+import pytest
+from numpy.testing import assert_allclose, assert_array_almost_equal
+
+from sklearn.metrics import DistanceMetric
+from sklearn.neighbors._ball_tree import (
+    BallTree,
+    kernel_norm,
+)
+from sklearn.neighbors._ball_tree import (
+    NeighborsHeap64 as NeighborsHeapBT,
+)
+from sklearn.neighbors._ball_tree import (
+    nodeheap_sort as nodeheap_sort_bt,
+)
+from sklearn.neighbors._ball_tree import (
+    simultaneous_sort as simultaneous_sort_bt,
+)
+from sklearn.neighbors._kd_tree import (
+    KDTree,
+)
+from sklearn.neighbors._kd_tree import (
+    NeighborsHeap64 as NeighborsHeapKDT,
+)
+from sklearn.neighbors._kd_tree import (
+    nodeheap_sort as nodeheap_sort_kdt,
+)
+from sklearn.neighbors._kd_tree import (
+    simultaneous_sort as simultaneous_sort_kdt,
+)
+from sklearn.utils import check_random_state
+
+rng = np.random.RandomState(42)
+V_mahalanobis = rng.rand(3, 3)
+V_mahalanobis = np.dot(V_mahalanobis, V_mahalanobis.T)
+
+DIMENSION = 3
+
+METRICS = {
+    "euclidean": {},
+    "manhattan": {},
+    "minkowski": dict(p=3),
+    "chebyshev": {},
+    "seuclidean": dict(V=rng.random_sample(DIMENSION)),
+    "mahalanobis": dict(V=V_mahalanobis),
+}
+
+KD_TREE_METRICS = ["euclidean", "manhattan", "chebyshev", "minkowski"]
+BALL_TREE_METRICS = list(METRICS)
+
+
+def dist_func(x1, x2, p):
+    return np.sum((x1 - x2) ** p) ** (1.0 / p)
+
+
+def compute_kernel_slow(Y, X, kernel, h):
+    d = np.sqrt(((Y[:, None, :] - X) ** 2).sum(-1))
+    norm = kernel_norm(h, X.shape[1], kernel)
+
+    if kernel == "gaussian":
+        return norm * np.exp(-0.5 * (d * d) / (h * h)).sum(-1)
+    elif kernel == "tophat":
+        return norm * (d < h).sum(-1)
+    elif kernel == "epanechnikov":
+        return norm * ((1.0 - (d * d) / (h * h)) * (d < h)).sum(-1)
+    elif kernel == "exponential":
+        return norm * (np.exp(-d / h)).sum(-1)
+    elif kernel == "linear":
+        return norm * ((1 - d / h) * (d < h)).sum(-1)
+    elif kernel == "cosine":
+        return norm * (np.cos(0.5 * np.pi * d / h) * (d < h)).sum(-1)
+    else:
+        raise ValueError("kernel not recognized")
+
+
+def brute_force_neighbors(X, Y, k, metric, **kwargs):
+    D = DistanceMetric.get_metric(metric, **kwargs).pairwise(Y, X)
+    ind = np.argsort(D, axis=1)[:, :k]
+    dist = D[np.arange(Y.shape[0])[:, None], ind]
+    return dist, ind
+
+
+@pytest.mark.parametrize("Cls", [KDTree, BallTree])
+@pytest.mark.parametrize(
+    "kernel", ["gaussian", "tophat", "epanechnikov", "exponential", "linear", "cosine"]
+)
+@pytest.mark.parametrize("h", [0.01, 0.1, 1])
+@pytest.mark.parametrize("rtol", [0, 1e-5])
+@pytest.mark.parametrize("atol", [1e-6, 1e-2])
+@pytest.mark.parametrize("breadth_first", [True, False])
+def test_kernel_density(
+    Cls, kernel, h, rtol, atol, breadth_first, n_samples=100, n_features=3
+):
+    rng = check_random_state(1)
+    X = rng.random_sample((n_samples, n_features))
+    Y = rng.random_sample((n_samples, n_features))
+    dens_true = compute_kernel_slow(Y, X, kernel, h)
+
+    tree = Cls(X, leaf_size=10)
+    dens = tree.kernel_density(
+        Y, h, atol=atol, rtol=rtol, kernel=kernel, breadth_first=breadth_first
+    )
+    assert_allclose(dens, dens_true, atol=atol, rtol=max(rtol, 1e-7))
+
+
+@pytest.mark.parametrize("Cls", [KDTree, BallTree])
+def test_neighbor_tree_query_radius(Cls, n_samples=100, n_features=10):
+    rng = check_random_state(0)
+    X = 2 * rng.random_sample(size=(n_samples, n_features)) - 1
+    query_pt = np.zeros(n_features, dtype=float)
+
+    eps = 1e-15  # roundoff error can cause test to fail
+    tree = Cls(X, leaf_size=5)
+    rad = np.sqrt(((X - query_pt) ** 2).sum(1))
+
+    for r in np.linspace(rad[0], rad[-1], 100):
+        ind = tree.query_radius([query_pt], r + eps)[0]
+        i = np.where(rad <= r + eps)[0]
+
+        ind.sort()
+        i.sort()
+
+        assert_array_almost_equal(i, ind)
+
+
+@pytest.mark.parametrize("Cls", [KDTree, BallTree])
+def test_neighbor_tree_query_radius_distance(Cls, n_samples=100, n_features=10):
+    rng = check_random_state(0)
+    X = 2 * rng.random_sample(size=(n_samples, n_features)) - 1
+    query_pt = np.zeros(n_features, dtype=float)
+
+    eps = 1e-15  # roundoff error can cause test to fail
+    tree = Cls(X, leaf_size=5)
+    rad = np.sqrt(((X - query_pt) ** 2).sum(1))
+
+    for r in np.linspace(rad[0], rad[-1], 100):
+        ind, dist = tree.query_radius([query_pt], r + eps, return_distance=True)
+
+        ind = ind[0]
+        dist = dist[0]
+
+        d = np.sqrt(((query_pt - X[ind]) ** 2).sum(1))
+
+        assert_array_almost_equal(d, dist)
+
+
+@pytest.mark.parametrize("Cls", [KDTree, BallTree])
+@pytest.mark.parametrize("dualtree", (True, False))
+def test_neighbor_tree_two_point(Cls, dualtree, n_samples=100, n_features=3):
+    rng = check_random_state(0)
+    X = rng.random_sample((n_samples, n_features))
+    Y = rng.random_sample((n_samples, n_features))
+    r = np.linspace(0, 1, 10)
+    tree = Cls(X, leaf_size=10)
+
+    D = DistanceMetric.get_metric("euclidean").pairwise(Y, X)
+    counts_true = [(D <= ri).sum() for ri in r]
+
+    counts = tree.two_point_correlation(Y, r=r, dualtree=dualtree)
+    assert_array_almost_equal(counts, counts_true)
+
+
+@pytest.mark.parametrize("NeighborsHeap", [NeighborsHeapBT, NeighborsHeapKDT])
+def test_neighbors_heap(NeighborsHeap, n_pts=5, n_nbrs=10):
+    heap = NeighborsHeap(n_pts, n_nbrs)
+    rng = check_random_state(0)
+
+    for row in range(n_pts):
+        d_in = rng.random_sample(2 * n_nbrs).astype(np.float64, copy=False)
+        i_in = np.arange(2 * n_nbrs, dtype=np.intp)
+        for d, i in zip(d_in, i_in):
+            heap.push(row, d, i)
+
+        ind = np.argsort(d_in)
+        d_in = d_in[ind]
+        i_in = i_in[ind]
+
+        d_heap, i_heap = heap.get_arrays(sort=True)
+
+        assert_array_almost_equal(d_in[:n_nbrs], d_heap[row])
+        assert_array_almost_equal(i_in[:n_nbrs], i_heap[row])
+
+
+@pytest.mark.parametrize("nodeheap_sort", [nodeheap_sort_bt, nodeheap_sort_kdt])
+def test_node_heap(nodeheap_sort, n_nodes=50):
+    rng = check_random_state(0)
+    vals = rng.random_sample(n_nodes).astype(np.float64, copy=False)
+
+    i1 = np.argsort(vals)
+    vals2, i2 = nodeheap_sort(vals)
+
+    assert_array_almost_equal(i1, i2)
+    assert_array_almost_equal(vals[i1], vals2)
+
+
+@pytest.mark.parametrize(
+    "simultaneous_sort", [simultaneous_sort_bt, simultaneous_sort_kdt]
+)
+def test_simultaneous_sort(simultaneous_sort, n_rows=10, n_pts=201):
+    rng = check_random_state(0)
+    dist = rng.random_sample((n_rows, n_pts)).astype(np.float64, copy=False)
+    ind = (np.arange(n_pts) + np.zeros((n_rows, 1))).astype(np.intp, copy=False)
+
+    dist2 = dist.copy()
+    ind2 = ind.copy()
+
+    # simultaneous sort rows using function
+    simultaneous_sort(dist, ind)
+
+    # simultaneous sort rows using numpy
+    i = np.argsort(dist2, axis=1)
+    row_ind = np.arange(n_rows)[:, None]
+    dist2 = dist2[row_ind, i]
+    ind2 = ind2[row_ind, i]
+
+    assert_array_almost_equal(dist, dist2)
+    assert_array_almost_equal(ind, ind2)
+
+
+@pytest.mark.parametrize("Cls", [KDTree, BallTree])
+def test_gaussian_kde(Cls, n_samples=1000):
+    # Compare gaussian KDE results to scipy.stats.gaussian_kde
+    from scipy.stats import gaussian_kde
+
+    rng = check_random_state(0)
+    x_in = rng.normal(0, 1, n_samples)
+    x_out = np.linspace(-5, 5, 30)
+
+    for h in [0.01, 0.1, 1]:
+        tree = Cls(x_in[:, None])
+        gkde = gaussian_kde(x_in, bw_method=h / np.std(x_in))
+
+        dens_tree = tree.kernel_density(x_out[:, None], h) / n_samples
+        dens_gkde = gkde.evaluate(x_out)
+
+        assert_array_almost_equal(dens_tree, dens_gkde, decimal=3)
+
+
+@pytest.mark.parametrize(
+    "Cls, metric",
+    itertools.chain(
+        [(KDTree, metric) for metric in KD_TREE_METRICS],
+        [(BallTree, metric) for metric in BALL_TREE_METRICS],
+    ),
+)
+@pytest.mark.parametrize("k", (1, 3, 5))
+@pytest.mark.parametrize("dualtree", (True, False))
+@pytest.mark.parametrize("breadth_first", (True, False))
+def test_nn_tree_query(Cls, metric, k, dualtree, breadth_first):
+    rng = check_random_state(0)
+    X = rng.random_sample((40, DIMENSION))
+    Y = rng.random_sample((10, DIMENSION))
+
+    kwargs = METRICS[metric]
+
+    kdt = Cls(X, leaf_size=1, metric=metric, **kwargs)
+    dist1, ind1 = kdt.query(Y, k, dualtree=dualtree, breadth_first=breadth_first)
+    dist2, ind2 = brute_force_neighbors(X, Y, k, metric, **kwargs)
+
+    # don't check indices here: if there are any duplicate distances,
+    # the indices may not match.  Distances should not have this problem.
+    assert_array_almost_equal(dist1, dist2)
+
+
+@pytest.mark.parametrize(
+    "Cls, metric",
+    [(KDTree, "euclidean"), (BallTree, "euclidean"), (BallTree, dist_func)],
+)
+@pytest.mark.parametrize("protocol", (0, 1, 2))
+def test_pickle(Cls, metric, protocol):
+    rng = check_random_state(0)
+    X = rng.random_sample((10, 3))
+
+    if hasattr(metric, "__call__"):
+        kwargs = {"p": 2}
+    else:
+        kwargs = {}
+
+    tree1 = Cls(X, leaf_size=1, metric=metric, **kwargs)
+
+    ind1, dist1 = tree1.query(X)
+
+    s = pickle.dumps(tree1, protocol=protocol)
+    tree2 = pickle.loads(s)
+
+    ind2, dist2 = tree2.query(X)
+
+    assert_array_almost_equal(ind1, ind2)
+    assert_array_almost_equal(dist1, dist2)
+
+    assert isinstance(tree2, Cls)

linedance-app/venv/lib/python3.12/site-packages/sklearn/neighbors/tests/test_quad_tree.py

@@ -0,0 +1,150 @@
+import pickle
+
+import numpy as np
+import pytest
+
+from sklearn.neighbors._quad_tree import _QuadTree
+from sklearn.utils import check_random_state
+
+
+def test_quadtree_boundary_computation():
+    # Introduce a point into a quad tree with boundaries not easy to compute.
+    Xs = []
+
+    # check a random case
+    Xs.append(np.array([[-1, 1], [-4, -1]], dtype=np.float32))
+    # check the case where only 0 are inserted
+    Xs.append(np.array([[0, 0], [0, 0]], dtype=np.float32))
+    # check the case where only negative are inserted
+    Xs.append(np.array([[-1, -2], [-4, 0]], dtype=np.float32))
+    # check the case where only small numbers are inserted
+    Xs.append(np.array([[-1e-6, 1e-6], [-4e-6, -1e-6]], dtype=np.float32))
+
+    for X in Xs:
+        tree = _QuadTree(n_dimensions=2, verbose=0)
+        tree.build_tree(X)
+        tree._check_coherence()
+
+
+def test_quadtree_similar_point():
+    # Introduce a point into a quad tree where a similar point already exists.
+    # Test will hang if it doesn't complete.
+    Xs = []
+
+    # check the case where points are actually different
+    Xs.append(np.array([[1, 2], [3, 4]], dtype=np.float32))
+    # check the case where points are the same on X axis
+    Xs.append(np.array([[1.0, 2.0], [1.0, 3.0]], dtype=np.float32))
+    # check the case where points are arbitrarily close on X axis
+    Xs.append(np.array([[1.00001, 2.0], [1.00002, 3.0]], dtype=np.float32))
+    # check the case where points are the same on Y axis
+    Xs.append(np.array([[1.0, 2.0], [3.0, 2.0]], dtype=np.float32))
+    # check the case where points are arbitrarily close on Y axis
+    Xs.append(np.array([[1.0, 2.00001], [3.0, 2.00002]], dtype=np.float32))
+    # check the case where points are arbitrarily close on both axes
+    Xs.append(np.array([[1.00001, 2.00001], [1.00002, 2.00002]], dtype=np.float32))
+
+    # check the case where points are arbitrarily close on both axes
+    # close to machine epsilon - x axis
+    Xs.append(np.array([[1, 0.0003817754041], [2, 0.0003817753750]], dtype=np.float32))
+
+    # check the case where points are arbitrarily close on both axes
+    # close to machine epsilon - y axis
+    Xs.append(
+        np.array([[0.0003817754041, 1.0], [0.0003817753750, 2.0]], dtype=np.float32)
+    )
+
+    for X in Xs:
+        tree = _QuadTree(n_dimensions=2, verbose=0)
+        tree.build_tree(X)
+        tree._check_coherence()
+
+
+@pytest.mark.parametrize("n_dimensions", (2, 3))
+@pytest.mark.parametrize("protocol", (0, 1, 2))
+def test_quad_tree_pickle(n_dimensions, protocol):
+    rng = check_random_state(0)
+
+    X = rng.random_sample((10, n_dimensions))
+
+    tree = _QuadTree(n_dimensions=n_dimensions, verbose=0)
+    tree.build_tree(X)
+
+    s = pickle.dumps(tree, protocol=protocol)
+    bt2 = pickle.loads(s)
+
+    for x in X:
+        cell_x_tree = tree.get_cell(x)
+        cell_x_bt2 = bt2.get_cell(x)
+        assert cell_x_tree == cell_x_bt2
+
+
+@pytest.mark.parametrize("n_dimensions", (2, 3))
+def test_qt_insert_duplicate(n_dimensions):
+    rng = check_random_state(0)
+
+    X = rng.random_sample((10, n_dimensions))
+    # create some duplicates
+    Xd = np.r_[X, X[:5]]
+    epsilon = 1e-6
+    # EPSILON=1e-6 is defined in sklearn/neighbors/_quad_tree.pyx but not
+    # accessible from Python
+    # add slight noise: duplicate detection should tolerate tiny numerical differences
+    Xd += epsilon * (rng.rand(*Xd.shape) - 0.5)
+    tree = _QuadTree(n_dimensions=n_dimensions, verbose=0)
+    tree.build_tree(Xd)
+
+    cumulative_size = tree.cumulative_size
+    leafs = tree.leafs
+
+    # Assert that the first 5 are indeed duplicated and that the next
+    # ones are single point leaf
+    for i, x in enumerate(X):
+        cell_id = tree.get_cell(x)
+        assert leafs[cell_id]
+        assert cumulative_size[cell_id] == 1 + (i < 5)
+
+
+def test_summarize():
+    # Simple check for quad tree's summarize
+
+    angle = 0.9
+    X = np.array(
+        [[-10.0, -10.0], [9.0, 10.0], [10.0, 9.0], [10.0, 10.0]], dtype=np.float32
+    )
+    query_pt = X[0, :]
+    n_dimensions = X.shape[1]
+    offset = n_dimensions + 2
+
+    qt = _QuadTree(n_dimensions, verbose=0)
+    qt.build_tree(X)
+
+    idx, summary = qt._py_summarize(query_pt, X, angle)
+
+    node_dist = summary[n_dimensions]
+    node_size = summary[n_dimensions + 1]
+
+    # Summary should contain only 1 node with size 3 and distance to
+    # X[1:] barycenter
+    barycenter = X[1:].mean(axis=0)
+    ds2c = ((X[0] - barycenter) ** 2).sum()
+
+    assert idx == offset
+    assert node_size == 3, "summary size = {}".format(node_size)
+    assert np.isclose(node_dist, ds2c)
+
+    # Summary should contain all 3 node with size 1 and distance to
+    # each point in X[1:] for ``angle=0``
+    idx, summary = qt._py_summarize(query_pt, X, 0.0)
+    barycenter = X[1:].mean(axis=0)
+    ds2c = ((X[0] - barycenter) ** 2).sum()
+
+    assert idx == 3 * (offset)
+    for i in range(3):
+        node_dist = summary[i * offset + n_dimensions]
+        node_size = summary[i * offset + n_dimensions + 1]
+
+        ds2c = ((X[0] - X[i + 1]) ** 2).sum()
+
+        assert node_size == 1, "summary size = {}".format(node_size)
+        assert np.isclose(node_dist, ds2c)