Videre

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

@@ -0,0 +1,53 @@
+"""Feature selection algorithms.
+
+These include univariate filter selection methods and the recursive feature elimination
+algorithm.
+"""
+
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
+from sklearn.feature_selection._base import SelectorMixin
+from sklearn.feature_selection._from_model import SelectFromModel
+from sklearn.feature_selection._mutual_info import (
+    mutual_info_classif,
+    mutual_info_regression,
+)
+from sklearn.feature_selection._rfe import RFE, RFECV
+from sklearn.feature_selection._sequential import SequentialFeatureSelector
+from sklearn.feature_selection._univariate_selection import (
+    GenericUnivariateSelect,
+    SelectFdr,
+    SelectFpr,
+    SelectFwe,
+    SelectKBest,
+    SelectPercentile,
+    chi2,
+    f_classif,
+    f_oneway,
+    f_regression,
+    r_regression,
+)
+from sklearn.feature_selection._variance_threshold import VarianceThreshold
+
+__all__ = [
+    "RFE",
+    "RFECV",
+    "GenericUnivariateSelect",
+    "SelectFdr",
+    "SelectFpr",
+    "SelectFromModel",
+    "SelectFwe",
+    "SelectKBest",
+    "SelectPercentile",
+    "SelectorMixin",
+    "SequentialFeatureSelector",
+    "VarianceThreshold",
+    "chi2",
+    "f_classif",
+    "f_oneway",
+    "f_regression",
+    "mutual_info_classif",
+    "mutual_info_regression",
+    "r_regression",
+]

linedance-app/venv/lib/python3.12/site-packages/sklearn/feature_selection/_base.py

@@ -0,0 +1,267 @@
+"""Generic feature selection mixin"""
+
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
+import warnings
+from abc import ABCMeta, abstractmethod
+from operator import attrgetter
+
+import numpy as np
+from scipy.sparse import csc_matrix, issparse
+
+from sklearn.base import TransformerMixin
+from sklearn.utils import _safe_indexing, check_array, safe_sqr
+from sklearn.utils._dataframe import is_pandas_df
+from sklearn.utils._set_output import _get_output_config
+from sklearn.utils._tags import get_tags
+from sklearn.utils.validation import (
+    _check_feature_names_in,
+    check_is_fitted,
+    validate_data,
+)
+
+
+class SelectorMixin(TransformerMixin, metaclass=ABCMeta):
+    """
+    Transformer mixin that performs feature selection given a support mask
+
+    This mixin provides a feature selector implementation with `transform` and
+    `inverse_transform` functionality given an implementation of
+    `_get_support_mask`.
+
+    Examples
+    --------
+    >>> import numpy as np
+    >>> from sklearn.datasets import load_iris
+    >>> from sklearn.base import BaseEstimator
+    >>> from sklearn.feature_selection import SelectorMixin
+    >>> class FeatureSelector(SelectorMixin, BaseEstimator):
+    ...    def fit(self, X, y=None):
+    ...        self.n_features_in_ = X.shape[1]
+    ...        return self
+    ...    def _get_support_mask(self):
+    ...        mask = np.zeros(self.n_features_in_, dtype=bool)
+    ...        mask[:2] = True  # select the first two features
+    ...        return mask
+    >>> X, y = load_iris(return_X_y=True)
+    >>> FeatureSelector().fit_transform(X, y).shape
+    (150, 2)
+    """
+
+    def get_support(self, indices=False):
+        """
+        Get a mask, or integer index, of the features selected.
+
+        Parameters
+        ----------
+        indices : bool, default=False
+            If True, the return value will be an array of integers, rather
+            than a boolean mask.
+
+        Returns
+        -------
+        support : array
+            An index that selects the retained features from a feature vector.
+            If `indices` is False, this is a boolean array of shape
+            [# input features], in which an element is True iff its
+            corresponding feature is selected for retention. If `indices` is
+            True, this is an integer array of shape [# output features] whose
+            values are indices into the input feature vector.
+        """
+        mask = self._get_support_mask()
+        return mask if not indices else np.nonzero(mask)[0]
+
+    @abstractmethod
+    def _get_support_mask(self):
+        """
+        Get the boolean mask indicating which features are selected
+
+        Returns
+        -------
+        support : boolean array of shape [# input features]
+            An element is True iff its corresponding feature is selected for
+            retention.
+        """
+
+    def transform(self, X):
+        """Reduce X to the selected features.
+
+        Parameters
+        ----------
+        X : array of shape [n_samples, n_features]
+            The input samples.
+
+        Returns
+        -------
+        X_r : array of shape [n_samples, n_selected_features]
+            The input samples with only the selected features.
+        """
+        # Preserve X when X is a dataframe and the output is configured to
+        # be pandas.
+        output_config_dense = _get_output_config("transform", estimator=self)["dense"]
+        preserve_X = output_config_dense != "default" and is_pandas_df(X)
+
+        # note: we use get_tags instead of __sklearn_tags__ because this is a
+        # public Mixin.
+        X = validate_data(
+            self,
+            X,
+            dtype=None,
+            accept_sparse="csr",
+            ensure_all_finite=not get_tags(self).input_tags.allow_nan,
+            skip_check_array=preserve_X,
+            reset=False,
+        )
+        return self._transform(X)
+
+    def _transform(self, X):
+        """Reduce X to the selected features."""
+        mask = self.get_support()
+        if not mask.any():
+            warnings.warn(
+                (
+                    "No features were selected: either the data is"
+                    " too noisy or the selection test too strict."
+                ),
+                UserWarning,
+            )
+            if hasattr(X, "iloc"):
+                return X.iloc[:, :0]
+            return np.empty(0, dtype=X.dtype).reshape((X.shape[0], 0))
+        return _safe_indexing(X, mask, axis=1)
+
+    def inverse_transform(self, X):
+        """Reverse the transformation operation.
+
+        Parameters
+        ----------
+        X : array of shape [n_samples, n_selected_features]
+            The input samples.
+
+        Returns
+        -------
+        X_original : array of shape [n_samples, n_original_features]
+            `X` with columns of zeros inserted where features would have
+            been removed by :meth:`transform`.
+        """
+        if issparse(X):
+            X = X.tocsc()
+            # insert additional entries in indptr:
+            # e.g. if transform changed indptr from [0 2 6 7] to [0 2 3]
+            # col_nonzeros here will be [2 0 1] so indptr becomes [0 2 2 3]
+            it = self.inverse_transform(np.diff(X.indptr).reshape(1, -1))
+            col_nonzeros = it.ravel()
+            indptr = np.concatenate([[0], np.cumsum(col_nonzeros)])
+            Xt = csc_matrix(
+                (X.data, X.indices, indptr),
+                shape=(X.shape[0], len(indptr) - 1),
+                dtype=X.dtype,
+            )
+            return Xt
+
+        support = self.get_support()
+        X = check_array(X, dtype=None)
+        if support.sum() != X.shape[1]:
+            raise ValueError("X has a different shape than during fitting.")
+
+        if X.ndim == 1:
+            X = X[None, :]
+        Xt = np.zeros((X.shape[0], support.size), dtype=X.dtype)
+        Xt[:, support] = X
+        return Xt
+
+    def get_feature_names_out(self, input_features=None):
+        """Mask feature names according to selected features.
+
+        Parameters
+        ----------
+        input_features : array-like of str or None, default=None
+            Input features.
+
+            - If `input_features` is `None`, then `feature_names_in_` is
+              used as feature names in. If `feature_names_in_` is not defined,
+              then the following input feature names are generated:
+              `["x0", "x1", ..., "x(n_features_in_ - 1)"]`.
+            - If `input_features` is an array-like, then `input_features` must
+              match `feature_names_in_` if `feature_names_in_` is defined.
+
+        Returns
+        -------
+        feature_names_out : ndarray of str objects
+            Transformed feature names.
+        """
+        check_is_fitted(self)
+        input_features = _check_feature_names_in(self, input_features)
+        return input_features[self.get_support()]
+
+
+def _get_feature_importances(estimator, getter, transform_func=None, norm_order=1):
+    """
+    Retrieve and aggregate (ndim > 1)  the feature importances
+    from an estimator. Also optionally applies transformation.
+
+    Parameters
+    ----------
+    estimator : estimator
+        A scikit-learn estimator from which we want to get the feature
+        importances.
+
+    getter : "auto", str or callable
+        An attribute or a callable to get the feature importance. If `"auto"`,
+        `estimator` is expected to expose `coef_` or `feature_importances`.
+
+    transform_func : {"norm", "square"}, default=None
+        The transform to apply to the feature importances. By default (`None`)
+        no transformation is applied.
+
+    norm_order : int, default=1
+        The norm order to apply when `transform_func="norm"`. Only applied
+        when `importances.ndim > 1`.
+
+    Returns
+    -------
+    importances : ndarray of shape (n_features,)
+        The features importances, optionally transformed.
+    """
+    if isinstance(getter, str):
+        if getter == "auto":
+            if hasattr(estimator, "coef_"):
+                getter = attrgetter("coef_")
+            elif hasattr(estimator, "feature_importances_"):
+                getter = attrgetter("feature_importances_")
+            else:
+                raise ValueError(
+                    "when `importance_getter=='auto'`, the underlying "
+                    f"estimator {estimator.__class__.__name__} should have "
+                    "`coef_` or `feature_importances_` attribute. Either "
+                    "pass a fitted estimator to feature selector or call fit "
+                    "before calling transform."
+                )
+        else:
+            getter = attrgetter(getter)
+    elif not callable(getter):
+        raise ValueError("`importance_getter` has to be a string or `callable`")
+
+    importances = getter(estimator)
+
+    if transform_func is None:
+        return importances
+    elif transform_func == "norm":
+        if importances.ndim == 1:
+            importances = np.abs(importances)
+        else:
+            importances = np.linalg.norm(importances, axis=0, ord=norm_order)
+    elif transform_func == "square":
+        if importances.ndim == 1:
+            importances = safe_sqr(importances)
+        else:
+            importances = safe_sqr(importances).sum(axis=0)
+    else:
+        raise ValueError(
+            "Valid values for `transform_func` are "
+            "None, 'norm' and 'square'. Those two "
+            "transformation are only supported now"
+        )
+
+    return importances

linedance-app/venv/lib/python3.12/site-packages/sklearn/feature_selection/_from_model.py

@@ -0,0 +1,519 @@
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
+from copy import deepcopy
+from numbers import Integral, Real
+
+import numpy as np
+
+from sklearn.base import BaseEstimator, MetaEstimatorMixin, _fit_context, clone
+from sklearn.exceptions import NotFittedError
+from sklearn.feature_selection._base import SelectorMixin, _get_feature_importances
+from sklearn.utils._param_validation import HasMethods, Interval, Options
+from sklearn.utils._tags import get_tags
+from sklearn.utils.metadata_routing import (
+    MetadataRouter,
+    MethodMapping,
+    _routing_enabled,
+    process_routing,
+)
+from sklearn.utils.metaestimators import available_if
+from sklearn.utils.validation import (
+    _check_feature_names,
+    _estimator_has,
+    check_is_fitted,
+    check_scalar,
+)
+
+
+def _calculate_threshold(estimator, importances, threshold):
+    """Interpret the threshold value"""
+
+    if threshold is None:
+        # determine default from estimator
+        est_name = estimator.__class__.__name__
+        is_l1_penalized = hasattr(estimator, "penalty") and estimator.penalty == "l1"
+        is_lasso = "Lasso" in est_name
+        is_elasticnet_l1_penalized = est_name == "ElasticNet" and (
+            hasattr(estimator, "l1_ratio") and np.isclose(estimator.l1_ratio, 1.0)
+        )
+        is_elasticnetcv_l1_penalized = est_name == "ElasticNetCV" and (
+            hasattr(estimator, "l1_ratio_") and np.isclose(estimator.l1_ratio_, 1.0)
+        )
+        is_logreg_l1_penalized = est_name == "LogisticRegression" and (
+            hasattr(estimator, "l1_ratio") and np.isclose(estimator.l1_ratio, 1.0)
+        )
+        is_logregcv_l1_penalized = est_name == "LogisticRegressionCV" and (
+            hasattr(estimator, "l1_ratio_")
+            and np.all(np.isclose(estimator.l1_ratio_, 1.0))
+        )
+        if (
+            is_l1_penalized
+            or is_lasso
+            or is_elasticnet_l1_penalized
+            or is_elasticnetcv_l1_penalized
+            or is_logreg_l1_penalized
+            or is_logregcv_l1_penalized
+        ):
+            # the natural default threshold is 0 when l1 penalty was used
+            threshold = 1e-5
+        else:
+            threshold = "mean"
+
+    if isinstance(threshold, str):
+        if "*" in threshold:
+            scale, reference = threshold.split("*")
+            scale = float(scale.strip())
+            reference = reference.strip()
+
+            if reference == "median":
+                reference = np.median(importances)
+            elif reference == "mean":
+                reference = np.mean(importances)
+            else:
+                raise ValueError("Unknown reference: " + reference)
+
+            threshold = scale * reference
+
+        elif threshold == "median":
+            threshold = np.median(importances)
+
+        elif threshold == "mean":
+            threshold = np.mean(importances)
+
+        else:
+            raise ValueError(
+                "Expected threshold='mean' or threshold='median' got %s" % threshold
+            )
+
+    else:
+        threshold = float(threshold)
+
+    return threshold
+
+
+class SelectFromModel(MetaEstimatorMixin, SelectorMixin, BaseEstimator):
+    """Meta-transformer for selecting features based on importance weights.
+
+    .. versionadded:: 0.17
+
+    Read more in the :ref:`User Guide <select_from_model>`.
+
+    Parameters
+    ----------
+    estimator : object
+        The base estimator from which the transformer is built.
+        This can be both a fitted (if ``prefit`` is set to True)
+        or a non-fitted estimator. The estimator should have a
+        ``feature_importances_`` or ``coef_`` attribute after fitting.
+        Otherwise, the ``importance_getter`` parameter should be used.
+
+    threshold : str or float, default=None
+        The threshold value to use for feature selection. Features whose
+        absolute importance value is greater or equal are kept while the others
+        are discarded. If "median" (resp. "mean"), then the ``threshold`` value
+        is the median (resp. the mean) of the feature importances. A scaling
+        factor (e.g., "1.25*mean") may also be used. If None and if the
+        estimator has a parameter penalty set to l1, either explicitly
+        or implicitly (e.g, Lasso), the threshold used is 1e-5.
+        Otherwise, "mean" is used by default.
+
+    prefit : bool, default=False
+        Whether a prefit model is expected to be passed into the constructor
+        directly or not.
+        If `True`, `estimator` must be a fitted estimator.
+        If `False`, `estimator` is fitted and updated by calling
+        `fit` and `partial_fit`, respectively.
+
+    norm_order : non-zero int, inf, -inf, default=1
+        Order of the norm used to filter the vectors of coefficients below
+        ``threshold`` in the case where the ``coef_`` attribute of the
+        estimator is of dimension 2.
+
+    max_features : int, callable, default=None
+        The maximum number of features to select.
+
+        - If an integer, then it specifies the maximum number of features to
+          allow.
+        - If a callable, then it specifies how to calculate the maximum number of
+          features allowed. The callable will receive `X` as input: `max_features(X)`.
+        - If `None`, then all features are kept.
+
+        To only select based on ``max_features``, set ``threshold=-np.inf``.
+
+        .. versionadded:: 0.20
+        .. versionchanged:: 1.1
+           `max_features` accepts a callable.
+
+    importance_getter : str or callable, default='auto'
+        If 'auto', uses the feature importance either through a ``coef_``
+        attribute or ``feature_importances_`` attribute of estimator.
+
+        Also accepts a string that specifies an attribute name/path
+        for extracting feature importance (implemented with `attrgetter`).
+        For example, give `regressor_.coef_` in case of
+        :class:`~sklearn.compose.TransformedTargetRegressor`  or
+        `named_steps.clf.feature_importances_` in case of
+        :class:`~sklearn.pipeline.Pipeline` with its last step named `clf`.
+
+        If `callable`, overrides the default feature importance getter.
+        The callable is passed with the fitted estimator and it should
+        return importance for each feature.
+
+        .. versionadded:: 0.24
+
+    Attributes
+    ----------
+    estimator_ : estimator
+        The base estimator from which the transformer is built. This attribute
+        exist only when `fit` has been called.
+
+        - If `prefit=True`, it is a deep copy of `estimator`.
+        - If `prefit=False`, it is a clone of `estimator` and fit on the data
+          passed to `fit` or `partial_fit`.
+
+    n_features_in_ : int
+        Number of features seen during :term:`fit`. Only defined if the
+        underlying estimator exposes such an attribute when fit.
+
+        .. versionadded:: 0.24
+
+    max_features_ : int
+        Maximum number of features calculated during :term:`fit`. Only defined
+        if the ``max_features`` is not `None`.
+
+        - If `max_features` is an `int`, then `max_features_ = max_features`.
+        - If `max_features` is a callable, then `max_features_ = max_features(X)`.
+
+        .. versionadded:: 1.1
+
+    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
+
+    threshold_ : float
+        The threshold value used for feature selection.
+
+    See Also
+    --------
+    RFE : Recursive feature elimination based on importance weights.
+    RFECV : Recursive feature elimination with built-in cross-validated
+        selection of the best number of features.
+    SequentialFeatureSelector : Sequential cross-validation based feature
+        selection. Does not rely on importance weights.
+
+    Notes
+    -----
+    Allows NaN/Inf in the input if the underlying estimator does as well.
+
+    Examples
+    --------
+    >>> from sklearn.feature_selection import SelectFromModel
+    >>> from sklearn.linear_model import LogisticRegression
+    >>> X = [[ 0.87, -1.34,  0.31 ],
+    ...      [-2.79, -0.02, -0.85 ],
+    ...      [-1.34, -0.48, -2.55 ],
+    ...      [ 1.92,  1.48,  0.65 ]]
+    >>> y = [0, 1, 0, 1]
+    >>> selector = SelectFromModel(estimator=LogisticRegression()).fit(X, y)
+    >>> selector.estimator_.coef_
+    array([[-0.3252,  0.8345,  0.4976]])
+    >>> selector.threshold_
+    np.float64(0.55249)
+    >>> selector.get_support()
+    array([False,  True, False])
+    >>> selector.transform(X)
+    array([[-1.34],
+           [-0.02],
+           [-0.48],
+           [ 1.48]])
+
+    Using a callable to create a selector that can use no more than half
+    of the input features.
+
+    >>> def half_callable(X):
+    ...     return round(len(X[0]) / 2)
+    >>> half_selector = SelectFromModel(estimator=LogisticRegression(),
+    ...                                 max_features=half_callable)
+    >>> _ = half_selector.fit(X, y)
+    >>> half_selector.max_features_
+    2
+    """
+
+    _parameter_constraints: dict = {
+        "estimator": [HasMethods("fit")],
+        "threshold": [Interval(Real, None, None, closed="both"), str, None],
+        "prefit": ["boolean"],
+        "norm_order": [
+            Interval(Integral, None, -1, closed="right"),
+            Interval(Integral, 1, None, closed="left"),
+            Options(Real, {np.inf, -np.inf}),
+        ],
+        "max_features": [Interval(Integral, 0, None, closed="left"), callable, None],
+        "importance_getter": [str, callable],
+    }
+
+    def __init__(
+        self,
+        estimator,
+        *,
+        threshold=None,
+        prefit=False,
+        norm_order=1,
+        max_features=None,
+        importance_getter="auto",
+    ):
+        self.estimator = estimator
+        self.threshold = threshold
+        self.prefit = prefit
+        self.importance_getter = importance_getter
+        self.norm_order = norm_order
+        self.max_features = max_features
+
+    def _get_support_mask(self):
+        estimator = getattr(self, "estimator_", self.estimator)
+        max_features = getattr(self, "max_features_", self.max_features)
+
+        if self.prefit:
+            try:
+                check_is_fitted(self.estimator)
+            except NotFittedError as exc:
+                raise NotFittedError(
+                    "When `prefit=True`, `estimator` is expected to be a fitted "
+                    "estimator."
+                ) from exc
+        if callable(max_features):
+            # This branch is executed when `transform` is called directly and thus
+            # `max_features_` is not set and we fallback using `self.max_features`
+            # that is not validated
+            raise NotFittedError(
+                "When `prefit=True` and `max_features` is a callable, call `fit` "
+                "before calling `transform`."
+            )
+        elif max_features is not None and not isinstance(max_features, Integral):
+            raise ValueError(
+                f"`max_features` must be an integer. Got `max_features={max_features}` "
+                "instead."
+            )
+
+        scores = _get_feature_importances(
+            estimator=estimator,
+            getter=self.importance_getter,
+            transform_func="norm",
+            norm_order=self.norm_order,
+        )
+        threshold = _calculate_threshold(estimator, scores, self.threshold)
+        if self.max_features is not None:
+            mask = np.zeros_like(scores, dtype=bool)
+            candidate_indices = np.argsort(-scores, kind="mergesort")[:max_features]
+            mask[candidate_indices] = True
+        else:
+            mask = np.ones_like(scores, dtype=bool)
+        mask[scores < threshold] = False
+        return mask
+
+    def _check_max_features(self, X):
+        if self.max_features is not None:
+            if callable(self.max_features):
+                max_features = self.max_features(X)
+            else:  # int
+                max_features = self.max_features
+
+            check_scalar(
+                max_features,
+                "max_features",
+                Integral,
+                min_val=0,
+                max_val=None,
+            )
+            self.max_features_ = max_features
+
+    @_fit_context(
+        # SelectFromModel.estimator is not validated yet
+        prefer_skip_nested_validation=False
+    )
+    def fit(self, X, y=None, **fit_params):
+        """Fit the SelectFromModel meta-transformer.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            The training input samples.
+
+        y : array-like of shape (n_samples,), default=None
+            The target values (integers that correspond to classes in
+            classification, real numbers in regression).
+
+        **fit_params : dict
+            - If `enable_metadata_routing=False` (default): Parameters directly passed
+              to the `fit` method of the sub-estimator. They are ignored if
+              `prefit=True`.
+
+            - If `enable_metadata_routing=True`: Parameters safely routed to the `fit`
+              method of the sub-estimator. They are ignored if `prefit=True`.
+
+            .. versionchanged:: 1.4
+                See :ref:`Metadata Routing User Guide <metadata_routing>` for
+                more details.
+
+        Returns
+        -------
+        self : object
+            Fitted estimator.
+        """
+        self._check_max_features(X)
+
+        if self.prefit:
+            try:
+                check_is_fitted(self.estimator)
+            except NotFittedError as exc:
+                raise NotFittedError(
+                    "When `prefit=True`, `estimator` is expected to be a fitted "
+                    "estimator."
+                ) from exc
+            self.estimator_ = deepcopy(self.estimator)
+        else:
+            if _routing_enabled():
+                routed_params = process_routing(self, "fit", **fit_params)
+                self.estimator_ = clone(self.estimator)
+                self.estimator_.fit(X, y, **routed_params.estimator.fit)
+            else:
+                # TODO(SLEP6): remove when metadata routing cannot be disabled.
+                self.estimator_ = clone(self.estimator)
+                self.estimator_.fit(X, y, **fit_params)
+
+        if hasattr(self.estimator_, "feature_names_in_"):
+            self.feature_names_in_ = self.estimator_.feature_names_in_
+        else:
+            _check_feature_names(self, X, reset=True)
+
+        return self
+
+    @property
+    def threshold_(self):
+        """Threshold value used for feature selection."""
+        scores = _get_feature_importances(
+            estimator=self.estimator_,
+            getter=self.importance_getter,
+            transform_func="norm",
+            norm_order=self.norm_order,
+        )
+        return _calculate_threshold(self.estimator, scores, self.threshold)
+
+    @available_if(_estimator_has("partial_fit"))
+    @_fit_context(
+        # SelectFromModel.estimator is not validated yet
+        prefer_skip_nested_validation=False
+    )
+    def partial_fit(self, X, y=None, **partial_fit_params):
+        """Fit the SelectFromModel meta-transformer only once.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            The training input samples.
+
+        y : array-like of shape (n_samples,), default=None
+            The target values (integers that correspond to classes in
+            classification, real numbers in regression).
+
+        **partial_fit_params : dict
+            - If `enable_metadata_routing=False` (default): Parameters directly passed
+              to the `partial_fit` method of the sub-estimator.
+
+            - If `enable_metadata_routing=True`: Parameters passed to the `partial_fit`
+              method of the sub-estimator. They are ignored if `prefit=True`.
+
+            .. versionchanged:: 1.4
+
+                `**partial_fit_params` are routed to the sub-estimator, if
+                `enable_metadata_routing=True` is set via
+                :func:`~sklearn.set_config`, which allows for aliasing.
+
+                See :ref:`Metadata Routing User Guide <metadata_routing>` for
+                more details.
+
+        Returns
+        -------
+        self : object
+            Fitted estimator.
+        """
+        first_call = not hasattr(self, "estimator_")
+
+        if first_call:
+            self._check_max_features(X)
+
+        if self.prefit:
+            if first_call:
+                try:
+                    check_is_fitted(self.estimator)
+                except NotFittedError as exc:
+                    raise NotFittedError(
+                        "When `prefit=True`, `estimator` is expected to be a fitted "
+                        "estimator."
+                    ) from exc
+                self.estimator_ = deepcopy(self.estimator)
+            return self
+
+        if first_call:
+            self.estimator_ = clone(self.estimator)
+        if _routing_enabled():
+            routed_params = process_routing(self, "partial_fit", **partial_fit_params)
+            self.estimator_ = clone(self.estimator)
+            self.estimator_.partial_fit(X, y, **routed_params.estimator.partial_fit)
+        else:
+            # TODO(SLEP6): remove when metadata routing cannot be disabled.
+            self.estimator_.partial_fit(X, y, **partial_fit_params)
+
+        if hasattr(self.estimator_, "feature_names_in_"):
+            self.feature_names_in_ = self.estimator_.feature_names_in_
+        else:
+            _check_feature_names(self, X, reset=first_call)
+
+        return self
+
+    @property
+    def n_features_in_(self):
+        """Number of features seen during `fit`."""
+        # For consistency with other estimators we raise an AttributeError so
+        # that hasattr() fails if the estimator isn't fitted.
+        try:
+            check_is_fitted(self)
+        except NotFittedError as nfe:
+            raise AttributeError(
+                "{} object has no n_features_in_ attribute.".format(
+                    self.__class__.__name__
+                )
+            ) from nfe
+
+        return self.estimator_.n_features_in_
+
+    def get_metadata_routing(self):
+        """Get metadata routing of this object.
+
+        Please check :ref:`User Guide <metadata_routing>` on how the routing
+        mechanism works.
+
+        .. versionadded:: 1.4
+
+        Returns
+        -------
+        routing : MetadataRouter
+            A :class:`~sklearn.utils.metadata_routing.MetadataRouter` encapsulating
+            routing information.
+        """
+        router = MetadataRouter(owner=self).add(
+            estimator=self.estimator,
+            method_mapping=MethodMapping()
+            .add(caller="partial_fit", callee="partial_fit")
+            .add(caller="fit", callee="fit"),
+        )
+        return router
+
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.input_tags.sparse = get_tags(self.estimator).input_tags.sparse
+        tags.input_tags.allow_nan = get_tags(self.estimator).input_tags.allow_nan
+        return tags

linedance-app/venv/lib/python3.12/site-packages/sklearn/feature_selection/_mutual_info.py

@@ -0,0 +1,580 @@
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
+from numbers import Integral
+
+import numpy as np
+from scipy.sparse import issparse
+from scipy.special import digamma
+
+from sklearn.metrics.cluster import mutual_info_score
+from sklearn.neighbors import KDTree, NearestNeighbors
+from sklearn.preprocessing import scale
+from sklearn.utils import check_random_state
+from sklearn.utils._param_validation import Interval, StrOptions, validate_params
+from sklearn.utils.multiclass import check_classification_targets
+from sklearn.utils.parallel import Parallel, delayed
+from sklearn.utils.validation import check_array, check_X_y
+
+
+def _compute_mi_cc(x, y, n_neighbors):
+    """Compute mutual information between two continuous variables.
+
+    Parameters
+    ----------
+    x, y : ndarray, shape (n_samples,)
+        Samples of two continuous random variables, must have an identical
+        shape.
+
+    n_neighbors : int
+        Number of nearest neighbors to search for each point, see [1]_.
+
+    Returns
+    -------
+    mi : float
+        Estimated mutual information in nat units. If it turned out to be
+        negative it is replaced by 0.
+
+    Notes
+    -----
+    True mutual information can't be negative. If its estimate by a numerical
+    method is negative, it means (providing the method is adequate) that the
+    mutual information is close to 0 and replacing it by 0 is a reasonable
+    strategy.
+
+    References
+    ----------
+    .. [1] A. Kraskov, H. Stogbauer and P. Grassberger, "Estimating mutual
+           information". Phys. Rev. E 69, 2004.
+    """
+    n_samples = x.size
+
+    x = x.reshape((-1, 1))
+    y = y.reshape((-1, 1))
+    xy = np.hstack((x, y))
+
+    # Here we rely on NearestNeighbors to select the fastest algorithm.
+    nn = NearestNeighbors(metric="chebyshev", n_neighbors=n_neighbors)
+
+    nn.fit(xy)
+    radius = nn.kneighbors()[0]
+    radius = np.nextafter(radius[:, -1], 0)
+
+    # KDTree is explicitly fit to allow for the querying of number of
+    # neighbors within a specified radius
+    kd = KDTree(x, metric="chebyshev")
+    nx = kd.query_radius(x, radius, count_only=True, return_distance=False)
+    nx = np.array(nx) - 1.0
+
+    kd = KDTree(y, metric="chebyshev")
+    ny = kd.query_radius(y, radius, count_only=True, return_distance=False)
+    ny = np.array(ny) - 1.0
+
+    mi = (
+        digamma(n_samples)
+        + digamma(n_neighbors)
+        - np.mean(digamma(nx + 1))
+        - np.mean(digamma(ny + 1))
+    )
+
+    return max(0, mi)
+
+
+def _compute_mi_cd(c, d, n_neighbors):
+    """Compute mutual information between continuous and discrete variables.
+
+    Parameters
+    ----------
+    c : ndarray, shape (n_samples,)
+        Samples of a continuous random variable.
+
+    d : ndarray, shape (n_samples,)
+        Samples of a discrete random variable.
+
+    n_neighbors : int
+        Number of nearest neighbors to search for each point, see [1]_.
+
+    Returns
+    -------
+    mi : float
+        Estimated mutual information in nat units. If it turned out to be
+        negative it is replaced by 0.
+
+    Notes
+    -----
+    True mutual information can't be negative. If its estimate by a numerical
+    method is negative, it means (providing the method is adequate) that the
+    mutual information is close to 0 and replacing it by 0 is a reasonable
+    strategy.
+
+    References
+    ----------
+    .. [1] B. C. Ross "Mutual Information between Discrete and Continuous
+       Data Sets". PLoS ONE 9(2), 2014.
+    """
+    n_samples = c.shape[0]
+    c = c.reshape((-1, 1))
+
+    radius = np.empty(n_samples)
+    label_counts = np.empty(n_samples)
+    k_all = np.empty(n_samples)
+    nn = NearestNeighbors()
+    for label in np.unique(d):
+        mask = d == label
+        count = np.sum(mask)
+        if count > 1:
+            k = min(n_neighbors, count - 1)
+            nn.set_params(n_neighbors=k)
+            nn.fit(c[mask])
+            r = nn.kneighbors()[0]
+            radius[mask] = np.nextafter(r[:, -1], 0)
+            k_all[mask] = k
+        label_counts[mask] = count
+
+    # Ignore points with unique labels.
+    mask = label_counts > 1
+    n_samples = np.sum(mask)
+    label_counts = label_counts[mask]
+    k_all = k_all[mask]
+    c = c[mask]
+    radius = radius[mask]
+
+    kd = KDTree(c)
+    m_all = kd.query_radius(c, radius, count_only=True, return_distance=False)
+    m_all = np.array(m_all)
+
+    mi = (
+        digamma(n_samples)
+        + np.mean(digamma(k_all))
+        - np.mean(digamma(label_counts))
+        - np.mean(digamma(m_all))
+    )
+
+    return max(0, mi)
+
+
+def _compute_mi(x, y, x_discrete, y_discrete, n_neighbors=3):
+    """Compute mutual information between two variables.
+
+    This is a simple wrapper which selects a proper function to call based on
+    whether `x` and `y` are discrete or not.
+    """
+    if x_discrete and y_discrete:
+        return mutual_info_score(x, y)
+    elif x_discrete and not y_discrete:
+        return _compute_mi_cd(y, x, n_neighbors)
+    elif not x_discrete and y_discrete:
+        return _compute_mi_cd(x, y, n_neighbors)
+    else:
+        return _compute_mi_cc(x, y, n_neighbors)
+
+
+def _iterate_columns(X, columns=None):
+    """Iterate over columns of a matrix.
+
+    Parameters
+    ----------
+    X : ndarray or csc_matrix, shape (n_samples, n_features)
+        Matrix over which to iterate.
+
+    columns : iterable or None, default=None
+        Indices of columns to iterate over. If None, iterate over all columns.
+
+    Yields
+    ------
+    x : ndarray, shape (n_samples,)
+        Columns of `X` in dense format.
+    """
+    if columns is None:
+        columns = range(X.shape[1])
+
+    if issparse(X):
+        for i in columns:
+            x = np.zeros(X.shape[0])
+            start_ptr, end_ptr = X.indptr[i], X.indptr[i + 1]
+            x[X.indices[start_ptr:end_ptr]] = X.data[start_ptr:end_ptr]
+            yield x
+    else:
+        for i in columns:
+            yield X[:, i]
+
+
+def _estimate_mi(
+    X,
+    y,
+    *,
+    discrete_features="auto",
+    discrete_target=False,
+    n_neighbors=3,
+    copy=True,
+    random_state=None,
+    n_jobs=None,
+):
+    """Estimate mutual information between the features and the target.
+
+    Parameters
+    ----------
+    X : array-like or sparse matrix, shape (n_samples, n_features)
+        Feature matrix.
+
+    y : array-like of shape (n_samples,)
+        Target vector.
+
+    discrete_features : {'auto', bool, array-like}, default='auto'
+        If bool, then determines whether to consider all features discrete
+        or continuous. If array, then it should be either a boolean mask
+        with shape (n_features,) or array with indices of discrete features.
+        If 'auto', it is assigned to False for dense `X` and to True for
+        sparse `X`.
+
+    discrete_target : bool, default=False
+        Whether to consider `y` as a discrete variable.
+
+    n_neighbors : int, default=3
+        Number of neighbors to use for MI estimation for continuous variables,
+        see [1]_ and [2]_. Higher values reduce variance of the estimation, but
+        could introduce a bias.
+
+    copy : bool, default=True
+        Whether to make a copy of the given data. If set to False, the initial
+        data will be overwritten.
+
+    random_state : int, RandomState instance or None, default=None
+        Determines random number generation for adding small noise to
+        continuous variables in order to remove repeated values.
+        Pass an int for reproducible results across multiple function calls.
+        See :term:`Glossary <random_state>`.
+
+    n_jobs : int, default=None
+        The number of jobs to use for computing the mutual information.
+        The parallelization is done on the columns of `X`.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See :term:`Glossary <n_jobs>`
+        for more details.
+
+        .. versionadded:: 1.5
+
+
+    Returns
+    -------
+    mi : ndarray, shape (n_features,)
+        Estimated mutual information between each feature and the target in
+        nat units. A negative value will be replaced by 0.
+
+    References
+    ----------
+    .. [1] A. Kraskov, H. Stogbauer and P. Grassberger, "Estimating mutual
+           information". Phys. Rev. E 69, 2004.
+    .. [2] B. C. Ross "Mutual Information between Discrete and Continuous
+           Data Sets". PLoS ONE 9(2), 2014.
+    """
+    X, y = check_X_y(X, y, accept_sparse="csc", y_numeric=not discrete_target)
+    n_samples, n_features = X.shape
+
+    if isinstance(discrete_features, (str, bool)):
+        if isinstance(discrete_features, str):
+            if discrete_features == "auto":
+                discrete_features = issparse(X)
+            else:
+                raise ValueError("Invalid string value for discrete_features.")
+        discrete_mask = np.empty(n_features, dtype=bool)
+        discrete_mask.fill(discrete_features)
+    else:
+        discrete_features = check_array(discrete_features, ensure_2d=False)
+        if discrete_features.dtype != "bool":
+            discrete_mask = np.zeros(n_features, dtype=bool)
+            discrete_mask[discrete_features] = True
+        else:
+            discrete_mask = discrete_features
+
+    continuous_mask = ~discrete_mask
+    if np.any(continuous_mask) and issparse(X):
+        raise ValueError("Sparse matrix `X` can't have continuous features.")
+
+    rng = check_random_state(random_state)
+    if np.any(continuous_mask):
+        X = X.astype(np.float64, copy=copy)
+        X[:, continuous_mask] = scale(
+            X[:, continuous_mask], with_mean=False, copy=False
+        )
+
+        # Add small noise to continuous features as advised in Kraskov et. al.
+        means = np.maximum(1, np.mean(np.abs(X[:, continuous_mask]), axis=0))
+        X[:, continuous_mask] += (
+            1e-10
+            * means
+            * rng.standard_normal(size=(n_samples, np.sum(continuous_mask)))
+        )
+
+    if not discrete_target:
+        y = scale(y, with_mean=False)
+        y += (
+            1e-10
+            * np.maximum(1, np.mean(np.abs(y)))
+            * rng.standard_normal(size=n_samples)
+        )
+
+    mi = Parallel(n_jobs=n_jobs)(
+        delayed(_compute_mi)(x, y, discrete_feature, discrete_target, n_neighbors)
+        for x, discrete_feature in zip(_iterate_columns(X), discrete_mask)
+    )
+
+    return np.array(mi)
+
+
+@validate_params(
+    {
+        "X": ["array-like", "sparse matrix"],
+        "y": ["array-like"],
+        "discrete_features": [StrOptions({"auto"}), "boolean", "array-like"],
+        "n_neighbors": [Interval(Integral, 1, None, closed="left")],
+        "copy": ["boolean"],
+        "random_state": ["random_state"],
+        "n_jobs": [Integral, None],
+    },
+    prefer_skip_nested_validation=True,
+)
+def mutual_info_regression(
+    X,
+    y,
+    *,
+    discrete_features="auto",
+    n_neighbors=3,
+    copy=True,
+    random_state=None,
+    n_jobs=None,
+):
+    """Estimate mutual information for a continuous target variable.
+
+    Mutual information (MI) [1]_ between two random variables is a non-negative
+    value, which measures the dependency between the variables. It is equal
+    to zero if and only if two random variables are independent, and higher
+    values mean higher dependency.
+
+    The function relies on nonparametric methods based on entropy estimation
+    from k-nearest neighbors distances as described in [2]_ and [3]_. Both
+    methods are based on the idea originally proposed in [4]_.
+
+    It can be used for univariate features selection, read more in the
+    :ref:`User Guide <univariate_feature_selection>`.
+
+    Parameters
+    ----------
+    X : array-like or sparse matrix, shape (n_samples, n_features)
+        Feature matrix.
+
+    y : array-like of shape (n_samples,)
+        Target vector.
+
+    discrete_features : {'auto', bool, array-like}, default='auto'
+        If bool, then determines whether to consider all features discrete
+        or continuous. If array, then it should be either a boolean mask
+        with shape (n_features,) or array with indices of discrete features.
+        If 'auto', it is assigned to False for dense `X` and to True for
+        sparse `X`.
+
+    n_neighbors : int, default=3
+        Number of neighbors to use for MI estimation for continuous variables,
+        see [2]_ and [3]_. Higher values reduce variance of the estimation, but
+        could introduce a bias.
+
+    copy : bool, default=True
+        Whether to make a copy of the given data. If set to False, the initial
+        data will be overwritten.
+
+    random_state : int, RandomState instance or None, default=None
+        Determines random number generation for adding small noise to
+        continuous variables in order to remove repeated values.
+        Pass an int for reproducible results across multiple function calls.
+        See :term:`Glossary <random_state>`.
+
+    n_jobs : int, default=None
+        The number of jobs to use for computing the mutual information.
+        The parallelization is done on the columns of `X`.
+
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See :term:`Glossary <n_jobs>`
+        for more details.
+
+        .. versionadded:: 1.5
+
+    Returns
+    -------
+    mi : ndarray, shape (n_features,)
+        Estimated mutual information between each feature and the target in
+        nat units.
+
+    Notes
+    -----
+    1. The term "discrete features" is used instead of naming them
+       "categorical", because it describes the essence more accurately.
+       For example, pixel intensities of an image are discrete features
+       (but hardly categorical) and you will get better results if mark them
+       as such. Also note, that treating a continuous variable as discrete and
+       vice versa will usually give incorrect results, so be attentive about
+       that.
+    2. True mutual information can't be negative. If its estimate turns out
+       to be negative, it is replaced by zero.
+
+    References
+    ----------
+    .. [1] `Mutual Information
+           <https://en.wikipedia.org/wiki/Mutual_information>`_
+           on Wikipedia.
+    .. [2] A. Kraskov, H. Stogbauer and P. Grassberger, "Estimating mutual
+           information". Phys. Rev. E 69, 2004.
+    .. [3] B. C. Ross "Mutual Information between Discrete and Continuous
+           Data Sets". PLoS ONE 9(2), 2014.
+    .. [4] L. F. Kozachenko, N. N. Leonenko, "Sample Estimate of the Entropy
+           of a Random Vector", Probl. Peredachi Inf., 23:2 (1987), 9-16
+
+    Examples
+    --------
+    >>> from sklearn.datasets import make_regression
+    >>> from sklearn.feature_selection import mutual_info_regression
+    >>> X, y = make_regression(
+    ...     n_samples=50, n_features=3, n_informative=1, noise=1e-4, random_state=42
+    ... )
+    >>> mutual_info_regression(X, y)
+    array([0.117, 2.645, 0.0287])
+    """
+    return _estimate_mi(
+        X,
+        y,
+        discrete_features=discrete_features,
+        discrete_target=False,
+        n_neighbors=n_neighbors,
+        copy=copy,
+        random_state=random_state,
+        n_jobs=n_jobs,
+    )
+
+
+@validate_params(
+    {
+        "X": ["array-like", "sparse matrix"],
+        "y": ["array-like"],
+        "discrete_features": [StrOptions({"auto"}), "boolean", "array-like"],
+        "n_neighbors": [Interval(Integral, 1, None, closed="left")],
+        "copy": ["boolean"],
+        "random_state": ["random_state"],
+        "n_jobs": [Integral, None],
+    },
+    prefer_skip_nested_validation=True,
+)
+def mutual_info_classif(
+    X,
+    y,
+    *,
+    discrete_features="auto",
+    n_neighbors=3,
+    copy=True,
+    random_state=None,
+    n_jobs=None,
+):
+    """Estimate mutual information for a discrete target variable.
+
+    Mutual information (MI) [1]_ between two random variables is a non-negative
+    value, which measures the dependency between the variables. It is equal
+    to zero if and only if two random variables are independent, and higher
+    values mean higher dependency.
+
+    The function relies on nonparametric methods based on entropy estimation
+    from k-nearest neighbors distances as described in [2]_ and [3]_. Both
+    methods are based on the idea originally proposed in [4]_.
+
+    It can be used for univariate features selection, read more in the
+    :ref:`User Guide <univariate_feature_selection>`.
+
+    Parameters
+    ----------
+    X : {array-like, sparse matrix} of shape (n_samples, n_features)
+        Feature matrix.
+
+    y : array-like of shape (n_samples,)
+        Target vector.
+
+    discrete_features : 'auto', bool or array-like, default='auto'
+        If bool, then determines whether to consider all features discrete
+        or continuous. If array, then it should be either a boolean mask
+        with shape (n_features,) or array with indices of discrete features.
+        If 'auto', it is assigned to False for dense `X` and to True for
+        sparse `X`.
+
+    n_neighbors : int, default=3
+        Number of neighbors to use for MI estimation for continuous variables,
+        see [2]_ and [3]_. Higher values reduce variance of the estimation, but
+        could introduce a bias.
+
+    copy : bool, default=True
+        Whether to make a copy of the given data. If set to False, the initial
+        data will be overwritten.
+
+    random_state : int, RandomState instance or None, default=None
+        Determines random number generation for adding small noise to
+        continuous variables in order to remove repeated values.
+        Pass an int for reproducible results across multiple function calls.
+        See :term:`Glossary <random_state>`.
+
+    n_jobs : int, default=None
+        The number of jobs to use for computing the mutual information.
+        The parallelization is done on the columns of `X`.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors. See :term:`Glossary <n_jobs>`
+        for more details.
+
+        .. versionadded:: 1.5
+
+    Returns
+    -------
+    mi : ndarray, shape (n_features,)
+        Estimated mutual information between each feature and the target in
+        nat units.
+
+    Notes
+    -----
+    1. The term "discrete features" is used instead of naming them
+       "categorical", because it describes the essence more accurately.
+       For example, pixel intensities of an image are discrete features
+       (but hardly categorical) and you will get better results if mark them
+       as such. Also note, that treating a continuous variable as discrete and
+       vice versa will usually give incorrect results, so be attentive about
+       that.
+    2. True mutual information can't be negative. If its estimate turns out
+       to be negative, it is replaced by zero.
+
+    References
+    ----------
+    .. [1] `Mutual Information
+           <https://en.wikipedia.org/wiki/Mutual_information>`_
+           on Wikipedia.
+    .. [2] A. Kraskov, H. Stogbauer and P. Grassberger, "Estimating mutual
+           information". Phys. Rev. E 69, 2004.
+    .. [3] B. C. Ross "Mutual Information between Discrete and Continuous
+           Data Sets". PLoS ONE 9(2), 2014.
+    .. [4] L. F. Kozachenko, N. N. Leonenko, "Sample Estimate of the Entropy
+           of a Random Vector:, Probl. Peredachi Inf., 23:2 (1987), 9-16
+
+    Examples
+    --------
+    >>> from sklearn.datasets import make_classification
+    >>> from sklearn.feature_selection import mutual_info_classif
+    >>> X, y = make_classification(
+    ...     n_samples=100, n_features=10, n_informative=2, n_clusters_per_class=1,
+    ...     shuffle=False, random_state=42
+    ... )
+    >>> mutual_info_classif(X, y)
+    array([0.589, 0.107, 0.196, 0.0968 , 0.,
+           0.   , 0.   , 0.   , 0.     , 0.])
+    """
+    check_classification_targets(y)
+    return _estimate_mi(
+        X,
+        y,
+        discrete_features=discrete_features,
+        discrete_target=True,
+        n_neighbors=n_neighbors,
+        copy=copy,
+        random_state=random_state,
+        n_jobs=n_jobs,
+    )

linedance-app/venv/lib/python3.12/site-packages/sklearn/feature_selection/_sequential.py

@@ -0,0 +1,369 @@
+"""
+Sequential feature selection
+"""
+
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
+from numbers import Integral, Real
+
+import numpy as np
+
+from sklearn.base import (
+    BaseEstimator,
+    MetaEstimatorMixin,
+    _fit_context,
+    clone,
+    is_classifier,
+)
+from sklearn.feature_selection._base import SelectorMixin
+from sklearn.metrics import check_scoring, get_scorer_names
+from sklearn.model_selection import check_cv, cross_val_score
+from sklearn.utils._metadata_requests import (
+    MetadataRouter,
+    MethodMapping,
+    _raise_for_params,
+    _routing_enabled,
+    process_routing,
+)
+from sklearn.utils._param_validation import HasMethods, Interval, RealNotInt, StrOptions
+from sklearn.utils._tags import get_tags
+from sklearn.utils.validation import check_is_fitted, validate_data
+
+
+class SequentialFeatureSelector(SelectorMixin, MetaEstimatorMixin, BaseEstimator):
+    """Transformer that performs Sequential Feature Selection.
+
+    This Sequential Feature Selector adds (forward selection) or
+    removes (backward selection) features to form a feature subset in a
+    greedy fashion. At each stage, this estimator chooses the best feature to
+    add or remove based on the cross-validation score of an estimator. In
+    the case of unsupervised learning, this Sequential Feature Selector
+    looks only at the features (X), not the desired outputs (y).
+
+    Read more in the :ref:`User Guide <sequential_feature_selection>`.
+
+    .. versionadded:: 0.24
+
+    Parameters
+    ----------
+    estimator : estimator instance
+        An unfitted estimator.
+
+    n_features_to_select : "auto", int or float, default="auto"
+        If `"auto"`, the behaviour depends on the `tol` parameter:
+
+        - if `tol` is not `None`, then features are selected while the score
+          change does not exceed `tol`.
+        - otherwise, half of the features are selected.
+
+        If integer, the parameter is the absolute number of features to select.
+        If float between 0 and 1, it is the fraction of features to select.
+
+        .. versionadded:: 1.1
+           The option `"auto"` was added in version 1.1.
+
+        .. versionchanged:: 1.3
+           The default changed from `"warn"` to `"auto"` in 1.3.
+
+    tol : float, default=None
+        If the score is not incremented by at least `tol` between two
+        consecutive feature additions or removals, stop adding or removing.
+
+        `tol` can be negative when removing features using `direction="backward"`.
+        `tol` is required to be strictly positive when doing forward selection.
+        It can be useful to reduce the number of features at the cost of a small
+        decrease in the score.
+
+        `tol` is enabled only when `n_features_to_select` is `"auto"`.
+
+        .. versionadded:: 1.1
+
+    direction : {'forward', 'backward'}, default='forward'
+        Whether to perform forward selection or backward selection.
+
+    scoring : str or callable, default=None
+        Scoring method to use for cross-validation. Options:
+
+        - str: see :ref:`scoring_string_names` for options.
+        - callable: a scorer callable object (e.g., function) with signature
+          ``scorer(estimator, X, y)`` that returns a single value.
+          See :ref:`scoring_callable` for details.
+        - `None`: the `estimator`'s
+          :ref:`default evaluation criterion <scoring_api_overview>` is used.
+
+    cv : int, cross-validation generator or an iterable, default=None
+        Determines the cross-validation splitting strategy.
+        Possible inputs for cv are:
+
+        - None, to use the default 5-fold cross validation,
+        - integer, to specify the number of folds in a `(Stratified)KFold`,
+        - :term:`CV splitter`,
+        - An iterable yielding (train, test) splits as arrays of indices.
+
+        For integer/None inputs, if the estimator is a classifier and ``y`` is
+        either binary or multiclass,
+        :class:`~sklearn.model_selection.StratifiedKFold` is used. In all other
+        cases, :class:`~sklearn.model_selection.KFold` is used. These splitters
+        are instantiated with `shuffle=False` so the splits will be the same
+        across calls.
+
+        Refer :ref:`User Guide <cross_validation>` for the various
+        cross-validation strategies that can be used here.
+
+    n_jobs : int, default=None
+        Number of jobs to run in parallel. When evaluating a new feature to
+        add or remove, the cross-validation procedure is parallel over the
+        folds.
+        ``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
+    ----------
+    n_features_in_ : int
+        Number of features seen during :term:`fit`. Only defined if the
+        underlying estimator exposes such an attribute when 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_features_to_select_ : int
+        The number of features that were selected.
+
+    support_ : ndarray of shape (n_features,), dtype=bool
+        The mask of selected features.
+
+    See Also
+    --------
+    GenericUnivariateSelect : Univariate feature selector with configurable
+        strategy.
+    RFE : Recursive feature elimination based on importance weights.
+    RFECV : Recursive feature elimination based on importance weights, with
+        automatic selection of the number of features.
+    SelectFromModel : Feature selection based on thresholds of importance
+        weights.
+
+    Examples
+    --------
+    >>> from sklearn.feature_selection import SequentialFeatureSelector
+    >>> from sklearn.neighbors import KNeighborsClassifier
+    >>> from sklearn.datasets import load_iris
+    >>> X, y = load_iris(return_X_y=True)
+    >>> knn = KNeighborsClassifier(n_neighbors=3)
+    >>> sfs = SequentialFeatureSelector(knn, n_features_to_select=3)
+    >>> sfs.fit(X, y)
+    SequentialFeatureSelector(estimator=KNeighborsClassifier(n_neighbors=3),
+                              n_features_to_select=3)
+    >>> sfs.get_support()
+    array([ True, False,  True,  True])
+    >>> sfs.transform(X).shape
+    (150, 3)
+    """
+
+    _parameter_constraints: dict = {
+        "estimator": [HasMethods(["fit"])],
+        "n_features_to_select": [
+            StrOptions({"auto"}),
+            Interval(RealNotInt, 0, 1, closed="right"),
+            Interval(Integral, 0, None, closed="neither"),
+        ],
+        "tol": [None, Interval(Real, None, None, closed="neither")],
+        "direction": [StrOptions({"forward", "backward"})],
+        "scoring": [None, StrOptions(set(get_scorer_names())), callable],
+        "cv": ["cv_object"],
+        "n_jobs": [None, Integral],
+    }
+
+    def __init__(
+        self,
+        estimator,
+        *,
+        n_features_to_select="auto",
+        tol=None,
+        direction="forward",
+        scoring=None,
+        cv=5,
+        n_jobs=None,
+    ):
+        self.estimator = estimator
+        self.n_features_to_select = n_features_to_select
+        self.tol = tol
+        self.direction = direction
+        self.scoring = scoring
+        self.cv = cv
+        self.n_jobs = n_jobs
+
+    @_fit_context(
+        # SequentialFeatureSelector.estimator is not validated yet
+        prefer_skip_nested_validation=False
+    )
+    def fit(self, X, y=None, **params):
+        """Learn the features to select from X.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            Training vectors, where `n_samples` is the number of samples and
+            `n_features` is the number of predictors.
+
+        y : array-like of shape (n_samples,), default=None
+            Target values. This parameter may be ignored for
+            unsupervised learning.
+
+        **params : dict, default=None
+            Parameters to be passed to the underlying `estimator`, `cv`
+            and `scorer` objects.
+
+            .. versionadded:: 1.6
+
+                Only available if `enable_metadata_routing=True`,
+                which can be set by using
+                ``sklearn.set_config(enable_metadata_routing=True)``.
+                See :ref:`Metadata Routing User Guide <metadata_routing>` for
+                more details.
+
+        Returns
+        -------
+        self : object
+            Returns the instance itself.
+        """
+        _raise_for_params(params, self, "fit")
+        tags = self.__sklearn_tags__()
+        X = validate_data(
+            self,
+            X,
+            accept_sparse="csc",
+            ensure_min_features=2,
+            ensure_all_finite=not tags.input_tags.allow_nan,
+        )
+        n_features = X.shape[1]
+
+        if self.n_features_to_select == "auto":
+            if self.tol is not None:
+                # With auto feature selection, `n_features_to_select_` will be updated
+                # to `support_.sum()` after features are selected.
+                self.n_features_to_select_ = n_features - 1
+            else:
+                self.n_features_to_select_ = n_features // 2
+        elif isinstance(self.n_features_to_select, Integral):
+            if self.n_features_to_select >= n_features:
+                raise ValueError("n_features_to_select must be < n_features.")
+            self.n_features_to_select_ = self.n_features_to_select
+        elif isinstance(self.n_features_to_select, Real):
+            self.n_features_to_select_ = int(n_features * self.n_features_to_select)
+
+        if self.tol is not None and self.tol < 0 and self.direction == "forward":
+            raise ValueError(
+                "tol must be strictly positive when doing forward selection"
+            )
+
+        cv = check_cv(self.cv, y, classifier=is_classifier(self.estimator))
+
+        cloned_estimator = clone(self.estimator)
+
+        # the current mask corresponds to the set of features:
+        # - that we have already *selected* if we do forward selection
+        # - that we have already *excluded* if we do backward selection
+        current_mask = np.zeros(shape=n_features, dtype=bool)
+        n_iterations = (
+            self.n_features_to_select_
+            if self.n_features_to_select == "auto" or self.direction == "forward"
+            else n_features - self.n_features_to_select_
+        )
+
+        old_score = -np.inf
+        is_auto_select = self.tol is not None and self.n_features_to_select == "auto"
+
+        # We only need to verify the routing here and not use the routed params
+        # because internally the actual routing will also take place inside the
+        # `cross_val_score` function.
+        if _routing_enabled():
+            process_routing(self, "fit", **params)
+        for _ in range(n_iterations):
+            new_feature_idx, new_score = self._get_best_new_feature_score(
+                cloned_estimator, X, y, cv, current_mask, **params
+            )
+            if is_auto_select and ((new_score - old_score) < self.tol):
+                break
+
+            old_score = new_score
+            current_mask[new_feature_idx] = True
+
+        if self.direction == "backward":
+            current_mask = ~current_mask
+
+        self.support_ = current_mask
+        self.n_features_to_select_ = self.support_.sum()
+
+        return self
+
+    def _get_best_new_feature_score(self, estimator, X, y, cv, current_mask, **params):
+        # Return the best new feature and its score to add to the current_mask,
+        # i.e. return the best new feature and its score to add (resp. remove)
+        # when doing forward selection (resp. backward selection).
+        # Feature will be added if the current score and past score are greater
+        # than tol when n_feature is auto,
+        candidate_feature_indices = np.flatnonzero(~current_mask)
+        scores = {}
+        for feature_idx in candidate_feature_indices:
+            candidate_mask = current_mask.copy()
+            candidate_mask[feature_idx] = True
+            if self.direction == "backward":
+                candidate_mask = ~candidate_mask
+            X_new = X[:, candidate_mask]
+            scores[feature_idx] = cross_val_score(
+                estimator,
+                X_new,
+                y,
+                cv=cv,
+                scoring=self.scoring,
+                n_jobs=self.n_jobs,
+                params=params,
+            ).mean()
+        new_feature_idx = max(scores, key=lambda feature_idx: scores[feature_idx])
+        return new_feature_idx, scores[new_feature_idx]
+
+    def _get_support_mask(self):
+        check_is_fitted(self)
+        return self.support_
+
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.input_tags.allow_nan = get_tags(self.estimator).input_tags.allow_nan
+        tags.input_tags.sparse = get_tags(self.estimator).input_tags.sparse
+        return tags
+
+    def get_metadata_routing(self):
+        """Get metadata routing of this object.
+
+        Please check :ref:`User Guide <metadata_routing>` on how the routing
+        mechanism works.
+
+        .. versionadded:: 1.6
+
+        Returns
+        -------
+        routing : MetadataRouter
+            A :class:`~sklearn.utils.metadata_routing.MetadataRouter` encapsulating
+            routing information.
+        """
+        router = MetadataRouter(owner=self)
+        router.add(
+            estimator=self.estimator,
+            method_mapping=MethodMapping().add(caller="fit", callee="fit"),
+        )
+        router.add(
+            splitter=check_cv(self.cv, classifier=is_classifier(self.estimator)),
+            method_mapping=MethodMapping().add(caller="fit", callee="split"),
+        )
+        router.add(
+            scorer=check_scoring(self.estimator, scoring=self.scoring),
+            method_mapping=MethodMapping().add(caller="fit", callee="score"),
+        )
+        return router

linedance-app/venv/lib/python3.12/site-packages/sklearn/feature_selection/_variance_threshold.py

@@ -0,0 +1,141 @@
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
+from numbers import Real
+
+import numpy as np
+
+from sklearn.base import BaseEstimator, _fit_context
+from sklearn.feature_selection._base import SelectorMixin
+from sklearn.utils._param_validation import Interval
+from sklearn.utils.sparsefuncs import mean_variance_axis, min_max_axis
+from sklearn.utils.validation import check_is_fitted, validate_data
+
+
+class VarianceThreshold(SelectorMixin, BaseEstimator):
+    """Feature selector that removes all low-variance features.
+
+    This feature selection algorithm looks only at the features (X), not the
+    desired outputs (y), and can thus be used for unsupervised learning.
+
+    Read more in the :ref:`User Guide <variance_threshold>`.
+
+    Parameters
+    ----------
+    threshold : float, default=0
+        Features with a training-set variance lower than this threshold will
+        be removed. The default is to keep all features with non-zero variance,
+        i.e. remove the features that have the same value in all samples.
+
+    Attributes
+    ----------
+    variances_ : array, shape (n_features,)
+        Variances of individual features.
+
+    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
+
+    See Also
+    --------
+    SelectFromModel: Meta-transformer for selecting features based on
+        importance weights.
+    SelectPercentile : Select features according to a percentile of the highest
+        scores.
+    SequentialFeatureSelector : Transformer that performs Sequential Feature
+        Selection.
+
+    Notes
+    -----
+    Allows NaN in the input.
+    Raises ValueError if no feature in X meets the variance threshold.
+
+    Examples
+    --------
+    The following dataset has integer features, two of which are the same
+    in every sample. These are removed with the default setting for threshold::
+
+        >>> from sklearn.feature_selection import VarianceThreshold
+        >>> X = [[0, 2, 0, 3], [0, 1, 4, 3], [0, 1, 1, 3]]
+        >>> selector = VarianceThreshold()
+        >>> selector.fit_transform(X)
+        array([[2, 0],
+               [1, 4],
+               [1, 1]])
+    """
+
+    _parameter_constraints: dict = {
+        "threshold": [Interval(Real, 0, None, closed="left")]
+    }
+
+    def __init__(self, threshold=0.0):
+        self.threshold = threshold
+
+    @_fit_context(prefer_skip_nested_validation=True)
+    def fit(self, X, y=None):
+        """Learn empirical variances from X.
+
+        Parameters
+        ----------
+        X : {array-like, sparse matrix}, shape (n_samples, n_features)
+            Data from which to compute variances, where `n_samples` is
+            the number of samples and `n_features` is the number of features.
+
+        y : any, default=None
+            Ignored. This parameter exists only for compatibility with
+            sklearn.pipeline.Pipeline.
+
+        Returns
+        -------
+        self : object
+            Returns the instance itself.
+        """
+        X = validate_data(
+            self,
+            X,
+            accept_sparse=("csr", "csc"),
+            dtype=np.float64,
+            ensure_all_finite="allow-nan",
+        )
+
+        if hasattr(X, "toarray"):  # sparse matrix
+            _, self.variances_ = mean_variance_axis(X, axis=0)
+            if self.threshold == 0:
+                mins, maxes = min_max_axis(X, axis=0)
+                peak_to_peaks = maxes - mins
+        else:
+            self.variances_ = np.nanvar(X, axis=0)
+            if self.threshold == 0:
+                peak_to_peaks = np.ptp(X, axis=0)
+
+        if self.threshold == 0:
+            # Use peak-to-peak to avoid numeric precision issues
+            # for constant features
+            compare_arr = np.array([self.variances_, peak_to_peaks])
+            self.variances_ = np.nanmin(compare_arr, axis=0)
+
+        if np.all(~np.isfinite(self.variances_) | (self.variances_ <= self.threshold)):
+            msg = "No feature in X meets the variance threshold {0:.5f}"
+            if X.shape[0] == 1:
+                msg += " (X contains only one sample)"
+            raise ValueError(msg.format(self.threshold))
+
+        return self
+
+    def _get_support_mask(self):
+        check_is_fitted(self)
+
+        return self.variances_ > self.threshold
+
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.input_tags.allow_nan = True
+        tags.input_tags.sparse = True
+        return tags

linedance-app/venv/lib/python3.12/site-packages/sklearn/feature_selection/tests/test_base.py

@@ -0,0 +1,154 @@
+import numpy as np
+import pytest
+from numpy.testing import assert_array_equal
+
+from sklearn.base import BaseEstimator
+from sklearn.feature_selection._base import SelectorMixin
+from sklearn.utils.fixes import CSC_CONTAINERS
+from sklearn.utils.validation import validate_data
+
+
+class StepSelector(SelectorMixin, BaseEstimator):
+    """Retain every `step` features (beginning with 0).
+
+    If `step < 1`, then no features are selected.
+    """
+
+    def __init__(self, step=2):
+        self.step = step
+
+    def fit(self, X, y=None):
+        X = validate_data(self, X, accept_sparse="csc")
+        return self
+
+    def _get_support_mask(self):
+        mask = np.zeros(self.n_features_in_, dtype=bool)
+        if self.step >= 1:
+            mask[:: self.step] = True
+        return mask
+
+
+support = [True, False] * 5
+support_inds = [0, 2, 4, 6, 8]
+X = np.arange(20).reshape(2, 10)
+Xt = np.arange(0, 20, 2).reshape(2, 5)
+Xinv = X.copy()
+Xinv[:, 1::2] = 0
+y = [0, 1]
+feature_names = list("ABCDEFGHIJ")
+feature_names_t = feature_names[::2]
+feature_names_inv = np.array(feature_names)
+feature_names_inv[1::2] = ""
+
+
+def test_transform_dense():
+    sel = StepSelector()
+    Xt_actual = sel.fit(X, y).transform(X)
+    Xt_actual2 = StepSelector().fit_transform(X, y)
+    assert_array_equal(Xt, Xt_actual)
+    assert_array_equal(Xt, Xt_actual2)
+
+    # Check dtype matches
+    assert np.int32 == sel.transform(X.astype(np.int32)).dtype
+    assert np.float32 == sel.transform(X.astype(np.float32)).dtype
+
+    # Check 1d list and other dtype:
+    names_t_actual = sel.transform([feature_names])
+    assert_array_equal(feature_names_t, names_t_actual.ravel())
+
+    # Check wrong shape raises error
+    with pytest.raises(ValueError):
+        sel.transform(np.array([[1], [2]]))
+
+
+@pytest.mark.parametrize("csc_container", CSC_CONTAINERS)
+def test_transform_sparse(csc_container):
+    X_sp = csc_container(X)
+    sel = StepSelector()
+    Xt_actual = sel.fit(X_sp).transform(X_sp)
+    Xt_actual2 = sel.fit_transform(X_sp)
+    assert_array_equal(Xt, Xt_actual.toarray())
+    assert_array_equal(Xt, Xt_actual2.toarray())
+
+    # Check dtype matches
+    assert np.int32 == sel.transform(X_sp.astype(np.int32)).dtype
+    assert np.float32 == sel.transform(X_sp.astype(np.float32)).dtype
+
+    # Check wrong shape raises error
+    with pytest.raises(ValueError):
+        sel.transform(np.array([[1], [2]]))
+
+
+def test_inverse_transform_dense():
+    sel = StepSelector()
+    Xinv_actual = sel.fit(X, y).inverse_transform(Xt)
+    assert_array_equal(Xinv, Xinv_actual)
+
+    # Check dtype matches
+    assert np.int32 == sel.inverse_transform(Xt.astype(np.int32)).dtype
+    assert np.float32 == sel.inverse_transform(Xt.astype(np.float32)).dtype
+
+    # Check 1d list and other dtype:
+    names_inv_actual = sel.inverse_transform([feature_names_t])
+    assert_array_equal(feature_names_inv, names_inv_actual.ravel())
+
+    # Check wrong shape raises error
+    with pytest.raises(ValueError):
+        sel.inverse_transform(np.array([[1], [2]]))
+
+
+@pytest.mark.parametrize("csc_container", CSC_CONTAINERS)
+def test_inverse_transform_sparse(csc_container):
+    X_sp = csc_container(X)
+    Xt_sp = csc_container(Xt)
+    sel = StepSelector()
+    Xinv_actual = sel.fit(X_sp).inverse_transform(Xt_sp)
+    assert_array_equal(Xinv, Xinv_actual.toarray())
+
+    # Check dtype matches
+    assert np.int32 == sel.inverse_transform(Xt_sp.astype(np.int32)).dtype
+    assert np.float32 == sel.inverse_transform(Xt_sp.astype(np.float32)).dtype
+
+    # Check wrong shape raises error
+    with pytest.raises(ValueError):
+        sel.inverse_transform(np.array([[1], [2]]))
+
+
+def test_get_support():
+    sel = StepSelector()
+    sel.fit(X, y)
+    assert_array_equal(support, sel.get_support())
+    assert_array_equal(support_inds, sel.get_support(indices=True))
+
+
+def test_output_dataframe():
+    """Check output dtypes for dataframes is consistent with the input dtypes."""
+    pd = pytest.importorskip("pandas")
+
+    X = pd.DataFrame(
+        {
+            "a": pd.Series([1.0, 2.4, 4.5], dtype=np.float32),
+            "b": pd.Series(["a", "b", "a"], dtype="category"),
+            "c": pd.Series(["j", "b", "b"], dtype="category"),
+            "d": pd.Series([3.0, 2.4, 1.2], dtype=np.float64),
+        }
+    )
+
+    for step in [2, 3]:
+        sel = StepSelector(step=step).set_output(transform="pandas")
+        sel.fit(X)
+
+        output = sel.transform(X)
+        for name, dtype in output.dtypes.items():
+            assert dtype == X.dtypes[name]
+
+    # step=0 will select nothing
+    sel0 = StepSelector(step=0).set_output(transform="pandas")
+    sel0.fit(X, y)
+
+    msg = "No features were selected"
+    with pytest.warns(UserWarning, match=msg):
+        output0 = sel0.transform(X)
+
+    assert_array_equal(output0.index, X.index)
+    assert output0.shape == (X.shape[0], 0)

linedance-app/venv/lib/python3.12/site-packages/sklearn/feature_selection/tests/test_chi2.py

@@ -0,0 +1,93 @@
+"""
+Tests for chi2, currently the only feature selection function designed
+specifically to work with sparse matrices.
+"""
+
+import warnings
+
+import numpy as np
+import pytest
+import scipy.stats
+
+from sklearn.feature_selection import SelectKBest, chi2
+from sklearn.feature_selection._univariate_selection import _chisquare
+from sklearn.utils._testing import assert_array_almost_equal, assert_array_equal
+from sklearn.utils.fixes import COO_CONTAINERS, CSR_CONTAINERS
+
+# Feature 0 is highly informative for class 1;
+# feature 1 is the same everywhere;
+# feature 2 is a bit informative for class 2.
+X = [[2, 1, 2], [9, 1, 1], [6, 1, 2], [0, 1, 2]]
+y = [0, 1, 2, 2]
+
+
+def mkchi2(k):
+    """Make k-best chi2 selector"""
+    return SelectKBest(chi2, k=k)
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+def test_chi2(csr_container):
+    # Test Chi2 feature extraction
+
+    chi2 = mkchi2(k=1).fit(X, y)
+    chi2 = mkchi2(k=1).fit(X, y)
+    assert_array_equal(chi2.get_support(indices=True), [0])
+    assert_array_equal(chi2.transform(X), np.array(X)[:, [0]])
+
+    chi2 = mkchi2(k=2).fit(X, y)
+    assert_array_equal(sorted(chi2.get_support(indices=True)), [0, 2])
+
+    Xsp = csr_container(X, dtype=np.float64)
+    chi2 = mkchi2(k=2).fit(Xsp, y)
+    assert_array_equal(sorted(chi2.get_support(indices=True)), [0, 2])
+    Xtrans = chi2.transform(Xsp)
+    assert_array_equal(Xtrans.shape, [Xsp.shape[0], 2])
+
+    # == doesn't work on scipy.sparse matrices
+    Xtrans = Xtrans.toarray()
+    Xtrans2 = mkchi2(k=2).fit_transform(Xsp, y).toarray()
+    assert_array_almost_equal(Xtrans, Xtrans2)
+
+
+@pytest.mark.parametrize("coo_container", COO_CONTAINERS)
+def test_chi2_coo(coo_container):
+    # Check that chi2 works with a COO matrix
+    # (as returned by CountVectorizer, DictVectorizer)
+    Xcoo = coo_container(X)
+    mkchi2(k=2).fit_transform(Xcoo, y)
+    # if we got here without an exception, we're safe
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+def test_chi2_negative(csr_container):
+    # Check for proper error on negative numbers in the input X.
+    X, y = [[0, 1], [-1e-20, 1]], [0, 1]
+    for X in (X, np.array(X), csr_container(X)):
+        with pytest.raises(ValueError):
+            chi2(X, y)
+
+
+def test_chi2_unused_feature():
+    # Unused feature should evaluate to NaN
+    # and should issue no runtime warning
+    with warnings.catch_warnings(record=True) as warned:
+        warnings.simplefilter("always")
+        chi, p = chi2([[1, 0], [0, 0]], [1, 0])
+        for w in warned:
+            if "divide by zero" in repr(w):
+                raise AssertionError("Found unexpected warning %s" % w)
+    assert_array_equal(chi, [1, np.nan])
+    assert_array_equal(p[1], np.nan)
+
+
+def test_chisquare():
+    # Test replacement for scipy.stats.chisquare against the original.
+    obs = np.array([[2.0, 2.0], [1.0, 1.0]])
+    exp = np.array([[1.5, 1.5], [1.5, 1.5]])
+    # call SciPy first because our version overwrites obs
+    chi_scp, p_scp = scipy.stats.chisquare(obs, exp)
+    chi_our, p_our = _chisquare(obs, exp)
+
+    assert_array_almost_equal(chi_scp, chi_our)
+    assert_array_almost_equal(p_scp, p_our)

linedance-app/venv/lib/python3.12/site-packages/sklearn/feature_selection/tests/test_from_model.py

@@ -0,0 +1,672 @@
+import re
+import warnings
+from unittest.mock import Mock
+
+import numpy as np
+import pytest
+
+from sklearn import datasets
+from sklearn.base import BaseEstimator
+from sklearn.cross_decomposition import CCA, PLSCanonical, PLSRegression
+from sklearn.datasets import make_friedman1, make_regression
+from sklearn.decomposition import PCA
+from sklearn.ensemble import HistGradientBoostingClassifier, RandomForestClassifier
+from sklearn.exceptions import NotFittedError
+from sklearn.feature_selection import SelectFromModel
+from sklearn.linear_model import (
+    ElasticNet,
+    ElasticNetCV,
+    Lasso,
+    LassoCV,
+    LinearRegression,
+    LogisticRegression,
+    SGDClassifier,
+)
+from sklearn.pipeline import make_pipeline
+from sklearn.svm import LinearSVC
+from sklearn.utils._testing import (
+    MinimalClassifier,
+    assert_allclose,
+    assert_array_almost_equal,
+    assert_array_equal,
+    skip_if_32bit,
+)
+
+
+class NaNTag(BaseEstimator):
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.input_tags.allow_nan = True
+        return tags
+
+
+class NoNaNTag(BaseEstimator):
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.input_tags.allow_nan = False
+        return tags
+
+
+class NaNTagRandomForest(RandomForestClassifier):
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.input_tags.allow_nan = True
+        return tags
+
+
+iris = datasets.load_iris()
+data, y = iris.data, iris.target
+
+
+def test_invalid_input():
+    clf = SGDClassifier(
+        alpha=0.1, max_iter=10, shuffle=True, random_state=None, tol=None
+    )
+    for threshold in ["gobbledigook", ".5 * gobbledigook"]:
+        model = SelectFromModel(clf, threshold=threshold)
+        model.fit(data, y)
+        with pytest.raises(ValueError):
+            model.transform(data)
+
+
+def test_input_estimator_unchanged():
+    # Test that SelectFromModel fits on a clone of the estimator.
+    est = RandomForestClassifier()
+    transformer = SelectFromModel(estimator=est)
+    transformer.fit(data, y)
+    assert transformer.estimator is est
+
+
+@pytest.mark.parametrize(
+    "max_features, err_type, err_msg",
+    [
+        (
+            lambda X: 1.5,
+            TypeError,
+            "max_features must be an instance of int, not float.",
+        ),
+        (
+            lambda X: -1,
+            ValueError,
+            "max_features ==",
+        ),
+    ],
+)
+def test_max_features_error(max_features, err_type, err_msg):
+    err_msg = re.escape(err_msg)
+    clf = RandomForestClassifier(n_estimators=5, random_state=0)
+
+    transformer = SelectFromModel(
+        estimator=clf, max_features=max_features, threshold=-np.inf
+    )
+    with pytest.raises(err_type, match=err_msg):
+        transformer.fit(data, y)
+
+
+@pytest.mark.parametrize("max_features", [0, 2, data.shape[1], None])
+def test_inferred_max_features_integer(max_features):
+    """Check max_features_ and output shape for integer max_features."""
+    clf = RandomForestClassifier(n_estimators=5, random_state=0)
+    transformer = SelectFromModel(
+        estimator=clf, max_features=max_features, threshold=-np.inf
+    )
+    X_trans = transformer.fit_transform(data, y)
+    if max_features is not None:
+        assert transformer.max_features_ == max_features
+        assert X_trans.shape[1] == transformer.max_features_
+    else:
+        assert not hasattr(transformer, "max_features_")
+        assert X_trans.shape[1] == data.shape[1]
+
+
+@pytest.mark.parametrize(
+    "max_features",
+    [lambda X: 1, lambda X: X.shape[1], lambda X: min(X.shape[1], 10000)],
+)
+def test_inferred_max_features_callable(max_features):
+    """Check max_features_ and output shape for callable max_features."""
+    clf = RandomForestClassifier(n_estimators=5, random_state=0)
+    transformer = SelectFromModel(
+        estimator=clf, max_features=max_features, threshold=-np.inf
+    )
+    X_trans = transformer.fit_transform(data, y)
+    assert transformer.max_features_ == max_features(data)
+    assert X_trans.shape[1] == transformer.max_features_
+
+
+@pytest.mark.parametrize("max_features", [lambda X: round(len(X[0]) / 2), 2])
+def test_max_features_array_like(max_features):
+    X = [
+        [0.87, -1.34, 0.31],
+        [-2.79, -0.02, -0.85],
+        [-1.34, -0.48, -2.55],
+        [1.92, 1.48, 0.65],
+    ]
+    y = [0, 1, 0, 1]
+
+    clf = RandomForestClassifier(n_estimators=5, random_state=0)
+    transformer = SelectFromModel(
+        estimator=clf, max_features=max_features, threshold=-np.inf
+    )
+    X_trans = transformer.fit_transform(X, y)
+    assert X_trans.shape[1] == transformer.max_features_
+
+
+@pytest.mark.parametrize(
+    "max_features",
+    [lambda X: min(X.shape[1], 10000), lambda X: X.shape[1], lambda X: 1],
+)
+def test_max_features_callable_data(max_features):
+    """Tests that the callable passed to `fit` is called on X."""
+    clf = RandomForestClassifier(n_estimators=50, random_state=0)
+    m = Mock(side_effect=max_features)
+    transformer = SelectFromModel(estimator=clf, max_features=m, threshold=-np.inf)
+    transformer.fit_transform(data, y)
+    m.assert_called_with(data)
+
+
+class FixedImportanceEstimator(BaseEstimator):
+    def __init__(self, importances):
+        self.importances = importances
+
+    def fit(self, X, y=None):
+        self.feature_importances_ = np.array(self.importances)
+
+
+def test_max_features():
+    # Test max_features parameter using various values
+    X, y = datasets.make_classification(
+        n_samples=1000,
+        n_features=10,
+        n_informative=3,
+        n_redundant=0,
+        n_repeated=0,
+        shuffle=False,
+        random_state=0,
+    )
+    max_features = X.shape[1]
+    est = RandomForestClassifier(n_estimators=50, random_state=0)
+
+    transformer1 = SelectFromModel(estimator=est, threshold=-np.inf)
+    transformer2 = SelectFromModel(
+        estimator=est, max_features=max_features, threshold=-np.inf
+    )
+    X_new1 = transformer1.fit_transform(X, y)
+    X_new2 = transformer2.fit_transform(X, y)
+    assert_allclose(X_new1, X_new2)
+
+    # Test max_features against actual model.
+    transformer1 = SelectFromModel(estimator=Lasso(alpha=0.025, random_state=42))
+    X_new1 = transformer1.fit_transform(X, y)
+    scores1 = np.abs(transformer1.estimator_.coef_)
+    candidate_indices1 = np.argsort(-scores1, kind="mergesort")
+
+    for n_features in range(1, X_new1.shape[1] + 1):
+        transformer2 = SelectFromModel(
+            estimator=Lasso(alpha=0.025, random_state=42),
+            max_features=n_features,
+            threshold=-np.inf,
+        )
+        X_new2 = transformer2.fit_transform(X, y)
+        scores2 = np.abs(transformer2.estimator_.coef_)
+        candidate_indices2 = np.argsort(-scores2, kind="mergesort")
+        assert_allclose(
+            X[:, candidate_indices1[:n_features]], X[:, candidate_indices2[:n_features]]
+        )
+    assert_allclose(transformer1.estimator_.coef_, transformer2.estimator_.coef_)
+
+
+def test_max_features_tiebreak():
+    # Test if max_features can break tie among feature importance
+    X, y = datasets.make_classification(
+        n_samples=1000,
+        n_features=10,
+        n_informative=3,
+        n_redundant=0,
+        n_repeated=0,
+        shuffle=False,
+        random_state=0,
+    )
+    max_features = X.shape[1]
+
+    feature_importances = np.array([4, 4, 4, 4, 3, 3, 3, 2, 2, 1])
+    for n_features in range(1, max_features + 1):
+        transformer = SelectFromModel(
+            FixedImportanceEstimator(feature_importances),
+            max_features=n_features,
+            threshold=-np.inf,
+        )
+        X_new = transformer.fit_transform(X, y)
+        selected_feature_indices = np.where(transformer._get_support_mask())[0]
+        assert_array_equal(selected_feature_indices, np.arange(n_features))
+        assert X_new.shape[1] == n_features
+
+
+def test_threshold_and_max_features():
+    X, y = datasets.make_classification(
+        n_samples=1000,
+        n_features=10,
+        n_informative=3,
+        n_redundant=0,
+        n_repeated=0,
+        shuffle=False,
+        random_state=0,
+    )
+    est = RandomForestClassifier(n_estimators=50, random_state=0)
+
+    transformer1 = SelectFromModel(estimator=est, max_features=3, threshold=-np.inf)
+    X_new1 = transformer1.fit_transform(X, y)
+
+    transformer2 = SelectFromModel(estimator=est, threshold=0.04)
+    X_new2 = transformer2.fit_transform(X, y)
+
+    transformer3 = SelectFromModel(estimator=est, max_features=3, threshold=0.04)
+    X_new3 = transformer3.fit_transform(X, y)
+    assert X_new3.shape[1] == min(X_new1.shape[1], X_new2.shape[1])
+    selected_indices = transformer3.transform(np.arange(X.shape[1])[np.newaxis, :])
+    assert_allclose(X_new3, X[:, selected_indices[0]])
+
+
+@skip_if_32bit
+def test_feature_importances():
+    X, y = datasets.make_classification(
+        n_samples=1000,
+        n_features=10,
+        n_informative=3,
+        n_redundant=0,
+        n_repeated=0,
+        shuffle=False,
+        random_state=0,
+    )
+
+    est = RandomForestClassifier(n_estimators=50, random_state=0)
+    for threshold, func in zip(["mean", "median"], [np.mean, np.median]):
+        transformer = SelectFromModel(estimator=est, threshold=threshold)
+        transformer.fit(X, y)
+        assert hasattr(transformer.estimator_, "feature_importances_")
+
+        X_new = transformer.transform(X)
+        assert X_new.shape[1] < X.shape[1]
+        importances = transformer.estimator_.feature_importances_
+
+        feature_mask = np.abs(importances) > func(importances)
+        assert_array_almost_equal(X_new, X[:, feature_mask])
+
+
+def test_sample_weight():
+    # Ensure sample weights are passed to underlying estimator
+    X, y = datasets.make_classification(
+        n_samples=100,
+        n_features=10,
+        n_informative=3,
+        n_redundant=0,
+        n_repeated=0,
+        shuffle=False,
+        random_state=0,
+    )
+
+    # Check with sample weights
+    sample_weight = np.ones(y.shape)
+    sample_weight[y == 1] *= 100
+
+    est = LogisticRegression(random_state=0, fit_intercept=False)
+    transformer = SelectFromModel(estimator=est)
+    transformer.fit(X, y, sample_weight=None)
+    mask = transformer._get_support_mask()
+    transformer.fit(X, y, sample_weight=sample_weight)
+    weighted_mask = transformer._get_support_mask()
+    assert not np.all(weighted_mask == mask)
+    transformer.fit(X, y, sample_weight=3 * sample_weight)
+    reweighted_mask = transformer._get_support_mask()
+    assert np.all(weighted_mask == reweighted_mask)
+
+
+@pytest.mark.parametrize(
+    "estimator",
+    [
+        Lasso(alpha=0.1, random_state=42),
+        LassoCV(random_state=42),
+        ElasticNet(l1_ratio=1, random_state=42),
+        ElasticNetCV(l1_ratio=[1], random_state=42),
+    ],
+)
+def test_coef_default_threshold(estimator):
+    X, y = datasets.make_classification(
+        n_samples=100,
+        n_features=10,
+        n_informative=3,
+        n_redundant=0,
+        n_repeated=0,
+        shuffle=False,
+        random_state=0,
+    )
+
+    # For the Lasso and related models, the threshold defaults to 1e-5
+    transformer = SelectFromModel(estimator=estimator)
+    transformer.fit(X, y)
+    X_new = transformer.transform(X)
+    mask = np.abs(transformer.estimator_.coef_) > 1e-5
+    assert_array_almost_equal(X_new, X[:, mask])
+
+
+@skip_if_32bit
+def test_2d_coef():
+    X, y = datasets.make_classification(
+        n_samples=1000,
+        n_features=10,
+        n_informative=3,
+        n_redundant=0,
+        n_repeated=0,
+        shuffle=False,
+        random_state=0,
+        n_classes=4,
+    )
+
+    est = LogisticRegression()
+    for threshold, func in zip(["mean", "median"], [np.mean, np.median]):
+        for order in [1, 2, np.inf]:
+            # Fit SelectFromModel a multi-class problem
+            transformer = SelectFromModel(
+                estimator=LogisticRegression(), threshold=threshold, norm_order=order
+            )
+            transformer.fit(X, y)
+            assert hasattr(transformer.estimator_, "coef_")
+            X_new = transformer.transform(X)
+            assert X_new.shape[1] < X.shape[1]
+
+            # Manually check that the norm is correctly performed
+            est.fit(X, y)
+            importances = np.linalg.norm(est.coef_, axis=0, ord=order)
+            feature_mask = importances > func(importances)
+            assert_array_almost_equal(X_new, X[:, feature_mask])
+
+
+def test_partial_fit():
+    est = SGDClassifier(
+        random_state=0, shuffle=False, max_iter=5, tol=None, learning_rate="pa1"
+    )
+    transformer = SelectFromModel(estimator=est)
+    transformer.partial_fit(data, y, classes=np.unique(y))
+    old_model = transformer.estimator_
+    transformer.partial_fit(data, y, classes=np.unique(y))
+    new_model = transformer.estimator_
+    assert old_model is new_model
+
+    X_transform = transformer.transform(data)
+    transformer.fit(np.vstack((data, data)), np.concatenate((y, y)))
+    assert_array_almost_equal(X_transform, transformer.transform(data))
+
+    # check that if est doesn't have partial_fit, neither does SelectFromModel
+    transformer = SelectFromModel(estimator=RandomForestClassifier())
+    assert not hasattr(transformer, "partial_fit")
+
+
+def test_calling_fit_reinitializes():
+    est = LinearSVC(random_state=0)
+    transformer = SelectFromModel(estimator=est)
+    transformer.fit(data, y)
+    transformer.set_params(estimator__C=100)
+    transformer.fit(data, y)
+    assert transformer.estimator_.C == 100
+
+
+def test_prefit():
+    # Test all possible combinations of the prefit parameter.
+
+    # Passing a prefit parameter with the selected model
+    # and fitting a unfit model with prefit=False should give same results.
+    clf = SGDClassifier(alpha=0.1, max_iter=10, shuffle=True, random_state=0, tol=None)
+    model = SelectFromModel(clf)
+    model.fit(data, y)
+    X_transform = model.transform(data)
+    clf.fit(data, y)
+    model = SelectFromModel(clf, prefit=True)
+    assert_array_almost_equal(model.transform(data), X_transform)
+    model.fit(data, y)
+    assert model.estimator_ is not clf
+
+    # Check that the model is rewritten if prefit=False and a fitted model is
+    # passed
+    model = SelectFromModel(clf, prefit=False)
+    model.fit(data, y)
+    assert_array_almost_equal(model.transform(data), X_transform)
+
+    # Check that passing an unfitted estimator with `prefit=True` raises a
+    # `ValueError`
+    clf = SGDClassifier(alpha=0.1, max_iter=10, shuffle=True, random_state=0, tol=None)
+    model = SelectFromModel(clf, prefit=True)
+    err_msg = "When `prefit=True`, `estimator` is expected to be a fitted estimator."
+    with pytest.raises(NotFittedError, match=err_msg):
+        model.fit(data, y)
+    with pytest.raises(NotFittedError, match=err_msg):
+        model.partial_fit(data, y)
+    with pytest.raises(NotFittedError, match=err_msg):
+        model.transform(data)
+
+    # Check that the internal parameters of prefitted model are not changed
+    # when calling `fit` or `partial_fit` with `prefit=True`
+    clf = SGDClassifier(alpha=0.1, max_iter=10, shuffle=True, tol=None).fit(data, y)
+    model = SelectFromModel(clf, prefit=True)
+    model.fit(data, y)
+    assert_allclose(model.estimator_.coef_, clf.coef_)
+    model.partial_fit(data, y)
+    assert_allclose(model.estimator_.coef_, clf.coef_)
+
+
+def test_prefit_max_features():
+    """Check the interaction between `prefit` and `max_features`."""
+    # case 1: an error should be raised at `transform` if `fit` was not called to
+    # validate the attributes
+    estimator = RandomForestClassifier(n_estimators=5, random_state=0)
+    estimator.fit(data, y)
+    model = SelectFromModel(estimator, prefit=True, max_features=lambda X: X.shape[1])
+
+    err_msg = (
+        "When `prefit=True` and `max_features` is a callable, call `fit` "
+        "before calling `transform`."
+    )
+    with pytest.raises(NotFittedError, match=err_msg):
+        model.transform(data)
+
+    # case 2: `max_features` is not validated and different from an integer
+    # FIXME: we cannot validate the upper bound of the attribute at transform
+    # and we should force calling `fit` if we intend to force the attribute
+    # to have such an upper bound.
+    max_features = 2.5
+    model.set_params(max_features=max_features)
+    with pytest.raises(ValueError, match="`max_features` must be an integer"):
+        model.transform(data)
+
+
+def test_get_feature_names_out_elasticnetcv():
+    """Check if ElasticNetCV works with a list of floats.
+
+    Non-regression test for #30936."""
+    X, y = make_regression(n_features=5, n_informative=3, random_state=0)
+    estimator = ElasticNetCV(l1_ratio=[0.25, 0.5, 0.75], random_state=0)
+    selector = SelectFromModel(estimator=estimator)
+    selector.fit(X, y)
+
+    names_out = selector.get_feature_names_out()
+    mask = selector.get_support()
+    expected = np.array([f"x{i}" for i in range(X.shape[1])])[mask]
+    assert_array_equal(names_out, expected)
+
+
+def test_prefit_get_feature_names_out():
+    """Check the interaction between prefit and the feature names."""
+    clf = RandomForestClassifier(n_estimators=2, random_state=0)
+    clf.fit(data, y)
+    model = SelectFromModel(clf, prefit=True, max_features=1)
+
+    name = type(model).__name__
+    err_msg = (
+        f"This {name} instance is not fitted yet. Call 'fit' with "
+        "appropriate arguments before using this estimator."
+    )
+    with pytest.raises(NotFittedError, match=err_msg):
+        model.get_feature_names_out()
+
+    model.fit(data, y)
+    feature_names = model.get_feature_names_out()
+    assert feature_names == ["x3"]
+
+
+def test_threshold_string():
+    est = RandomForestClassifier(n_estimators=50, random_state=0)
+    model = SelectFromModel(est, threshold="0.5*mean")
+    model.fit(data, y)
+    X_transform = model.transform(data)
+
+    # Calculate the threshold from the estimator directly.
+    est.fit(data, y)
+    threshold = 0.5 * np.mean(est.feature_importances_)
+    mask = est.feature_importances_ > threshold
+    assert_array_almost_equal(X_transform, data[:, mask])
+
+
+def test_threshold_without_refitting():
+    # Test that the threshold can be set without refitting the model.
+    clf = SGDClassifier(alpha=0.1, max_iter=10, shuffle=True, random_state=0, tol=None)
+    model = SelectFromModel(clf, threshold="0.1 * mean")
+    model.fit(data, y)
+    X_transform = model.transform(data)
+
+    # Set a higher threshold to filter out more features.
+    model.threshold = "1.0 * mean"
+    assert X_transform.shape[1] > model.transform(data).shape[1]
+
+
+def test_fit_accepts_nan_inf():
+    # Test that fit doesn't check for np.inf and np.nan values.
+    clf = HistGradientBoostingClassifier(random_state=0)
+
+    model = SelectFromModel(estimator=clf)
+
+    nan_data = data.copy()
+    nan_data[0] = np.nan
+    nan_data[1] = np.inf
+
+    model.fit(data, y)
+
+
+def test_transform_accepts_nan_inf():
+    # Test that transform doesn't check for np.inf and np.nan values.
+    clf = NaNTagRandomForest(n_estimators=100, random_state=0)
+    nan_data = data.copy()
+
+    model = SelectFromModel(estimator=clf)
+    model.fit(nan_data, y)
+
+    nan_data[0] = np.nan
+    nan_data[1] = np.inf
+
+    model.transform(nan_data)
+
+
+def test_allow_nan_tag_comes_from_estimator():
+    allow_nan_est = NaNTag()
+    model = SelectFromModel(estimator=allow_nan_est)
+    assert model.__sklearn_tags__().input_tags.allow_nan is True
+
+    no_nan_est = NoNaNTag()
+    model = SelectFromModel(estimator=no_nan_est)
+    assert model.__sklearn_tags__().input_tags.allow_nan is False
+
+
+def _pca_importances(pca_estimator):
+    return np.abs(pca_estimator.explained_variance_)
+
+
+@pytest.mark.parametrize(
+    "estimator, importance_getter",
+    [
+        (
+            make_pipeline(PCA(random_state=0), LogisticRegression()),
+            "named_steps.logisticregression.coef_",
+        ),
+        (PCA(random_state=0), _pca_importances),
+    ],
+)
+def test_importance_getter(estimator, importance_getter):
+    selector = SelectFromModel(
+        estimator, threshold="mean", importance_getter=importance_getter
+    )
+    selector.fit(data, y)
+    assert selector.transform(data).shape[1] == 1
+
+
+@pytest.mark.parametrize("PLSEstimator", [CCA, PLSCanonical, PLSRegression])
+def test_select_from_model_pls(PLSEstimator):
+    """Check the behaviour of SelectFromModel with PLS estimators.
+
+    Non-regression test for:
+    https://github.com/scikit-learn/scikit-learn/issues/12410
+    """
+    X, y = make_friedman1(n_samples=50, n_features=10, random_state=0)
+    estimator = PLSEstimator(n_components=1)
+    model = make_pipeline(SelectFromModel(estimator), estimator).fit(X, y)
+    assert model.score(X, y) > 0.5
+
+
+def test_estimator_does_not_support_feature_names():
+    """SelectFromModel works with estimators that do not support feature_names_in_.
+
+    Non-regression test for #21949.
+    """
+    pytest.importorskip("pandas")
+    X, y = datasets.load_iris(as_frame=True, return_X_y=True)
+    all_feature_names = set(X.columns)
+
+    def importance_getter(estimator):
+        return np.arange(X.shape[1])
+
+    selector = SelectFromModel(
+        MinimalClassifier(), importance_getter=importance_getter
+    ).fit(X, y)
+
+    # selector learns the feature names itself
+    assert_array_equal(selector.feature_names_in_, X.columns)
+
+    feature_names_out = set(selector.get_feature_names_out())
+    assert feature_names_out < all_feature_names
+
+    with warnings.catch_warnings():
+        warnings.simplefilter("error", UserWarning)
+
+        selector.transform(X.iloc[1:3])
+
+
+@pytest.mark.parametrize("as_frame", [True, False])
+def test_partial_fit_validate_feature_names(as_frame):
+    """Test that partial_fit from SelectFromModel validates `feature_names_in_`."""
+    pytest.importorskip("pandas")
+    X, y = datasets.load_iris(as_frame=as_frame, return_X_y=True)
+
+    selector = SelectFromModel(estimator=SGDClassifier(), max_features=4).partial_fit(
+        X, y, classes=[0, 1, 2]
+    )
+    if as_frame:
+        assert_array_equal(selector.feature_names_in_, X.columns)
+    else:
+        assert not hasattr(selector, "feature_names_in_")
+
+
+def test_from_model_estimator_attribute_error():
+    """Check that we raise the proper AttributeError when the estimator
+    does not implement the `partial_fit` method, which is decorated with
+    `available_if`.
+
+    Non-regression test for:
+    https://github.com/scikit-learn/scikit-learn/issues/28108
+    """
+    # `LinearRegression` does not implement 'partial_fit' and should raise an
+    # AttributeError
+    from_model = SelectFromModel(estimator=LinearRegression())
+
+    outer_msg = "This 'SelectFromModel' has no attribute 'partial_fit'"
+    inner_msg = "'LinearRegression' object has no attribute 'partial_fit'"
+    with pytest.raises(AttributeError, match=outer_msg) as exec_info:
+        from_model.fit(data, y).partial_fit(data)
+    assert isinstance(exec_info.value.__cause__, AttributeError)
+    assert inner_msg in str(exec_info.value.__cause__)

linedance-app/venv/lib/python3.12/site-packages/sklearn/feature_selection/tests/test_mutual_info.py

@@ -0,0 +1,270 @@
+import numpy as np
+import pytest
+
+from sklearn.datasets import make_classification, make_regression
+from sklearn.feature_selection import mutual_info_classif, mutual_info_regression
+from sklearn.feature_selection._mutual_info import _compute_mi
+from sklearn.utils import check_random_state
+from sklearn.utils._testing import (
+    assert_allclose,
+    assert_array_equal,
+)
+from sklearn.utils.fixes import CSR_CONTAINERS
+
+
+def test_compute_mi_dd():
+    # In discrete case computations are straightforward and can be done
+    # by hand on given vectors.
+    x = np.array([0, 1, 1, 0, 0])
+    y = np.array([1, 0, 0, 0, 1])
+
+    H_x = H_y = -(3 / 5) * np.log(3 / 5) - (2 / 5) * np.log(2 / 5)
+    H_xy = -1 / 5 * np.log(1 / 5) - 2 / 5 * np.log(2 / 5) - 2 / 5 * np.log(2 / 5)
+    I_xy = H_x + H_y - H_xy
+
+    assert_allclose(_compute_mi(x, y, x_discrete=True, y_discrete=True), I_xy)
+
+
+def test_compute_mi_cc(global_dtype):
+    # For two continuous variables a good approach is to test on bivariate
+    # normal distribution, where mutual information is known.
+
+    # Mean of the distribution, irrelevant for mutual information.
+    mean = np.zeros(2)
+
+    # Setup covariance matrix with correlation coeff. equal 0.5.
+    sigma_1 = 1
+    sigma_2 = 10
+    corr = 0.5
+    cov = np.array(
+        [
+            [sigma_1**2, corr * sigma_1 * sigma_2],
+            [corr * sigma_1 * sigma_2, sigma_2**2],
+        ]
+    )
+
+    # True theoretical mutual information.
+    I_theory = np.log(sigma_1) + np.log(sigma_2) - 0.5 * np.log(np.linalg.det(cov))
+
+    rng = check_random_state(0)
+    Z = rng.multivariate_normal(mean, cov, size=1000).astype(global_dtype, copy=False)
+
+    x, y = Z[:, 0], Z[:, 1]
+
+    # Theory and computed values won't be very close
+    # We here check with a large relative tolerance
+    for n_neighbors in [3, 5, 7]:
+        I_computed = _compute_mi(
+            x, y, x_discrete=False, y_discrete=False, n_neighbors=n_neighbors
+        )
+        assert_allclose(I_computed, I_theory, rtol=1e-1)
+
+
+def test_compute_mi_cd(global_dtype):
+    # To test define a joint distribution as follows:
+    # p(x, y) = p(x) p(y | x)
+    # X ~ Bernoulli(p)
+    # (Y | x = 0) ~ Uniform(-1, 1)
+    # (Y | x = 1) ~ Uniform(0, 2)
+
+    # Use the following formula for mutual information:
+    # I(X; Y) = H(Y) - H(Y | X)
+    # Two entropies can be computed by hand:
+    # H(Y) = -(1-p)/2 * ln((1-p)/2) - p/2*log(p/2) - 1/2*log(1/2)
+    # H(Y | X) = ln(2)
+
+    # Now we need to implement sampling from out distribution, which is
+    # done easily using conditional distribution logic.
+
+    n_samples = 1000
+    rng = check_random_state(0)
+
+    for p in [0.3, 0.5, 0.7]:
+        x = rng.uniform(size=n_samples) > p
+
+        y = np.empty(n_samples, global_dtype)
+        mask = x == 0
+        y[mask] = rng.uniform(-1, 1, size=np.sum(mask))
+        y[~mask] = rng.uniform(0, 2, size=np.sum(~mask))
+
+        I_theory = -0.5 * (
+            (1 - p) * np.log(0.5 * (1 - p)) + p * np.log(0.5 * p) + np.log(0.5)
+        ) - np.log(2)
+
+        # Assert the same tolerance.
+        for n_neighbors in [3, 5, 7]:
+            I_computed = _compute_mi(
+                x, y, x_discrete=True, y_discrete=False, n_neighbors=n_neighbors
+            )
+            assert_allclose(I_computed, I_theory, rtol=1e-1)
+
+
+def test_compute_mi_cd_unique_label(global_dtype):
+    # Test that adding unique label doesn't change MI.
+    n_samples = 100
+    x = np.random.uniform(size=n_samples) > 0.5
+
+    y = np.empty(n_samples, global_dtype)
+    mask = x == 0
+    y[mask] = np.random.uniform(-1, 1, size=np.sum(mask))
+    y[~mask] = np.random.uniform(0, 2, size=np.sum(~mask))
+
+    mi_1 = _compute_mi(x, y, x_discrete=True, y_discrete=False)
+
+    x = np.hstack((x, 2))
+    y = np.hstack((y, 10))
+    mi_2 = _compute_mi(x, y, x_discrete=True, y_discrete=False)
+
+    assert_allclose(mi_1, mi_2)
+
+
+# We are going test that feature ordering by MI matches our expectations.
+def test_mutual_info_classif_discrete(global_dtype):
+    X = np.array(
+        [[0, 0, 0], [1, 1, 0], [2, 0, 1], [2, 0, 1], [2, 0, 1]], dtype=global_dtype
+    )
+    y = np.array([0, 1, 2, 2, 1])
+
+    # Here X[:, 0] is the most informative feature, and X[:, 1] is weakly
+    # informative.
+    mi = mutual_info_classif(X, y, discrete_features=True)
+    assert_array_equal(np.argsort(-mi), np.array([0, 2, 1]))
+
+
+def test_mutual_info_regression(global_dtype):
+    # We generate sample from multivariate normal distribution, using
+    # transformation from initially uncorrelated variables. The zero
+    # variables after transformation is selected as the target vector,
+    # it has the strongest correlation with the variable 2, and
+    # the weakest correlation with the variable 1.
+    T = np.array([[1, 0.5, 2, 1], [0, 1, 0.1, 0.0], [0, 0.1, 1, 0.1], [0, 0.1, 0.1, 1]])
+    cov = T.dot(T.T)
+    mean = np.zeros(4)
+
+    rng = check_random_state(0)
+    Z = rng.multivariate_normal(mean, cov, size=1000).astype(global_dtype, copy=False)
+    X = Z[:, 1:]
+    y = Z[:, 0]
+
+    mi = mutual_info_regression(X, y, random_state=0)
+    assert_array_equal(np.argsort(-mi), np.array([1, 2, 0]))
+    # XXX: should mutual_info_regression be fixed to avoid
+    # up-casting float32 inputs to float64?
+    assert mi.dtype == np.float64
+
+
+def test_mutual_info_classif_mixed(global_dtype):
+    # Here the target is discrete and there are two continuous and one
+    # discrete feature. The idea of this test is clear from the code.
+    rng = check_random_state(0)
+    X = rng.rand(1000, 3).astype(global_dtype, copy=False)
+    X[:, 1] += X[:, 0]
+    y = ((0.5 * X[:, 0] + X[:, 2]) > 0.5).astype(int)
+    X[:, 2] = X[:, 2] > 0.5
+
+    mi = mutual_info_classif(X, y, discrete_features=[2], n_neighbors=3, random_state=0)
+    assert_array_equal(np.argsort(-mi), [2, 0, 1])
+    for n_neighbors in [5, 7, 9]:
+        mi_nn = mutual_info_classif(
+            X, y, discrete_features=[2], n_neighbors=n_neighbors, random_state=0
+        )
+        # Check that the continuous values have a higher MI with greater
+        # n_neighbors
+        assert mi_nn[0] > mi[0]
+        assert mi_nn[1] > mi[1]
+        # The n_neighbors should not have any effect on the discrete value
+        # The MI should be the same
+        assert mi_nn[2] == mi[2]
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+def test_mutual_info_options(global_dtype, csr_container):
+    X = np.array(
+        [[0, 0, 0], [1, 1, 0], [2, 0, 1], [2, 0, 1], [2, 0, 1]], dtype=global_dtype
+    )
+    y = np.array([0, 1, 2, 2, 1], dtype=global_dtype)
+    X_csr = csr_container(X)
+
+    for mutual_info in (mutual_info_regression, mutual_info_classif):
+        with pytest.raises(ValueError):
+            mutual_info(X_csr, y, discrete_features=False)
+        with pytest.raises(ValueError):
+            mutual_info(X, y, discrete_features="manual")
+        with pytest.raises(ValueError):
+            mutual_info(X_csr, y, discrete_features=[True, False, True])
+        with pytest.raises(IndexError):
+            mutual_info(X, y, discrete_features=[True, False, True, False])
+        with pytest.raises(IndexError):
+            mutual_info(X, y, discrete_features=[1, 4])
+
+        mi_1 = mutual_info(X, y, discrete_features="auto", random_state=0)
+        mi_2 = mutual_info(X, y, discrete_features=False, random_state=0)
+        mi_3 = mutual_info(X_csr, y, discrete_features="auto", random_state=0)
+        mi_4 = mutual_info(X_csr, y, discrete_features=True, random_state=0)
+        mi_5 = mutual_info(X, y, discrete_features=[True, False, True], random_state=0)
+        mi_6 = mutual_info(X, y, discrete_features=[0, 2], random_state=0)
+
+        assert_allclose(mi_1, mi_2)
+        assert_allclose(mi_3, mi_4)
+        assert_allclose(mi_5, mi_6)
+
+        assert not np.allclose(mi_1, mi_3)
+
+
+@pytest.mark.parametrize("correlated", [True, False])
+def test_mutual_information_symmetry_classif_regression(correlated, global_random_seed):
+    """Check that `mutual_info_classif` and `mutual_info_regression` are
+    symmetric by switching the target `y` as `feature` in `X` and vice
+    versa.
+
+    Non-regression test for:
+    https://github.com/scikit-learn/scikit-learn/issues/23720
+    """
+    rng = np.random.RandomState(global_random_seed)
+    n = 100
+    d = rng.randint(10, size=n)
+
+    if correlated:
+        c = d.astype(np.float64)
+    else:
+        c = rng.normal(0, 1, size=n)
+
+    mi_classif = mutual_info_classif(
+        c[:, None], d, discrete_features=[False], random_state=global_random_seed
+    )
+
+    mi_regression = mutual_info_regression(
+        d[:, None], c, discrete_features=[True], random_state=global_random_seed
+    )
+
+    assert mi_classif == pytest.approx(mi_regression)
+
+
+def test_mutual_info_regression_X_int_dtype(global_random_seed):
+    """Check that results agree when X is integer dtype and float dtype.
+
+    Non-regression test for Issue #26696.
+    """
+    rng = np.random.RandomState(global_random_seed)
+    X = rng.randint(100, size=(100, 10))
+    X_float = X.astype(np.float64, copy=True)
+    y = rng.randint(100, size=100)
+
+    expected = mutual_info_regression(X_float, y, random_state=global_random_seed)
+    result = mutual_info_regression(X, y, random_state=global_random_seed)
+    assert_allclose(result, expected)
+
+
+@pytest.mark.parametrize(
+    "mutual_info_func, data_generator",
+    [
+        (mutual_info_regression, make_regression),
+        (mutual_info_classif, make_classification),
+    ],
+)
+def test_mutual_info_n_jobs(global_random_seed, mutual_info_func, data_generator):
+    """Check that results are consistent with different `n_jobs`."""
+    X, y = data_generator(random_state=global_random_seed)
+    single_job = mutual_info_func(X, y, random_state=global_random_seed, n_jobs=1)
+    multi_job = mutual_info_func(X, y, random_state=global_random_seed, n_jobs=2)
+    assert_allclose(single_job, multi_job)

linedance-app/venv/lib/python3.12/site-packages/sklearn/feature_selection/tests/test_rfe.py

@@ -0,0 +1,755 @@
+"""
+Testing Recursive feature elimination
+"""
+
+import re
+from operator import attrgetter
+
+import numpy as np
+import pytest
+from joblib import parallel_backend
+from numpy.testing import assert_allclose, assert_array_almost_equal, assert_array_equal
+
+from sklearn.base import BaseEstimator, ClassifierMixin, is_classifier
+from sklearn.compose import TransformedTargetRegressor
+from sklearn.cross_decomposition import CCA, PLSCanonical, PLSRegression
+from sklearn.datasets import load_iris, make_classification, make_friedman1
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.feature_selection import RFE, RFECV
+from sklearn.impute import SimpleImputer
+from sklearn.linear_model import LinearRegression, LogisticRegression
+from sklearn.metrics import get_scorer, make_scorer, zero_one_loss
+from sklearn.model_selection import GroupKFold, cross_val_score
+from sklearn.pipeline import make_pipeline
+from sklearn.preprocessing import StandardScaler
+from sklearn.svm import SVC, SVR, LinearSVR
+from sklearn.utils import check_random_state
+from sklearn.utils._testing import ignore_warnings
+from sklearn.utils.fixes import CSR_CONTAINERS
+
+
+class MockClassifier(ClassifierMixin, BaseEstimator):
+    """
+    Dummy classifier to test recursive feature elimination
+    """
+
+    def __init__(self, foo_param=0):
+        self.foo_param = foo_param
+
+    def fit(self, X, y):
+        assert len(X) == len(y)
+        self.coef_ = np.ones(X.shape[1], dtype=np.float64)
+        self.classes_ = sorted(set(y))
+        return self
+
+    def predict(self, T):
+        return np.ones(T.shape[0])
+
+    predict_proba = predict
+    decision_function = predict
+    transform = predict
+
+    def score(self, X=None, y=None):
+        return 0.0
+
+    def get_params(self, deep=True):
+        return {"foo_param": self.foo_param}
+
+    def set_params(self, **params):
+        return self
+
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.input_tags.allow_nan = True
+        return tags
+
+
+def test_rfe_features_importance():
+    generator = check_random_state(0)
+    iris = load_iris()
+    # Add some irrelevant features. Random seed is set to make sure that
+    # irrelevant features are always irrelevant.
+    X = np.c_[iris.data, generator.normal(size=(len(iris.data), 6))]
+    y = iris.target
+
+    clf = RandomForestClassifier(n_estimators=20, random_state=generator, max_depth=2)
+    rfe = RFE(estimator=clf, n_features_to_select=4, step=0.1)
+    rfe.fit(X, y)
+    assert len(rfe.ranking_) == X.shape[1]
+
+    clf_svc = SVC(kernel="linear")
+    rfe_svc = RFE(estimator=clf_svc, n_features_to_select=4, step=0.1)
+    rfe_svc.fit(X, y)
+
+    # Check if the supports are equal
+    assert_array_equal(rfe.get_support(), rfe_svc.get_support())
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+def test_rfe(csr_container):
+    generator = check_random_state(0)
+    iris = load_iris()
+    # Add some irrelevant features. Random seed is set to make sure that
+    # irrelevant features are always irrelevant.
+    X = np.c_[iris.data, generator.normal(size=(len(iris.data), 6))]
+    X_sparse = csr_container(X)
+    y = iris.target
+
+    # dense model
+    clf = SVC(kernel="linear")
+    rfe = RFE(estimator=clf, n_features_to_select=4, step=0.1)
+    rfe.fit(X, y)
+    X_r = rfe.transform(X)
+    clf.fit(X_r, y)
+    assert len(rfe.ranking_) == X.shape[1]
+
+    # sparse model
+    clf_sparse = SVC(kernel="linear")
+    rfe_sparse = RFE(estimator=clf_sparse, n_features_to_select=4, step=0.1)
+    rfe_sparse.fit(X_sparse, y)
+    X_r_sparse = rfe_sparse.transform(X_sparse)
+
+    assert X_r.shape == iris.data.shape
+    assert_array_almost_equal(X_r[:10], iris.data[:10])
+
+    assert_array_almost_equal(rfe.predict(X), clf.predict(iris.data))
+    assert rfe.score(X, y) == clf.score(iris.data, iris.target)
+    assert_array_almost_equal(X_r, X_r_sparse.toarray())
+
+
+def test_RFE_fit_score_params():
+    # Make sure RFE passes the metadata down to fit and score methods of the
+    # underlying estimator
+    class TestEstimator(BaseEstimator, ClassifierMixin):
+        def fit(self, X, y, prop=None):
+            if prop is None:
+                raise ValueError("fit: prop cannot be None")
+            self.svc_ = SVC(kernel="linear").fit(X, y)
+            self.coef_ = self.svc_.coef_
+            return self
+
+        def score(self, X, y, prop=None):
+            if prop is None:
+                raise ValueError("score: prop cannot be None")
+            return self.svc_.score(X, y)
+
+    X, y = load_iris(return_X_y=True)
+    with pytest.raises(ValueError, match="fit: prop cannot be None"):
+        RFE(estimator=TestEstimator()).fit(X, y)
+    with pytest.raises(ValueError, match="score: prop cannot be None"):
+        RFE(estimator=TestEstimator()).fit(X, y, prop="foo").score(X, y)
+
+    RFE(estimator=TestEstimator()).fit(X, y, prop="foo").score(X, y, prop="foo")
+
+
+def test_rfe_percent_n_features():
+    # test that the results are the same
+    generator = check_random_state(0)
+    iris = load_iris()
+    # Add some irrelevant features. Random seed is set to make sure that
+    # irrelevant features are always irrelevant.
+    X = np.c_[iris.data, generator.normal(size=(len(iris.data), 6))]
+    y = iris.target
+    # there are 10 features in the data. We select 40%.
+    clf = SVC(kernel="linear")
+    rfe_num = RFE(estimator=clf, n_features_to_select=4, step=0.1)
+    rfe_num.fit(X, y)
+
+    rfe_perc = RFE(estimator=clf, n_features_to_select=0.4, step=0.1)
+    rfe_perc.fit(X, y)
+
+    assert_array_equal(rfe_perc.ranking_, rfe_num.ranking_)
+    assert_array_equal(rfe_perc.support_, rfe_num.support_)
+
+
+def test_rfe_mockclassifier():
+    generator = check_random_state(0)
+    iris = load_iris()
+    # Add some irrelevant features. Random seed is set to make sure that
+    # irrelevant features are always irrelevant.
+    X = np.c_[iris.data, generator.normal(size=(len(iris.data), 6))]
+    y = iris.target
+
+    # dense model
+    clf = MockClassifier()
+    rfe = RFE(estimator=clf, n_features_to_select=4, step=0.1)
+    rfe.fit(X, y)
+    X_r = rfe.transform(X)
+    clf.fit(X_r, y)
+    assert len(rfe.ranking_) == X.shape[1]
+    assert X_r.shape == iris.data.shape
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+def test_rfecv(csr_container):
+    generator = check_random_state(0)
+    iris = load_iris()
+    # Add some irrelevant features. Random seed is set to make sure that
+    # irrelevant features are always irrelevant.
+    X = np.c_[iris.data, generator.normal(size=(len(iris.data), 6))]
+    y = list(iris.target)  # regression test: list should be supported
+
+    # Test using the score function
+    rfecv = RFECV(estimator=SVC(kernel="linear"), step=1)
+    rfecv.fit(X, y)
+    # non-regression test for missing worst feature:
+
+    for key in rfecv.cv_results_.keys():
+        assert len(rfecv.cv_results_[key]) == X.shape[1]
+
+    assert len(rfecv.ranking_) == X.shape[1]
+    X_r = rfecv.transform(X)
+
+    # All the noisy variable were filtered out
+    assert_array_equal(X_r, iris.data)
+
+    # same in sparse
+    rfecv_sparse = RFECV(estimator=SVC(kernel="linear"), step=1)
+    X_sparse = csr_container(X)
+    rfecv_sparse.fit(X_sparse, y)
+    X_r_sparse = rfecv_sparse.transform(X_sparse)
+    assert_array_equal(X_r_sparse.toarray(), iris.data)
+
+    # Test using a customized loss function
+    scoring = make_scorer(zero_one_loss, greater_is_better=False)
+    rfecv = RFECV(estimator=SVC(kernel="linear"), step=1, scoring=scoring)
+    ignore_warnings(rfecv.fit)(X, y)
+    X_r = rfecv.transform(X)
+    assert_array_equal(X_r, iris.data)
+
+    # Test using a scorer
+    scorer = get_scorer("accuracy")
+    rfecv = RFECV(estimator=SVC(kernel="linear"), step=1, scoring=scorer)
+    rfecv.fit(X, y)
+    X_r = rfecv.transform(X)
+    assert_array_equal(X_r, iris.data)
+
+    # Test fix on cv_results_
+    def test_scorer(estimator, X, y):
+        return 1.0
+
+    rfecv = RFECV(estimator=SVC(kernel="linear"), step=1, scoring=test_scorer)
+    rfecv.fit(X, y)
+
+    # In the event of cross validation score ties, the expected behavior of
+    # RFECV is to return the FEWEST features that maximize the CV score.
+    # Because test_scorer always returns 1.0 in this example, RFECV should
+    # reduce the dimensionality to a single feature (i.e. n_features_ = 1)
+    assert rfecv.n_features_ == 1
+
+    # Same as the first two tests, but with step=2
+    rfecv = RFECV(estimator=SVC(kernel="linear"), step=2)
+    rfecv.fit(X, y)
+
+    for key in rfecv.cv_results_.keys():
+        assert len(rfecv.cv_results_[key]) == 6
+
+    assert len(rfecv.ranking_) == X.shape[1]
+    X_r = rfecv.transform(X)
+    assert_array_equal(X_r, iris.data)
+
+    rfecv_sparse = RFECV(estimator=SVC(kernel="linear"), step=2)
+    X_sparse = csr_container(X)
+    rfecv_sparse.fit(X_sparse, y)
+    X_r_sparse = rfecv_sparse.transform(X_sparse)
+    assert_array_equal(X_r_sparse.toarray(), iris.data)
+
+    # Verifying that steps < 1 don't blow up.
+    rfecv_sparse = RFECV(estimator=SVC(kernel="linear"), step=0.2)
+    X_sparse = csr_container(X)
+    rfecv_sparse.fit(X_sparse, y)
+    X_r_sparse = rfecv_sparse.transform(X_sparse)
+    assert_array_equal(X_r_sparse.toarray(), iris.data)
+
+
+def test_rfecv_mockclassifier():
+    generator = check_random_state(0)
+    iris = load_iris()
+    X = np.c_[iris.data, generator.normal(size=(len(iris.data), 6))]
+    y = list(iris.target)  # regression test: list should be supported
+
+    # Test using the score function
+    rfecv = RFECV(estimator=MockClassifier(), step=1)
+    rfecv.fit(X, y)
+    # non-regression test for missing worst feature:
+
+    for key in rfecv.cv_results_.keys():
+        assert len(rfecv.cv_results_[key]) == X.shape[1]
+
+    assert len(rfecv.ranking_) == X.shape[1]
+
+
+def test_rfecv_verbose_output():
+    # Check verbose=1 is producing an output.
+    import sys
+    from io import StringIO
+
+    sys.stdout = StringIO()
+
+    generator = check_random_state(0)
+    iris = load_iris()
+    X = np.c_[iris.data, generator.normal(size=(len(iris.data), 6))]
+    y = list(iris.target)
+
+    rfecv = RFECV(estimator=SVC(kernel="linear"), step=1, verbose=1)
+    rfecv.fit(X, y)
+
+    verbose_output = sys.stdout
+    verbose_output.seek(0)
+    assert len(verbose_output.readline()) > 0
+
+
+def test_rfecv_cv_results_size(global_random_seed):
+    generator = check_random_state(global_random_seed)
+    iris = load_iris()
+    X = np.c_[iris.data, generator.normal(size=(len(iris.data), 6))]
+    y = list(iris.target)  # regression test: list should be supported
+
+    # Non-regression test for varying combinations of step and
+    # min_features_to_select.
+    for step, min_features_to_select in [[2, 1], [2, 2], [3, 3]]:
+        rfecv = RFECV(
+            estimator=MockClassifier(),
+            step=step,
+            min_features_to_select=min_features_to_select,
+        )
+        rfecv.fit(X, y)
+
+        score_len = np.ceil((X.shape[1] - min_features_to_select) / step) + 1
+
+        for key in rfecv.cv_results_.keys():
+            assert len(rfecv.cv_results_[key]) == score_len
+
+        assert len(rfecv.ranking_) == X.shape[1]
+        assert rfecv.n_features_ >= min_features_to_select
+
+
+def test_rfe_estimator_tags():
+    rfe = RFE(SVC(kernel="linear"))
+    assert is_classifier(rfe)
+    # make sure that cross-validation is stratified
+    iris = load_iris()
+    score = cross_val_score(rfe, iris.data, iris.target)
+    assert score.min() > 0.7
+
+
+def test_rfe_min_step(global_random_seed):
+    n_features = 10
+    X, y = make_friedman1(
+        n_samples=50, n_features=n_features, random_state=global_random_seed
+    )
+    n_samples, n_features = X.shape
+    estimator = SVR(kernel="linear")
+
+    # Test when floor(step * n_features) <= 0
+    selector = RFE(estimator, step=0.01)
+    sel = selector.fit(X, y)
+    assert sel.support_.sum() == n_features // 2
+
+    # Test when step is between (0,1) and floor(step * n_features) > 0
+    selector = RFE(estimator, step=0.20)
+    sel = selector.fit(X, y)
+    assert sel.support_.sum() == n_features // 2
+
+    # Test when step is an integer
+    selector = RFE(estimator, step=5)
+    sel = selector.fit(X, y)
+    assert sel.support_.sum() == n_features // 2
+
+
+def test_number_of_subsets_of_features(global_random_seed):
+    # In RFE, 'number_of_subsets_of_features'
+    # = the number of iterations in '_fit'
+    # = max(ranking_)
+    # = 1 + (n_features + step - n_features_to_select - 1) // step
+    # After optimization #4534, this number
+    # = 1 + np.ceil((n_features - n_features_to_select) / float(step))
+    # This test case is to test their equivalence, refer to #4534 and #3824
+
+    def formula1(n_features, n_features_to_select, step):
+        return 1 + ((n_features + step - n_features_to_select - 1) // step)
+
+    def formula2(n_features, n_features_to_select, step):
+        return 1 + np.ceil((n_features - n_features_to_select) / float(step))
+
+    # RFE
+    # Case 1, n_features - n_features_to_select is divisible by step
+    # Case 2, n_features - n_features_to_select is not divisible by step
+    n_features_list = [11, 11]
+    n_features_to_select_list = [3, 3]
+    step_list = [2, 3]
+    for n_features, n_features_to_select, step in zip(
+        n_features_list, n_features_to_select_list, step_list
+    ):
+        generator = check_random_state(global_random_seed)
+        X = generator.normal(size=(100, n_features))
+        y = generator.rand(100).round()
+        rfe = RFE(
+            estimator=SVC(kernel="linear"),
+            n_features_to_select=n_features_to_select,
+            step=step,
+        )
+        rfe.fit(X, y)
+        # this number also equals to the maximum of ranking_
+        assert np.max(rfe.ranking_) == formula1(n_features, n_features_to_select, step)
+        assert np.max(rfe.ranking_) == formula2(n_features, n_features_to_select, step)
+
+    # In RFECV, 'fit' calls 'RFE._fit'
+    # 'number_of_subsets_of_features' of RFE
+    # = the size of each score in 'cv_results_' of RFECV
+    # = the number of iterations of the for loop before optimization #4534
+
+    # RFECV, n_features_to_select = 1
+    # Case 1, n_features - 1 is divisible by step
+    # Case 2, n_features - 1 is not divisible by step
+
+    n_features_to_select = 1
+    n_features_list = [11, 10]
+    step_list = [2, 2]
+    for n_features, step in zip(n_features_list, step_list):
+        generator = check_random_state(global_random_seed)
+        X = generator.normal(size=(100, n_features))
+        y = generator.rand(100).round()
+        rfecv = RFECV(estimator=SVC(kernel="linear"), step=step)
+        rfecv.fit(X, y)
+
+        for key in rfecv.cv_results_.keys():
+            assert len(rfecv.cv_results_[key]) == formula1(
+                n_features, n_features_to_select, step
+            )
+            assert len(rfecv.cv_results_[key]) == formula2(
+                n_features, n_features_to_select, step
+            )
+
+
+def test_rfe_cv_n_jobs(global_random_seed):
+    generator = check_random_state(global_random_seed)
+    iris = load_iris()
+    X = np.c_[iris.data, generator.normal(size=(len(iris.data), 6))]
+    y = iris.target
+
+    rfecv = RFECV(estimator=SVC(kernel="linear"))
+    rfecv.fit(X, y)
+    rfecv_ranking = rfecv.ranking_
+
+    rfecv_cv_results_ = rfecv.cv_results_
+
+    rfecv.set_params(n_jobs=2)
+    rfecv.fit(X, y)
+    assert_array_almost_equal(rfecv.ranking_, rfecv_ranking)
+
+    assert rfecv_cv_results_.keys() == rfecv.cv_results_.keys()
+    for key in rfecv_cv_results_.keys():
+        assert rfecv_cv_results_[key] == pytest.approx(rfecv.cv_results_[key])
+
+
+def test_rfe_cv_groups():
+    generator = check_random_state(0)
+    iris = load_iris()
+    number_groups = 4
+    groups = np.floor(np.linspace(0, number_groups, len(iris.target)))
+    X = iris.data
+    y = (iris.target > 0).astype(int)
+
+    est_groups = RFECV(
+        estimator=RandomForestClassifier(random_state=generator),
+        step=1,
+        scoring="accuracy",
+        cv=GroupKFold(n_splits=2),
+    )
+    est_groups.fit(X, y, groups=groups)
+    assert est_groups.n_features_ > 0
+
+
+@pytest.mark.parametrize(
+    "importance_getter", [attrgetter("regressor_.coef_"), "regressor_.coef_"]
+)
+@pytest.mark.parametrize("selector, expected_n_features", [(RFE, 5), (RFECV, 4)])
+def test_rfe_wrapped_estimator(importance_getter, selector, expected_n_features):
+    # Non-regression test for
+    # https://github.com/scikit-learn/scikit-learn/issues/15312
+    X, y = make_friedman1(n_samples=50, n_features=10, random_state=0)
+    estimator = LinearSVR(random_state=0)
+
+    log_estimator = TransformedTargetRegressor(
+        regressor=estimator, func=np.log, inverse_func=np.exp
+    )
+
+    selector = selector(log_estimator, importance_getter=importance_getter)
+    sel = selector.fit(X, y)
+    assert sel.support_.sum() == expected_n_features
+
+
+@pytest.mark.parametrize(
+    "importance_getter, err_type",
+    [
+        ("auto", ValueError),
+        ("random", AttributeError),
+        (lambda x: x.importance, AttributeError),
+    ],
+)
+@pytest.mark.parametrize("Selector", [RFE, RFECV])
+def test_rfe_importance_getter_validation(importance_getter, err_type, Selector):
+    X, y = make_friedman1(n_samples=50, n_features=10, random_state=42)
+    estimator = LinearSVR()
+    log_estimator = TransformedTargetRegressor(
+        regressor=estimator, func=np.log, inverse_func=np.exp
+    )
+
+    with pytest.raises(err_type):
+        model = Selector(log_estimator, importance_getter=importance_getter)
+        model.fit(X, y)
+
+
+@pytest.mark.parametrize("cv", [None, 5])
+def test_rfe_allow_nan_inf_in_x(cv):
+    iris = load_iris()
+    X = iris.data
+    y = iris.target
+
+    # add nan and inf value to X
+    X[0][0] = np.nan
+    X[0][1] = np.inf
+
+    clf = MockClassifier()
+    if cv is not None:
+        rfe = RFECV(estimator=clf, cv=cv)
+    else:
+        rfe = RFE(estimator=clf)
+    rfe.fit(X, y)
+    rfe.transform(X)
+
+
+def test_w_pipeline_2d_coef_():
+    pipeline = make_pipeline(StandardScaler(), LogisticRegression())
+
+    data, y = load_iris(return_X_y=True)
+    sfm = RFE(
+        pipeline,
+        n_features_to_select=2,
+        importance_getter="named_steps.logisticregression.coef_",
+    )
+
+    sfm.fit(data, y)
+    assert sfm.transform(data).shape[1] == 2
+
+
+def test_rfecv_std_and_mean(global_random_seed):
+    generator = check_random_state(global_random_seed)
+    iris = load_iris()
+    X = np.c_[iris.data, generator.normal(size=(len(iris.data), 6))]
+    y = iris.target
+
+    rfecv = RFECV(estimator=SVC(kernel="linear"))
+    rfecv.fit(X, y)
+    split_keys = [
+        key
+        for key in rfecv.cv_results_.keys()
+        if re.search(r"split\d+_test_score", key)
+    ]
+    cv_scores = np.asarray([rfecv.cv_results_[key] for key in split_keys])
+    expected_mean = np.mean(cv_scores, axis=0)
+    expected_std = np.std(cv_scores, axis=0)
+
+    assert_allclose(rfecv.cv_results_["mean_test_score"], expected_mean)
+    assert_allclose(rfecv.cv_results_["std_test_score"], expected_std)
+
+
+@pytest.mark.parametrize(
+    ["min_features_to_select", "n_features", "step", "cv_results_n_features"],
+    [
+        [1, 4, 1, np.array([1, 2, 3, 4])],
+        [1, 5, 1, np.array([1, 2, 3, 4, 5])],
+        [1, 4, 2, np.array([1, 2, 4])],
+        [1, 5, 2, np.array([1, 3, 5])],
+        [1, 4, 3, np.array([1, 4])],
+        [1, 5, 3, np.array([1, 2, 5])],
+        [1, 4, 4, np.array([1, 4])],
+        [1, 5, 4, np.array([1, 5])],
+        [4, 4, 2, np.array([4])],
+        [4, 5, 1, np.array([4, 5])],
+        [4, 5, 2, np.array([4, 5])],
+    ],
+)
+def test_rfecv_cv_results_n_features(
+    min_features_to_select,
+    n_features,
+    step,
+    cv_results_n_features,
+):
+    X, y = make_classification(
+        n_samples=20, n_features=n_features, n_informative=n_features, n_redundant=0
+    )
+    rfecv = RFECV(
+        estimator=SVC(kernel="linear"),
+        step=step,
+        min_features_to_select=min_features_to_select,
+    )
+    rfecv.fit(X, y)
+    assert_array_equal(rfecv.cv_results_["n_features"], cv_results_n_features)
+    assert all(
+        len(value) == len(rfecv.cv_results_["n_features"])
+        for value in rfecv.cv_results_.values()
+    )
+
+
+@pytest.mark.parametrize("ClsRFE", [RFE, RFECV])
+def test_multioutput(ClsRFE):
+    X = np.random.normal(size=(10, 3))
+    y = np.random.randint(2, size=(10, 2))
+    clf = RandomForestClassifier(n_estimators=5)
+    rfe_test = ClsRFE(clf)
+    rfe_test.fit(X, y)
+
+
+@pytest.mark.parametrize("ClsRFE", [RFE, RFECV])
+def test_pipeline_with_nans(ClsRFE):
+    """Check that RFE works with pipeline that accept nans.
+
+    Non-regression test for gh-21743.
+    """
+    X, y = load_iris(return_X_y=True)
+    X[0, 0] = np.nan
+
+    pipe = make_pipeline(
+        SimpleImputer(),
+        StandardScaler(),
+        LogisticRegression(),
+    )
+
+    fs = ClsRFE(
+        estimator=pipe,
+        importance_getter="named_steps.logisticregression.coef_",
+    )
+    fs.fit(X, y)
+
+
+@pytest.mark.parametrize("ClsRFE", [RFE, RFECV])
+@pytest.mark.parametrize("PLSEstimator", [CCA, PLSCanonical, PLSRegression])
+def test_rfe_pls(ClsRFE, PLSEstimator):
+    """Check the behaviour of RFE with PLS estimators.
+
+    Non-regression test for:
+    https://github.com/scikit-learn/scikit-learn/issues/12410
+    """
+    X, y = make_friedman1(n_samples=50, n_features=10, random_state=0)
+    estimator = PLSEstimator(n_components=1)
+    selector = ClsRFE(estimator, step=1).fit(X, y)
+    assert selector.score(X, y) > 0.5
+
+
+def test_rfe_estimator_attribute_error():
+    """Check that we raise the proper AttributeError when the estimator
+    does not implement the `decision_function` method, which is decorated with
+    `available_if`.
+
+    Non-regression test for:
+    https://github.com/scikit-learn/scikit-learn/issues/28108
+    """
+    iris = load_iris()
+
+    # `LinearRegression` does not implement 'decision_function' and should raise an
+    # AttributeError
+    rfe = RFE(estimator=LinearRegression())
+
+    outer_msg = "This 'RFE' has no attribute 'decision_function'"
+    inner_msg = "'LinearRegression' object has no attribute 'decision_function'"
+    with pytest.raises(AttributeError, match=outer_msg) as exec_info:
+        rfe.fit(iris.data, iris.target).decision_function(iris.data)
+    assert isinstance(exec_info.value.__cause__, AttributeError)
+    assert inner_msg in str(exec_info.value.__cause__)
+
+
+@pytest.mark.parametrize(
+    "ClsRFE, param", [(RFE, "n_features_to_select"), (RFECV, "min_features_to_select")]
+)
+def test_rfe_n_features_to_select_warning(ClsRFE, param):
+    """Check if the correct warning is raised when trying to initialize a RFE
+    object with a n_features_to_select attribute larger than the number of
+    features present in the X variable that is passed to the fit method
+    """
+    X, y = make_classification(n_features=20, random_state=0)
+
+    with pytest.warns(UserWarning, match=f"{param}=21 > n_features=20"):
+        # Create RFE/RFECV with n_features_to_select/min_features_to_select
+        # larger than the number of features present in the X variable
+        clsrfe = ClsRFE(estimator=LogisticRegression(), **{param: 21})
+        clsrfe.fit(X, y)
+
+
+def test_rfe_with_sample_weight():
+    """Test that `RFE` works correctly with sample weights."""
+    X, y = make_classification(random_state=0)
+    n_samples = X.shape[0]
+
+    # Assign the first half of the samples with twice the weight
+    sample_weight = np.ones_like(y)
+    sample_weight[: n_samples // 2] = 2
+
+    # Duplicate the first half of the data samples to replicate the effect
+    # of sample weights for comparison
+    X2 = np.concatenate([X, X[: n_samples // 2]], axis=0)
+    y2 = np.concatenate([y, y[: n_samples // 2]])
+
+    estimator = SVC(kernel="linear")
+
+    rfe_sw = RFE(estimator=estimator, step=0.1)
+    rfe_sw.fit(X, y, sample_weight=sample_weight)
+
+    rfe = RFE(estimator=estimator, step=0.1)
+    rfe.fit(X2, y2)
+
+    assert_array_equal(rfe_sw.ranking_, rfe.ranking_)
+
+    # Also verify that when sample weights are not doubled the results
+    # are different from the duplicated data
+    rfe_sw_2 = RFE(estimator=estimator, step=0.1)
+    sample_weight_2 = np.ones_like(y)
+    rfe_sw_2.fit(X, y, sample_weight=sample_weight_2)
+
+    assert not np.array_equal(rfe_sw_2.ranking_, rfe.ranking_)
+
+
+def test_rfe_with_joblib_threading_backend(global_random_seed):
+    X, y = make_classification(random_state=global_random_seed)
+
+    clf = LogisticRegression()
+    rfe = RFECV(
+        estimator=clf,
+        n_jobs=2,
+    )
+
+    rfe.fit(X, y)
+    ranking_ref = rfe.ranking_
+
+    with parallel_backend("threading"):
+        rfe.fit(X, y)
+
+    assert_array_equal(ranking_ref, rfe.ranking_)
+
+
+def test_results_per_cv_in_rfecv(global_random_seed):
+    """
+    Test that the results of RFECV are consistent across the different folds
+    in terms of length of the arrays.
+    """
+    X, y = make_classification(random_state=global_random_seed)
+
+    clf = LogisticRegression()
+    rfecv = RFECV(
+        estimator=clf,
+        n_jobs=2,
+        cv=5,
+    )
+
+    rfecv.fit(X, y)
+
+    assert len(rfecv.cv_results_["split1_test_score"]) == len(
+        rfecv.cv_results_["split2_test_score"]
+    )
+    assert len(rfecv.cv_results_["split1_support"]) == len(
+        rfecv.cv_results_["split2_support"]
+    )
+    assert len(rfecv.cv_results_["split1_ranking"]) == len(
+        rfecv.cv_results_["split2_ranking"]
+    )

linedance-app/venv/lib/python3.12/site-packages/sklearn/feature_selection/tests/test_sequential.py

@@ -0,0 +1,332 @@
+import numpy as np
+import pytest
+from numpy.testing import assert_array_equal
+
+from sklearn.cluster import KMeans
+from sklearn.datasets import make_blobs, make_classification, make_regression
+from sklearn.ensemble import HistGradientBoostingRegressor
+from sklearn.feature_selection import SequentialFeatureSelector
+from sklearn.linear_model import LinearRegression
+from sklearn.model_selection import LeaveOneGroupOut, cross_val_score
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.pipeline import make_pipeline
+from sklearn.preprocessing import StandardScaler
+from sklearn.utils.fixes import CSR_CONTAINERS
+
+
+def test_bad_n_features_to_select():
+    n_features = 5
+    X, y = make_regression(n_features=n_features)
+    sfs = SequentialFeatureSelector(LinearRegression(), n_features_to_select=n_features)
+    with pytest.raises(ValueError, match="n_features_to_select must be < n_features"):
+        sfs.fit(X, y)
+
+
+@pytest.mark.parametrize("direction", ("forward", "backward"))
+@pytest.mark.parametrize("n_features_to_select", (1, 5, 9, "auto"))
+def test_n_features_to_select(direction, n_features_to_select):
+    # Make sure n_features_to_select is respected
+
+    n_features = 10
+    X, y = make_regression(n_features=n_features, random_state=0)
+    sfs = SequentialFeatureSelector(
+        LinearRegression(),
+        n_features_to_select=n_features_to_select,
+        direction=direction,
+        cv=2,
+    )
+    sfs.fit(X, y)
+
+    if n_features_to_select == "auto":
+        n_features_to_select = n_features // 2
+
+    assert sfs.get_support(indices=True).shape[0] == n_features_to_select
+    assert sfs.n_features_to_select_ == n_features_to_select
+    assert sfs.transform(X).shape[1] == n_features_to_select
+
+
+@pytest.mark.parametrize("direction", ("forward", "backward"))
+def test_n_features_to_select_auto(direction):
+    """Check the behaviour of `n_features_to_select="auto"` with different
+    values for the parameter `tol`.
+    """
+
+    n_features = 10
+    tol = 1e-3
+    X, y = make_regression(n_features=n_features, random_state=0)
+    sfs = SequentialFeatureSelector(
+        LinearRegression(),
+        n_features_to_select="auto",
+        tol=tol,
+        direction=direction,
+        cv=2,
+    )
+    sfs.fit(X, y)
+
+    max_features_to_select = n_features - 1
+
+    assert sfs.get_support(indices=True).shape[0] <= max_features_to_select
+    assert sfs.n_features_to_select_ <= max_features_to_select
+    assert sfs.transform(X).shape[1] <= max_features_to_select
+    assert sfs.get_support(indices=True).shape[0] == sfs.n_features_to_select_
+
+
+@pytest.mark.parametrize("direction", ("forward", "backward"))
+def test_n_features_to_select_stopping_criterion(direction):
+    """Check the behaviour stopping criterion for feature selection
+    depending on the values of `n_features_to_select` and `tol`.
+
+    When `direction` is `'forward'`, select a new features at random
+    among those not currently selected in selector.support_,
+    build a new version of the data that includes all the features
+    in selector.support_ + this newly selected feature.
+    And check that the cross-validation score of the model trained on
+    this new dataset variant is lower than the model with
+    the selected forward selected features or at least does not improve
+    by more than the tol margin.
+
+    When `direction` is `'backward'`, instead of adding a new feature
+    to selector.support_, try to remove one of those selected features at random
+    And check that the cross-validation score is either decreasing or
+    not improving by more than the tol margin.
+    """
+
+    X, y = make_regression(n_features=50, n_informative=10, random_state=0)
+
+    tol = 1e-3
+
+    sfs = SequentialFeatureSelector(
+        LinearRegression(),
+        n_features_to_select="auto",
+        tol=tol,
+        direction=direction,
+        cv=2,
+    )
+    sfs.fit(X, y)
+    selected_X = sfs.transform(X)
+
+    rng = np.random.RandomState(0)
+
+    added_candidates = list(set(range(X.shape[1])) - set(sfs.get_support(indices=True)))
+    added_X = np.hstack(
+        [
+            selected_X,
+            (X[:, rng.choice(added_candidates)])[:, np.newaxis],
+        ]
+    )
+
+    removed_candidate = rng.choice(list(range(sfs.n_features_to_select_)))
+    removed_X = np.delete(selected_X, removed_candidate, axis=1)
+
+    plain_cv_score = cross_val_score(LinearRegression(), X, y, cv=2).mean()
+    sfs_cv_score = cross_val_score(LinearRegression(), selected_X, y, cv=2).mean()
+    added_cv_score = cross_val_score(LinearRegression(), added_X, y, cv=2).mean()
+    removed_cv_score = cross_val_score(LinearRegression(), removed_X, y, cv=2).mean()
+
+    assert sfs_cv_score >= plain_cv_score
+
+    if direction == "forward":
+        assert (sfs_cv_score - added_cv_score) <= tol
+        assert (sfs_cv_score - removed_cv_score) >= tol
+    else:
+        assert (added_cv_score - sfs_cv_score) <= tol
+        assert (removed_cv_score - sfs_cv_score) <= tol
+
+
+@pytest.mark.parametrize("direction", ("forward", "backward"))
+@pytest.mark.parametrize(
+    "n_features_to_select, expected",
+    (
+        (0.1, 1),
+        (1.0, 10),
+        (0.5, 5),
+    ),
+)
+def test_n_features_to_select_float(direction, n_features_to_select, expected):
+    # Test passing a float as n_features_to_select
+    X, y = make_regression(n_features=10)
+    sfs = SequentialFeatureSelector(
+        LinearRegression(),
+        n_features_to_select=n_features_to_select,
+        direction=direction,
+        cv=2,
+    )
+    sfs.fit(X, y)
+    assert sfs.n_features_to_select_ == expected
+
+
+@pytest.mark.parametrize("seed", range(10))
+@pytest.mark.parametrize("direction", ("forward", "backward"))
+@pytest.mark.parametrize(
+    "n_features_to_select, expected_selected_features",
+    [
+        (2, [0, 2]),  # f1 is dropped since it has no predictive power
+        (1, [2]),  # f2 is more predictive than f0 so it's kept
+    ],
+)
+def test_sanity(seed, direction, n_features_to_select, expected_selected_features):
+    # Basic sanity check: 3 features, only f0 and f2 are correlated with the
+    # target, f2 having a stronger correlation than f0. We expect f1 to be
+    # dropped, and f2 to always be selected.
+
+    rng = np.random.RandomState(seed)
+    n_samples = 100
+    X = rng.randn(n_samples, 3)
+    y = 3 * X[:, 0] - 10 * X[:, 2]
+
+    sfs = SequentialFeatureSelector(
+        LinearRegression(),
+        n_features_to_select=n_features_to_select,
+        direction=direction,
+        cv=2,
+    )
+    sfs.fit(X, y)
+    assert_array_equal(sfs.get_support(indices=True), expected_selected_features)
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+def test_sparse_support(csr_container):
+    # Make sure sparse data is supported
+
+    X, y = make_regression(n_features=10)
+    X = csr_container(X)
+    sfs = SequentialFeatureSelector(
+        LinearRegression(), n_features_to_select="auto", cv=2
+    )
+    sfs.fit(X, y)
+    sfs.transform(X)
+
+
+def test_nan_support():
+    # Make sure nans are OK if the underlying estimator supports nans
+
+    rng = np.random.RandomState(0)
+    n_samples, n_features = 40, 4
+    X, y = make_regression(n_samples, n_features, random_state=0)
+    nan_mask = rng.randint(0, 2, size=(n_samples, n_features), dtype=bool)
+    X[nan_mask] = np.nan
+    sfs = SequentialFeatureSelector(
+        HistGradientBoostingRegressor(), n_features_to_select="auto", cv=2
+    )
+    sfs.fit(X, y)
+    sfs.transform(X)
+
+    with pytest.raises(ValueError, match="Input X contains NaN"):
+        # LinearRegression does not support nans
+        SequentialFeatureSelector(
+            LinearRegression(), n_features_to_select="auto", cv=2
+        ).fit(X, y)
+
+
+def test_pipeline_support():
+    # Make sure that pipelines can be passed into SFS and that SFS can be
+    # passed into a pipeline
+
+    n_samples, n_features = 50, 3
+    X, y = make_regression(n_samples, n_features, random_state=0)
+
+    # pipeline in SFS
+    pipe = make_pipeline(StandardScaler(), LinearRegression())
+    sfs = SequentialFeatureSelector(pipe, n_features_to_select="auto", cv=2)
+    sfs.fit(X, y)
+    sfs.transform(X)
+
+    # SFS in pipeline
+    sfs = SequentialFeatureSelector(
+        LinearRegression(), n_features_to_select="auto", cv=2
+    )
+    pipe = make_pipeline(StandardScaler(), sfs)
+    pipe.fit(X, y)
+    pipe.transform(X)
+
+
+@pytest.mark.parametrize("n_features_to_select", (2, 3))
+def test_unsupervised_model_fit(n_features_to_select):
+    # Make sure that models without classification labels are not being
+    # validated
+
+    X, y = make_blobs(n_features=4)
+    sfs = SequentialFeatureSelector(
+        KMeans(n_init=1),
+        n_features_to_select=n_features_to_select,
+    )
+    sfs.fit(X)
+    assert sfs.transform(X).shape[1] == n_features_to_select
+
+
+@pytest.mark.parametrize("y", ("no_validation", 1j, 99.9, np.nan, 3))
+def test_no_y_validation_model_fit(y):
+    # Make sure that other non-conventional y labels are not accepted
+
+    X, clusters = make_blobs(n_features=6)
+    sfs = SequentialFeatureSelector(
+        KMeans(),
+        n_features_to_select=3,
+    )
+
+    with pytest.raises((TypeError, ValueError)):
+        sfs.fit(X, y)
+
+
+def test_forward_neg_tol_error():
+    """Check that we raise an error when tol<0 and direction='forward'"""
+    X, y = make_regression(n_features=10, random_state=0)
+    sfs = SequentialFeatureSelector(
+        LinearRegression(),
+        n_features_to_select="auto",
+        direction="forward",
+        tol=-1e-3,
+    )
+
+    with pytest.raises(ValueError, match="tol must be strictly positive"):
+        sfs.fit(X, y)
+
+
+def test_backward_neg_tol():
+    """Check that SequentialFeatureSelector works negative tol
+
+    non-regression test for #25525
+    """
+    X, y = make_regression(n_features=10, random_state=0)
+    lr = LinearRegression()
+    initial_score = lr.fit(X, y).score(X, y)
+
+    sfs = SequentialFeatureSelector(
+        lr,
+        n_features_to_select="auto",
+        direction="backward",
+        tol=-1e-3,
+    )
+    Xr = sfs.fit_transform(X, y)
+    new_score = lr.fit(Xr, y).score(Xr, y)
+
+    assert 0 < sfs.get_support().sum() < X.shape[1]
+    assert new_score < initial_score
+
+
+def test_cv_generator_support():
+    """Check that no exception raised when cv is generator
+
+    non-regression test for #25957
+    """
+    X, y = make_classification(random_state=0)
+
+    groups = np.zeros_like(y, dtype=int)
+    groups[y.size // 2 :] = 1
+
+    cv = LeaveOneGroupOut()
+    splits = cv.split(X, y, groups=groups)
+
+    knc = KNeighborsClassifier(n_neighbors=5)
+
+    sfs = SequentialFeatureSelector(knc, n_features_to_select=5, cv=splits)
+    sfs.fit(X, y)
+
+
+def test_fit_rejects_params_with_no_routing_enabled():
+    X, y = make_classification(random_state=42)
+    est = LinearRegression()
+    sfs = SequentialFeatureSelector(estimator=est)
+
+    with pytest.raises(ValueError, match="is only supported if"):
+        sfs.fit(X, y, sample_weight=np.ones_like(y))

linedance-app/venv/lib/python3.12/site-packages/sklearn/feature_selection/tests/test_variance_threshold.py

@@ -0,0 +1,72 @@
+import numpy as np
+import pytest
+
+from sklearn.feature_selection import VarianceThreshold
+from sklearn.utils._testing import assert_array_equal
+from sklearn.utils.fixes import BSR_CONTAINERS, CSC_CONTAINERS, CSR_CONTAINERS
+
+data = [[0, 1, 2, 3, 4], [0, 2, 2, 3, 5], [1, 1, 2, 4, 0]]
+
+data2 = [[-0.13725701]] * 10
+
+
+@pytest.mark.parametrize(
+    "sparse_container", [None] + BSR_CONTAINERS + CSC_CONTAINERS + CSR_CONTAINERS
+)
+def test_zero_variance(sparse_container):
+    # Test VarianceThreshold with default setting, zero variance.
+    X = data if sparse_container is None else sparse_container(data)
+    sel = VarianceThreshold().fit(X)
+    assert_array_equal([0, 1, 3, 4], sel.get_support(indices=True))
+
+
+def test_zero_variance_value_error():
+    # Test VarianceThreshold with default setting, zero variance, error cases.
+    with pytest.raises(ValueError):
+        VarianceThreshold().fit([[0, 1, 2, 3]])
+    with pytest.raises(ValueError):
+        VarianceThreshold().fit([[0, 1], [0, 1]])
+
+
+@pytest.mark.parametrize("sparse_container", [None] + CSR_CONTAINERS)
+def test_variance_threshold(sparse_container):
+    # Test VarianceThreshold with custom variance.
+    X = data if sparse_container is None else sparse_container(data)
+    X = VarianceThreshold(threshold=0.4).fit_transform(X)
+    assert (len(data), 1) == X.shape
+
+
+@pytest.mark.skipif(
+    np.var(data2) == 0,
+    reason=(
+        "This test is not valid for this platform, "
+        "as it relies on numerical instabilities."
+    ),
+)
+@pytest.mark.parametrize(
+    "sparse_container", [None] + BSR_CONTAINERS + CSC_CONTAINERS + CSR_CONTAINERS
+)
+def test_zero_variance_floating_point_error(sparse_container):
+    # Test that VarianceThreshold(0.0).fit eliminates features that have
+    # the same value in every sample, even when floating point errors
+    # cause np.var not to be 0 for the feature.
+    # See #13691
+    X = data2 if sparse_container is None else sparse_container(data2)
+    msg = "No feature in X meets the variance threshold 0.00000"
+    with pytest.raises(ValueError, match=msg):
+        VarianceThreshold().fit(X)
+
+
+@pytest.mark.parametrize(
+    "sparse_container", [None] + BSR_CONTAINERS + CSC_CONTAINERS + CSR_CONTAINERS
+)
+def test_variance_nan(sparse_container):
+    arr = np.array(data, dtype=np.float64)
+    # add single NaN and feature should still be included
+    arr[0, 0] = np.nan
+    # make all values in feature NaN and feature should be rejected
+    arr[:, 1] = np.nan
+
+    X = arr if sparse_container is None else sparse_container(arr)
+    sel = VarianceThreshold().fit(X)
+    assert_array_equal([0, 3, 4], sel.get_support(indices=True))