Videre

linedance-app/venv/lib/python3.12/site-packages/sklearn/cluster/tests/common.py

@@ -0,0 +1,37 @@
+"""
+Common utilities for testing clustering.
+
+"""
+
+import numpy as np
+
+###############################################################################
+# Generate sample data
+
+
+def generate_clustered_data(
+    seed=0, n_clusters=3, n_features=2, n_samples_per_cluster=20, std=0.4
+):
+    prng = np.random.RandomState(seed)
+
+    # the data is voluntary shifted away from zero to check clustering
+    # algorithm robustness with regards to non centered data
+    means = (
+        np.array(
+            [
+                [1, 1, 1, 0],
+                [-1, -1, 0, 1],
+                [1, -1, 1, 1],
+                [-1, 1, 1, 0],
+            ]
+        )
+        + 10
+    )
+
+    X = np.empty((0, n_features))
+    for i in range(n_clusters):
+        X = np.r_[
+            X,
+            means[i][:n_features] + std * prng.randn(n_samples_per_cluster, n_features),
+        ]
+    return X

linedance-app/venv/lib/python3.12/site-packages/sklearn/cluster/tests/test_affinity_propagation.py

@@ -0,0 +1,321 @@
+"""
+Testing for Clustering methods
+
+"""
+
+import warnings
+
+import numpy as np
+import pytest
+
+from sklearn.cluster import AffinityPropagation, affinity_propagation
+from sklearn.cluster._affinity_propagation import _equal_similarities_and_preferences
+from sklearn.datasets import make_blobs
+from sklearn.exceptions import ConvergenceWarning, NotFittedError
+from sklearn.metrics import euclidean_distances
+from sklearn.utils._testing import assert_allclose, assert_array_equal
+from sklearn.utils.fixes import CSR_CONTAINERS
+
+n_clusters = 3
+centers = np.array([[1, 1], [-1, -1], [1, -1]]) + 10
+X, _ = make_blobs(
+    n_samples=60,
+    n_features=2,
+    centers=centers,
+    cluster_std=0.4,
+    shuffle=True,
+    random_state=0,
+)
+
+# TODO: AffinityPropagation must preserve dtype for its fitted attributes
+# and test must be created accordingly to this new behavior.
+# For more details, see: https://github.com/scikit-learn/scikit-learn/issues/11000
+
+
+def test_affinity_propagation(global_random_seed, global_dtype):
+    """Test consistency of the affinity propagations."""
+    S = -euclidean_distances(X.astype(global_dtype, copy=False), squared=True)
+    preference = np.median(S) * 10
+    cluster_centers_indices, labels = affinity_propagation(
+        S, preference=preference, random_state=global_random_seed
+    )
+
+    n_clusters_ = len(cluster_centers_indices)
+
+    assert n_clusters == n_clusters_
+
+
+def test_affinity_propagation_precomputed():
+    """Check equality of precomputed affinity matrix to internally computed affinity
+    matrix.
+    """
+    S = -euclidean_distances(X, squared=True)
+    preference = np.median(S) * 10
+    af = AffinityPropagation(
+        preference=preference, affinity="precomputed", random_state=28
+    )
+    labels_precomputed = af.fit(S).labels_
+
+    af = AffinityPropagation(preference=preference, verbose=True, random_state=37)
+    labels = af.fit(X).labels_
+
+    assert_array_equal(labels, labels_precomputed)
+
+    cluster_centers_indices = af.cluster_centers_indices_
+
+    n_clusters_ = len(cluster_centers_indices)
+    assert np.unique(labels).size == n_clusters_
+    assert n_clusters == n_clusters_
+
+
+def test_affinity_propagation_no_copy():
+    """Check behaviour of not copying the input data."""
+    S = -euclidean_distances(X, squared=True)
+    S_original = S.copy()
+    preference = np.median(S) * 10
+    assert not np.allclose(S.diagonal(), preference)
+
+    # with copy=True S should not be modified
+    affinity_propagation(S, preference=preference, copy=True, random_state=0)
+    assert_allclose(S, S_original)
+    assert not np.allclose(S.diagonal(), preference)
+    assert_allclose(S.diagonal(), np.zeros(S.shape[0]))
+
+    # with copy=False S will be modified inplace
+    affinity_propagation(S, preference=preference, copy=False, random_state=0)
+    assert_allclose(S.diagonal(), preference)
+
+    # test that copy=True and copy=False lead to the same result
+    S = S_original.copy()
+    af = AffinityPropagation(preference=preference, verbose=True, random_state=0)
+
+    labels = af.fit(X).labels_
+    _, labels_no_copy = affinity_propagation(
+        S, preference=preference, copy=False, random_state=74
+    )
+    assert_array_equal(labels, labels_no_copy)
+
+
+def test_affinity_propagation_affinity_shape():
+    """Check the shape of the affinity matrix when using `affinity_propagation."""
+    S = -euclidean_distances(X, squared=True)
+    err_msg = "The matrix of similarities must be a square array"
+    with pytest.raises(ValueError, match=err_msg):
+        affinity_propagation(S[:, :-1])
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+def test_affinity_propagation_precomputed_with_sparse_input(csr_container):
+    err_msg = "Sparse data was passed for X, but dense data is required"
+    with pytest.raises(TypeError, match=err_msg):
+        AffinityPropagation(affinity="precomputed").fit(csr_container((3, 3)))
+
+
+def test_affinity_propagation_predict(global_random_seed, global_dtype):
+    # Test AffinityPropagation.predict
+    af = AffinityPropagation(affinity="euclidean", random_state=global_random_seed)
+    X_ = X.astype(global_dtype, copy=False)
+    labels = af.fit_predict(X_)
+    labels2 = af.predict(X_)
+    assert_array_equal(labels, labels2)
+
+
+def test_affinity_propagation_predict_error():
+    # Test exception in AffinityPropagation.predict
+    # Not fitted.
+    af = AffinityPropagation(affinity="euclidean")
+    with pytest.raises(NotFittedError):
+        af.predict(X)
+
+    # Predict not supported when affinity="precomputed".
+    S = np.dot(X, X.T)
+    af = AffinityPropagation(affinity="precomputed", random_state=57)
+    af.fit(S)
+    with pytest.raises(ValueError, match="expecting 60 features as input"):
+        af.predict(X)
+
+
+def test_affinity_propagation_fit_non_convergence(global_dtype):
+    # In case of non-convergence of affinity_propagation(), the cluster
+    # centers should be an empty array and training samples should be labelled
+    # as noise (-1)
+    X = np.array([[0, 0], [1, 1], [-2, -2]], dtype=global_dtype)
+
+    # Force non-convergence by allowing only a single iteration
+    af = AffinityPropagation(preference=-10, max_iter=1, random_state=82)
+
+    with pytest.warns(ConvergenceWarning):
+        af.fit(X)
+    assert_allclose(np.empty((0, 2)), af.cluster_centers_)
+    assert_array_equal(np.array([-1, -1, -1]), af.labels_)
+
+
+def test_affinity_propagation_equal_mutual_similarities(global_dtype):
+    X = np.array([[-1, 1], [1, -1]], dtype=global_dtype)
+    S = -euclidean_distances(X, squared=True)
+
+    # setting preference > similarity
+    with pytest.warns(UserWarning, match="mutually equal"):
+        cluster_center_indices, labels = affinity_propagation(S, preference=0)
+
+    # expect every sample to become an exemplar
+    assert_array_equal([0, 1], cluster_center_indices)
+    assert_array_equal([0, 1], labels)
+
+    # setting preference < similarity
+    with pytest.warns(UserWarning, match="mutually equal"):
+        cluster_center_indices, labels = affinity_propagation(S, preference=-10)
+
+    # expect one cluster, with arbitrary (first) sample as exemplar
+    assert_array_equal([0], cluster_center_indices)
+    assert_array_equal([0, 0], labels)
+
+    # setting different preferences
+    with warnings.catch_warnings():
+        warnings.simplefilter("error", UserWarning)
+        cluster_center_indices, labels = affinity_propagation(
+            S, preference=[-20, -10], random_state=37
+        )
+
+    # expect one cluster, with highest-preference sample as exemplar
+    assert_array_equal([1], cluster_center_indices)
+    assert_array_equal([0, 0], labels)
+
+
+def test_affinity_propagation_predict_non_convergence(global_dtype):
+    # In case of non-convergence of affinity_propagation(), the cluster
+    # centers should be an empty array
+    X = np.array([[0, 0], [1, 1], [-2, -2]], dtype=global_dtype)
+
+    # Force non-convergence by allowing only a single iteration
+    with pytest.warns(ConvergenceWarning):
+        af = AffinityPropagation(preference=-10, max_iter=1, random_state=75).fit(X)
+
+    # At prediction time, consider new samples as noise since there are no
+    # clusters
+    to_predict = np.array([[2, 2], [3, 3], [4, 4]])
+    with pytest.warns(ConvergenceWarning):
+        y = af.predict(to_predict)
+    assert_array_equal(np.array([-1, -1, -1]), y)
+
+
+def test_affinity_propagation_non_convergence_regressiontest(global_dtype):
+    X = np.array(
+        [[1, 0, 0, 0, 0, 0], [0, 1, 1, 1, 0, 0], [0, 0, 1, 0, 0, 1]], dtype=global_dtype
+    )
+    af = AffinityPropagation(affinity="euclidean", max_iter=2, random_state=34)
+    msg = (
+        "Affinity propagation did not converge, this model may return degenerate"
+        " cluster centers and labels."
+    )
+    with pytest.warns(ConvergenceWarning, match=msg):
+        af.fit(X)
+
+    assert_array_equal(np.array([0, 0, 0]), af.labels_)
+
+
+def test_equal_similarities_and_preferences(global_dtype):
+    # Unequal distances
+    X = np.array([[0, 0], [1, 1], [-2, -2]], dtype=global_dtype)
+    S = -euclidean_distances(X, squared=True)
+
+    assert not _equal_similarities_and_preferences(S, np.array(0))
+    assert not _equal_similarities_and_preferences(S, np.array([0, 0]))
+    assert not _equal_similarities_and_preferences(S, np.array([0, 1]))
+
+    # Equal distances
+    X = np.array([[0, 0], [1, 1]], dtype=global_dtype)
+    S = -euclidean_distances(X, squared=True)
+
+    # Different preferences
+    assert not _equal_similarities_and_preferences(S, np.array([0, 1]))
+
+    # Same preferences
+    assert _equal_similarities_and_preferences(S, np.array([0, 0]))
+    assert _equal_similarities_and_preferences(S, np.array(0))
+
+
+def test_affinity_propagation_random_state():
+    """Check that different random states lead to different initialisations
+    by looking at the center locations after two iterations.
+    """
+    centers = [[1, 1], [-1, -1], [1, -1]]
+    X, labels_true = make_blobs(
+        n_samples=300, centers=centers, cluster_std=0.5, random_state=0
+    )
+    # random_state = 0
+    ap = AffinityPropagation(convergence_iter=1, max_iter=2, random_state=0)
+    ap.fit(X)
+    centers0 = ap.cluster_centers_
+
+    # random_state = 76
+    ap = AffinityPropagation(convergence_iter=1, max_iter=2, random_state=76)
+    ap.fit(X)
+    centers76 = ap.cluster_centers_
+    # check that the centers have not yet converged to the same solution
+    assert np.mean((centers0 - centers76) ** 2) > 1
+
+
+@pytest.mark.parametrize("container", CSR_CONTAINERS + [np.array])
+def test_affinity_propagation_convergence_warning_dense_sparse(container, global_dtype):
+    """
+    Check that having sparse or dense `centers` format should not
+    influence the convergence.
+    Non-regression test for gh-13334.
+    """
+    centers = container(np.zeros((1, 10)))
+    rng = np.random.RandomState(42)
+    X = rng.rand(40, 10).astype(global_dtype, copy=False)
+    y = (4 * rng.rand(40)).astype(int)
+    ap = AffinityPropagation(random_state=46)
+    ap.fit(X, y)
+    ap.cluster_centers_ = centers
+    with warnings.catch_warnings():
+        warnings.simplefilter("error", ConvergenceWarning)
+        assert_array_equal(ap.predict(X), np.zeros(X.shape[0], dtype=int))
+
+
+# FIXME; this test is broken with different random states, needs to be revisited
+def test_correct_clusters(global_dtype):
+    # Test to fix incorrect clusters due to dtype change
+    # (non-regression test for issue #10832)
+    X = np.array(
+        [[1, 0, 0, 0], [0, 1, 1, 0], [0, 1, 1, 0], [0, 0, 0, 1]], dtype=global_dtype
+    )
+    afp = AffinityPropagation(preference=1, affinity="precomputed", random_state=0).fit(
+        X
+    )
+    expected = np.array([0, 1, 1, 2])
+    assert_array_equal(afp.labels_, expected)
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+def test_sparse_input_for_predict(csr_container):
+    # Test to make sure sparse inputs are accepted for predict
+    # (non-regression test for issue #20049)
+    af = AffinityPropagation(affinity="euclidean", random_state=42)
+    af.fit(X)
+    labels = af.predict(csr_container((2, 2)))
+    assert_array_equal(labels, (2, 2))
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+def test_sparse_input_for_fit_predict(csr_container):
+    # Test to make sure sparse inputs are accepted for fit_predict
+    # (non-regression test for issue #20049)
+    af = AffinityPropagation(affinity="euclidean", random_state=42)
+    rng = np.random.RandomState(42)
+    X = csr_container(rng.randint(0, 2, size=(5, 5)))
+    labels = af.fit_predict(X)
+    assert_array_equal(labels, (0, 1, 1, 2, 3))
+
+
+def test_affinity_propagation_equal_points():
+    """Make sure we do not assign multiple clusters to equal points.
+
+    Non-regression test for:
+    https://github.com/scikit-learn/scikit-learn/pull/20043
+    """
+    X = np.zeros((8, 1))
+    af = AffinityPropagation(affinity="euclidean", damping=0.5, random_state=42).fit(X)
+    assert np.all(af.labels_ == 0)

linedance-app/venv/lib/python3.12/site-packages/sklearn/cluster/tests/test_bicluster.py

@@ -0,0 +1,265 @@
+"""Testing for Spectral Biclustering methods"""
+
+import numpy as np
+import pytest
+from scipy.sparse import issparse
+
+from sklearn.base import BaseEstimator, BiclusterMixin, clone
+from sklearn.cluster import SpectralBiclustering, SpectralCoclustering
+from sklearn.cluster._bicluster import (
+    _bistochastic_normalize,
+    _log_normalize,
+    _scale_normalize,
+)
+from sklearn.datasets import make_biclusters, make_checkerboard
+from sklearn.metrics import consensus_score, v_measure_score
+from sklearn.model_selection import ParameterGrid
+from sklearn.utils._testing import (
+    assert_almost_equal,
+    assert_array_almost_equal,
+    assert_array_equal,
+)
+from sklearn.utils.fixes import CSR_CONTAINERS
+
+
+class MockBiclustering(BiclusterMixin, BaseEstimator):
+    # Mock object for testing get_submatrix.
+    def __init__(self):
+        pass
+
+    def get_indices(self, i):
+        # Overridden to reproduce old get_submatrix test.
+        return (
+            np.where([True, True, False, False, True])[0],
+            np.where([False, False, True, True])[0],
+        )
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+def test_get_submatrix(csr_container):
+    data = np.arange(20).reshape(5, 4)
+    model = MockBiclustering()
+
+    for X in (data, csr_container(data), data.tolist()):
+        submatrix = model.get_submatrix(0, X)
+        if issparse(submatrix):
+            submatrix = submatrix.toarray()
+        assert_array_equal(submatrix, [[2, 3], [6, 7], [18, 19]])
+        submatrix[:] = -1
+        if issparse(X):
+            X = X.toarray()
+        assert np.all(X != -1)
+
+
+def _test_shape_indices(model):
+    # Test get_shape and get_indices on fitted model.
+    for i in range(model.n_clusters):
+        m, n = model.get_shape(i)
+        i_ind, j_ind = model.get_indices(i)
+        assert len(i_ind) == m
+        assert len(j_ind) == n
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+def test_spectral_coclustering(global_random_seed, csr_container):
+    # Test Dhillon's Spectral CoClustering on a simple problem.
+    param_grid = {
+        "svd_method": ["randomized", "arpack"],
+        "n_svd_vecs": [None, 20],
+        "mini_batch": [False, True],
+        "init": ["k-means++"],
+        "n_init": [10],
+    }
+    S, rows, cols = make_biclusters(
+        (30, 30), 3, noise=0.1, random_state=global_random_seed
+    )
+    S -= S.min()  # needs to be nonnegative before making it sparse
+    S = np.where(S < 1, 0, S)  # threshold some values
+    for mat in (S, csr_container(S)):
+        for kwargs in ParameterGrid(param_grid):
+            model = SpectralCoclustering(
+                n_clusters=3, random_state=global_random_seed, **kwargs
+            )
+            model.fit(mat)
+
+            assert model.rows_.shape == (3, 30)
+            assert_array_equal(model.rows_.sum(axis=0), np.ones(30))
+            assert_array_equal(model.columns_.sum(axis=0), np.ones(30))
+            assert consensus_score(model.biclusters_, (rows, cols)) == 1
+
+            _test_shape_indices(model)
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+def test_spectral_biclustering(global_random_seed, csr_container):
+    # Test Kluger methods on a checkerboard dataset.
+    S, rows, cols = make_checkerboard(
+        (30, 30), 3, noise=0.5, random_state=global_random_seed
+    )
+
+    non_default_params = {
+        "method": ["scale", "log"],
+        "svd_method": ["arpack"],
+        "n_svd_vecs": [20],
+        "mini_batch": [True],
+    }
+
+    for mat in (S, csr_container(S)):
+        for param_name, param_values in non_default_params.items():
+            for param_value in param_values:
+                model = SpectralBiclustering(
+                    n_clusters=3,
+                    n_init=3,
+                    init="k-means++",
+                    random_state=global_random_seed,
+                )
+                model.set_params(**dict([(param_name, param_value)]))
+
+                if issparse(mat) and model.get_params().get("method") == "log":
+                    # cannot take log of sparse matrix
+                    with pytest.raises(ValueError):
+                        model.fit(mat)
+                    continue
+                else:
+                    model.fit(mat)
+
+                assert model.rows_.shape == (9, 30)
+                assert model.columns_.shape == (9, 30)
+                assert_array_equal(model.rows_.sum(axis=0), np.repeat(3, 30))
+                assert_array_equal(model.columns_.sum(axis=0), np.repeat(3, 30))
+                assert consensus_score(model.biclusters_, (rows, cols)) == 1
+
+                _test_shape_indices(model)
+
+
+def _do_scale_test(scaled):
+    """Check that rows sum to one constant, and columns to another."""
+    row_sum = scaled.sum(axis=1)
+    col_sum = scaled.sum(axis=0)
+    if issparse(scaled):
+        row_sum = np.asarray(row_sum).squeeze()
+        col_sum = np.asarray(col_sum).squeeze()
+    assert_array_almost_equal(row_sum, np.tile(row_sum.mean(), 100), decimal=1)
+    assert_array_almost_equal(col_sum, np.tile(col_sum.mean(), 100), decimal=1)
+
+
+def _do_bistochastic_test(scaled):
+    """Check that rows and columns sum to the same constant."""
+    _do_scale_test(scaled)
+    assert_almost_equal(scaled.sum(axis=0).mean(), scaled.sum(axis=1).mean(), decimal=1)
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+def test_scale_normalize(global_random_seed, csr_container):
+    generator = np.random.RandomState(global_random_seed)
+    X = generator.rand(100, 100)
+    for mat in (X, csr_container(X)):
+        scaled, _, _ = _scale_normalize(mat)
+        _do_scale_test(scaled)
+        if issparse(mat):
+            assert issparse(scaled)
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+def test_bistochastic_normalize(global_random_seed, csr_container):
+    generator = np.random.RandomState(global_random_seed)
+    X = generator.rand(100, 100)
+    for mat in (X, csr_container(X)):
+        scaled = _bistochastic_normalize(mat)
+        _do_bistochastic_test(scaled)
+        if issparse(mat):
+            assert issparse(scaled)
+
+
+def test_log_normalize(global_random_seed):
+    # adding any constant to a log-scaled matrix should make it
+    # bistochastic
+    generator = np.random.RandomState(global_random_seed)
+    mat = generator.rand(100, 100)
+    scaled = _log_normalize(mat) + 1
+    _do_bistochastic_test(scaled)
+
+
+def test_fit_best_piecewise(global_random_seed):
+    model = SpectralBiclustering(random_state=global_random_seed)
+    vectors = np.array([[0, 0, 0, 1, 1, 1], [2, 2, 2, 3, 3, 3], [0, 1, 2, 3, 4, 5]])
+    best = model._fit_best_piecewise(vectors, n_best=2, n_clusters=2)
+    assert_array_equal(best, vectors[:2])
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+def test_project_and_cluster(global_random_seed, csr_container):
+    model = SpectralBiclustering(random_state=global_random_seed)
+    data = np.array([[1, 1, 1], [1, 1, 1], [3, 6, 3], [3, 6, 3]])
+    vectors = np.array([[1, 0], [0, 1], [0, 0]])
+    for mat in (data, csr_container(data)):
+        labels = model._project_and_cluster(mat, vectors, n_clusters=2)
+        assert_almost_equal(v_measure_score(labels, [0, 0, 1, 1]), 1.0)
+
+
+def test_perfect_checkerboard(global_random_seed):
+    # XXX Previously failed on build bot (not reproducible)
+    model = SpectralBiclustering(
+        3, svd_method="arpack", random_state=global_random_seed
+    )
+
+    S, rows, cols = make_checkerboard(
+        (30, 30), 3, noise=0, random_state=global_random_seed
+    )
+    model.fit(S)
+    assert consensus_score(model.biclusters_, (rows, cols)) == 1
+
+    S, rows, cols = make_checkerboard(
+        (40, 30), 3, noise=0, random_state=global_random_seed
+    )
+    model.fit(S)
+    assert consensus_score(model.biclusters_, (rows, cols)) == 1
+
+    S, rows, cols = make_checkerboard(
+        (30, 40), 3, noise=0, random_state=global_random_seed
+    )
+    model.fit(S)
+    assert consensus_score(model.biclusters_, (rows, cols)) == 1
+
+
+@pytest.mark.parametrize(
+    "params, type_err, err_msg",
+    [
+        (
+            {"n_clusters": 6},
+            ValueError,
+            "n_clusters should be <= n_samples=5",
+        ),
+        (
+            {"n_clusters": (3, 3, 3)},
+            ValueError,
+            "Incorrect parameter n_clusters",
+        ),
+        (
+            {"n_clusters": (3, 6)},
+            ValueError,
+            "Incorrect parameter n_clusters",
+        ),
+        (
+            {"n_components": 3, "n_best": 4},
+            ValueError,
+            "n_best=4 must be <= n_components=3",
+        ),
+    ],
+)
+def test_spectralbiclustering_parameter_validation(params, type_err, err_msg):
+    """Check parameters validation in `SpectralBiClustering`"""
+    data = np.arange(25).reshape((5, 5))
+    model = SpectralBiclustering(**params)
+    with pytest.raises(type_err, match=err_msg):
+        model.fit(data)
+
+
+@pytest.mark.parametrize("est", (SpectralBiclustering(), SpectralCoclustering()))
+def test_n_features_in_(est):
+    X, _, _ = make_biclusters((3, 3), 3, random_state=0)
+
+    est = clone(est)
+    assert not hasattr(est, "n_features_in_")
+    est.fit(X)
+    assert est.n_features_in_ == 3

linedance-app/venv/lib/python3.12/site-packages/sklearn/cluster/tests/test_birch.py

@@ -0,0 +1,242 @@
+"""
+Tests for the birch clustering algorithm.
+"""
+
+import numpy as np
+import pytest
+
+from sklearn.cluster import AgglomerativeClustering, Birch
+from sklearn.cluster.tests.common import generate_clustered_data
+from sklearn.datasets import make_blobs
+from sklearn.exceptions import ConvergenceWarning
+from sklearn.metrics import pairwise_distances_argmin, v_measure_score
+from sklearn.utils._testing import assert_allclose, assert_array_equal
+from sklearn.utils.fixes import CSR_CONTAINERS
+
+
+def test_n_samples_leaves_roots(global_random_seed, global_dtype):
+    # Sanity check for the number of samples in leaves and roots
+    X, y = make_blobs(n_samples=10, random_state=global_random_seed)
+    X = X.astype(global_dtype, copy=False)
+    brc = Birch()
+    brc.fit(X)
+    n_samples_root = sum([sc.n_samples_ for sc in brc.root_.subclusters_])
+    n_samples_leaves = sum(
+        [sc.n_samples_ for leaf in brc._get_leaves() for sc in leaf.subclusters_]
+    )
+    assert n_samples_leaves == X.shape[0]
+    assert n_samples_root == X.shape[0]
+
+
+def test_partial_fit(global_random_seed, global_dtype):
+    # Test that fit is equivalent to calling partial_fit multiple times
+    X, y = make_blobs(n_samples=100, random_state=global_random_seed)
+    X = X.astype(global_dtype, copy=False)
+    brc = Birch(n_clusters=3)
+    brc.fit(X)
+    brc_partial = Birch(n_clusters=None)
+    brc_partial.partial_fit(X[:50])
+    brc_partial.partial_fit(X[50:])
+    assert_allclose(brc_partial.subcluster_centers_, brc.subcluster_centers_)
+
+    # Test that same global labels are obtained after calling partial_fit
+    # with None
+    brc_partial.set_params(n_clusters=3)
+    brc_partial.partial_fit(None)
+    assert_array_equal(brc_partial.subcluster_labels_, brc.subcluster_labels_)
+
+
+def test_birch_predict(global_random_seed, global_dtype):
+    # Test the predict method predicts the nearest centroid.
+    rng = np.random.RandomState(global_random_seed)
+    X = generate_clustered_data(n_clusters=3, n_features=3, n_samples_per_cluster=10)
+    X = X.astype(global_dtype, copy=False)
+
+    # n_samples * n_samples_per_cluster
+    shuffle_indices = np.arange(30)
+    rng.shuffle(shuffle_indices)
+    X_shuffle = X[shuffle_indices, :]
+    brc = Birch(n_clusters=4, threshold=1.0)
+    brc.fit(X_shuffle)
+
+    # Birch must preserve inputs' dtype
+    assert brc.subcluster_centers_.dtype == global_dtype
+
+    assert_array_equal(brc.labels_, brc.predict(X_shuffle))
+    centroids = brc.subcluster_centers_
+    nearest_centroid = brc.subcluster_labels_[
+        pairwise_distances_argmin(X_shuffle, centroids)
+    ]
+    assert_allclose(v_measure_score(nearest_centroid, brc.labels_), 1.0)
+
+
+def test_n_clusters(global_random_seed, global_dtype):
+    # Test that n_clusters param works properly
+    X, y = make_blobs(n_samples=100, centers=10, random_state=global_random_seed)
+    X = X.astype(global_dtype, copy=False)
+    brc1 = Birch(n_clusters=10)
+    brc1.fit(X)
+    assert len(brc1.subcluster_centers_) > 10
+    assert len(np.unique(brc1.labels_)) == 10
+
+    # Test that n_clusters = Agglomerative Clustering gives
+    # the same results.
+    gc = AgglomerativeClustering(n_clusters=10)
+    brc2 = Birch(n_clusters=gc)
+    brc2.fit(X)
+    assert_array_equal(brc1.subcluster_labels_, brc2.subcluster_labels_)
+    assert_array_equal(brc1.labels_, brc2.labels_)
+
+    # Test that a small number of clusters raises a warning.
+    brc4 = Birch(threshold=10000.0)
+    with pytest.warns(ConvergenceWarning):
+        brc4.fit(X)
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+def test_sparse_X(global_random_seed, global_dtype, csr_container):
+    # Test that sparse and dense data give same results
+    X, y = make_blobs(n_samples=100, centers=10, random_state=global_random_seed)
+    X = X.astype(global_dtype, copy=False)
+    brc = Birch(n_clusters=10)
+    brc.fit(X)
+
+    csr = csr_container(X)
+    brc_sparse = Birch(n_clusters=10)
+    brc_sparse.fit(csr)
+
+    # Birch must preserve inputs' dtype
+    assert brc_sparse.subcluster_centers_.dtype == global_dtype
+
+    assert_array_equal(brc.labels_, brc_sparse.labels_)
+    assert_allclose(brc.subcluster_centers_, brc_sparse.subcluster_centers_)
+
+
+def test_partial_fit_second_call_error_checks():
+    # second partial fit calls will error when n_features is not consistent
+    # with the first call
+    X, y = make_blobs(n_samples=100)
+    brc = Birch(n_clusters=3)
+    brc.partial_fit(X, y)
+
+    msg = "X has 1 features, but Birch is expecting 2 features"
+    with pytest.raises(ValueError, match=msg):
+        brc.partial_fit(X[:, [0]], y)
+
+
+def check_branching_factor(node, branching_factor):
+    subclusters = node.subclusters_
+    assert branching_factor >= len(subclusters)
+    for cluster in subclusters:
+        if cluster.child_:
+            check_branching_factor(cluster.child_, branching_factor)
+
+
+def test_branching_factor(global_random_seed, global_dtype):
+    # Test that nodes have at max branching_factor number of subclusters
+    X, y = make_blobs(random_state=global_random_seed)
+    X = X.astype(global_dtype, copy=False)
+    branching_factor = 9
+
+    # Purposefully set a low threshold to maximize the subclusters.
+    brc = Birch(n_clusters=None, branching_factor=branching_factor, threshold=0.01)
+    brc.fit(X)
+    check_branching_factor(brc.root_, branching_factor)
+    brc = Birch(n_clusters=3, branching_factor=branching_factor, threshold=0.01)
+    brc.fit(X)
+    check_branching_factor(brc.root_, branching_factor)
+
+
+def check_threshold(birch_instance, threshold):
+    """Use the leaf linked list for traversal"""
+    current_leaf = birch_instance.dummy_leaf_.next_leaf_
+    while current_leaf:
+        subclusters = current_leaf.subclusters_
+        for sc in subclusters:
+            assert threshold >= sc.radius
+        current_leaf = current_leaf.next_leaf_
+
+
+def test_threshold(global_random_seed, global_dtype):
+    # Test that the leaf subclusters have a threshold lesser than radius
+    X, y = make_blobs(n_samples=80, centers=4, random_state=global_random_seed)
+    X = X.astype(global_dtype, copy=False)
+    brc = Birch(threshold=0.5, n_clusters=None)
+    brc.fit(X)
+    check_threshold(brc, 0.5)
+
+    brc = Birch(threshold=5.0, n_clusters=None)
+    brc.fit(X)
+    check_threshold(brc, 5.0)
+
+
+def test_birch_n_clusters_long_int():
+    # Check that birch supports n_clusters with np.int64 dtype, for instance
+    # coming from np.arange. #16484
+    X, _ = make_blobs(random_state=0)
+    n_clusters = np.int64(5)
+    Birch(n_clusters=n_clusters).fit(X)
+
+
+def test_feature_names_out():
+    """Check `get_feature_names_out` for `Birch`."""
+    X, _ = make_blobs(n_samples=80, n_features=4, random_state=0)
+    brc = Birch(n_clusters=4)
+    brc.fit(X)
+    n_clusters = brc.subcluster_centers_.shape[0]
+
+    names_out = brc.get_feature_names_out()
+    assert_array_equal([f"birch{i}" for i in range(n_clusters)], names_out)
+
+
+def test_transform_match_across_dtypes(global_random_seed):
+    X, _ = make_blobs(n_samples=80, n_features=4, random_state=global_random_seed)
+    brc = Birch(n_clusters=4, threshold=1.1)
+    Y_64 = brc.fit_transform(X)
+    Y_32 = brc.fit_transform(X.astype(np.float32))
+
+    assert_allclose(Y_64, Y_32, atol=1e-6)
+
+
+def test_subcluster_dtype(global_dtype):
+    X = make_blobs(n_samples=80, n_features=4, random_state=0)[0].astype(
+        global_dtype, copy=False
+    )
+    brc = Birch(n_clusters=4)
+    assert brc.fit(X).subcluster_centers_.dtype == global_dtype
+
+
+def test_both_subclusters_updated():
+    """Check that both subclusters are updated when a node a split, even when there are
+    duplicated data points. Non-regression test for #23269.
+    """
+
+    X = np.array(
+        [
+            [-2.6192791, -1.5053215],
+            [-2.9993038, -1.6863596],
+            [-2.3724914, -1.3438171],
+            [-2.336792, -1.3417323],
+            [-2.4089134, -1.3290224],
+            [-2.3724914, -1.3438171],
+            [-3.364009, -1.8846745],
+            [-2.3724914, -1.3438171],
+            [-2.617677, -1.5003285],
+            [-2.2960556, -1.3260119],
+            [-2.3724914, -1.3438171],
+            [-2.5459878, -1.4533926],
+            [-2.25979, -1.3003055],
+            [-2.4089134, -1.3290224],
+            [-2.3724914, -1.3438171],
+            [-2.4089134, -1.3290224],
+            [-2.5459878, -1.4533926],
+            [-2.3724914, -1.3438171],
+            [-2.9720619, -1.7058647],
+            [-2.336792, -1.3417323],
+            [-2.3724914, -1.3438171],
+        ],
+        dtype=np.float32,
+    )
+
+    # no error
+    Birch(branching_factor=5, threshold=1e-5, n_clusters=None).fit(X)

linedance-app/venv/lib/python3.12/site-packages/sklearn/cluster/tests/test_bisect_k_means.py

@@ -0,0 +1,158 @@
+import numpy as np
+import pytest
+
+from sklearn.cluster import BisectingKMeans
+from sklearn.metrics import v_measure_score
+from sklearn.utils._testing import assert_allclose, assert_array_equal
+from sklearn.utils.fixes import CSR_CONTAINERS
+
+
+@pytest.mark.parametrize("bisecting_strategy", ["biggest_inertia", "largest_cluster"])
+@pytest.mark.parametrize("init", ["k-means++", "random"])
+def test_three_clusters(bisecting_strategy, init):
+    """Tries to perform bisect k-means for three clusters to check
+    if splitting data is performed correctly.
+    """
+    X = np.array(
+        [[1, 1], [10, 1], [3, 1], [10, 0], [2, 1], [10, 2], [10, 8], [10, 9], [10, 10]]
+    )
+    bisect_means = BisectingKMeans(
+        n_clusters=3,
+        random_state=0,
+        bisecting_strategy=bisecting_strategy,
+        init=init,
+    )
+    bisect_means.fit(X)
+
+    expected_centers = [[2, 1], [10, 1], [10, 9]]
+    expected_labels = [0, 1, 0, 1, 0, 1, 2, 2, 2]
+
+    assert_allclose(
+        sorted(expected_centers), sorted(bisect_means.cluster_centers_.tolist())
+    )
+    assert_allclose(v_measure_score(expected_labels, bisect_means.labels_), 1.0)
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+def test_sparse(csr_container):
+    """Test Bisecting K-Means with sparse data.
+
+    Checks if labels and centers are the same between dense and sparse.
+    """
+
+    rng = np.random.RandomState(0)
+
+    X = rng.rand(20, 2)
+    X[X < 0.8] = 0
+    X_csr = csr_container(X)
+
+    bisect_means = BisectingKMeans(n_clusters=3, random_state=0)
+
+    bisect_means.fit(X_csr)
+    sparse_centers = bisect_means.cluster_centers_
+
+    bisect_means.fit(X)
+    normal_centers = bisect_means.cluster_centers_
+
+    # Check if results is the same for dense and sparse data
+    assert_allclose(normal_centers, sparse_centers, atol=1e-8)
+
+
+@pytest.mark.parametrize("n_clusters", [4, 5])
+def test_n_clusters(n_clusters):
+    """Test if resulting labels are in range [0, n_clusters - 1]."""
+
+    rng = np.random.RandomState(0)
+    X = rng.rand(10, 2)
+
+    bisect_means = BisectingKMeans(n_clusters=n_clusters, random_state=0)
+    bisect_means.fit(X)
+
+    assert_array_equal(np.unique(bisect_means.labels_), np.arange(n_clusters))
+
+
+def test_one_cluster():
+    """Test single cluster."""
+
+    X = np.array([[1, 2], [10, 2], [10, 8]])
+
+    bisect_means = BisectingKMeans(n_clusters=1, random_state=0).fit(X)
+
+    # All labels from fit or predict should be equal 0
+    assert all(bisect_means.labels_ == 0)
+    assert all(bisect_means.predict(X) == 0)
+
+    assert_allclose(bisect_means.cluster_centers_, X.mean(axis=0).reshape(1, -1))
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS + [None])
+def test_fit_predict(csr_container):
+    """Check if labels from fit(X) method are same as from fit(X).predict(X)."""
+    rng = np.random.RandomState(0)
+
+    X = rng.rand(10, 2)
+
+    if csr_container is not None:
+        X[X < 0.8] = 0
+        X = csr_container(X)
+
+    bisect_means = BisectingKMeans(n_clusters=3, random_state=0)
+    bisect_means.fit(X)
+
+    assert_array_equal(bisect_means.labels_, bisect_means.predict(X))
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS + [None])
+def test_dtype_preserved(csr_container, global_dtype):
+    """Check that centers dtype is the same as input data dtype."""
+    rng = np.random.RandomState(0)
+    X = rng.rand(10, 2).astype(global_dtype, copy=False)
+
+    if csr_container is not None:
+        X[X < 0.8] = 0
+        X = csr_container(X)
+
+    km = BisectingKMeans(n_clusters=3, random_state=0)
+    km.fit(X)
+
+    assert km.cluster_centers_.dtype == global_dtype
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS + [None])
+def test_float32_float64_equivalence(csr_container):
+    """Check that the results are the same between float32 and float64."""
+    rng = np.random.RandomState(0)
+    X = rng.rand(10, 2)
+
+    if csr_container is not None:
+        X[X < 0.8] = 0
+        X = csr_container(X)
+
+    km64 = BisectingKMeans(n_clusters=3, random_state=0).fit(X)
+    km32 = BisectingKMeans(n_clusters=3, random_state=0).fit(X.astype(np.float32))
+
+    assert_allclose(km32.cluster_centers_, km64.cluster_centers_)
+    assert_array_equal(km32.labels_, km64.labels_)
+
+
+@pytest.mark.parametrize("algorithm", ("lloyd", "elkan"))
+def test_no_crash_on_empty_bisections(algorithm):
+    # Non-regression test for:
+    # https://github.com/scikit-learn/scikit-learn/issues/27081
+    rng = np.random.RandomState(0)
+    X_train = rng.rand(3000, 10)
+    bkm = BisectingKMeans(n_clusters=10, algorithm=algorithm).fit(X_train)
+
+    # predict on scaled data to trigger pathologic case
+    # where the inner mask leads to empty bisections.
+    X_test = 50 * rng.rand(100, 10)
+    labels = bkm.predict(X_test)  # should not crash with idiv by 0
+    assert np.isin(np.unique(labels), np.arange(10)).all()
+
+
+def test_one_feature():
+    # Check that no error is raised when there is only one feature
+    # Non-regression test for:
+    # https://github.com/scikit-learn/scikit-learn/issues/27236
+    X = np.random.normal(size=(128, 1))
+    BisectingKMeans(bisecting_strategy="biggest_inertia", random_state=0).fit(X)

linedance-app/venv/lib/python3.12/site-packages/sklearn/cluster/tests/test_dbscan.py

@@ -0,0 +1,434 @@
+"""
+Tests for DBSCAN clustering algorithm
+"""
+
+import pickle
+import warnings
+
+import numpy as np
+import pytest
+from scipy.spatial import distance
+
+from sklearn.cluster import DBSCAN, dbscan
+from sklearn.cluster.tests.common import generate_clustered_data
+from sklearn.metrics.pairwise import pairwise_distances
+from sklearn.neighbors import NearestNeighbors
+from sklearn.utils._testing import assert_array_equal
+from sklearn.utils.fixes import CSR_CONTAINERS, LIL_CONTAINERS
+
+n_clusters = 3
+X = generate_clustered_data(n_clusters=n_clusters)
+
+
+def test_dbscan_similarity():
+    # Tests the DBSCAN algorithm with a similarity array.
+    # Parameters chosen specifically for this task.
+    eps = 0.15
+    min_samples = 10
+    # Compute similarities
+    D = distance.squareform(distance.pdist(X))
+    D /= np.max(D)
+    # Compute DBSCAN
+    core_samples, labels = dbscan(
+        D, metric="precomputed", eps=eps, min_samples=min_samples
+    )
+    # number of clusters, ignoring noise if present
+    n_clusters_1 = len(set(labels)) - (1 if -1 in labels else 0)
+
+    assert n_clusters_1 == n_clusters
+
+    db = DBSCAN(metric="precomputed", eps=eps, min_samples=min_samples)
+    labels = db.fit(D).labels_
+
+    n_clusters_2 = len(set(labels)) - int(-1 in labels)
+    assert n_clusters_2 == n_clusters
+
+
+def test_dbscan_feature():
+    # Tests the DBSCAN algorithm with a feature vector array.
+    # Parameters chosen specifically for this task.
+    # Different eps to other test, because distance is not normalised.
+    eps = 0.8
+    min_samples = 10
+    metric = "euclidean"
+    # Compute DBSCAN
+    # parameters chosen for task
+    core_samples, labels = dbscan(X, metric=metric, eps=eps, min_samples=min_samples)
+
+    # number of clusters, ignoring noise if present
+    n_clusters_1 = len(set(labels)) - int(-1 in labels)
+    assert n_clusters_1 == n_clusters
+
+    db = DBSCAN(metric=metric, eps=eps, min_samples=min_samples)
+    labels = db.fit(X).labels_
+
+    n_clusters_2 = len(set(labels)) - int(-1 in labels)
+    assert n_clusters_2 == n_clusters
+
+
+@pytest.mark.parametrize("lil_container", LIL_CONTAINERS)
+def test_dbscan_sparse(lil_container):
+    core_sparse, labels_sparse = dbscan(lil_container(X), eps=0.8, min_samples=10)
+    core_dense, labels_dense = dbscan(X, eps=0.8, min_samples=10)
+    assert_array_equal(core_dense, core_sparse)
+    assert_array_equal(labels_dense, labels_sparse)
+
+
+@pytest.mark.parametrize("include_self", [False, True])
+def test_dbscan_sparse_precomputed(include_self):
+    D = pairwise_distances(X)
+    nn = NearestNeighbors(radius=0.9).fit(X)
+    X_ = X if include_self else None
+    D_sparse = nn.radius_neighbors_graph(X=X_, mode="distance")
+    # Ensure it is sparse not merely on diagonals:
+    assert D_sparse.nnz < D.shape[0] * (D.shape[0] - 1)
+    core_sparse, labels_sparse = dbscan(
+        D_sparse, eps=0.8, min_samples=10, metric="precomputed"
+    )
+    core_dense, labels_dense = dbscan(D, eps=0.8, min_samples=10, metric="precomputed")
+    assert_array_equal(core_dense, core_sparse)
+    assert_array_equal(labels_dense, labels_sparse)
+
+
+def test_dbscan_sparse_precomputed_different_eps():
+    # test that precomputed neighbors graph is filtered if computed with
+    # a radius larger than DBSCAN's eps.
+    lower_eps = 0.2
+    nn = NearestNeighbors(radius=lower_eps).fit(X)
+    D_sparse = nn.radius_neighbors_graph(X, mode="distance")
+    dbscan_lower = dbscan(D_sparse, eps=lower_eps, metric="precomputed")
+
+    higher_eps = lower_eps + 0.7
+    nn = NearestNeighbors(radius=higher_eps).fit(X)
+    D_sparse = nn.radius_neighbors_graph(X, mode="distance")
+    dbscan_higher = dbscan(D_sparse, eps=lower_eps, metric="precomputed")
+
+    assert_array_equal(dbscan_lower[0], dbscan_higher[0])
+    assert_array_equal(dbscan_lower[1], dbscan_higher[1])
+
+
+@pytest.mark.parametrize("metric", ["precomputed", "minkowski"])
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS + [None])
+def test_dbscan_input_not_modified(metric, csr_container):
+    # test that the input is not modified by dbscan
+    X = np.random.RandomState(0).rand(10, 10)
+    X = csr_container(X) if csr_container is not None else X
+    X_copy = X.copy()
+    dbscan(X, metric=metric)
+
+    if csr_container is not None:
+        assert_array_equal(X.toarray(), X_copy.toarray())
+    else:
+        assert_array_equal(X, X_copy)
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+def test_dbscan_input_not_modified_precomputed_sparse_nodiag(csr_container):
+    """Check that we don't modify in-place the pre-computed sparse matrix.
+
+    Non-regression test for:
+    https://github.com/scikit-learn/scikit-learn/issues/27508
+    """
+    X = np.random.RandomState(0).rand(10, 10)
+    # Add zeros on the diagonal that will be implicit when creating
+    # the sparse matrix. If `X` is modified in-place, the zeros from
+    # the diagonal will be made explicit.
+    np.fill_diagonal(X, 0)
+    X = csr_container(X)
+    assert all(row != col for row, col in zip(*X.nonzero()))
+    X_copy = X.copy()
+    dbscan(X, metric="precomputed")
+    # Make sure that we did not modify `X` in-place even by creating
+    # explicit 0s values.
+    assert X.nnz == X_copy.nnz
+    assert_array_equal(X.toarray(), X_copy.toarray())
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+def test_dbscan_no_core_samples(csr_container):
+    rng = np.random.RandomState(0)
+    X = rng.rand(40, 10)
+    X[X < 0.8] = 0
+
+    for X_ in [X, csr_container(X)]:
+        db = DBSCAN(min_samples=6).fit(X_)
+        assert_array_equal(db.components_, np.empty((0, X_.shape[1])))
+        assert_array_equal(db.labels_, -1)
+        assert db.core_sample_indices_.shape == (0,)
+
+
+def test_dbscan_callable():
+    # Tests the DBSCAN algorithm with a callable metric.
+    # Parameters chosen specifically for this task.
+    # Different eps to other test, because distance is not normalised.
+    eps = 0.8
+    min_samples = 10
+    # metric is the function reference, not the string key.
+    metric = distance.euclidean
+    # Compute DBSCAN
+    # parameters chosen for task
+    core_samples, labels = dbscan(
+        X, metric=metric, eps=eps, min_samples=min_samples, algorithm="ball_tree"
+    )
+
+    # number of clusters, ignoring noise if present
+    n_clusters_1 = len(set(labels)) - int(-1 in labels)
+    assert n_clusters_1 == n_clusters
+
+    db = DBSCAN(metric=metric, eps=eps, min_samples=min_samples, algorithm="ball_tree")
+    labels = db.fit(X).labels_
+
+    n_clusters_2 = len(set(labels)) - int(-1 in labels)
+    assert n_clusters_2 == n_clusters
+
+
+def test_dbscan_metric_params():
+    # Tests that DBSCAN works with the metrics_params argument.
+    eps = 0.8
+    min_samples = 10
+    p = 1
+
+    # Compute DBSCAN with metric_params arg
+
+    with warnings.catch_warnings(record=True) as warns:
+        db = DBSCAN(
+            metric="minkowski",
+            metric_params={"p": p},
+            eps=eps,
+            p=None,
+            min_samples=min_samples,
+            algorithm="ball_tree",
+        ).fit(X)
+    assert not warns, warns[0].message
+    core_sample_1, labels_1 = db.core_sample_indices_, db.labels_
+
+    # Test that sample labels are the same as passing Minkowski 'p' directly
+    db = DBSCAN(
+        metric="minkowski", eps=eps, min_samples=min_samples, algorithm="ball_tree", p=p
+    ).fit(X)
+    core_sample_2, labels_2 = db.core_sample_indices_, db.labels_
+
+    assert_array_equal(core_sample_1, core_sample_2)
+    assert_array_equal(labels_1, labels_2)
+
+    # Minkowski with p=1 should be equivalent to Manhattan distance
+    db = DBSCAN(
+        metric="manhattan", eps=eps, min_samples=min_samples, algorithm="ball_tree"
+    ).fit(X)
+    core_sample_3, labels_3 = db.core_sample_indices_, db.labels_
+
+    assert_array_equal(core_sample_1, core_sample_3)
+    assert_array_equal(labels_1, labels_3)
+
+    with pytest.warns(
+        SyntaxWarning,
+        match=(
+            "Parameter p is found in metric_params. "
+            "The corresponding parameter from __init__ "
+            "is ignored."
+        ),
+    ):
+        # Test that checks p is ignored in favor of metric_params={'p': <val>}
+        db = DBSCAN(
+            metric="minkowski",
+            metric_params={"p": p},
+            eps=eps,
+            p=p + 1,
+            min_samples=min_samples,
+            algorithm="ball_tree",
+        ).fit(X)
+        core_sample_4, labels_4 = db.core_sample_indices_, db.labels_
+
+    assert_array_equal(core_sample_1, core_sample_4)
+    assert_array_equal(labels_1, labels_4)
+
+
+def test_dbscan_balltree():
+    # Tests the DBSCAN algorithm with balltree for neighbor calculation.
+    eps = 0.8
+    min_samples = 10
+
+    D = pairwise_distances(X)
+    core_samples, labels = dbscan(
+        D, metric="precomputed", eps=eps, min_samples=min_samples
+    )
+
+    # number of clusters, ignoring noise if present
+    n_clusters_1 = len(set(labels)) - int(-1 in labels)
+    assert n_clusters_1 == n_clusters
+
+    db = DBSCAN(p=2.0, eps=eps, min_samples=min_samples, algorithm="ball_tree")
+    labels = db.fit(X).labels_
+
+    n_clusters_2 = len(set(labels)) - int(-1 in labels)
+    assert n_clusters_2 == n_clusters
+
+    db = DBSCAN(p=2.0, eps=eps, min_samples=min_samples, algorithm="kd_tree")
+    labels = db.fit(X).labels_
+
+    n_clusters_3 = len(set(labels)) - int(-1 in labels)
+    assert n_clusters_3 == n_clusters
+
+    db = DBSCAN(p=1.0, eps=eps, min_samples=min_samples, algorithm="ball_tree")
+    labels = db.fit(X).labels_
+
+    n_clusters_4 = len(set(labels)) - int(-1 in labels)
+    assert n_clusters_4 == n_clusters
+
+    db = DBSCAN(leaf_size=20, eps=eps, min_samples=min_samples, algorithm="ball_tree")
+    labels = db.fit(X).labels_
+
+    n_clusters_5 = len(set(labels)) - int(-1 in labels)
+    assert n_clusters_5 == n_clusters
+
+
+def test_input_validation():
+    # DBSCAN.fit should accept a list of lists.
+    X = [[1.0, 2.0], [3.0, 4.0]]
+    DBSCAN().fit(X)  # must not raise exception
+
+
+def test_pickle():
+    obj = DBSCAN()
+    s = pickle.dumps(obj)
+    assert type(pickle.loads(s)) is obj.__class__
+
+
+def test_boundaries():
+    # ensure min_samples is inclusive of core point
+    core, _ = dbscan([[0], [1]], eps=2, min_samples=2)
+    assert 0 in core
+    # ensure eps is inclusive of circumference
+    core, _ = dbscan([[0], [1], [1]], eps=1, min_samples=2)
+    assert 0 in core
+    core, _ = dbscan([[0], [1], [1]], eps=0.99, min_samples=2)
+    assert 0 not in core
+
+
+def test_weighted_dbscan(global_random_seed):
+    # ensure sample_weight is validated
+    with pytest.raises(ValueError):
+        dbscan([[0], [1]], sample_weight=[2])
+    with pytest.raises(ValueError):
+        dbscan([[0], [1]], sample_weight=[2, 3, 4])
+
+    # ensure sample_weight has an effect
+    assert_array_equal([], dbscan([[0], [1]], sample_weight=None, min_samples=6)[0])
+    assert_array_equal([], dbscan([[0], [1]], sample_weight=[5, 5], min_samples=6)[0])
+    assert_array_equal([0], dbscan([[0], [1]], sample_weight=[6, 5], min_samples=6)[0])
+    assert_array_equal(
+        [0, 1], dbscan([[0], [1]], sample_weight=[6, 6], min_samples=6)[0]
+    )
+
+    # points within eps of each other:
+    assert_array_equal(
+        [0, 1], dbscan([[0], [1]], eps=1.5, sample_weight=[5, 1], min_samples=6)[0]
+    )
+    # and effect of non-positive and non-integer sample_weight:
+    assert_array_equal(
+        [], dbscan([[0], [1]], sample_weight=[5, 0], eps=1.5, min_samples=6)[0]
+    )
+    assert_array_equal(
+        [0, 1], dbscan([[0], [1]], sample_weight=[5.9, 0.1], eps=1.5, min_samples=6)[0]
+    )
+    assert_array_equal(
+        [0, 1], dbscan([[0], [1]], sample_weight=[6, 0], eps=1.5, min_samples=6)[0]
+    )
+    assert_array_equal(
+        [], dbscan([[0], [1]], sample_weight=[6, -1], eps=1.5, min_samples=6)[0]
+    )
+
+    # for non-negative sample_weight, cores should be identical to repetition
+    rng = np.random.RandomState(global_random_seed)
+    sample_weight = rng.randint(0, 5, X.shape[0])
+    core1, label1 = dbscan(X, sample_weight=sample_weight)
+    assert len(label1) == len(X)
+
+    X_repeated = np.repeat(X, sample_weight, axis=0)
+    core_repeated, label_repeated = dbscan(X_repeated)
+    core_repeated_mask = np.zeros(X_repeated.shape[0], dtype=bool)
+    core_repeated_mask[core_repeated] = True
+    core_mask = np.zeros(X.shape[0], dtype=bool)
+    core_mask[core1] = True
+    assert_array_equal(np.repeat(core_mask, sample_weight), core_repeated_mask)
+
+    # sample_weight should work with precomputed distance matrix
+    D = pairwise_distances(X)
+    core3, label3 = dbscan(D, sample_weight=sample_weight, metric="precomputed")
+    assert_array_equal(core1, core3)
+    assert_array_equal(label1, label3)
+
+    # sample_weight should work with estimator
+    est = DBSCAN().fit(X, sample_weight=sample_weight)
+    core4 = est.core_sample_indices_
+    label4 = est.labels_
+    assert_array_equal(core1, core4)
+    assert_array_equal(label1, label4)
+
+    est = DBSCAN()
+    label5 = est.fit_predict(X, sample_weight=sample_weight)
+    core5 = est.core_sample_indices_
+    assert_array_equal(core1, core5)
+    assert_array_equal(label1, label5)
+    assert_array_equal(label1, est.labels_)
+
+
+@pytest.mark.parametrize("algorithm", ["brute", "kd_tree", "ball_tree"])
+def test_dbscan_core_samples_toy(algorithm):
+    X = [[0], [2], [3], [4], [6], [8], [10]]
+    n_samples = len(X)
+
+    # Degenerate case: every sample is a core sample, either with its own
+    # cluster or including other close core samples.
+    core_samples, labels = dbscan(X, algorithm=algorithm, eps=1, min_samples=1)
+    assert_array_equal(core_samples, np.arange(n_samples))
+    assert_array_equal(labels, [0, 1, 1, 1, 2, 3, 4])
+
+    # With eps=1 and min_samples=2 only the 3 samples from the denser area
+    # are core samples. All other points are isolated and considered noise.
+    core_samples, labels = dbscan(X, algorithm=algorithm, eps=1, min_samples=2)
+    assert_array_equal(core_samples, [1, 2, 3])
+    assert_array_equal(labels, [-1, 0, 0, 0, -1, -1, -1])
+
+    # Only the sample in the middle of the dense area is core. Its two
+    # neighbors are edge samples. Remaining samples are noise.
+    core_samples, labels = dbscan(X, algorithm=algorithm, eps=1, min_samples=3)
+    assert_array_equal(core_samples, [2])
+    assert_array_equal(labels, [-1, 0, 0, 0, -1, -1, -1])
+
+    # It's no longer possible to extract core samples with eps=1:
+    # everything is noise.
+    core_samples, labels = dbscan(X, algorithm=algorithm, eps=1, min_samples=4)
+    assert_array_equal(core_samples, [])
+    assert_array_equal(labels, np.full(n_samples, -1.0))
+
+
+def test_dbscan_precomputed_metric_with_degenerate_input_arrays():
+    # see https://github.com/scikit-learn/scikit-learn/issues/4641 for
+    # more details
+    X = np.eye(10)
+    labels = DBSCAN(eps=0.5, metric="precomputed").fit(X).labels_
+    assert len(set(labels)) == 1
+
+    X = np.zeros((10, 10))
+    labels = DBSCAN(eps=0.5, metric="precomputed").fit(X).labels_
+    assert len(set(labels)) == 1
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+def test_dbscan_precomputed_metric_with_initial_rows_zero(csr_container):
+    # sample matrix with initial two row all zero
+    ar = np.array(
+        [
+            [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
+            [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
+            [0.0, 0.0, 0.0, 0.0, 0.1, 0.0, 0.0],
+            [0.0, 0.0, 0.0, 0.0, 0.1, 0.0, 0.0],
+            [0.0, 0.0, 0.1, 0.1, 0.0, 0.0, 0.3],
+            [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.1],
+            [0.0, 0.0, 0.0, 0.0, 0.3, 0.1, 0.0],
+        ]
+    )
+    matrix = csr_container(ar)
+    labels = DBSCAN(eps=0.2, metric="precomputed", min_samples=2).fit(matrix).labels_
+    assert_array_equal(labels, [-1, -1, 0, 0, 0, 1, 1])

linedance-app/venv/lib/python3.12/site-packages/sklearn/cluster/tests/test_feature_agglomeration.py

@@ -0,0 +1,55 @@
+"""
+Tests for sklearn.cluster._feature_agglomeration
+"""
+
+import numpy as np
+from numpy.testing import assert_array_equal
+
+from sklearn.cluster import FeatureAgglomeration
+from sklearn.datasets import make_blobs
+from sklearn.utils._testing import assert_array_almost_equal
+
+
+def test_feature_agglomeration():
+    n_clusters = 1
+    X = np.array([0, 0, 1]).reshape(1, 3)  # (n_samples, n_features)
+
+    agglo_mean = FeatureAgglomeration(n_clusters=n_clusters, pooling_func=np.mean)
+    agglo_median = FeatureAgglomeration(n_clusters=n_clusters, pooling_func=np.median)
+    agglo_mean.fit(X)
+    agglo_median.fit(X)
+
+    assert np.size(np.unique(agglo_mean.labels_)) == n_clusters
+    assert np.size(np.unique(agglo_median.labels_)) == n_clusters
+    assert np.size(agglo_mean.labels_) == X.shape[1]
+    assert np.size(agglo_median.labels_) == X.shape[1]
+
+    # Test transform
+    Xt_mean = agglo_mean.transform(X)
+    Xt_median = agglo_median.transform(X)
+    assert Xt_mean.shape[1] == n_clusters
+    assert Xt_median.shape[1] == n_clusters
+    assert Xt_mean == np.array([1 / 3.0])
+    assert Xt_median == np.array([0.0])
+
+    # Test inverse transform
+    X_full_mean = agglo_mean.inverse_transform(Xt_mean)
+    X_full_median = agglo_median.inverse_transform(Xt_median)
+    assert np.unique(X_full_mean[0]).size == n_clusters
+    assert np.unique(X_full_median[0]).size == n_clusters
+
+    assert_array_almost_equal(agglo_mean.transform(X_full_mean), Xt_mean)
+    assert_array_almost_equal(agglo_median.transform(X_full_median), Xt_median)
+
+
+def test_feature_agglomeration_feature_names_out():
+    """Check `get_feature_names_out` for `FeatureAgglomeration`."""
+    X, _ = make_blobs(n_features=6, random_state=0)
+    agglo = FeatureAgglomeration(n_clusters=3)
+    agglo.fit(X)
+    n_clusters = agglo.n_clusters_
+
+    names_out = agglo.get_feature_names_out()
+    assert_array_equal(
+        [f"featureagglomeration{i}" for i in range(n_clusters)], names_out
+    )

linedance-app/venv/lib/python3.12/site-packages/sklearn/cluster/tests/test_hdbscan.py

@@ -0,0 +1,605 @@
+"""
+Tests for HDBSCAN clustering algorithm
+Based on the DBSCAN test code
+"""
+
+import numpy as np
+import pytest
+from scipy import stats
+from scipy.spatial import distance
+
+from sklearn.cluster import HDBSCAN
+from sklearn.cluster._hdbscan._tree import (
+    CONDENSED_dtype,
+    _condense_tree,
+    _do_labelling,
+)
+from sklearn.cluster._hdbscan.hdbscan import _OUTLIER_ENCODING
+from sklearn.datasets import make_blobs
+from sklearn.metrics import fowlkes_mallows_score
+from sklearn.metrics.pairwise import _VALID_METRICS, euclidean_distances
+from sklearn.neighbors import BallTree, KDTree
+from sklearn.preprocessing import StandardScaler
+from sklearn.utils import shuffle
+from sklearn.utils._testing import assert_allclose, assert_array_equal
+from sklearn.utils.fixes import CSC_CONTAINERS, CSR_CONTAINERS
+
+X, y = make_blobs(n_samples=200, random_state=10)
+X, y = shuffle(X, y, random_state=7)
+X = StandardScaler().fit_transform(X)
+
+ALGORITHMS = [
+    "kd_tree",
+    "ball_tree",
+    "brute",
+    "auto",
+]
+
+OUTLIER_SET = {-1} | {out["label"] for _, out in _OUTLIER_ENCODING.items()}
+
+
+def check_label_quality(labels, threshold=0.99):
+    n_clusters = len(set(labels) - OUTLIER_SET)
+    assert n_clusters == 3
+    assert fowlkes_mallows_score(labels, y) > threshold
+
+
+@pytest.mark.parametrize("outlier_type", _OUTLIER_ENCODING)
+def test_outlier_data(outlier_type):
+    """
+    Tests if np.inf and np.nan data are each treated as special outliers.
+    """
+    outlier = {
+        "infinite": np.inf,
+        "missing": np.nan,
+    }[outlier_type]
+    prob_check = {
+        "infinite": lambda x, y: x == y,
+        "missing": lambda x, y: np.isnan(x),
+    }[outlier_type]
+    label = _OUTLIER_ENCODING[outlier_type]["label"]
+    prob = _OUTLIER_ENCODING[outlier_type]["prob"]
+
+    X_outlier = X.copy()
+    X_outlier[0] = [outlier, 1]
+    X_outlier[5] = [outlier, outlier]
+    model = HDBSCAN(copy=False).fit(X_outlier)
+
+    (missing_labels_idx,) = (model.labels_ == label).nonzero()
+    assert_array_equal(missing_labels_idx, [0, 5])
+
+    (missing_probs_idx,) = (prob_check(model.probabilities_, prob)).nonzero()
+    assert_array_equal(missing_probs_idx, [0, 5])
+
+    clean_indices = list(range(1, 5)) + list(range(6, 200))
+    clean_model = HDBSCAN(copy=False).fit(X_outlier[clean_indices])
+    assert_array_equal(clean_model.labels_, model.labels_[clean_indices])
+
+
+def test_hdbscan_distance_matrix():
+    """
+    Tests that HDBSCAN works with precomputed distance matrices, and throws the
+    appropriate errors when needed.
+    """
+    D = euclidean_distances(X)
+    D_original = D.copy()
+    labels = HDBSCAN(metric="precomputed", copy=True).fit_predict(D)
+
+    assert_allclose(D, D_original)
+    check_label_quality(labels)
+
+    msg = r"The precomputed distance matrix.*has shape"
+    with pytest.raises(ValueError, match=msg):
+        HDBSCAN(metric="precomputed", copy=True).fit_predict(X)
+
+    msg = r"The precomputed distance matrix.*values"
+    # Ensure the matrix is not symmetric
+    D[0, 1] = 10
+    D[1, 0] = 1
+    with pytest.raises(ValueError, match=msg):
+        HDBSCAN(metric="precomputed", copy=False).fit_predict(D)
+
+
+@pytest.mark.parametrize("sparse_constructor", [*CSR_CONTAINERS, *CSC_CONTAINERS])
+def test_hdbscan_sparse_distance_matrix(sparse_constructor):
+    """
+    Tests that HDBSCAN works with sparse distance matrices.
+    """
+    D = distance.squareform(distance.pdist(X))
+    D /= np.max(D)
+
+    threshold = stats.scoreatpercentile(D.flatten(), 50)
+
+    D[D >= threshold] = 0.0
+    D = sparse_constructor(D)
+    D.eliminate_zeros()
+
+    labels = HDBSCAN(metric="precomputed", copy=False).fit_predict(D)
+    check_label_quality(labels)
+
+
+def test_hdbscan_feature_array():
+    """
+    Tests that HDBSCAN works with feature array, including an arbitrary
+    goodness of fit check. Note that the check is a simple heuristic.
+    """
+    labels = HDBSCAN(copy=False).fit_predict(X)
+
+    # Check that clustering is arbitrarily good
+    # This is a heuristic to guard against regression
+    check_label_quality(labels)
+
+
+@pytest.mark.parametrize("algo", ALGORITHMS)
+@pytest.mark.parametrize("metric", _VALID_METRICS)
+def test_hdbscan_algorithms(algo, metric):
+    """
+    Tests that HDBSCAN works with the expected combinations of algorithms and
+    metrics, or raises the expected errors.
+    """
+    labels = HDBSCAN(algorithm=algo, copy=False).fit_predict(X)
+    check_label_quality(labels)
+
+    # Validation for brute is handled by `pairwise_distances`
+    if algo in ("brute", "auto"):
+        return
+
+    ALGOS_TREES = {
+        "kd_tree": KDTree,
+        "ball_tree": BallTree,
+    }
+    metric_params = {
+        "mahalanobis": {"V": np.eye(X.shape[1])},
+        "seuclidean": {"V": np.ones(X.shape[1])},
+        "minkowski": {"p": 2},
+        "wminkowski": {"p": 2, "w": np.ones(X.shape[1])},
+    }.get(metric, None)
+
+    hdb = HDBSCAN(
+        algorithm=algo,
+        metric=metric,
+        metric_params=metric_params,
+        copy=False,
+    )
+
+    if metric not in ALGOS_TREES[algo].valid_metrics:
+        with pytest.raises(ValueError):
+            hdb.fit(X)
+    elif metric == "wminkowski":
+        with pytest.warns(FutureWarning):
+            hdb.fit(X)
+    else:
+        hdb.fit(X)
+
+
+def test_dbscan_clustering():
+    """
+    Tests that HDBSCAN can generate a sufficiently accurate dbscan clustering.
+    This test is more of a sanity check than a rigorous evaluation.
+    """
+    clusterer = HDBSCAN(copy=False).fit(X)
+    labels = clusterer.dbscan_clustering(0.3)
+
+    # We use a looser threshold due to dbscan producing a more constrained
+    # clustering representation
+    check_label_quality(labels, threshold=0.92)
+
+
+@pytest.mark.parametrize("cut_distance", (0.1, 0.5, 1))
+def test_dbscan_clustering_outlier_data(cut_distance):
+    """
+    Tests if np.inf and np.nan data are each treated as special outliers.
+    """
+    missing_label = _OUTLIER_ENCODING["missing"]["label"]
+    infinite_label = _OUTLIER_ENCODING["infinite"]["label"]
+
+    X_outlier = X.copy()
+    X_outlier[0] = [np.inf, 1]
+    X_outlier[2] = [1, np.nan]
+    X_outlier[5] = [np.inf, np.nan]
+    model = HDBSCAN(copy=False).fit(X_outlier)
+    labels = model.dbscan_clustering(cut_distance=cut_distance)
+
+    missing_labels_idx = np.flatnonzero(labels == missing_label)
+    assert_array_equal(missing_labels_idx, [2, 5])
+
+    infinite_labels_idx = np.flatnonzero(labels == infinite_label)
+    assert_array_equal(infinite_labels_idx, [0])
+
+    clean_idx = list(set(range(200)) - set(missing_labels_idx + infinite_labels_idx))
+    clean_model = HDBSCAN(copy=False).fit(X_outlier[clean_idx])
+    clean_labels = clean_model.dbscan_clustering(cut_distance=cut_distance)
+    assert_array_equal(clean_labels, labels[clean_idx])
+
+
+def test_hdbscan_best_balltree_metric():
+    """
+    Tests that HDBSCAN using `BallTree` works.
+    """
+    labels = HDBSCAN(
+        metric="seuclidean", metric_params={"V": np.ones(X.shape[1])}, copy=False
+    ).fit_predict(X)
+    check_label_quality(labels)
+
+
+def test_hdbscan_no_clusters():
+    """
+    Tests that HDBSCAN correctly does not generate a valid cluster when the
+    `min_cluster_size` is too large for the data.
+    """
+    labels = HDBSCAN(min_cluster_size=len(X) - 1, copy=False).fit_predict(X)
+    assert set(labels).issubset(OUTLIER_SET)
+
+
+def test_hdbscan_min_cluster_size():
+    """
+    Test that the smallest non-noise cluster has at least `min_cluster_size`
+    many points
+    """
+    for min_cluster_size in range(2, len(X), 1):
+        labels = HDBSCAN(min_cluster_size=min_cluster_size, copy=False).fit_predict(X)
+        true_labels = [label for label in labels if label != -1]
+        if len(true_labels) != 0:
+            assert np.min(np.bincount(true_labels)) >= min_cluster_size
+
+
+def test_hdbscan_callable_metric():
+    """
+    Tests that HDBSCAN works when passed a callable metric.
+    """
+    metric = distance.euclidean
+    labels = HDBSCAN(metric=metric, copy=False).fit_predict(X)
+    check_label_quality(labels)
+
+
+@pytest.mark.parametrize("tree", ["kd_tree", "ball_tree"])
+def test_hdbscan_precomputed_non_brute(tree):
+    """
+    Tests that HDBSCAN correctly raises an error when passing precomputed data
+    while requesting a tree-based algorithm.
+    """
+    hdb = HDBSCAN(metric="precomputed", algorithm=tree, copy=False)
+    msg = "precomputed is not a valid metric for"
+    with pytest.raises(ValueError, match=msg):
+        hdb.fit(X)
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+def test_hdbscan_sparse(csr_container):
+    """
+    Tests that HDBSCAN works correctly when passing sparse feature data.
+    Evaluates correctness by comparing against the same data passed as a dense
+    array.
+    """
+
+    dense_labels = HDBSCAN(copy=False).fit(X).labels_
+    check_label_quality(dense_labels)
+
+    _X_sparse = csr_container(X)
+    X_sparse = _X_sparse.copy()
+    sparse_labels = HDBSCAN(copy=False).fit(X_sparse).labels_
+    assert_array_equal(dense_labels, sparse_labels)
+
+    # Compare that the sparse and dense non-precomputed routines return the same labels
+    # where the 0th observation contains the outlier.
+    for outlier_val, outlier_type in ((np.inf, "infinite"), (np.nan, "missing")):
+        X_dense = X.copy()
+        X_dense[0, 0] = outlier_val
+        dense_labels = HDBSCAN(copy=False).fit(X_dense).labels_
+        check_label_quality(dense_labels)
+        assert dense_labels[0] == _OUTLIER_ENCODING[outlier_type]["label"]
+
+        X_sparse = _X_sparse.copy()
+        X_sparse[0, 0] = outlier_val
+        sparse_labels = HDBSCAN(copy=False).fit(X_sparse).labels_
+        assert_array_equal(dense_labels, sparse_labels)
+
+    msg = "Sparse data matrices only support algorithm `brute`."
+    with pytest.raises(ValueError, match=msg):
+        HDBSCAN(metric="euclidean", algorithm="ball_tree", copy=False).fit(X_sparse)
+
+
+@pytest.mark.parametrize("algorithm", ALGORITHMS)
+def test_hdbscan_centers(algorithm):
+    """
+    Tests that HDBSCAN centers are calculated and stored properly, and are
+    accurate to the data.
+    """
+    centers = [(0.0, 0.0), (3.0, 3.0)]
+    H, _ = make_blobs(n_samples=2000, random_state=0, centers=centers, cluster_std=0.5)
+    hdb = HDBSCAN(store_centers="both", copy=False).fit(H)
+
+    for center, centroid, medoid in zip(centers, hdb.centroids_, hdb.medoids_):
+        assert_allclose(center, centroid, rtol=1, atol=0.05)
+        assert_allclose(center, medoid, rtol=1, atol=0.05)
+
+    # Ensure that nothing is done for noise
+    hdb = HDBSCAN(
+        algorithm=algorithm,
+        store_centers="both",
+        min_cluster_size=X.shape[0],
+        copy=False,
+    ).fit(X)
+    assert hdb.centroids_.shape[0] == 0
+    assert hdb.medoids_.shape[0] == 0
+
+
+def test_hdbscan_allow_single_cluster_with_epsilon():
+    """
+    Tests that HDBSCAN single-cluster selection with epsilon works correctly.
+    """
+    rng = np.random.RandomState(0)
+    no_structure = rng.rand(150, 2)
+    # without epsilon we should see many noise points as children of root.
+    labels = HDBSCAN(
+        min_cluster_size=5,
+        cluster_selection_epsilon=0.0,
+        cluster_selection_method="eom",
+        allow_single_cluster=True,
+        copy=False,
+    ).fit_predict(no_structure)
+    unique_labels, counts = np.unique(labels, return_counts=True)
+    assert len(unique_labels) == 2
+
+    # Arbitrary heuristic. Would prefer something more precise.
+    assert counts[unique_labels == -1] > 30
+
+    # for this random seed an epsilon of 0.18 will produce exactly 2 noise
+    # points at that cut in single linkage.
+    labels = HDBSCAN(
+        min_cluster_size=5,
+        cluster_selection_epsilon=0.18,
+        cluster_selection_method="eom",
+        allow_single_cluster=True,
+        algorithm="kd_tree",
+        copy=False,
+    ).fit_predict(no_structure)
+    unique_labels, counts = np.unique(labels, return_counts=True)
+    assert len(unique_labels) == 2
+    assert counts[unique_labels == -1] == 2
+
+
+def test_hdbscan_better_than_dbscan():
+    """
+    Validate that HDBSCAN can properly cluster this difficult synthetic
+    dataset. Note that DBSCAN fails on this (see HDBSCAN plotting
+    example)
+    """
+    centers = [[-0.85, -0.85], [-0.85, 0.85], [3, 3], [3, -3]]
+    X, y = make_blobs(
+        n_samples=750,
+        centers=centers,
+        cluster_std=[0.2, 0.35, 1.35, 1.35],
+        random_state=0,
+    )
+    labels = HDBSCAN(copy=False).fit(X).labels_
+
+    n_clusters = len(set(labels)) - int(-1 in labels)
+    assert n_clusters == 4
+    fowlkes_mallows_score(labels, y) > 0.99
+
+
+@pytest.mark.parametrize(
+    "kwargs, X",
+    [
+        ({"metric": "precomputed"}, np.array([[1, np.inf], [np.inf, 1]])),
+        ({"metric": "precomputed"}, [[1, 2], [2, 1]]),
+        ({}, [[1, 2], [3, 4]]),
+    ],
+)
+def test_hdbscan_usable_inputs(X, kwargs):
+    """
+    Tests that HDBSCAN works correctly for array-likes and precomputed inputs
+    with non-finite points.
+    """
+    HDBSCAN(min_samples=1, copy=False, **kwargs).fit(X)
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+def test_hdbscan_sparse_distances_too_few_nonzero(csr_container):
+    """
+    Tests that HDBSCAN raises the correct error when there are too few
+    non-zero distances.
+    """
+    X = csr_container(np.zeros((10, 10)))
+
+    msg = "There exists points with fewer than"
+    with pytest.raises(ValueError, match=msg):
+        HDBSCAN(metric="precomputed", copy=False).fit(X)
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+def test_hdbscan_sparse_distances_disconnected_graph(csr_container):
+    """
+    Tests that HDBSCAN raises the correct error when the distance matrix
+    has multiple connected components.
+    """
+    # Create symmetric sparse matrix with 2 connected components
+    X = np.zeros((20, 20))
+    X[:5, :5] = 1
+    X[5:, 15:] = 1
+    X = X + X.T
+    X = csr_container(X)
+    msg = "HDBSCAN cannot be performed on a disconnected graph"
+    with pytest.raises(ValueError, match=msg):
+        HDBSCAN(metric="precomputed", copy=False).fit(X)
+
+
+def test_hdbscan_tree_invalid_metric():
+    """
+    Tests that HDBSCAN correctly raises an error for invalid metric choices.
+    """
+    metric_callable = lambda x: x
+    msg = (
+        ".* is not a valid metric for a .*-based algorithm\\. Please select a different"
+        " metric\\."
+    )
+
+    # Callables are not supported for either
+    with pytest.raises(ValueError, match=msg):
+        HDBSCAN(algorithm="kd_tree", metric=metric_callable, copy=False).fit(X)
+    with pytest.raises(ValueError, match=msg):
+        HDBSCAN(algorithm="ball_tree", metric=metric_callable, copy=False).fit(X)
+
+    # The set of valid metrics for KDTree at the time of writing this test is a
+    # strict subset of those supported in BallTree
+    metrics_not_kd = list(set(BallTree.valid_metrics) - set(KDTree.valid_metrics))
+    if len(metrics_not_kd) > 0:
+        with pytest.raises(ValueError, match=msg):
+            HDBSCAN(algorithm="kd_tree", metric=metrics_not_kd[0], copy=False).fit(X)
+
+
+def test_hdbscan_too_many_min_samples():
+    """
+    Tests that HDBSCAN correctly raises an error when setting `min_samples`
+    larger than the number of samples.
+    """
+    hdb = HDBSCAN(min_samples=len(X) + 1, copy=False)
+    msg = r"min_samples (.*) must be at most"
+    with pytest.raises(ValueError, match=msg):
+        hdb.fit(X)
+
+
+def test_hdbscan_precomputed_dense_nan():
+    """
+    Tests that HDBSCAN correctly raises an error when providing precomputed
+    distances with `np.nan` values.
+    """
+    X_nan = X.copy()
+    X_nan[0, 0] = np.nan
+    msg = "np.nan values found in precomputed-dense"
+    hdb = HDBSCAN(metric="precomputed", copy=False)
+    with pytest.raises(ValueError, match=msg):
+        hdb.fit(X_nan)
+
+
+@pytest.mark.parametrize("allow_single_cluster", [True, False])
+@pytest.mark.parametrize("epsilon", [0, 0.1])
+def test_labelling_distinct(global_random_seed, allow_single_cluster, epsilon):
+    """
+    Tests that the `_do_labelling` helper function correctly assigns labels.
+    """
+    n_samples = 48
+    X, y = make_blobs(
+        n_samples,
+        random_state=global_random_seed,
+        # Ensure the clusters are distinct with no overlap
+        centers=[
+            [0, 0],
+            [10, 0],
+            [0, 10],
+        ],
+    )
+
+    est = HDBSCAN(copy=False).fit(X)
+    condensed_tree = _condense_tree(
+        est._single_linkage_tree_, min_cluster_size=est.min_cluster_size
+    )
+    clusters = {n_samples + 2, n_samples + 3, n_samples + 4}
+    cluster_label_map = {n_samples + 2: 0, n_samples + 3: 1, n_samples + 4: 2}
+    labels = _do_labelling(
+        condensed_tree=condensed_tree,
+        clusters=clusters,
+        cluster_label_map=cluster_label_map,
+        allow_single_cluster=allow_single_cluster,
+        cluster_selection_epsilon=epsilon,
+    )
+
+    first_with_label = {_y: np.where(y == _y)[0][0] for _y in list(set(y))}
+    y_to_labels = {_y: labels[first_with_label[_y]] for _y in list(set(y))}
+    aligned_target = np.vectorize(y_to_labels.get)(y)
+    assert_array_equal(labels, aligned_target)
+
+
+def test_labelling_thresholding():
+    """
+    Tests that the `_do_labelling` helper function correctly thresholds the
+    incoming lambda values given various `cluster_selection_epsilon` values.
+    """
+    n_samples = 5
+    MAX_LAMBDA = 1.5
+    condensed_tree = np.array(
+        [
+            (5, 2, MAX_LAMBDA, 1),
+            (5, 1, 0.1, 1),
+            (5, 0, MAX_LAMBDA, 1),
+            (5, 3, 0.2, 1),
+            (5, 4, 0.3, 1),
+        ],
+        dtype=CONDENSED_dtype,
+    )
+    labels = _do_labelling(
+        condensed_tree=condensed_tree,
+        clusters={n_samples},
+        cluster_label_map={n_samples: 0, n_samples + 1: 1},
+        allow_single_cluster=True,
+        cluster_selection_epsilon=1,
+    )
+    num_noise = condensed_tree["value"] < 1
+    assert sum(num_noise) == sum(labels == -1)
+
+    labels = _do_labelling(
+        condensed_tree=condensed_tree,
+        clusters={n_samples},
+        cluster_label_map={n_samples: 0, n_samples + 1: 1},
+        allow_single_cluster=True,
+        cluster_selection_epsilon=0,
+    )
+    # The threshold should be calculated per-sample based on the largest
+    # lambda of any simbling node. In this case, all points are siblings
+    # and the largest value is exactly MAX_LAMBDA.
+    num_noise = condensed_tree["value"] < MAX_LAMBDA
+    assert sum(num_noise) == sum(labels == -1)
+
+
+@pytest.mark.parametrize("store_centers", ["centroid", "medoid"])
+def test_hdbscan_error_precomputed_and_store_centers(store_centers):
+    """Check that we raise an error if the centers are requested together with
+    a precomputed input matrix.
+
+    Non-regression test for:
+    https://github.com/scikit-learn/scikit-learn/issues/27893
+    """
+    rng = np.random.RandomState(0)
+    X = rng.random((100, 2))
+    X_dist = euclidean_distances(X)
+    err_msg = "Cannot store centers when using a precomputed distance matrix."
+    with pytest.raises(ValueError, match=err_msg):
+        HDBSCAN(
+            metric="precomputed",
+            store_centers=store_centers,
+            copy=False,
+        ).fit(X_dist)
+
+
+@pytest.mark.parametrize("valid_algo", ["auto", "brute"])
+def test_hdbscan_cosine_metric_valid_algorithm(valid_algo):
+    """Test that HDBSCAN works with the "cosine" metric when the algorithm is set
+    to "brute" or "auto".
+
+    Non-regression test for issue #28631
+    """
+    HDBSCAN(metric="cosine", algorithm=valid_algo, copy=False).fit_predict(X)
+
+
+@pytest.mark.parametrize("invalid_algo", ["kd_tree", "ball_tree"])
+def test_hdbscan_cosine_metric_invalid_algorithm(invalid_algo):
+    """Test that HDBSCAN raises an informative error is raised when an unsupported
+    algorithm is used with the "cosine" metric.
+    """
+    hdbscan = HDBSCAN(metric="cosine", algorithm=invalid_algo, copy=False)
+    with pytest.raises(ValueError, match="cosine is not a valid metric"):
+        hdbscan.fit_predict(X)
+
+
+# TODO(1.10): remove this test
+def test_hdbscan_default_copy_warning():
+    """
+    Test that HDBSCAN raises a FutureWarning when the `copy`
+    parameter is not set.
+    """
+    X = np.random.RandomState(0).random((100, 2))
+    msg = r"The default value of `copy` will change from False to True in 1.10."
+    with pytest.warns(FutureWarning, match=msg):
+        hdb = HDBSCAN(min_cluster_size=20)
+        hdb.fit(X)

linedance-app/venv/lib/python3.12/site-packages/sklearn/cluster/tests/test_hierarchical.py

@@ -0,0 +1,889 @@
+"""
+Several basic tests for hierarchical clustering procedures
+
+"""
+
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
+import itertools
+import shutil
+from functools import partial
+from tempfile import mkdtemp
+
+import numpy as np
+import pytest
+from scipy.cluster import hierarchy
+from scipy.sparse.csgraph import connected_components
+
+from sklearn.cluster import AgglomerativeClustering, FeatureAgglomeration, ward_tree
+from sklearn.cluster._agglomerative import (
+    _TREE_BUILDERS,
+    _fix_connectivity,
+    _hc_cut,
+    linkage_tree,
+)
+from sklearn.cluster._hierarchical_fast import (
+    average_merge,
+    max_merge,
+    mst_linkage_core,
+)
+from sklearn.datasets import make_circles, make_moons
+from sklearn.feature_extraction.image import grid_to_graph
+from sklearn.metrics import DistanceMetric
+from sklearn.metrics.cluster import adjusted_rand_score, normalized_mutual_info_score
+from sklearn.metrics.pairwise import (
+    PAIRED_DISTANCES,
+    cosine_distances,
+    manhattan_distances,
+    pairwise_distances,
+)
+from sklearn.metrics.tests.test_dist_metrics import METRICS_DEFAULT_PARAMS
+from sklearn.neighbors import kneighbors_graph
+from sklearn.utils._fast_dict import IntFloatDict
+from sklearn.utils._testing import (
+    assert_almost_equal,
+    assert_array_almost_equal,
+    assert_array_equal,
+    create_memmap_backed_data,
+    ignore_warnings,
+)
+from sklearn.utils.fixes import LIL_CONTAINERS
+
+
+def test_linkage_misc():
+    # Misc tests on linkage
+    rng = np.random.RandomState(42)
+    X = rng.normal(size=(5, 5))
+
+    with pytest.raises(ValueError):
+        linkage_tree(X, linkage="foo")
+
+    with pytest.raises(ValueError):
+        linkage_tree(X, connectivity=np.ones((4, 4)))
+
+    # Smoke test FeatureAgglomeration
+    FeatureAgglomeration().fit(X)
+
+    # test hierarchical clustering on a precomputed distances matrix
+    dis = cosine_distances(X)
+
+    res = linkage_tree(dis, affinity="precomputed")
+    assert_array_equal(res[0], linkage_tree(X, affinity="cosine")[0])
+
+    # test hierarchical clustering on a precomputed distances matrix
+    res = linkage_tree(X, affinity=manhattan_distances)
+    assert_array_equal(res[0], linkage_tree(X, affinity="manhattan")[0])
+
+
+def test_structured_linkage_tree():
+    # Check that we obtain the correct solution for structured linkage trees.
+    rng = np.random.RandomState(0)
+    mask = np.ones([10, 10], dtype=bool)
+    # Avoiding a mask with only 'True' entries
+    mask[4:7, 4:7] = 0
+    X = rng.randn(50, 100)
+    connectivity = grid_to_graph(*mask.shape)
+    for tree_builder in _TREE_BUILDERS.values():
+        children, n_components, n_leaves, parent = tree_builder(
+            X.T, connectivity=connectivity
+        )
+        n_nodes = 2 * X.shape[1] - 1
+        assert len(children) + n_leaves == n_nodes
+        # Check that ward_tree raises a ValueError with a connectivity matrix
+        # of the wrong shape
+        with pytest.raises(ValueError):
+            tree_builder(X.T, connectivity=np.ones((4, 4)))
+        # Check that fitting with no samples raises an error
+        with pytest.raises(ValueError):
+            tree_builder(X.T[:0], connectivity=connectivity)
+
+
+def test_unstructured_linkage_tree():
+    # Check that we obtain the correct solution for unstructured linkage trees.
+    rng = np.random.RandomState(0)
+    X = rng.randn(50, 100)
+    for this_X in (X, X[0]):
+        # With specified a number of clusters just for the sake of
+        # raising a warning and testing the warning code
+        with ignore_warnings():
+            with pytest.warns(UserWarning):
+                children, n_nodes, n_leaves, parent = ward_tree(this_X.T, n_clusters=10)
+        n_nodes = 2 * X.shape[1] - 1
+        assert len(children) + n_leaves == n_nodes
+
+    for tree_builder in _TREE_BUILDERS.values():
+        for this_X in (X, X[0]):
+            with ignore_warnings():
+                with pytest.warns(UserWarning):
+                    children, n_nodes, n_leaves, parent = tree_builder(
+                        this_X.T, n_clusters=10
+                    )
+            n_nodes = 2 * X.shape[1] - 1
+            assert len(children) + n_leaves == n_nodes
+
+
+def test_height_linkage_tree():
+    # Check that the height of the results of linkage tree is sorted.
+    rng = np.random.RandomState(0)
+    mask = np.ones([10, 10], dtype=bool)
+    X = rng.randn(50, 100)
+    connectivity = grid_to_graph(*mask.shape)
+    for linkage_func in _TREE_BUILDERS.values():
+        children, n_nodes, n_leaves, parent = linkage_func(
+            X.T, connectivity=connectivity
+        )
+        n_nodes = 2 * X.shape[1] - 1
+        assert len(children) + n_leaves == n_nodes
+
+
+def test_zero_cosine_linkage_tree():
+    # Check that zero vectors in X produce an error when
+    # 'cosine' affinity is used
+    X = np.array([[0, 1], [0, 0]])
+    msg = "Cosine affinity cannot be used when X contains zero vectors"
+    with pytest.raises(ValueError, match=msg):
+        linkage_tree(X, affinity="cosine")
+
+
+@pytest.mark.parametrize("n_clusters, distance_threshold", [(None, 0.5), (10, None)])
+@pytest.mark.parametrize("compute_distances", [True, False])
+@pytest.mark.parametrize("linkage", ["ward", "complete", "average", "single"])
+def test_agglomerative_clustering_distances(
+    n_clusters, compute_distances, distance_threshold, linkage
+):
+    # Check that when `compute_distances` is True or `distance_threshold` is
+    # given, the fitted model has an attribute `distances_`.
+    rng = np.random.RandomState(0)
+    mask = np.ones([10, 10], dtype=bool)
+    n_samples = 100
+    X = rng.randn(n_samples, 50)
+    connectivity = grid_to_graph(*mask.shape)
+
+    clustering = AgglomerativeClustering(
+        n_clusters=n_clusters,
+        connectivity=connectivity,
+        linkage=linkage,
+        distance_threshold=distance_threshold,
+        compute_distances=compute_distances,
+    )
+    clustering.fit(X)
+    if compute_distances or (distance_threshold is not None):
+        assert hasattr(clustering, "distances_")
+        n_children = clustering.children_.shape[0]
+        n_nodes = n_children + 1
+        assert clustering.distances_.shape == (n_nodes - 1,)
+    else:
+        assert not hasattr(clustering, "distances_")
+
+
+@pytest.mark.parametrize("lil_container", LIL_CONTAINERS)
+def test_agglomerative_clustering(global_random_seed, lil_container):
+    # Check that we obtain the correct number of clusters with
+    # agglomerative clustering.
+    rng = np.random.RandomState(global_random_seed)
+    mask = np.ones([10, 10], dtype=bool)
+    n_samples = 100
+    X = rng.randn(n_samples, 50)
+    connectivity = grid_to_graph(*mask.shape)
+    for linkage in ("ward", "complete", "average", "single"):
+        clustering = AgglomerativeClustering(
+            n_clusters=10, connectivity=connectivity, linkage=linkage
+        )
+        clustering.fit(X)
+        # test caching
+        try:
+            tempdir = mkdtemp()
+            clustering = AgglomerativeClustering(
+                n_clusters=10,
+                connectivity=connectivity,
+                memory=tempdir,
+                linkage=linkage,
+            )
+            clustering.fit(X)
+            labels = clustering.labels_
+            assert np.size(np.unique(labels)) == 10
+        finally:
+            shutil.rmtree(tempdir)
+        # Turn caching off now
+        clustering = AgglomerativeClustering(
+            n_clusters=10, connectivity=connectivity, linkage=linkage
+        )
+        # Check that we obtain the same solution with early-stopping of the
+        # tree building
+        clustering.compute_full_tree = False
+        clustering.fit(X)
+        assert_almost_equal(normalized_mutual_info_score(clustering.labels_, labels), 1)
+        clustering.connectivity = None
+        clustering.fit(X)
+        assert np.size(np.unique(clustering.labels_)) == 10
+        # Check that we raise a TypeError on dense matrices
+        clustering = AgglomerativeClustering(
+            n_clusters=10,
+            connectivity=lil_container(connectivity.toarray()[:10, :10]),
+            linkage=linkage,
+        )
+        with pytest.raises(ValueError):
+            clustering.fit(X)
+
+    # Test that using ward with another metric than euclidean raises an
+    # exception
+    clustering = AgglomerativeClustering(
+        n_clusters=10,
+        connectivity=connectivity.toarray(),
+        metric="manhattan",
+        linkage="ward",
+    )
+    with pytest.raises(ValueError):
+        clustering.fit(X)
+
+    # Test using another metric than euclidean works with linkage complete
+    for metric in PAIRED_DISTANCES.keys():
+        # Compare our (structured) implementation to scipy
+        clustering = AgglomerativeClustering(
+            n_clusters=10,
+            connectivity=np.ones((n_samples, n_samples)),
+            metric=metric,
+            linkage="complete",
+        )
+        clustering.fit(X)
+        clustering2 = AgglomerativeClustering(
+            n_clusters=10, connectivity=None, metric=metric, linkage="complete"
+        )
+        clustering2.fit(X)
+        assert_almost_equal(
+            normalized_mutual_info_score(clustering2.labels_, clustering.labels_), 1
+        )
+
+    # Test that using a distance matrix (affinity = 'precomputed') has same
+    # results (with connectivity constraints)
+    clustering = AgglomerativeClustering(
+        n_clusters=10, connectivity=connectivity, linkage="complete"
+    )
+    clustering.fit(X)
+    X_dist = pairwise_distances(X)
+    clustering2 = AgglomerativeClustering(
+        n_clusters=10,
+        connectivity=connectivity,
+        metric="precomputed",
+        linkage="complete",
+    )
+    clustering2.fit(X_dist)
+    assert_array_equal(clustering.labels_, clustering2.labels_)
+
+
+def test_agglomerative_clustering_memory_mapped():
+    """AgglomerativeClustering must work on mem-mapped dataset.
+
+    Non-regression test for issue #19875.
+    """
+    rng = np.random.RandomState(0)
+    Xmm = create_memmap_backed_data(rng.randn(50, 100))
+    AgglomerativeClustering(metric="euclidean", linkage="single").fit(Xmm)
+
+
+def test_ward_agglomeration(global_random_seed):
+    # Check that we obtain the correct solution in a simplistic case
+    rng = np.random.RandomState(global_random_seed)
+    mask = np.ones([10, 10], dtype=bool)
+    X = rng.randn(50, 100)
+    connectivity = grid_to_graph(*mask.shape)
+    agglo = FeatureAgglomeration(n_clusters=5, connectivity=connectivity)
+    agglo.fit(X)
+    assert np.size(np.unique(agglo.labels_)) == 5
+
+    X_red = agglo.transform(X)
+    assert X_red.shape[1] == 5
+    X_full = agglo.inverse_transform(X_red)
+    assert np.unique(X_full[0]).size == 5
+    assert_array_almost_equal(agglo.transform(X_full), X_red)
+
+    # Check that fitting with no samples raises a ValueError
+    with pytest.raises(ValueError):
+        agglo.fit(X[:0])
+
+
+def test_single_linkage_clustering():
+    # Check that we get the correct result in two emblematic cases
+    moons, moon_labels = make_moons(noise=0.05, random_state=42)
+    clustering = AgglomerativeClustering(n_clusters=2, linkage="single")
+    clustering.fit(moons)
+    assert_almost_equal(
+        normalized_mutual_info_score(clustering.labels_, moon_labels), 1
+    )
+
+    circles, circle_labels = make_circles(factor=0.5, noise=0.025, random_state=42)
+    clustering = AgglomerativeClustering(n_clusters=2, linkage="single")
+    clustering.fit(circles)
+    assert_almost_equal(
+        normalized_mutual_info_score(clustering.labels_, circle_labels), 1
+    )
+
+
+def assess_same_labelling(cut1, cut2):
+    """Util for comparison with scipy"""
+    co_clust = []
+    for cut in [cut1, cut2]:
+        n = len(cut)
+        k = cut.max() + 1
+        ecut = np.zeros((n, k))
+        ecut[np.arange(n), cut] = 1
+        co_clust.append(np.dot(ecut, ecut.T))
+    assert (co_clust[0] == co_clust[1]).all()
+
+
+def test_sparse_scikit_vs_scipy(global_random_seed):
+    # Test scikit linkage with full connectivity (i.e. unstructured) vs scipy
+    n, p, k = 10, 5, 3
+    rng = np.random.RandomState(global_random_seed)
+
+    # Not using a lil_matrix here, just to check that non sparse
+    # matrices are well handled
+    connectivity = np.ones((n, n))
+    for linkage in _TREE_BUILDERS.keys():
+        for i in range(5):
+            X = 0.1 * rng.normal(size=(n, p))
+            X -= 4.0 * np.arange(n)[:, np.newaxis]
+            X -= X.mean(axis=1)[:, np.newaxis]
+
+            out = hierarchy.linkage(X, method=linkage)
+
+            children_ = out[:, :2].astype(int, copy=False)
+            children, _, n_leaves, _ = _TREE_BUILDERS[linkage](
+                X, connectivity=connectivity
+            )
+
+            # Sort the order of child nodes per row for consistency
+            children.sort(axis=1)
+            assert_array_equal(
+                children,
+                children_,
+                "linkage tree differs from scipy impl for linkage: " + linkage,
+            )
+
+            cut = _hc_cut(k, children, n_leaves)
+            cut_ = _hc_cut(k, children_, n_leaves)
+            assess_same_labelling(cut, cut_)
+
+    # Test error management in _hc_cut
+    with pytest.raises(ValueError):
+        _hc_cut(n_leaves + 1, children, n_leaves)
+
+
+# Make sure our custom mst_linkage_core gives
+# the same results as scipy's builtin
+def test_vector_scikit_single_vs_scipy_single(global_random_seed):
+    n_samples, n_features, n_clusters = 10, 5, 3
+    rng = np.random.RandomState(global_random_seed)
+    X = 0.1 * rng.normal(size=(n_samples, n_features))
+    X -= 4.0 * np.arange(n_samples)[:, np.newaxis]
+    X -= X.mean(axis=1)[:, np.newaxis]
+
+    out = hierarchy.linkage(X, method="single")
+    children_scipy = out[:, :2].astype(int)
+
+    children, _, n_leaves, _ = _TREE_BUILDERS["single"](X)
+
+    # Sort the order of child nodes per row for consistency
+    children.sort(axis=1)
+    assert_array_equal(
+        children,
+        children_scipy,
+        "linkage tree differs from scipy impl for single linkage.",
+    )
+
+    cut = _hc_cut(n_clusters, children, n_leaves)
+    cut_scipy = _hc_cut(n_clusters, children_scipy, n_leaves)
+    assess_same_labelling(cut, cut_scipy)
+
+
+@pytest.mark.parametrize("metric_param_grid", METRICS_DEFAULT_PARAMS)
+def test_mst_linkage_core_memory_mapped(metric_param_grid):
+    """The MST-LINKAGE-CORE algorithm must work on mem-mapped dataset.
+
+    Non-regression test for issue #19875.
+    """
+    rng = np.random.RandomState(seed=1)
+    X = rng.normal(size=(20, 4))
+    Xmm = create_memmap_backed_data(X)
+    metric, param_grid = metric_param_grid
+    keys = param_grid.keys()
+    for vals in itertools.product(*param_grid.values()):
+        kwargs = dict(zip(keys, vals))
+        distance_metric = DistanceMetric.get_metric(metric, **kwargs)
+        mst = mst_linkage_core(X, distance_metric)
+        mst_mm = mst_linkage_core(Xmm, distance_metric)
+        np.testing.assert_equal(mst, mst_mm)
+
+
+def test_identical_points():
+    # Ensure identical points are handled correctly when using mst with
+    # a sparse connectivity matrix
+    X = np.array([[0, 0, 0], [0, 0, 0], [1, 1, 1], [1, 1, 1], [2, 2, 2], [2, 2, 2]])
+    true_labels = np.array([0, 0, 1, 1, 2, 2])
+    connectivity = kneighbors_graph(X, n_neighbors=3, include_self=False)
+    connectivity = 0.5 * (connectivity + connectivity.T)
+    connectivity, n_components = _fix_connectivity(X, connectivity, "euclidean")
+
+    for linkage in ("single", "average", "average", "ward"):
+        clustering = AgglomerativeClustering(
+            n_clusters=3, linkage=linkage, connectivity=connectivity
+        )
+        clustering.fit(X)
+
+        assert_almost_equal(
+            normalized_mutual_info_score(clustering.labels_, true_labels), 1
+        )
+
+
+def test_connectivity_propagation():
+    # Check that connectivity in the ward tree is propagated correctly during
+    # merging.
+    X = np.array(
+        [
+            (0.014, 0.120),
+            (0.014, 0.099),
+            (0.014, 0.097),
+            (0.017, 0.153),
+            (0.017, 0.153),
+            (0.018, 0.153),
+            (0.018, 0.153),
+            (0.018, 0.153),
+            (0.018, 0.153),
+            (0.018, 0.153),
+            (0.018, 0.153),
+            (0.018, 0.153),
+            (0.018, 0.152),
+            (0.018, 0.149),
+            (0.018, 0.144),
+        ]
+    )
+    connectivity = kneighbors_graph(X, 10, include_self=False)
+    ward = AgglomerativeClustering(
+        n_clusters=4, connectivity=connectivity, linkage="ward"
+    )
+    # If changes are not propagated correctly, fit crashes with an
+    # IndexError
+    ward.fit(X)
+
+
+def test_ward_tree_children_order(global_random_seed):
+    # Check that children are ordered in the same way for both structured and
+    # unstructured versions of ward_tree.
+
+    # test on five random datasets
+    n, p = 10, 5
+    rng = np.random.RandomState(global_random_seed)
+
+    connectivity = np.ones((n, n))
+    for i in range(5):
+        X = 0.1 * rng.normal(size=(n, p))
+        X -= 4.0 * np.arange(n)[:, np.newaxis]
+        X -= X.mean(axis=1)[:, np.newaxis]
+
+        out_unstructured = ward_tree(X)
+        out_structured = ward_tree(X, connectivity=connectivity)
+
+        assert_array_equal(out_unstructured[0], out_structured[0])
+
+
+def test_ward_linkage_tree_return_distance(global_random_seed):
+    # Test return_distance option on linkage and ward trees
+
+    # test that return_distance when set true, gives same
+    # output on both structured and unstructured clustering.
+    n, p = 10, 5
+    rng = np.random.RandomState(global_random_seed)
+
+    connectivity = np.ones((n, n))
+    for i in range(5):
+        X = 0.1 * rng.normal(size=(n, p))
+        X -= 4.0 * np.arange(n)[:, np.newaxis]
+        X -= X.mean(axis=1)[:, np.newaxis]
+
+        out_unstructured = ward_tree(X, return_distance=True)
+        out_structured = ward_tree(X, connectivity=connectivity, return_distance=True)
+
+        # get children
+        children_unstructured = out_unstructured[0]
+        children_structured = out_structured[0]
+
+        # check if we got the same clusters
+        assert_array_equal(children_unstructured, children_structured)
+
+        # check if the distances are the same
+        dist_unstructured = out_unstructured[-1]
+        dist_structured = out_structured[-1]
+
+        assert_array_almost_equal(dist_unstructured, dist_structured)
+
+        for linkage in ["average", "complete", "single"]:
+            structured_items = linkage_tree(
+                X, connectivity=connectivity, linkage=linkage, return_distance=True
+            )[-1]
+            unstructured_items = linkage_tree(X, linkage=linkage, return_distance=True)[
+                -1
+            ]
+            structured_dist = structured_items[-1]
+            unstructured_dist = unstructured_items[-1]
+            structured_children = structured_items[0]
+            unstructured_children = unstructured_items[0]
+            assert_array_almost_equal(structured_dist, unstructured_dist)
+            assert_array_almost_equal(structured_children, unstructured_children)
+
+    # test on the following dataset where we know the truth
+    # taken from scipy/cluster/tests/hierarchy_test_data.py
+    X = np.array(
+        [
+            [1.43054825, -7.5693489],
+            [6.95887839, 6.82293382],
+            [2.87137846, -9.68248579],
+            [7.87974764, -6.05485803],
+            [8.24018364, -6.09495602],
+            [7.39020262, 8.54004355],
+        ]
+    )
+    # truth
+    linkage_X_ward = np.array(
+        [
+            [3.0, 4.0, 0.36265956, 2.0],
+            [1.0, 5.0, 1.77045373, 2.0],
+            [0.0, 2.0, 2.55760419, 2.0],
+            [6.0, 8.0, 9.10208346, 4.0],
+            [7.0, 9.0, 24.7784379, 6.0],
+        ]
+    )
+
+    linkage_X_complete = np.array(
+        [
+            [3.0, 4.0, 0.36265956, 2.0],
+            [1.0, 5.0, 1.77045373, 2.0],
+            [0.0, 2.0, 2.55760419, 2.0],
+            [6.0, 8.0, 6.96742194, 4.0],
+            [7.0, 9.0, 18.77445997, 6.0],
+        ]
+    )
+
+    linkage_X_average = np.array(
+        [
+            [3.0, 4.0, 0.36265956, 2.0],
+            [1.0, 5.0, 1.77045373, 2.0],
+            [0.0, 2.0, 2.55760419, 2.0],
+            [6.0, 8.0, 6.55832839, 4.0],
+            [7.0, 9.0, 15.44089605, 6.0],
+        ]
+    )
+
+    n_samples, n_features = np.shape(X)
+    connectivity_X = np.ones((n_samples, n_samples))
+
+    out_X_unstructured = ward_tree(X, return_distance=True)
+    out_X_structured = ward_tree(X, connectivity=connectivity_X, return_distance=True)
+
+    # check that the labels are the same
+    assert_array_equal(linkage_X_ward[:, :2], out_X_unstructured[0])
+    assert_array_equal(linkage_X_ward[:, :2], out_X_structured[0])
+
+    # check that the distances are correct
+    assert_array_almost_equal(linkage_X_ward[:, 2], out_X_unstructured[4])
+    assert_array_almost_equal(linkage_X_ward[:, 2], out_X_structured[4])
+
+    linkage_options = ["complete", "average", "single"]
+    X_linkage_truth = [linkage_X_complete, linkage_X_average]
+    for linkage, X_truth in zip(linkage_options, X_linkage_truth):
+        out_X_unstructured = linkage_tree(X, return_distance=True, linkage=linkage)
+        out_X_structured = linkage_tree(
+            X, connectivity=connectivity_X, linkage=linkage, return_distance=True
+        )
+
+        # check that the labels are the same
+        assert_array_equal(X_truth[:, :2], out_X_unstructured[0])
+        assert_array_equal(X_truth[:, :2], out_X_structured[0])
+
+        # check that the distances are correct
+        assert_array_almost_equal(X_truth[:, 2], out_X_unstructured[4])
+        assert_array_almost_equal(X_truth[:, 2], out_X_structured[4])
+
+
+def test_connectivity_fixing_non_lil():
+    # Check non regression of a bug if a non item assignable connectivity is
+    # provided with more than one component.
+    # create dummy data
+    x = np.array([[0, 0], [1, 1]])
+    # create a mask with several components to force connectivity fixing
+    m = np.array([[True, False], [False, True]])
+    c = grid_to_graph(n_x=2, n_y=2, mask=m)
+    w = AgglomerativeClustering(connectivity=c, linkage="ward")
+    with pytest.warns(UserWarning):
+        w.fit(x)
+
+
+def test_int_float_dict():
+    rng = np.random.RandomState(0)
+    keys = np.unique(rng.randint(100, size=10).astype(np.intp, copy=False))
+    values = rng.rand(len(keys))
+
+    d = IntFloatDict(keys, values)
+    for key, value in zip(keys, values):
+        assert d[key] == value
+
+    other_keys = np.arange(50, dtype=np.intp)[::2]
+    other_values = np.full(50, 0.5)[::2]
+    other = IntFloatDict(other_keys, other_values)
+    # Complete smoke test
+    max_merge(d, other, mask=np.ones(100, dtype=np.intp), n_a=1, n_b=1)
+    average_merge(d, other, mask=np.ones(100, dtype=np.intp), n_a=1, n_b=1)
+
+
+def test_connectivity_callable():
+    rng = np.random.RandomState(0)
+    X = rng.rand(20, 5)
+    connectivity = kneighbors_graph(X, 3, include_self=False)
+    aglc1 = AgglomerativeClustering(connectivity=connectivity)
+    aglc2 = AgglomerativeClustering(
+        connectivity=partial(kneighbors_graph, n_neighbors=3, include_self=False)
+    )
+    aglc1.fit(X)
+    aglc2.fit(X)
+    assert_array_equal(aglc1.labels_, aglc2.labels_)
+
+
+def test_connectivity_ignores_diagonal():
+    rng = np.random.RandomState(0)
+    X = rng.rand(20, 5)
+    connectivity = kneighbors_graph(X, 3, include_self=False)
+    connectivity_include_self = kneighbors_graph(X, 3, include_self=True)
+    aglc1 = AgglomerativeClustering(connectivity=connectivity)
+    aglc2 = AgglomerativeClustering(connectivity=connectivity_include_self)
+    aglc1.fit(X)
+    aglc2.fit(X)
+    assert_array_equal(aglc1.labels_, aglc2.labels_)
+
+
+def test_compute_full_tree():
+    # Test that the full tree is computed if n_clusters is small
+    rng = np.random.RandomState(0)
+    X = rng.randn(10, 2)
+    connectivity = kneighbors_graph(X, 5, include_self=False)
+
+    # When n_clusters is less, the full tree should be built
+    # that is the number of merges should be n_samples - 1
+    agc = AgglomerativeClustering(n_clusters=2, connectivity=connectivity)
+    agc.fit(X)
+    n_samples = X.shape[0]
+    n_nodes = agc.children_.shape[0]
+    assert n_nodes == n_samples - 1
+
+    # When n_clusters is large, greater than max of 100 and 0.02 * n_samples.
+    # we should stop when there are n_clusters.
+    n_clusters = 101
+    X = rng.randn(200, 2)
+    connectivity = kneighbors_graph(X, 10, include_self=False)
+    agc = AgglomerativeClustering(n_clusters=n_clusters, connectivity=connectivity)
+    agc.fit(X)
+    n_samples = X.shape[0]
+    n_nodes = agc.children_.shape[0]
+    assert n_nodes == n_samples - n_clusters
+
+
+def test_n_components():
+    # Test n_components returned by linkage, average and ward tree
+    rng = np.random.RandomState(0)
+    X = rng.rand(5, 5)
+
+    # Connectivity matrix having five components.
+    connectivity = np.eye(5)
+
+    for linkage_func in _TREE_BUILDERS.values():
+        assert ignore_warnings(linkage_func)(X, connectivity=connectivity)[1] == 5
+
+
+def test_affinity_passed_to_fix_connectivity():
+    # Test that the affinity parameter is actually passed to the pairwise
+    # function
+
+    size = 2
+    rng = np.random.RandomState(0)
+    X = rng.randn(size, size)
+    mask = np.array([True, False, False, True])
+
+    connectivity = grid_to_graph(n_x=size, n_y=size, mask=mask, return_as=np.ndarray)
+
+    class FakeAffinity:
+        def __init__(self):
+            self.counter = 0
+
+        def increment(self, *args, **kwargs):
+            self.counter += 1
+            return self.counter
+
+    fa = FakeAffinity()
+
+    linkage_tree(X, connectivity=connectivity, affinity=fa.increment)
+
+    assert fa.counter == 3
+
+
+@pytest.mark.parametrize("linkage", ["ward", "complete", "average"])
+def test_agglomerative_clustering_with_distance_threshold(linkage, global_random_seed):
+    # Check that we obtain the correct number of clusters with
+    # agglomerative clustering with distance_threshold.
+    rng = np.random.RandomState(global_random_seed)
+    mask = np.ones([10, 10], dtype=bool)
+    n_samples = 100
+    X = rng.randn(n_samples, 50)
+    connectivity = grid_to_graph(*mask.shape)
+    # test when distance threshold is set to 10
+    distance_threshold = 10
+    for conn in [None, connectivity]:
+        clustering = AgglomerativeClustering(
+            n_clusters=None,
+            distance_threshold=distance_threshold,
+            connectivity=conn,
+            linkage=linkage,
+        )
+        clustering.fit(X)
+        clusters_produced = clustering.labels_
+        num_clusters_produced = len(np.unique(clustering.labels_))
+        # test if the clusters produced match the point in the linkage tree
+        # where the distance exceeds the threshold
+        tree_builder = _TREE_BUILDERS[linkage]
+        children, n_components, n_leaves, parent, distances = tree_builder(
+            X, connectivity=conn, n_clusters=None, return_distance=True
+        )
+        num_clusters_at_threshold = (
+            np.count_nonzero(distances >= distance_threshold) + 1
+        )
+        # test number of clusters produced
+        assert num_clusters_at_threshold == num_clusters_produced
+        # test clusters produced
+        clusters_at_threshold = _hc_cut(
+            n_clusters=num_clusters_produced, children=children, n_leaves=n_leaves
+        )
+        assert np.array_equiv(clusters_produced, clusters_at_threshold)
+
+
+def test_small_distance_threshold(global_random_seed):
+    rng = np.random.RandomState(global_random_seed)
+    n_samples = 10
+    X = rng.randint(-300, 300, size=(n_samples, 3))
+    # this should result in all data in their own clusters, given that
+    # their pairwise distances are bigger than .1 (which may not be the case
+    # with a different random seed).
+    clustering = AgglomerativeClustering(
+        n_clusters=None, distance_threshold=1.0, linkage="single"
+    ).fit(X)
+    # check that the pairwise distances are indeed all larger than .1
+    all_distances = pairwise_distances(X, metric="minkowski", p=2)
+    np.fill_diagonal(all_distances, np.inf)
+    assert np.all(all_distances > 0.1)
+    assert clustering.n_clusters_ == n_samples
+
+
+def test_cluster_distances_with_distance_threshold(global_random_seed):
+    rng = np.random.RandomState(global_random_seed)
+    n_samples = 100
+    X = rng.randint(-10, 10, size=(n_samples, 3))
+    # check the distances within the clusters and with other clusters
+    distance_threshold = 4
+    clustering = AgglomerativeClustering(
+        n_clusters=None, distance_threshold=distance_threshold, linkage="single"
+    ).fit(X)
+    labels = clustering.labels_
+    D = pairwise_distances(X, metric="minkowski", p=2)
+    # to avoid taking the 0 diagonal in min()
+    np.fill_diagonal(D, np.inf)
+    for label in np.unique(labels):
+        in_cluster_mask = labels == label
+        max_in_cluster_distance = (
+            D[in_cluster_mask][:, in_cluster_mask].min(axis=0).max()
+        )
+        min_out_cluster_distance = (
+            D[in_cluster_mask][:, ~in_cluster_mask].min(axis=0).min()
+        )
+        # single data point clusters only have that inf diagonal here
+        if in_cluster_mask.sum() > 1:
+            assert max_in_cluster_distance < distance_threshold
+        assert min_out_cluster_distance >= distance_threshold
+
+
+@pytest.mark.parametrize("linkage", ["ward", "complete", "average"])
+@pytest.mark.parametrize(
+    ("threshold", "y_true"), [(0.5, [1, 0]), (1.0, [1, 0]), (1.5, [0, 0])]
+)
+def test_agglomerative_clustering_with_distance_threshold_edge_case(
+    linkage, threshold, y_true
+):
+    # test boundary case of distance_threshold matching the distance
+    X = [[0], [1]]
+    clusterer = AgglomerativeClustering(
+        n_clusters=None, distance_threshold=threshold, linkage=linkage
+    )
+    y_pred = clusterer.fit_predict(X)
+    assert adjusted_rand_score(y_true, y_pred) == 1
+
+
+def test_dist_threshold_invalid_parameters():
+    X = [[0], [1]]
+    with pytest.raises(ValueError, match="Exactly one of "):
+        AgglomerativeClustering(n_clusters=None, distance_threshold=None).fit(X)
+
+    with pytest.raises(ValueError, match="Exactly one of "):
+        AgglomerativeClustering(n_clusters=2, distance_threshold=1).fit(X)
+
+    X = [[0], [1]]
+    with pytest.raises(ValueError, match="compute_full_tree must be True if"):
+        AgglomerativeClustering(
+            n_clusters=None, distance_threshold=1, compute_full_tree=False
+        ).fit(X)
+
+
+def test_invalid_shape_precomputed_dist_matrix():
+    # Check that an error is raised when affinity='precomputed'
+    # and a non square matrix is passed (PR #16257).
+    rng = np.random.RandomState(0)
+    X = rng.rand(5, 3)
+    with pytest.raises(
+        ValueError,
+        match=r"Distance matrix should be square, got matrix of shape \(5, 3\)",
+    ):
+        AgglomerativeClustering(metric="precomputed", linkage="complete").fit(X)
+
+
+def test_precomputed_connectivity_metric_with_2_connected_components():
+    """Check that connecting components works when connectivity and
+    affinity are both precomputed and the number of connected components is
+    greater than 1. Non-regression test for #16151.
+    """
+
+    connectivity_matrix = np.array(
+        [
+            [0, 1, 1, 0, 0],
+            [0, 0, 1, 0, 0],
+            [0, 0, 0, 0, 0],
+            [0, 0, 0, 0, 1],
+            [0, 0, 0, 0, 0],
+        ]
+    )
+    # ensure that connectivity_matrix has two connected components
+    assert connected_components(connectivity_matrix)[0] == 2
+
+    rng = np.random.RandomState(0)
+    X = rng.randn(5, 10)
+
+    X_dist = pairwise_distances(X)
+    clusterer_precomputed = AgglomerativeClustering(
+        metric="precomputed", connectivity=connectivity_matrix, linkage="complete"
+    )
+    msg = "Completing it to avoid stopping the tree early"
+    with pytest.warns(UserWarning, match=msg):
+        clusterer_precomputed.fit(X_dist)
+
+    clusterer = AgglomerativeClustering(
+        connectivity=connectivity_matrix, linkage="complete"
+    )
+    with pytest.warns(UserWarning, match=msg):
+        clusterer.fit(X)
+
+    assert_array_equal(clusterer.labels_, clusterer_precomputed.labels_)
+    assert_array_equal(clusterer.children_, clusterer_precomputed.children_)

linedance-app/venv/lib/python3.12/site-packages/sklearn/cluster/tests/test_mean_shift.py

@@ -0,0 +1,218 @@
+"""
+Testing for mean shift clustering methods
+
+"""
+
+import warnings
+
+import numpy as np
+import pytest
+
+from sklearn.cluster import MeanShift, estimate_bandwidth, get_bin_seeds, mean_shift
+from sklearn.datasets import make_blobs
+from sklearn.metrics import v_measure_score
+from sklearn.utils._testing import assert_allclose, assert_array_equal
+
+n_clusters = 3
+centers = np.array([[1, 1], [-1, -1], [1, -1]]) + 10
+X, _ = make_blobs(
+    n_samples=300,
+    n_features=2,
+    centers=centers,
+    cluster_std=0.4,
+    shuffle=True,
+    random_state=11,
+)
+
+
+def test_convergence_of_1d_constant_data():
+    # Test convergence using 1D constant data
+    # Non-regression test for:
+    # https://github.com/scikit-learn/scikit-learn/issues/28926
+    model = MeanShift()
+    n_iter = model.fit(np.ones(10).reshape(-1, 1)).n_iter_
+    assert n_iter < model.max_iter
+
+
+def test_estimate_bandwidth():
+    # Test estimate_bandwidth
+    bandwidth = estimate_bandwidth(X, n_samples=200)
+    assert 0.9 <= bandwidth <= 1.5
+
+
+def test_estimate_bandwidth_1sample(global_dtype):
+    # Test estimate_bandwidth when n_samples=1 and quantile<1, so that
+    # n_neighbors is set to 1.
+    bandwidth = estimate_bandwidth(
+        X.astype(global_dtype, copy=False), n_samples=1, quantile=0.3
+    )
+
+    assert bandwidth.dtype == X.dtype
+    assert bandwidth == pytest.approx(0.0, abs=1e-5)
+
+
+@pytest.mark.parametrize(
+    "bandwidth, cluster_all, expected, first_cluster_label",
+    [(1.2, True, 3, 0), (1.2, False, 4, -1)],
+)
+def test_mean_shift(
+    global_dtype, bandwidth, cluster_all, expected, first_cluster_label
+):
+    # Test MeanShift algorithm
+    X_with_global_dtype = X.astype(global_dtype, copy=False)
+    ms = MeanShift(bandwidth=bandwidth, cluster_all=cluster_all)
+    labels = ms.fit(X_with_global_dtype).labels_
+    labels_unique = np.unique(labels)
+    n_clusters_ = len(labels_unique)
+    assert n_clusters_ == expected
+    assert labels_unique[0] == first_cluster_label
+    assert ms.cluster_centers_.dtype == global_dtype
+
+    cluster_centers, labels_mean_shift = mean_shift(
+        X_with_global_dtype, cluster_all=cluster_all
+    )
+    labels_mean_shift_unique = np.unique(labels_mean_shift)
+    n_clusters_mean_shift = len(labels_mean_shift_unique)
+    assert n_clusters_mean_shift == expected
+    assert labels_mean_shift_unique[0] == first_cluster_label
+    assert cluster_centers.dtype == global_dtype
+
+
+# TODO: remove mark once loky bug is fixed:
+# https://github.com/joblib/loky/issues/458
+@pytest.mark.thread_unsafe
+def test_parallel(global_dtype, global_random_seed):
+    centers = np.array([[1, 1], [-1, -1], [1, -1]]) + 10
+    X, _ = make_blobs(
+        n_samples=50,
+        n_features=2,
+        centers=centers,
+        cluster_std=0.4,
+        shuffle=True,
+        random_state=global_random_seed,
+    )
+
+    X = X.astype(global_dtype, copy=False)
+
+    ms1 = MeanShift(n_jobs=2)
+    ms1.fit(X)
+
+    ms2 = MeanShift()
+    ms2.fit(X)
+
+    assert_allclose(ms1.cluster_centers_, ms2.cluster_centers_)
+    assert ms1.cluster_centers_.dtype == ms2.cluster_centers_.dtype
+    assert_array_equal(ms1.labels_, ms2.labels_)
+
+
+def test_meanshift_predict(global_dtype):
+    # Test MeanShift.predict
+    ms = MeanShift(bandwidth=1.2)
+    X_with_global_dtype = X.astype(global_dtype, copy=False)
+    labels = ms.fit_predict(X_with_global_dtype)
+    labels2 = ms.predict(X_with_global_dtype)
+    assert_array_equal(labels, labels2)
+
+
+def test_meanshift_all_orphans():
+    # init away from the data, crash with a sensible warning
+    ms = MeanShift(bandwidth=0.1, seeds=[[-9, -9], [-10, -10]])
+    msg = "No point was within bandwidth=0.1"
+    with pytest.raises(ValueError, match=msg):
+        ms.fit(
+            X,
+        )
+
+
+def test_unfitted():
+    # Non-regression: before fit, there should be not fitted attributes.
+    ms = MeanShift()
+    assert not hasattr(ms, "cluster_centers_")
+    assert not hasattr(ms, "labels_")
+
+
+def test_cluster_intensity_tie(global_dtype):
+    X = np.array([[1, 1], [2, 1], [1, 0], [4, 7], [3, 5], [3, 6]], dtype=global_dtype)
+    c1 = MeanShift(bandwidth=2).fit(X)
+
+    X = np.array([[4, 7], [3, 5], [3, 6], [1, 1], [2, 1], [1, 0]], dtype=global_dtype)
+    c2 = MeanShift(bandwidth=2).fit(X)
+    assert_array_equal(c1.labels_, [1, 1, 1, 0, 0, 0])
+    assert_array_equal(c2.labels_, [0, 0, 0, 1, 1, 1])
+
+
+def test_bin_seeds(global_dtype):
+    # Test the bin seeding technique which can be used in the mean shift
+    # algorithm
+    # Data is just 6 points in the plane
+    X = np.array(
+        [[1.0, 1.0], [1.4, 1.4], [1.8, 1.2], [2.0, 1.0], [2.1, 1.1], [0.0, 0.0]],
+        dtype=global_dtype,
+    )
+
+    # With a bin coarseness of 1.0 and min_bin_freq of 1, 3 bins should be
+    # found
+    ground_truth = {(1.0, 1.0), (2.0, 1.0), (0.0, 0.0)}
+    test_bins = get_bin_seeds(X, 1, 1)
+    test_result = set(tuple(p) for p in test_bins)
+    assert len(ground_truth.symmetric_difference(test_result)) == 0
+
+    # With a bin coarseness of 1.0 and min_bin_freq of 2, 2 bins should be
+    # found
+    ground_truth = {(1.0, 1.0), (2.0, 1.0)}
+    test_bins = get_bin_seeds(X, 1, 2)
+    test_result = set(tuple(p) for p in test_bins)
+    assert len(ground_truth.symmetric_difference(test_result)) == 0
+
+    # With a bin size of 0.01 and min_bin_freq of 1, 6 bins should be found
+    # we bail and use the whole data here.
+    with warnings.catch_warnings(record=True):
+        test_bins = get_bin_seeds(X, 0.01, 1)
+    assert_allclose(test_bins, X)
+
+    # tight clusters around [0, 0] and [1, 1], only get two bins
+    X, _ = make_blobs(
+        n_samples=100,
+        n_features=2,
+        centers=[[0, 0], [1, 1]],
+        cluster_std=0.1,
+        random_state=0,
+    )
+    X = X.astype(global_dtype, copy=False)
+    test_bins = get_bin_seeds(X, 1)
+    assert_array_equal(test_bins, [[0, 0], [1, 1]])
+
+
+@pytest.mark.parametrize("max_iter", [1, 100])
+def test_max_iter(max_iter):
+    clusters1, _ = mean_shift(X, max_iter=max_iter)
+    ms = MeanShift(max_iter=max_iter).fit(X)
+    clusters2 = ms.cluster_centers_
+
+    assert ms.n_iter_ <= ms.max_iter
+    assert len(clusters1) == len(clusters2)
+
+    for c1, c2 in zip(clusters1, clusters2):
+        assert np.allclose(c1, c2)
+
+
+def test_mean_shift_zero_bandwidth(global_dtype):
+    # Check that mean shift works when the estimated bandwidth is 0.
+    X = np.array([1, 1, 1, 2, 2, 2, 3, 3], dtype=global_dtype).reshape(-1, 1)
+
+    # estimate_bandwidth with default args returns 0 on this dataset
+    bandwidth = estimate_bandwidth(X)
+    assert bandwidth == 0
+
+    # get_bin_seeds with a 0 bin_size should return the dataset itself
+    assert get_bin_seeds(X, bin_size=bandwidth) is X
+
+    # MeanShift with binning and a 0 estimated bandwidth should be equivalent
+    # to no binning.
+    ms_binning = MeanShift(bin_seeding=True, bandwidth=None).fit(X)
+    ms_nobinning = MeanShift(bin_seeding=False).fit(X)
+    expected_labels = np.array([0, 0, 0, 1, 1, 1, 2, 2])
+
+    assert v_measure_score(ms_binning.labels_, expected_labels) == pytest.approx(1)
+    assert v_measure_score(ms_nobinning.labels_, expected_labels) == pytest.approx(1)
+    assert_allclose(ms_binning.cluster_centers_, ms_nobinning.cluster_centers_)

linedance-app/venv/lib/python3.12/site-packages/sklearn/cluster/tests/test_optics.py

@@ -0,0 +1,874 @@
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
+import warnings
+
+import numpy as np
+import pytest
+
+from sklearn.cluster import DBSCAN, OPTICS
+from sklearn.cluster._optics import _extend_region, _extract_xi_labels
+from sklearn.cluster.tests.common import generate_clustered_data
+from sklearn.datasets import make_blobs
+from sklearn.exceptions import DataConversionWarning, EfficiencyWarning
+from sklearn.metrics.cluster import contingency_matrix
+from sklearn.metrics.pairwise import pairwise_distances
+from sklearn.utils import shuffle
+from sklearn.utils._testing import assert_allclose, assert_array_equal
+from sklearn.utils.fixes import CSR_CONTAINERS
+
+rng = np.random.RandomState(0)
+n_points_per_cluster = 10
+C1 = [-5, -2] + 0.8 * rng.randn(n_points_per_cluster, 2)
+C2 = [4, -1] + 0.1 * rng.randn(n_points_per_cluster, 2)
+C3 = [1, -2] + 0.2 * rng.randn(n_points_per_cluster, 2)
+C4 = [-2, 3] + 0.3 * rng.randn(n_points_per_cluster, 2)
+C5 = [3, -2] + 1.6 * rng.randn(n_points_per_cluster, 2)
+C6 = [5, 6] + 2 * rng.randn(n_points_per_cluster, 2)
+X = np.vstack((C1, C2, C3, C4, C5, C6))
+
+
+@pytest.mark.parametrize(
+    ("r_plot", "end"),
+    [
+        [[10, 8.9, 8.8, 8.7, 7, 10], 3],
+        [[10, 8.9, 8.8, 8.7, 8.6, 7, 10], 0],
+        [[10, 8.9, 8.8, 8.7, 7, 6, np.inf], 4],
+        [[10, 8.9, 8.8, 8.7, 7, 6, np.inf], 4],
+    ],
+)
+def test_extend_downward(r_plot, end):
+    r_plot = np.array(r_plot)
+    ratio = r_plot[:-1] / r_plot[1:]
+    steep_downward = ratio >= 1 / 0.9
+    upward = ratio < 1
+
+    e = _extend_region(steep_downward, upward, 0, 2)
+    assert e == end
+
+
+@pytest.mark.parametrize(
+    ("r_plot", "end"),
+    [
+        [[1, 2, 2.1, 2.2, 4, 8, 8, np.inf], 6],
+        [[1, 2, 2.1, 2.2, 2.3, 4, 8, 8, np.inf], 0],
+        [[1, 2, 2.1, 2, np.inf], 0],
+        [[1, 2, 2.1, np.inf], 2],
+    ],
+)
+def test_extend_upward(r_plot, end):
+    r_plot = np.array(r_plot)
+    ratio = r_plot[:-1] / r_plot[1:]
+    steep_upward = ratio <= 0.9
+    downward = ratio > 1
+
+    e = _extend_region(steep_upward, downward, 0, 2)
+    assert e == end
+
+
+@pytest.mark.parametrize(
+    ("ordering", "clusters", "expected"),
+    [
+        [[0, 1, 2, 3], [[0, 1], [2, 3]], [0, 0, 1, 1]],
+        [[0, 1, 2, 3], [[0, 1], [3, 3]], [0, 0, -1, 1]],
+        [[0, 1, 2, 3], [[0, 1], [3, 3], [0, 3]], [0, 0, -1, 1]],
+        [[3, 1, 2, 0], [[0, 1], [3, 3], [0, 3]], [1, 0, -1, 0]],
+    ],
+)
+def test_the_extract_xi_labels(ordering, clusters, expected):
+    labels = _extract_xi_labels(ordering, clusters)
+
+    assert_array_equal(labels, expected)
+
+
+def test_extract_xi(global_dtype):
+    # small and easy test (no clusters around other clusters)
+    # but with a clear noise data.
+    # global_random_seed is not used here since the expected labels
+    # are hardcoded for these specific data.
+    rng = np.random.RandomState(0)
+    n_points_per_cluster = 5
+
+    C1 = [-5, -2] + 0.8 * rng.randn(n_points_per_cluster, 2)
+    C2 = [4, -1] + 0.1 * rng.randn(n_points_per_cluster, 2)
+    C3 = [1, -2] + 0.2 * rng.randn(n_points_per_cluster, 2)
+    C4 = [-2, 3] + 0.3 * rng.randn(n_points_per_cluster, 2)
+    C5 = [3, -2] + 0.6 * rng.randn(n_points_per_cluster, 2)
+    C6 = [5, 6] + 0.2 * rng.randn(n_points_per_cluster, 2)
+
+    X = np.vstack((C1, C2, C3, C4, C5, np.array([[100, 100]]), C6)).astype(
+        global_dtype, copy=False
+    )
+    expected_labels = np.r_[[2] * 5, [0] * 5, [1] * 5, [3] * 5, [1] * 5, -1, [4] * 5]
+    X, expected_labels = shuffle(X, expected_labels, random_state=rng)
+
+    clust = OPTICS(
+        min_samples=3, min_cluster_size=2, max_eps=20, cluster_method="xi", xi=0.4
+    ).fit(X)
+    assert_array_equal(clust.labels_, expected_labels)
+
+    # check float min_samples and min_cluster_size
+    clust = OPTICS(
+        min_samples=0.1, min_cluster_size=0.08, max_eps=20, cluster_method="xi", xi=0.4
+    ).fit(X)
+    assert_array_equal(clust.labels_, expected_labels)
+
+    X = np.vstack((C1, C2, C3, C4, C5, np.array([[100, 100]] * 2), C6)).astype(
+        global_dtype, copy=False
+    )
+    expected_labels = np.r_[
+        [1] * 5, [3] * 5, [2] * 5, [0] * 5, [2] * 5, -1, -1, [4] * 5
+    ]
+    X, expected_labels = shuffle(X, expected_labels, random_state=rng)
+
+    clust = OPTICS(
+        min_samples=3, min_cluster_size=3, max_eps=20, cluster_method="xi", xi=0.3
+    ).fit(X)
+    # this may fail if the predecessor correction is not at work!
+    assert_array_equal(clust.labels_, expected_labels)
+
+    C1 = [[0, 0], [0, 0.1], [0, -0.1], [0.1, 0]]
+    C2 = [[10, 10], [10, 9], [10, 11], [9, 10]]
+    C3 = [[100, 100], [100, 90], [100, 110], [90, 100]]
+    X = np.vstack((C1, C2, C3)).astype(global_dtype, copy=False)
+    expected_labels = np.r_[[0] * 4, [1] * 4, [2] * 4]
+    X, expected_labels = shuffle(X, expected_labels, random_state=rng)
+
+    clust = OPTICS(
+        min_samples=2, min_cluster_size=2, max_eps=np.inf, cluster_method="xi", xi=0.04
+    ).fit(X)
+    assert_array_equal(clust.labels_, expected_labels)
+
+
+def test_cluster_hierarchy(global_dtype, global_random_seed):
+    rng = np.random.RandomState(global_random_seed)
+    n_points_per_cluster = 100
+    C1 = [0, 0] + 2 * rng.randn(n_points_per_cluster, 2).astype(
+        global_dtype, copy=False
+    )
+    C2 = [0, 0] + 50 * rng.randn(n_points_per_cluster, 2).astype(
+        global_dtype, copy=False
+    )
+    X = np.vstack((C1, C2))
+    X = shuffle(X, random_state=rng)
+
+    clusters = OPTICS(min_samples=20, xi=0.2).fit(X).cluster_hierarchy_
+    assert clusters.shape == (2, 2)
+
+    # The first cluster should contain all point from C1 but due to how the data is
+    # generated, some points from C2 may end up in it.
+    assert 100 <= np.diff(clusters[0]) + 1 <= 115
+    # The second cluster should contain all points from C1 and C2.
+    assert np.diff(clusters[-1]) + 1 == 200
+
+
+@pytest.mark.parametrize(
+    "csr_container, metric",
+    [(None, "minkowski")] + [(container, "euclidean") for container in CSR_CONTAINERS],
+)
+def test_correct_number_of_clusters(metric, csr_container):
+    # in 'auto' mode
+
+    n_clusters = 3
+    X = generate_clustered_data(n_clusters=n_clusters)
+    # Parameters chosen specifically for this task.
+    # Compute OPTICS
+    clust = OPTICS(max_eps=5.0 * 6.0, min_samples=4, xi=0.1, metric=metric)
+    clust.fit(csr_container(X) if csr_container is not None else X)
+    # number of clusters, ignoring noise if present
+    n_clusters_1 = len(set(clust.labels_)) - int(-1 in clust.labels_)
+    assert n_clusters_1 == n_clusters
+
+    # check attribute types and sizes
+    assert clust.labels_.shape == (len(X),)
+    assert clust.labels_.dtype.kind == "i"
+
+    assert clust.reachability_.shape == (len(X),)
+    assert clust.reachability_.dtype.kind == "f"
+
+    assert clust.core_distances_.shape == (len(X),)
+    assert clust.core_distances_.dtype.kind == "f"
+
+    assert clust.ordering_.shape == (len(X),)
+    assert clust.ordering_.dtype.kind == "i"
+    assert set(clust.ordering_) == set(range(len(X)))
+
+
+def test_minimum_number_of_sample_check():
+    # test that we check a minimum number of samples
+    msg = "min_samples must be no greater than"
+
+    # Compute OPTICS
+    X = [[1, 1]]
+    clust = OPTICS(max_eps=5.0 * 0.3, min_samples=10, min_cluster_size=1.0)
+
+    # Run the fit
+    with pytest.raises(ValueError, match=msg):
+        clust.fit(X)
+
+
+def test_bad_extract():
+    # Test an extraction of eps too close to original eps
+    msg = "Specify an epsilon smaller than 0.15. Got 0.3."
+    centers = [[1, 1], [-1, -1], [1, -1]]
+    X, labels_true = make_blobs(
+        n_samples=750, centers=centers, cluster_std=0.4, random_state=0
+    )
+
+    # Compute OPTICS
+    clust = OPTICS(max_eps=5.0 * 0.03, cluster_method="dbscan", eps=0.3, min_samples=10)
+    with pytest.raises(ValueError, match=msg):
+        clust.fit(X)
+
+
+def test_bad_reachability():
+    msg = "All reachability values are inf. Set a larger max_eps."
+    centers = [[1, 1], [-1, -1], [1, -1]]
+    X, labels_true = make_blobs(
+        n_samples=750, centers=centers, cluster_std=0.4, random_state=0
+    )
+
+    with pytest.warns(UserWarning, match=msg):
+        clust = OPTICS(max_eps=5.0 * 0.003, min_samples=10, eps=0.015)
+        clust.fit(X)
+
+
+def test_nowarn_if_metric_bool_data_bool():
+    # make sure no warning is raised if metric and data are both boolean
+    # non-regression test for
+    # https://github.com/scikit-learn/scikit-learn/issues/18996
+
+    pairwise_metric = "rogerstanimoto"
+    X = np.random.randint(2, size=(5, 2), dtype=bool)
+
+    with warnings.catch_warnings():
+        warnings.simplefilter("error", DataConversionWarning)
+
+        OPTICS(metric=pairwise_metric).fit(X)
+
+
+def test_warn_if_metric_bool_data_no_bool():
+    # make sure a *single* conversion warning is raised if metric is boolean
+    # but data isn't
+    # non-regression test for
+    # https://github.com/scikit-learn/scikit-learn/issues/18996
+
+    pairwise_metric = "rogerstanimoto"
+    X = np.random.randint(2, size=(5, 2), dtype=np.int32)
+    msg = f"Data will be converted to boolean for metric {pairwise_metric}"
+
+    with pytest.warns(DataConversionWarning, match=msg) as warn_record:
+        # Silence a DeprecationWarning from joblib <= 1.5.1 in Python 3.14+.
+        warnings.filterwarnings(
+            "ignore",
+            message="'asyncio.iscoroutinefunction' is deprecated",
+            category=DeprecationWarning,
+        )
+        OPTICS(metric=pairwise_metric).fit(X)
+        assert len(warn_record) == 1
+
+
+def test_nowarn_if_metric_no_bool():
+    # make sure no conversion warning is raised if
+    # metric isn't boolean, no matter what the data type is
+    pairwise_metric = "minkowski"
+    X_bool = np.random.randint(2, size=(5, 2), dtype=bool)
+    X_num = np.random.randint(2, size=(5, 2), dtype=np.int32)
+
+    with warnings.catch_warnings():
+        warnings.simplefilter("error", DataConversionWarning)
+
+        # fit boolean data
+        OPTICS(metric=pairwise_metric).fit(X_bool)
+        # fit numeric data
+        OPTICS(metric=pairwise_metric).fit(X_num)
+
+
+def test_close_extract():
+    # Test extract where extraction eps is close to scaled max_eps
+
+    centers = [[1, 1], [-1, -1], [1, -1]]
+    X, labels_true = make_blobs(
+        n_samples=750, centers=centers, cluster_std=0.4, random_state=0
+    )
+
+    # Compute OPTICS
+    clust = OPTICS(max_eps=1.0, cluster_method="dbscan", eps=0.3, min_samples=10).fit(X)
+    # Cluster ordering starts at 0; max cluster label = 2 is 3 clusters
+    assert max(clust.labels_) == 2
+
+
+@pytest.mark.parametrize("eps", [0.1, 0.3, 0.5])
+@pytest.mark.parametrize("min_samples", [3, 10, 20])
+@pytest.mark.parametrize(
+    "csr_container, metric",
+    [(None, "minkowski"), (None, "euclidean")]
+    + [(container, "euclidean") for container in CSR_CONTAINERS],
+)
+def test_dbscan_optics_parity(eps, min_samples, metric, global_dtype, csr_container):
+    # Test that OPTICS clustering labels are <= 5% difference of DBSCAN
+
+    centers = [[1, 1], [-1, -1], [1, -1]]
+    X, labels_true = make_blobs(
+        n_samples=150, centers=centers, cluster_std=0.4, random_state=0
+    )
+    X = csr_container(X) if csr_container is not None else X
+
+    X = X.astype(global_dtype, copy=False)
+
+    # calculate optics with dbscan extract at 0.3 epsilon
+    op = OPTICS(
+        min_samples=min_samples, cluster_method="dbscan", eps=eps, metric=metric
+    ).fit(X)
+
+    # calculate dbscan labels
+    db = DBSCAN(eps=eps, min_samples=min_samples).fit(X)
+
+    contingency = contingency_matrix(db.labels_, op.labels_)
+    agree = min(
+        np.sum(np.max(contingency, axis=0)), np.sum(np.max(contingency, axis=1))
+    )
+    disagree = X.shape[0] - agree
+
+    percent_mismatch = np.round((disagree - 1) / X.shape[0], 2)
+
+    # verify label mismatch is <= 5% labels
+    assert percent_mismatch <= 0.05
+
+
+def test_min_samples_edge_case(global_dtype):
+    C1 = [[0, 0], [0, 0.1], [0, -0.1]]
+    C2 = [[10, 10], [10, 9], [10, 11]]
+    C3 = [[100, 100], [100, 96], [100, 106]]
+    X = np.vstack((C1, C2, C3)).astype(global_dtype, copy=False)
+
+    expected_labels = np.r_[[0] * 3, [1] * 3, [2] * 3]
+    clust = OPTICS(min_samples=3, max_eps=7, cluster_method="xi", xi=0.04).fit(X)
+    assert_array_equal(clust.labels_, expected_labels)
+
+    expected_labels = np.r_[[0] * 3, [1] * 3, [-1] * 3]
+    clust = OPTICS(min_samples=3, max_eps=3, cluster_method="xi", xi=0.04).fit(X)
+    assert_array_equal(clust.labels_, expected_labels)
+
+    expected_labels = np.r_[[-1] * 9]
+    with pytest.warns(UserWarning, match="All reachability values"):
+        clust = OPTICS(min_samples=4, max_eps=3, cluster_method="xi", xi=0.04).fit(X)
+        assert_array_equal(clust.labels_, expected_labels)
+
+
+# try arbitrary minimum sizes
+@pytest.mark.parametrize("min_cluster_size", range(2, X.shape[0] // 10, 23))
+def test_min_cluster_size(min_cluster_size, global_dtype):
+    redX = X[::2].astype(global_dtype, copy=False)  # reduce for speed
+    clust = OPTICS(min_samples=9, min_cluster_size=min_cluster_size).fit(redX)
+    cluster_sizes = np.bincount(clust.labels_[clust.labels_ != -1])
+    if cluster_sizes.size:
+        assert min(cluster_sizes) >= min_cluster_size
+    # check behaviour is the same when min_cluster_size is a fraction
+    clust_frac = OPTICS(
+        min_samples=9,
+        min_cluster_size=min_cluster_size / redX.shape[0],
+    )
+    clust_frac.fit(redX)
+    assert_array_equal(clust.labels_, clust_frac.labels_)
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+def test_min_cluster_size_invalid2(csr_container):
+    clust = OPTICS(min_cluster_size=len(X) + 1)
+    with pytest.raises(ValueError, match="must be no greater than the "):
+        clust.fit(X)
+
+    clust = OPTICS(min_cluster_size=len(X) + 1, metric="euclidean")
+    with pytest.raises(ValueError, match="must be no greater than the "):
+        clust.fit(csr_container(X))
+
+
+def test_processing_order():
+    # Ensure that we consider all unprocessed points,
+    # not only direct neighbors. when picking the next point.
+    Y = [[0], [10], [-10], [25]]
+
+    clust = OPTICS(min_samples=3, max_eps=15).fit(Y)
+    assert_array_equal(clust.reachability_, [np.inf, 10, 10, 15])
+    assert_array_equal(clust.core_distances_, [10, 15, np.inf, np.inf])
+    assert_array_equal(clust.ordering_, [0, 1, 2, 3])
+
+
+def test_compare_to_ELKI():
+    # Expected values, computed with (future) ELKI 0.7.5 using:
+    # java -jar elki.jar cli -dbc.in csv -dbc.filter FixedDBIDsFilter
+    #   -algorithm clustering.optics.OPTICSHeap -optics.minpts 5
+    # where the FixedDBIDsFilter gives 0-indexed ids.
+    r1 = [
+        np.inf,
+        1.0574896366427478,
+        0.7587934993548423,
+        0.7290174038973836,
+        0.7290174038973836,
+        0.7290174038973836,
+        0.6861627576116127,
+        0.7587934993548423,
+        0.9280118450166668,
+        1.1748022534146194,
+        3.3355455741292257,
+        0.49618389254482587,
+        0.2552805046961355,
+        0.2552805046961355,
+        0.24944622248445714,
+        0.24944622248445714,
+        0.24944622248445714,
+        0.2552805046961355,
+        0.2552805046961355,
+        0.3086779122185853,
+        4.163024452756142,
+        1.623152630340929,
+        0.45315840475822655,
+        0.25468325192031926,
+        0.2254004358159971,
+        0.18765711877083036,
+        0.1821471333893275,
+        0.1821471333893275,
+        0.18765711877083036,
+        0.18765711877083036,
+        0.2240202988740153,
+        1.154337614548715,
+        1.342604473837069,
+        1.323308536402633,
+        0.8607514948648837,
+        0.27219111215810565,
+        0.13260875220533205,
+        0.13260875220533205,
+        0.09890587675958984,
+        0.09890587675958984,
+        0.13548790801634494,
+        0.1575483940837384,
+        0.17515137170530226,
+        0.17575920159442388,
+        0.27219111215810565,
+        0.6101447895405373,
+        1.3189208094864302,
+        1.323308536402633,
+        2.2509184159764577,
+        2.4517810628594527,
+        3.675977064404973,
+        3.8264795626020365,
+        2.9130735341510614,
+        2.9130735341510614,
+        2.9130735341510614,
+        2.9130735341510614,
+        2.8459300127258036,
+        2.8459300127258036,
+        2.8459300127258036,
+        3.0321982337972537,
+    ]
+    o1 = [
+        0,
+        3,
+        6,
+        4,
+        7,
+        8,
+        2,
+        9,
+        5,
+        1,
+        31,
+        30,
+        32,
+        34,
+        33,
+        38,
+        39,
+        35,
+        37,
+        36,
+        44,
+        21,
+        23,
+        24,
+        22,
+        25,
+        27,
+        29,
+        26,
+        28,
+        20,
+        40,
+        45,
+        46,
+        10,
+        15,
+        11,
+        13,
+        17,
+        19,
+        18,
+        12,
+        16,
+        14,
+        47,
+        49,
+        43,
+        48,
+        42,
+        41,
+        53,
+        57,
+        51,
+        52,
+        56,
+        59,
+        54,
+        55,
+        58,
+        50,
+    ]
+    p1 = [
+        -1,
+        0,
+        3,
+        6,
+        6,
+        6,
+        8,
+        3,
+        7,
+        5,
+        1,
+        31,
+        30,
+        30,
+        34,
+        34,
+        34,
+        32,
+        32,
+        37,
+        36,
+        44,
+        21,
+        23,
+        24,
+        22,
+        25,
+        25,
+        22,
+        22,
+        22,
+        21,
+        40,
+        45,
+        46,
+        10,
+        15,
+        15,
+        13,
+        13,
+        15,
+        11,
+        19,
+        15,
+        10,
+        47,
+        12,
+        45,
+        14,
+        43,
+        42,
+        53,
+        57,
+        57,
+        57,
+        57,
+        59,
+        59,
+        59,
+        58,
+    ]
+
+    # Tests against known extraction array
+    # Does NOT work with metric='euclidean', because sklearn euclidean has
+    # worse numeric precision. 'minkowski' is slower but more accurate.
+    clust1 = OPTICS(min_samples=5).fit(X)
+
+    assert_array_equal(clust1.ordering_, np.array(o1))
+    assert_array_equal(clust1.predecessor_[clust1.ordering_], np.array(p1))
+    assert_allclose(clust1.reachability_[clust1.ordering_], np.array(r1))
+    # ELKI currently does not print the core distances (which are not used much
+    # in literature, but we can at least ensure to have this consistency:
+    for i in clust1.ordering_[1:]:
+        assert clust1.reachability_[i] >= clust1.core_distances_[clust1.predecessor_[i]]
+
+    # Expected values, computed with (future) ELKI 0.7.5 using
+    r2 = [
+        np.inf,
+        np.inf,
+        np.inf,
+        np.inf,
+        np.inf,
+        np.inf,
+        np.inf,
+        np.inf,
+        np.inf,
+        np.inf,
+        np.inf,
+        0.27219111215810565,
+        0.13260875220533205,
+        0.13260875220533205,
+        0.09890587675958984,
+        0.09890587675958984,
+        0.13548790801634494,
+        0.1575483940837384,
+        0.17515137170530226,
+        0.17575920159442388,
+        0.27219111215810565,
+        0.4928068613197889,
+        np.inf,
+        0.2666183922512113,
+        0.18765711877083036,
+        0.1821471333893275,
+        0.1821471333893275,
+        0.1821471333893275,
+        0.18715928772277457,
+        0.18765711877083036,
+        0.18765711877083036,
+        0.25468325192031926,
+        np.inf,
+        0.2552805046961355,
+        0.2552805046961355,
+        0.24944622248445714,
+        0.24944622248445714,
+        0.24944622248445714,
+        0.2552805046961355,
+        0.2552805046961355,
+        0.3086779122185853,
+        0.34466409325984865,
+        np.inf,
+        np.inf,
+        np.inf,
+        np.inf,
+        np.inf,
+        np.inf,
+        np.inf,
+        np.inf,
+        np.inf,
+        np.inf,
+        np.inf,
+        np.inf,
+        np.inf,
+        np.inf,
+        np.inf,
+        np.inf,
+        np.inf,
+        np.inf,
+    ]
+    o2 = [
+        0,
+        1,
+        2,
+        3,
+        4,
+        5,
+        6,
+        7,
+        8,
+        9,
+        10,
+        15,
+        11,
+        13,
+        17,
+        19,
+        18,
+        12,
+        16,
+        14,
+        47,
+        46,
+        20,
+        22,
+        25,
+        23,
+        27,
+        29,
+        24,
+        26,
+        28,
+        21,
+        30,
+        32,
+        34,
+        33,
+        38,
+        39,
+        35,
+        37,
+        36,
+        31,
+        40,
+        41,
+        42,
+        43,
+        44,
+        45,
+        48,
+        49,
+        50,
+        51,
+        52,
+        53,
+        54,
+        55,
+        56,
+        57,
+        58,
+        59,
+    ]
+    p2 = [
+        -1,
+        -1,
+        -1,
+        -1,
+        -1,
+        -1,
+        -1,
+        -1,
+        -1,
+        -1,
+        -1,
+        10,
+        15,
+        15,
+        13,
+        13,
+        15,
+        11,
+        19,
+        15,
+        10,
+        47,
+        -1,
+        20,
+        22,
+        25,
+        25,
+        25,
+        25,
+        22,
+        22,
+        23,
+        -1,
+        30,
+        30,
+        34,
+        34,
+        34,
+        32,
+        32,
+        37,
+        38,
+        -1,
+        -1,
+        -1,
+        -1,
+        -1,
+        -1,
+        -1,
+        -1,
+        -1,
+        -1,
+        -1,
+        -1,
+        -1,
+        -1,
+        -1,
+        -1,
+        -1,
+        -1,
+    ]
+    clust2 = OPTICS(min_samples=5, max_eps=0.5).fit(X)
+
+    assert_array_equal(clust2.ordering_, np.array(o2))
+    assert_array_equal(clust2.predecessor_[clust2.ordering_], np.array(p2))
+    assert_allclose(clust2.reachability_[clust2.ordering_], np.array(r2))
+
+    index = np.where(clust1.core_distances_ <= 0.5)[0]
+    assert_allclose(clust1.core_distances_[index], clust2.core_distances_[index])
+
+
+def test_extract_dbscan(global_dtype, global_random_seed):
+    # testing an easy dbscan case. Not including clusters with different
+    # densities.
+    rng = np.random.RandomState(global_random_seed)
+    n_points_per_cluster = 20
+    C1 = [-5, -2] + 0.2 * rng.randn(n_points_per_cluster, 2)
+    C2 = [4, -1] + 0.2 * rng.randn(n_points_per_cluster, 2)
+    C3 = [1, 2] + 0.2 * rng.randn(n_points_per_cluster, 2)
+    C4 = [-2, 3] + 0.2 * rng.randn(n_points_per_cluster, 2)
+    X = np.vstack((C1, C2, C3, C4)).astype(global_dtype, copy=False)
+
+    clust = OPTICS(cluster_method="dbscan", eps=0.5).fit(X)
+    assert_array_equal(
+        np.sort(np.unique(clust.labels_[clust.labels_ != -1])), [0, 1, 2, 3]
+    )
+
+
+@pytest.mark.parametrize("csr_container", [None] + CSR_CONTAINERS)
+def test_precomputed_dists(global_dtype, csr_container):
+    redX = X[::2].astype(global_dtype, copy=False)
+    dists = pairwise_distances(redX, metric="euclidean")
+    dists = csr_container(dists) if csr_container is not None else dists
+    with warnings.catch_warnings():
+        warnings.simplefilter("ignore", EfficiencyWarning)
+        clust1 = OPTICS(min_samples=10, algorithm="brute", metric="precomputed").fit(
+            dists
+        )
+    clust2 = OPTICS(min_samples=10, algorithm="brute", metric="euclidean").fit(redX)
+
+    assert_allclose(clust1.reachability_, clust2.reachability_)
+    assert_array_equal(clust1.labels_, clust2.labels_)
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+def test_optics_input_not_modified_precomputed_sparse_nodiag(
+    csr_container, global_random_seed
+):
+    """Check that we don't modify in-place the pre-computed sparse matrix.
+    Non-regression test for:
+    https://github.com/scikit-learn/scikit-learn/issues/27508
+    """
+    X = np.random.RandomState(global_random_seed).rand(6, 6)
+    # Add zeros on the diagonal that will be implicit when creating
+    # the sparse matrix. If `X` is modified in-place, the zeros from
+    # the diagonal will be made explicit.
+    np.fill_diagonal(X, 0)
+    X = csr_container(X)
+    assert all(row != col for row, col in zip(*X.nonzero()))
+    X_copy = X.copy()
+    OPTICS(metric="precomputed").fit(X)
+    # Make sure that we did not modify `X` in-place even by creating
+    # explicit 0s values.
+    assert X.nnz == X_copy.nnz
+    assert_array_equal(X.toarray(), X_copy.toarray())
+
+
+def test_optics_predecessor_correction_ordering():
+    """Check that cluster correction using predecessor is working as expected.
+
+    In the following example, the predecessor correction was not working properly
+    since it was not using the right indices.
+
+    This non-regression test check that reordering the data does not change the results.
+
+    Non-regression test for:
+    https://github.com/scikit-learn/scikit-learn/issues/26324
+    """
+    X_1 = np.array([1, 2, 3, 1, 8, 8, 7, 100]).reshape(-1, 1)
+    reorder = [0, 1, 2, 4, 5, 6, 7, 3]
+    X_2 = X_1[reorder]
+
+    optics_1 = OPTICS(min_samples=3, metric="euclidean").fit(X_1)
+    optics_2 = OPTICS(min_samples=3, metric="euclidean").fit(X_2)
+
+    assert_array_equal(optics_1.labels_[reorder], optics_2.labels_)

linedance-app/venv/lib/python3.12/site-packages/sklearn/cluster/tests/test_spectral.py

@@ -0,0 +1,335 @@
+"""Testing for Spectral Clustering methods"""
+
+import pickle
+import re
+
+import numpy as np
+import pytest
+from scipy.linalg import LinAlgError
+
+from sklearn.cluster import SpectralClustering, spectral_clustering
+from sklearn.cluster._spectral import cluster_qr, discretize
+from sklearn.datasets import make_blobs
+from sklearn.feature_extraction import img_to_graph
+from sklearn.metrics import adjusted_rand_score
+from sklearn.metrics.pairwise import kernel_metrics, rbf_kernel
+from sklearn.neighbors import NearestNeighbors
+from sklearn.utils import check_random_state
+from sklearn.utils._testing import assert_array_equal
+from sklearn.utils.fixes import COO_CONTAINERS, CSR_CONTAINERS
+
+try:
+    from pyamg import smoothed_aggregation_solver  # noqa: F401
+
+    amg_loaded = True
+except ImportError:
+    amg_loaded = False
+
+centers = np.array([[1, 1], [-1, -1], [1, -1]]) + 10
+X, _ = make_blobs(
+    n_samples=60,
+    n_features=2,
+    centers=centers,
+    cluster_std=0.4,
+    shuffle=True,
+    random_state=0,
+)
+
+
+@pytest.mark.parametrize("csr_container", CSR_CONTAINERS)
+@pytest.mark.parametrize("eigen_solver", ("arpack", "lobpcg"))
+@pytest.mark.parametrize("assign_labels", ("kmeans", "discretize", "cluster_qr"))
+def test_spectral_clustering(
+    eigen_solver, assign_labels, csr_container, global_random_seed
+):
+    S = np.array(
+        [
+            [1.0, 1.0, 1.0, 0.2, 0.0, 0.0, 0.0],
+            [1.0, 1.0, 1.0, 0.2, 0.0, 0.0, 0.0],
+            [1.0, 1.0, 1.0, 0.2, 0.0, 0.0, 0.0],
+            [0.2, 0.2, 0.2, 1.0, 1.0, 1.0, 1.0],
+            [0.0, 0.0, 0.0, 1.0, 1.0, 1.0, 1.0],
+            [0.0, 0.0, 0.0, 1.0, 1.0, 1.0, 1.0],
+            [0.0, 0.0, 0.0, 1.0, 1.0, 1.0, 1.0],
+        ]
+    )
+
+    for mat in (S, csr_container(S)):
+        model = SpectralClustering(
+            random_state=global_random_seed,
+            n_clusters=2,
+            affinity="precomputed",
+            eigen_solver=eigen_solver,
+            assign_labels=assign_labels,
+        ).fit(mat)
+        labels = model.labels_
+        if labels[0] == 0:
+            labels = 1 - labels
+
+        assert adjusted_rand_score(labels, [1, 1, 1, 0, 0, 0, 0]) == 1
+
+        model_copy = pickle.loads(pickle.dumps(model))
+        assert model_copy.n_clusters == model.n_clusters
+        assert model_copy.eigen_solver == model.eigen_solver
+        assert_array_equal(model_copy.labels_, model.labels_)
+
+
+@pytest.mark.parametrize("coo_container", COO_CONTAINERS)
+@pytest.mark.parametrize("assign_labels", ("kmeans", "discretize", "cluster_qr"))
+def test_spectral_clustering_sparse(assign_labels, coo_container, global_random_seed):
+    X, y = make_blobs(
+        n_samples=20,
+        random_state=global_random_seed,
+        centers=[[1, 1], [-1, -1]],
+        cluster_std=0.01,
+    )
+
+    S = rbf_kernel(X, gamma=1)
+    S = np.maximum(S - 1e-4, 0)
+    S = coo_container(S)
+
+    labels = (
+        SpectralClustering(
+            random_state=global_random_seed,
+            n_clusters=2,
+            affinity="precomputed",
+            assign_labels=assign_labels,
+        )
+        .fit(S)
+        .labels_
+    )
+    assert adjusted_rand_score(y, labels) == 1
+
+
+def test_precomputed_nearest_neighbors_filtering(global_random_seed):
+    # Test precomputed graph filtering when containing too many neighbors
+    X, y = make_blobs(
+        n_samples=250,
+        random_state=global_random_seed,
+        centers=[[1, 1, 1], [-1, -1, -1]],
+        cluster_std=0.01,
+    )
+
+    n_neighbors = 2
+    results = []
+    for additional_neighbors in [0, 10]:
+        nn = NearestNeighbors(n_neighbors=n_neighbors + additional_neighbors).fit(X)
+        graph = nn.kneighbors_graph(X, mode="distance")
+        labels = (
+            SpectralClustering(
+                random_state=global_random_seed,
+                n_clusters=2,
+                affinity="precomputed_nearest_neighbors",
+                n_neighbors=n_neighbors,
+            )
+            .fit(graph)
+            .labels_
+        )
+        results.append(labels)
+
+    assert_array_equal(results[0], results[1])
+
+
+def test_affinities(global_random_seed):
+    # Note: in the following, random_state has been selected to have
+    # a dataset that yields a stable eigen decomposition both when built
+    # on OSX and Linux
+    X, y = make_blobs(
+        n_samples=20, random_state=0, centers=[[1, 1], [-1, -1]], cluster_std=0.01
+    )
+    # nearest neighbors affinity
+    sp = SpectralClustering(n_clusters=2, affinity="nearest_neighbors", random_state=0)
+    with pytest.warns(UserWarning, match="not fully connected"):
+        sp.fit(X)
+    assert adjusted_rand_score(y, sp.labels_) == 1
+
+    sp = SpectralClustering(n_clusters=2, gamma=2, random_state=global_random_seed)
+    labels = sp.fit(X).labels_
+    assert adjusted_rand_score(y, labels) == 1
+
+    X = check_random_state(10).rand(10, 5) * 10
+
+    kernels_available = kernel_metrics()
+    for kern in kernels_available:
+        # Additive chi^2 gives a negative similarity matrix which
+        # doesn't make sense for spectral clustering
+        if kern != "additive_chi2":
+            sp = SpectralClustering(n_clusters=2, affinity=kern, random_state=0)
+            labels = sp.fit(X).labels_
+            assert (X.shape[0],) == labels.shape
+
+    sp = SpectralClustering(n_clusters=2, affinity=lambda x, y: 1, random_state=0)
+    labels = sp.fit(X).labels_
+    assert (X.shape[0],) == labels.shape
+
+    def histogram(x, y, **kwargs):
+        # Histogram kernel implemented as a callable.
+        assert kwargs == {}  # no kernel_params that we didn't ask for
+        return np.minimum(x, y).sum()
+
+    sp = SpectralClustering(n_clusters=2, affinity=histogram, random_state=0)
+    labels = sp.fit(X).labels_
+    assert (X.shape[0],) == labels.shape
+
+
+def test_cluster_qr(global_random_seed):
+    # cluster_qr by itself should not be used for clustering generic data
+    # other than the rows of the eigenvectors within spectral clustering,
+    # but cluster_qr must still preserve the labels for different dtypes
+    # of the generic fixed input even if the labels may be meaningless.
+    random_state = np.random.RandomState(seed=global_random_seed)
+    n_samples, n_components = 10, 5
+    data = random_state.randn(n_samples, n_components)
+    labels_float64 = cluster_qr(data.astype(np.float64))
+    # Each sample is assigned a cluster identifier
+    assert labels_float64.shape == (n_samples,)
+    # All components should be covered by the assignment
+    assert np.array_equal(np.unique(labels_float64), np.arange(n_components))
+    # Single precision data should yield the same cluster assignments
+    labels_float32 = cluster_qr(data.astype(np.float32))
+    assert np.array_equal(labels_float64, labels_float32)
+
+
+def test_cluster_qr_permutation_invariance(global_random_seed):
+    # cluster_qr must be invariant to sample permutation.
+    random_state = np.random.RandomState(seed=global_random_seed)
+    n_samples, n_components = 100, 5
+    data = random_state.randn(n_samples, n_components)
+    perm = random_state.permutation(n_samples)
+    assert np.array_equal(
+        cluster_qr(data)[perm],
+        cluster_qr(data[perm]),
+    )
+
+
+@pytest.mark.parametrize("coo_container", COO_CONTAINERS)
+@pytest.mark.parametrize("n_samples", [50, 100, 150, 500])
+def test_discretize(n_samples, coo_container, global_random_seed):
+    # Test the discretize using a noise assignment matrix
+    random_state = np.random.RandomState(seed=global_random_seed)
+    for n_class in range(2, 10):
+        # random class labels
+        y_true = random_state.randint(0, n_class + 1, n_samples)
+        y_true = np.array(y_true, float)
+        # noise class assignment matrix
+        y_indicator = coo_container(
+            (np.ones(n_samples), (np.arange(n_samples), y_true)),
+            shape=(n_samples, n_class + 1),
+        )
+        y_true_noisy = y_indicator.toarray() + 0.1 * random_state.randn(
+            n_samples, n_class + 1
+        )
+        y_pred = discretize(y_true_noisy, random_state=random_state)
+        assert adjusted_rand_score(y_true, y_pred) > 0.8
+
+
+def test_spectral_clustering_with_arpack_amg_solvers(global_random_seed):
+    # Test that spectral_clustering is the same for arpack and amg solver
+    # Based on toy example from plot_segmentation_toy.py
+
+    # a small two coin image
+    x, y = np.indices((40, 40))
+
+    center1, center2 = (14, 12), (20, 25)
+    radius1, radius2 = 8, 7
+
+    circle1 = (x - center1[0]) ** 2 + (y - center1[1]) ** 2 < radius1**2
+    circle2 = (x - center2[0]) ** 2 + (y - center2[1]) ** 2 < radius2**2
+
+    circles = circle1 | circle2
+    mask = circles.copy()
+    img = circles.astype(float)
+
+    graph = img_to_graph(img, mask=mask)
+    graph.data = np.exp(-graph.data / graph.data.std())
+
+    labels_arpack = spectral_clustering(
+        graph, n_clusters=2, eigen_solver="arpack", random_state=global_random_seed
+    )
+
+    assert len(np.unique(labels_arpack)) == 2
+
+    if amg_loaded:
+        labels_amg = spectral_clustering(
+            graph, n_clusters=2, eigen_solver="amg", random_state=global_random_seed
+        )
+        assert adjusted_rand_score(labels_arpack, labels_amg) == 1
+    else:
+        with pytest.raises(ValueError):
+            spectral_clustering(graph, n_clusters=2, eigen_solver="amg", random_state=0)
+
+
+def test_n_components(global_random_seed):
+    # Test that after adding n_components, result is different and
+    # n_components = n_clusters by default
+    X, y = make_blobs(
+        n_samples=20,
+        random_state=global_random_seed,
+        centers=[[1, 1], [-1, -1]],
+        cluster_std=0.01,
+    )
+    sp = SpectralClustering(n_clusters=2, random_state=global_random_seed)
+    labels = sp.fit(X).labels_
+    # set n_components = n_cluster and test if result is the same
+    labels_same_ncomp = (
+        SpectralClustering(
+            n_clusters=2, n_components=2, random_state=global_random_seed
+        )
+        .fit(X)
+        .labels_
+    )
+    # test that n_components=n_clusters by default
+    assert_array_equal(labels, labels_same_ncomp)
+
+    # test that n_components affect result
+    # n_clusters=8 by default, and set n_components=2
+    labels_diff_ncomp = (
+        SpectralClustering(n_components=2, random_state=global_random_seed)
+        .fit(X)
+        .labels_
+    )
+    assert not np.array_equal(labels, labels_diff_ncomp)
+
+
+@pytest.mark.parametrize("assign_labels", ("kmeans", "discretize", "cluster_qr"))
+def test_verbose(assign_labels, capsys):
+    # Check verbose mode of KMeans for better coverage.
+    X, y = make_blobs(
+        n_samples=20, random_state=0, centers=[[1, 1], [-1, -1]], cluster_std=0.01
+    )
+
+    SpectralClustering(n_clusters=2, random_state=42, verbose=1).fit(X)
+
+    captured = capsys.readouterr()
+
+    assert re.search(r"Computing label assignment using", captured.out)
+
+    if assign_labels == "kmeans":
+        assert re.search(r"Initialization complete", captured.out)
+        assert re.search(r"Iteration [0-9]+, inertia", captured.out)
+
+
+def test_spectral_clustering_np_matrix_raises():
+    """Check that spectral_clustering raises an informative error when passed
+    an np.matrix. See #10993"""
+    X = np.matrix([[0.0, 2.0], [2.0, 0.0]])
+
+    msg = r"np\.matrix is not supported. Please convert to a numpy array"
+    with pytest.raises(TypeError, match=msg):
+        spectral_clustering(X)
+
+
+def test_spectral_clustering_not_infinite_loop(capsys, monkeypatch):
+    """Check that discretize raises LinAlgError when svd never converges.
+
+    Non-regression test for #21380
+    """
+
+    def new_svd(*args, **kwargs):
+        raise LinAlgError()
+
+    monkeypatch.setattr(np.linalg, "svd", new_svd)
+    vectors = np.ones((10, 4))
+
+    with pytest.raises(LinAlgError, match="SVD did not converge"):
+        discretize(vectors)