add read me

venv/lib/python3.12/site-packages/sklearn/covariance/tests/test_covariance.py

@@ -0,0 +1,374 @@
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
+import numpy as np
+import pytest
+
+from sklearn import datasets
+from sklearn.covariance import (
+    OAS,
+    EmpiricalCovariance,
+    LedoitWolf,
+    ShrunkCovariance,
+    empirical_covariance,
+    ledoit_wolf,
+    ledoit_wolf_shrinkage,
+    oas,
+    shrunk_covariance,
+)
+from sklearn.covariance._shrunk_covariance import _ledoit_wolf
+from sklearn.utils._testing import (
+    assert_allclose,
+    assert_almost_equal,
+    assert_array_almost_equal,
+    assert_array_equal,
+)
+
+from .._shrunk_covariance import _oas
+
+X, _ = datasets.load_diabetes(return_X_y=True)
+X_1d = X[:, 0]
+n_samples, n_features = X.shape
+
+
+def test_covariance():
+    # Tests Covariance module on a simple dataset.
+    # test covariance fit from data
+    cov = EmpiricalCovariance()
+    cov.fit(X)
+    emp_cov = empirical_covariance(X)
+    assert_array_almost_equal(emp_cov, cov.covariance_, 4)
+    assert_almost_equal(cov.error_norm(emp_cov), 0)
+    assert_almost_equal(cov.error_norm(emp_cov, norm="spectral"), 0)
+    assert_almost_equal(cov.error_norm(emp_cov, norm="frobenius"), 0)
+    assert_almost_equal(cov.error_norm(emp_cov, scaling=False), 0)
+    assert_almost_equal(cov.error_norm(emp_cov, squared=False), 0)
+    with pytest.raises(NotImplementedError):
+        cov.error_norm(emp_cov, norm="foo")
+    # Mahalanobis distances computation test
+    mahal_dist = cov.mahalanobis(X)
+    assert np.amin(mahal_dist) > 0
+
+    # test with n_features = 1
+    X_1d = X[:, 0].reshape((-1, 1))
+    cov = EmpiricalCovariance()
+    cov.fit(X_1d)
+    assert_array_almost_equal(empirical_covariance(X_1d), cov.covariance_, 4)
+    assert_almost_equal(cov.error_norm(empirical_covariance(X_1d)), 0)
+    assert_almost_equal(cov.error_norm(empirical_covariance(X_1d), norm="spectral"), 0)
+
+    # test with one sample
+    # Create X with 1 sample and 5 features
+    X_1sample = np.arange(5).reshape(1, 5)
+    cov = EmpiricalCovariance()
+    warn_msg = "Only one sample available. You may want to reshape your data array"
+    with pytest.warns(UserWarning, match=warn_msg):
+        cov.fit(X_1sample)
+
+    assert_array_almost_equal(cov.covariance_, np.zeros(shape=(5, 5), dtype=np.float64))
+
+    # test integer type
+    X_integer = np.asarray([[0, 1], [1, 0]])
+    result = np.asarray([[0.25, -0.25], [-0.25, 0.25]])
+    assert_array_almost_equal(empirical_covariance(X_integer), result)
+
+    # test centered case
+    cov = EmpiricalCovariance(assume_centered=True)
+    cov.fit(X)
+    assert_array_equal(cov.location_, np.zeros(X.shape[1]))
+
+
+@pytest.mark.parametrize("n_matrices", [1, 3])
+def test_shrunk_covariance_func(n_matrices):
+    """Check `shrunk_covariance` function."""
+
+    n_features = 2
+    cov = np.ones((n_features, n_features))
+    cov_target = np.array([[1, 0.5], [0.5, 1]])
+
+    if n_matrices > 1:
+        cov = np.repeat(cov[np.newaxis, ...], n_matrices, axis=0)
+        cov_target = np.repeat(cov_target[np.newaxis, ...], n_matrices, axis=0)
+
+    cov_shrunk = shrunk_covariance(cov, 0.5)
+    assert_allclose(cov_shrunk, cov_target)
+
+
+def test_shrunk_covariance():
+    """Check consistency between `ShrunkCovariance` and `shrunk_covariance`."""
+
+    # Tests ShrunkCovariance module on a simple dataset.
+    # compare shrunk covariance obtained from data and from MLE estimate
+    cov = ShrunkCovariance(shrinkage=0.5)
+    cov.fit(X)
+    assert_array_almost_equal(
+        shrunk_covariance(empirical_covariance(X), shrinkage=0.5), cov.covariance_, 4
+    )
+
+    # same test with shrinkage not provided
+    cov = ShrunkCovariance()
+    cov.fit(X)
+    assert_array_almost_equal(
+        shrunk_covariance(empirical_covariance(X)), cov.covariance_, 4
+    )
+
+    # same test with shrinkage = 0 (<==> empirical_covariance)
+    cov = ShrunkCovariance(shrinkage=0.0)
+    cov.fit(X)
+    assert_array_almost_equal(empirical_covariance(X), cov.covariance_, 4)
+
+    # test with n_features = 1
+    X_1d = X[:, 0].reshape((-1, 1))
+    cov = ShrunkCovariance(shrinkage=0.3)
+    cov.fit(X_1d)
+    assert_array_almost_equal(empirical_covariance(X_1d), cov.covariance_, 4)
+
+    # test shrinkage coeff on a simple data set (without saving precision)
+    cov = ShrunkCovariance(shrinkage=0.5, store_precision=False)
+    cov.fit(X)
+    assert cov.precision_ is None
+
+
+def test_ledoit_wolf():
+    # Tests LedoitWolf module on a simple dataset.
+    # test shrinkage coeff on a simple data set
+    X_centered = X - X.mean(axis=0)
+    lw = LedoitWolf(assume_centered=True)
+    lw.fit(X_centered)
+    shrinkage_ = lw.shrinkage_
+
+    score_ = lw.score(X_centered)
+    assert_almost_equal(
+        ledoit_wolf_shrinkage(X_centered, assume_centered=True), shrinkage_
+    )
+    assert_almost_equal(
+        ledoit_wolf_shrinkage(X_centered, assume_centered=True, block_size=6),
+        shrinkage_,
+    )
+    # compare shrunk covariance obtained from data and from MLE estimate
+    lw_cov_from_mle, lw_shrinkage_from_mle = ledoit_wolf(
+        X_centered, assume_centered=True
+    )
+    assert_array_almost_equal(lw_cov_from_mle, lw.covariance_, 4)
+    assert_almost_equal(lw_shrinkage_from_mle, lw.shrinkage_)
+    # compare estimates given by LW and ShrunkCovariance
+    scov = ShrunkCovariance(shrinkage=lw.shrinkage_, assume_centered=True)
+    scov.fit(X_centered)
+    assert_array_almost_equal(scov.covariance_, lw.covariance_, 4)
+
+    # test with n_features = 1
+    X_1d = X[:, 0].reshape((-1, 1))
+    lw = LedoitWolf(assume_centered=True)
+    lw.fit(X_1d)
+    lw_cov_from_mle, lw_shrinkage_from_mle = ledoit_wolf(X_1d, assume_centered=True)
+    assert_array_almost_equal(lw_cov_from_mle, lw.covariance_, 4)
+    assert_almost_equal(lw_shrinkage_from_mle, lw.shrinkage_)
+    assert_array_almost_equal((X_1d**2).sum() / n_samples, lw.covariance_, 4)
+
+    # test shrinkage coeff on a simple data set (without saving precision)
+    lw = LedoitWolf(store_precision=False, assume_centered=True)
+    lw.fit(X_centered)
+    assert_almost_equal(lw.score(X_centered), score_, 4)
+    assert lw.precision_ is None
+
+    # Same tests without assuming centered data
+    # test shrinkage coeff on a simple data set
+    lw = LedoitWolf()
+    lw.fit(X)
+    assert_almost_equal(lw.shrinkage_, shrinkage_, 4)
+    assert_almost_equal(lw.shrinkage_, ledoit_wolf_shrinkage(X))
+    assert_almost_equal(lw.shrinkage_, ledoit_wolf(X)[1])
+    assert_almost_equal(
+        lw.shrinkage_, _ledoit_wolf(X=X, assume_centered=False, block_size=10000)[1]
+    )
+    assert_almost_equal(lw.score(X), score_, 4)
+    # compare shrunk covariance obtained from data and from MLE estimate
+    lw_cov_from_mle, lw_shrinkage_from_mle = ledoit_wolf(X)
+    assert_array_almost_equal(lw_cov_from_mle, lw.covariance_, 4)
+    assert_almost_equal(lw_shrinkage_from_mle, lw.shrinkage_)
+    # compare estimates given by LW and ShrunkCovariance
+    scov = ShrunkCovariance(shrinkage=lw.shrinkage_)
+    scov.fit(X)
+    assert_array_almost_equal(scov.covariance_, lw.covariance_, 4)
+
+    # test with n_features = 1
+    X_1d = X[:, 0].reshape((-1, 1))
+    lw = LedoitWolf()
+    lw.fit(X_1d)
+    assert_allclose(
+        X_1d.var(ddof=0),
+        _ledoit_wolf(X=X_1d, assume_centered=False, block_size=10000)[0],
+    )
+    lw_cov_from_mle, lw_shrinkage_from_mle = ledoit_wolf(X_1d)
+    assert_array_almost_equal(lw_cov_from_mle, lw.covariance_, 4)
+    assert_almost_equal(lw_shrinkage_from_mle, lw.shrinkage_)
+    assert_array_almost_equal(empirical_covariance(X_1d), lw.covariance_, 4)
+
+    # test with one sample
+    # warning should be raised when using only 1 sample
+    X_1sample = np.arange(5).reshape(1, 5)
+    lw = LedoitWolf()
+
+    warn_msg = "Only one sample available. You may want to reshape your data array"
+    with pytest.warns(UserWarning, match=warn_msg):
+        lw.fit(X_1sample)
+
+    assert_array_almost_equal(lw.covariance_, np.zeros(shape=(5, 5), dtype=np.float64))
+
+    # test shrinkage coeff on a simple data set (without saving precision)
+    lw = LedoitWolf(store_precision=False)
+    lw.fit(X)
+    assert_almost_equal(lw.score(X), score_, 4)
+    assert lw.precision_ is None
+
+
+def _naive_ledoit_wolf_shrinkage(X):
+    # A simple implementation of the formulas from Ledoit & Wolf
+
+    # The computation below achieves the following computations of the
+    # "O. Ledoit and M. Wolf, A Well-Conditioned Estimator for
+    # Large-Dimensional Covariance Matrices"
+    # beta and delta are given in the beginning of section 3.2
+    n_samples, n_features = X.shape
+    emp_cov = empirical_covariance(X, assume_centered=False)
+    mu = np.trace(emp_cov) / n_features
+    delta_ = emp_cov.copy()
+    delta_.flat[:: n_features + 1] -= mu
+    delta = (delta_**2).sum() / n_features
+    X2 = X**2
+    beta_ = (
+        1.0
+        / (n_features * n_samples)
+        * np.sum(np.dot(X2.T, X2) / n_samples - emp_cov**2)
+    )
+
+    beta = min(beta_, delta)
+    shrinkage = beta / delta
+    return shrinkage
+
+
+def test_ledoit_wolf_small():
+    # Compare our blocked implementation to the naive implementation
+    X_small = X[:, :4]
+    lw = LedoitWolf()
+    lw.fit(X_small)
+    shrinkage_ = lw.shrinkage_
+
+    assert_almost_equal(shrinkage_, _naive_ledoit_wolf_shrinkage(X_small))
+
+
+def test_ledoit_wolf_large():
+    # test that ledoit_wolf doesn't error on data that is wider than block_size
+    rng = np.random.RandomState(0)
+    # use a number of features that is larger than the block-size
+    X = rng.normal(size=(10, 20))
+    lw = LedoitWolf(block_size=10).fit(X)
+    # check that covariance is about diagonal (random normal noise)
+    assert_almost_equal(lw.covariance_, np.eye(20), 0)
+    cov = lw.covariance_
+
+    # check that the result is consistent with not splitting data into blocks.
+    lw = LedoitWolf(block_size=25).fit(X)
+    assert_almost_equal(lw.covariance_, cov)
+
+
+@pytest.mark.parametrize(
+    "ledoit_wolf_fitting_function", [LedoitWolf().fit, ledoit_wolf_shrinkage]
+)
+def test_ledoit_wolf_empty_array(ledoit_wolf_fitting_function):
+    """Check that we validate X and raise proper error with 0-sample array."""
+    X_empty = np.zeros((0, 2))
+    with pytest.raises(ValueError, match="Found array with 0 sample"):
+        ledoit_wolf_fitting_function(X_empty)
+
+
+def test_oas():
+    # Tests OAS module on a simple dataset.
+    # test shrinkage coeff on a simple data set
+    X_centered = X - X.mean(axis=0)
+    oa = OAS(assume_centered=True)
+    oa.fit(X_centered)
+    shrinkage_ = oa.shrinkage_
+    score_ = oa.score(X_centered)
+    # compare shrunk covariance obtained from data and from MLE estimate
+    oa_cov_from_mle, oa_shrinkage_from_mle = oas(X_centered, assume_centered=True)
+    assert_array_almost_equal(oa_cov_from_mle, oa.covariance_, 4)
+    assert_almost_equal(oa_shrinkage_from_mle, oa.shrinkage_)
+    # compare estimates given by OAS and ShrunkCovariance
+    scov = ShrunkCovariance(shrinkage=oa.shrinkage_, assume_centered=True)
+    scov.fit(X_centered)
+    assert_array_almost_equal(scov.covariance_, oa.covariance_, 4)
+
+    # test with n_features = 1
+    X_1d = X[:, 0:1]
+    oa = OAS(assume_centered=True)
+    oa.fit(X_1d)
+    oa_cov_from_mle, oa_shrinkage_from_mle = oas(X_1d, assume_centered=True)
+    assert_array_almost_equal(oa_cov_from_mle, oa.covariance_, 4)
+    assert_almost_equal(oa_shrinkage_from_mle, oa.shrinkage_)
+    assert_array_almost_equal((X_1d**2).sum() / n_samples, oa.covariance_, 4)
+
+    # test shrinkage coeff on a simple data set (without saving precision)
+    oa = OAS(store_precision=False, assume_centered=True)
+    oa.fit(X_centered)
+    assert_almost_equal(oa.score(X_centered), score_, 4)
+    assert oa.precision_ is None
+
+    # Same tests without assuming centered data--------------------------------
+    # test shrinkage coeff on a simple data set
+    oa = OAS()
+    oa.fit(X)
+    assert_almost_equal(oa.shrinkage_, shrinkage_, 4)
+    assert_almost_equal(oa.score(X), score_, 4)
+    # compare shrunk covariance obtained from data and from MLE estimate
+    oa_cov_from_mle, oa_shrinkage_from_mle = oas(X)
+    assert_array_almost_equal(oa_cov_from_mle, oa.covariance_, 4)
+    assert_almost_equal(oa_shrinkage_from_mle, oa.shrinkage_)
+    # compare estimates given by OAS and ShrunkCovariance
+    scov = ShrunkCovariance(shrinkage=oa.shrinkage_)
+    scov.fit(X)
+    assert_array_almost_equal(scov.covariance_, oa.covariance_, 4)
+
+    # test with n_features = 1
+    X_1d = X[:, 0].reshape((-1, 1))
+    oa = OAS()
+    oa.fit(X_1d)
+    oa_cov_from_mle, oa_shrinkage_from_mle = oas(X_1d)
+    assert_array_almost_equal(oa_cov_from_mle, oa.covariance_, 4)
+    assert_almost_equal(oa_shrinkage_from_mle, oa.shrinkage_)
+    assert_array_almost_equal(empirical_covariance(X_1d), oa.covariance_, 4)
+
+    # test with one sample
+    # warning should be raised when using only 1 sample
+    X_1sample = np.arange(5).reshape(1, 5)
+    oa = OAS()
+    warn_msg = "Only one sample available. You may want to reshape your data array"
+    with pytest.warns(UserWarning, match=warn_msg):
+        oa.fit(X_1sample)
+
+    assert_array_almost_equal(oa.covariance_, np.zeros(shape=(5, 5), dtype=np.float64))
+
+    # test shrinkage coeff on a simple data set (without saving precision)
+    oa = OAS(store_precision=False)
+    oa.fit(X)
+    assert_almost_equal(oa.score(X), score_, 4)
+    assert oa.precision_ is None
+
+    # test function _oas without assuming centered data
+    X_1f = X[:, 0:1]
+    oa = OAS()
+    oa.fit(X_1f)
+    # compare shrunk covariance obtained from data and from MLE estimate
+    _oa_cov_from_mle, _oa_shrinkage_from_mle = _oas(X_1f)
+    assert_array_almost_equal(_oa_cov_from_mle, oa.covariance_, 4)
+    assert_almost_equal(_oa_shrinkage_from_mle, oa.shrinkage_)
+    assert_array_almost_equal((X_1f**2).sum() / n_samples, oa.covariance_, 4)
+
+
+def test_EmpiricalCovariance_validates_mahalanobis():
+    """Checks that EmpiricalCovariance validates data with mahalanobis."""
+    cov = EmpiricalCovariance().fit(X)
+
+    msg = f"X has 2 features, but \\w+ is expecting {X.shape[1]} features as input"
+    with pytest.raises(ValueError, match=msg):
+        cov.mahalanobis(X[:, :2])

venv/lib/python3.12/site-packages/sklearn/covariance/tests/test_elliptic_envelope.py

@@ -0,0 +1,52 @@
+"""
+Testing for Elliptic Envelope algorithm (sklearn.covariance.elliptic_envelope).
+"""
+
+import numpy as np
+import pytest
+
+from sklearn.covariance import EllipticEnvelope
+from sklearn.exceptions import NotFittedError
+from sklearn.utils._testing import (
+    assert_almost_equal,
+    assert_array_almost_equal,
+    assert_array_equal,
+)
+
+
+def test_elliptic_envelope(global_random_seed):
+    rnd = np.random.RandomState(global_random_seed)
+    X = rnd.randn(100, 10)
+    clf = EllipticEnvelope(contamination=0.1)
+    with pytest.raises(NotFittedError):
+        clf.predict(X)
+    with pytest.raises(NotFittedError):
+        clf.decision_function(X)
+    clf.fit(X)
+    y_pred = clf.predict(X)
+    scores = clf.score_samples(X)
+    decisions = clf.decision_function(X)
+
+    assert_array_almost_equal(scores, -clf.mahalanobis(X))
+    assert_array_almost_equal(clf.mahalanobis(X), clf.dist_)
+    assert_almost_equal(
+        clf.score(X, np.ones(100)), (100 - y_pred[y_pred == -1].size) / 100.0
+    )
+    assert sum(y_pred == -1) == sum(decisions < 0)
+
+
+def test_score_samples():
+    X_train = [[1, 1], [1, 2], [2, 1]]
+    clf1 = EllipticEnvelope(contamination=0.2).fit(X_train)
+    clf2 = EllipticEnvelope().fit(X_train)
+    assert_array_equal(
+        clf1.score_samples([[2.0, 2.0]]),
+        clf1.decision_function([[2.0, 2.0]]) + clf1.offset_,
+    )
+    assert_array_equal(
+        clf2.score_samples([[2.0, 2.0]]),
+        clf2.decision_function([[2.0, 2.0]]) + clf2.offset_,
+    )
+    assert_array_equal(
+        clf1.score_samples([[2.0, 2.0]]), clf2.score_samples([[2.0, 2.0]])
+    )

venv/lib/python3.12/site-packages/sklearn/covariance/tests/test_graphical_lasso.py

@@ -0,0 +1,318 @@
+"""Test the graphical_lasso module."""
+
+import sys
+from io import StringIO
+
+import numpy as np
+import pytest
+from numpy.testing import assert_allclose
+from scipy import linalg
+
+from sklearn import config_context, datasets
+from sklearn.covariance import (
+    GraphicalLasso,
+    GraphicalLassoCV,
+    empirical_covariance,
+    graphical_lasso,
+)
+from sklearn.datasets import make_sparse_spd_matrix
+from sklearn.model_selection import GroupKFold
+from sklearn.utils import check_random_state
+from sklearn.utils._testing import (
+    _convert_container,
+    assert_array_almost_equal,
+    assert_array_less,
+)
+
+
+def test_graphical_lassos(random_state=1):
+    """Test the graphical lasso solvers.
+
+    This checks is unstable for some random seeds where the covariance found with "cd"
+    and "lars" solvers are different (4 cases / 100 tries).
+    """
+    # Sample data from a sparse multivariate normal
+    dim = 20
+    n_samples = 100
+    random_state = check_random_state(random_state)
+    prec = make_sparse_spd_matrix(dim, alpha=0.95, random_state=random_state)
+    cov = linalg.inv(prec)
+    X = random_state.multivariate_normal(np.zeros(dim), cov, size=n_samples)
+    emp_cov = empirical_covariance(X)
+
+    for alpha in (0.0, 0.1, 0.25):
+        covs = dict()
+        icovs = dict()
+        for method in ("cd", "lars"):
+            cov_, icov_, costs = graphical_lasso(
+                emp_cov, return_costs=True, alpha=alpha, mode=method
+            )
+            covs[method] = cov_
+            icovs[method] = icov_
+            costs, dual_gap = np.array(costs).T
+            # Check that the costs always decrease (doesn't hold if alpha == 0)
+            if not alpha == 0:
+                # use 1e-12 since the cost can be exactly 0
+                assert_array_less(np.diff(costs), 1e-12)
+        # Check that the 2 approaches give similar results
+        assert_allclose(covs["cd"], covs["lars"], atol=5e-4)
+        assert_allclose(icovs["cd"], icovs["lars"], atol=5e-4)
+
+    # Smoke test the estimator
+    model = GraphicalLasso(alpha=0.25).fit(X)
+    model.score(X)
+    assert_array_almost_equal(model.covariance_, covs["cd"], decimal=4)
+    assert_array_almost_equal(model.covariance_, covs["lars"], decimal=4)
+
+    # For a centered matrix, assume_centered could be chosen True or False
+    # Check that this returns indeed the same result for centered data
+    Z = X - X.mean(0)
+    precs = list()
+    for assume_centered in (False, True):
+        prec_ = GraphicalLasso(assume_centered=assume_centered).fit(Z).precision_
+        precs.append(prec_)
+    assert_array_almost_equal(precs[0], precs[1])
+
+
+def test_graphical_lasso_when_alpha_equals_0():
+    """Test graphical_lasso's early return condition when alpha=0."""
+    X = np.random.randn(100, 10)
+    emp_cov = empirical_covariance(X, assume_centered=True)
+
+    model = GraphicalLasso(alpha=0, covariance="precomputed").fit(emp_cov)
+    assert_allclose(model.precision_, np.linalg.inv(emp_cov))
+
+    _, precision = graphical_lasso(emp_cov, alpha=0)
+    assert_allclose(precision, np.linalg.inv(emp_cov))
+
+
+@pytest.mark.parametrize("mode", ["cd", "lars"])
+def test_graphical_lasso_n_iter(mode):
+    X, _ = datasets.make_classification(n_samples=5_000, n_features=20, random_state=0)
+    emp_cov = empirical_covariance(X)
+
+    _, _, n_iter = graphical_lasso(
+        emp_cov, 0.2, mode=mode, max_iter=2, return_n_iter=True
+    )
+    assert n_iter == 2
+
+
+def test_graphical_lasso_iris():
+    # Hard-coded solution from R glasso package for alpha=1.0
+    # (need to set penalize.diagonal to FALSE)
+    cov_R = np.array(
+        [
+            [0.68112222, 0.0000000, 0.265820, 0.02464314],
+            [0.00000000, 0.1887129, 0.000000, 0.00000000],
+            [0.26582000, 0.0000000, 3.095503, 0.28697200],
+            [0.02464314, 0.0000000, 0.286972, 0.57713289],
+        ]
+    )
+    icov_R = np.array(
+        [
+            [1.5190747, 0.000000, -0.1304475, 0.0000000],
+            [0.0000000, 5.299055, 0.0000000, 0.0000000],
+            [-0.1304475, 0.000000, 0.3498624, -0.1683946],
+            [0.0000000, 0.000000, -0.1683946, 1.8164353],
+        ]
+    )
+    X = datasets.load_iris().data
+    emp_cov = empirical_covariance(X)
+    for method in ("cd", "lars"):
+        cov, icov = graphical_lasso(emp_cov, alpha=1.0, return_costs=False, mode=method)
+        assert_array_almost_equal(cov, cov_R)
+        assert_array_almost_equal(icov, icov_R)
+
+
+def test_graph_lasso_2D():
+    # Hard-coded solution from Python skggm package
+    # obtained by calling `quic(emp_cov, lam=.1, tol=1e-8)`
+    cov_skggm = np.array([[3.09550269, 1.186972], [1.186972, 0.57713289]])
+
+    icov_skggm = np.array([[1.52836773, -3.14334831], [-3.14334831, 8.19753385]])
+    X = datasets.load_iris().data[:, 2:]
+    emp_cov = empirical_covariance(X)
+    for method in ("cd", "lars"):
+        cov, icov = graphical_lasso(emp_cov, alpha=0.1, return_costs=False, mode=method)
+        assert_array_almost_equal(cov, cov_skggm)
+        assert_array_almost_equal(icov, icov_skggm)
+
+
+def test_graphical_lasso_iris_singular():
+    # Small subset of rows to test the rank-deficient case
+    # Need to choose samples such that none of the variances are zero
+    indices = np.arange(10, 13)
+
+    # Hard-coded solution from R glasso package for alpha=0.01
+    cov_R = np.array(
+        [
+            [0.08, 0.056666662595, 0.00229729713223, 0.00153153142149],
+            [0.056666662595, 0.082222222222, 0.00333333333333, 0.00222222222222],
+            [0.002297297132, 0.003333333333, 0.00666666666667, 0.00009009009009],
+            [0.001531531421, 0.002222222222, 0.00009009009009, 0.00222222222222],
+        ]
+    )
+    icov_R = np.array(
+        [
+            [24.42244057, -16.831679593, 0.0, 0.0],
+            [-16.83168201, 24.351841681, -6.206896552, -12.5],
+            [0.0, -6.206896171, 153.103448276, 0.0],
+            [0.0, -12.499999143, 0.0, 462.5],
+        ]
+    )
+    X = datasets.load_iris().data[indices, :]
+    emp_cov = empirical_covariance(X)
+    for method in ("cd", "lars"):
+        cov, icov = graphical_lasso(
+            emp_cov, alpha=0.01, return_costs=False, mode=method
+        )
+        assert_array_almost_equal(cov, cov_R, decimal=5)
+        assert_array_almost_equal(icov, icov_R, decimal=5)
+
+
+def test_graphical_lasso_cv(random_state=1):
+    # Sample data from a sparse multivariate normal
+    dim = 5
+    n_samples = 6
+    random_state = check_random_state(random_state)
+    prec = make_sparse_spd_matrix(dim, alpha=0.96, random_state=random_state)
+    cov = linalg.inv(prec)
+    X = random_state.multivariate_normal(np.zeros(dim), cov, size=n_samples)
+    # Capture stdout, to smoke test the verbose mode
+    orig_stdout = sys.stdout
+    try:
+        sys.stdout = StringIO()
+        # We need verbose very high so that Parallel prints on stdout
+        GraphicalLassoCV(verbose=100, alphas=5, tol=1e-1).fit(X)
+    finally:
+        sys.stdout = orig_stdout
+
+
+@pytest.mark.parametrize("alphas_container_type", ["list", "tuple", "array"])
+def test_graphical_lasso_cv_alphas_iterable(alphas_container_type):
+    """Check that we can pass an array-like to `alphas`.
+
+    Non-regression test for:
+    https://github.com/scikit-learn/scikit-learn/issues/22489
+    """
+    true_cov = np.array(
+        [
+            [0.8, 0.0, 0.2, 0.0],
+            [0.0, 0.4, 0.0, 0.0],
+            [0.2, 0.0, 0.3, 0.1],
+            [0.0, 0.0, 0.1, 0.7],
+        ]
+    )
+    rng = np.random.RandomState(0)
+    X = rng.multivariate_normal(mean=[0, 0, 0, 0], cov=true_cov, size=200)
+    alphas = _convert_container([0.02, 0.03], alphas_container_type)
+    GraphicalLassoCV(alphas=alphas, tol=1e-1, n_jobs=1).fit(X)
+
+
+@pytest.mark.parametrize(
+    "alphas,err_type,err_msg",
+    [
+        ([-0.02, 0.03], ValueError, "must be > 0"),
+        ([0, 0.03], ValueError, "must be > 0"),
+        (["not_number", 0.03], TypeError, "must be an instance of float"),
+    ],
+)
+def test_graphical_lasso_cv_alphas_invalid_array(alphas, err_type, err_msg):
+    """Check that if an array-like containing a value
+    outside of (0, inf] is passed to `alphas`, a ValueError is raised.
+    Check if a string is passed, a TypeError is raised.
+    """
+    true_cov = np.array(
+        [
+            [0.8, 0.0, 0.2, 0.0],
+            [0.0, 0.4, 0.0, 0.0],
+            [0.2, 0.0, 0.3, 0.1],
+            [0.0, 0.0, 0.1, 0.7],
+        ]
+    )
+    rng = np.random.RandomState(0)
+    X = rng.multivariate_normal(mean=[0, 0, 0, 0], cov=true_cov, size=200)
+
+    with pytest.raises(err_type, match=err_msg):
+        GraphicalLassoCV(alphas=alphas, tol=1e-1, n_jobs=1).fit(X)
+
+
+def test_graphical_lasso_cv_scores():
+    splits = 4
+    n_alphas = 5
+    n_refinements = 3
+    true_cov = np.array(
+        [
+            [0.8, 0.0, 0.2, 0.0],
+            [0.0, 0.4, 0.0, 0.0],
+            [0.2, 0.0, 0.3, 0.1],
+            [0.0, 0.0, 0.1, 0.7],
+        ]
+    )
+    rng = np.random.RandomState(0)
+    X = rng.multivariate_normal(mean=[0, 0, 0, 0], cov=true_cov, size=200)
+    cov = GraphicalLassoCV(cv=splits, alphas=n_alphas, n_refinements=n_refinements).fit(
+        X
+    )
+
+    _assert_graphical_lasso_cv_scores(
+        cov=cov,
+        n_splits=splits,
+        n_refinements=n_refinements,
+        n_alphas=n_alphas,
+    )
+
+
+@config_context(enable_metadata_routing=True)
+def test_graphical_lasso_cv_scores_with_routing(global_random_seed):
+    """Check that `GraphicalLassoCV` internally dispatches metadata to
+    the splitter.
+    """
+    splits = 5
+    n_alphas = 5
+    n_refinements = 3
+    true_cov = np.array(
+        [
+            [0.8, 0.0, 0.2, 0.0],
+            [0.0, 0.4, 0.0, 0.0],
+            [0.2, 0.0, 0.3, 0.1],
+            [0.0, 0.0, 0.1, 0.7],
+        ]
+    )
+    rng = np.random.RandomState(global_random_seed)
+    X = rng.multivariate_normal(mean=[0, 0, 0, 0], cov=true_cov, size=300)
+    n_samples = X.shape[0]
+    groups = rng.randint(0, 5, n_samples)
+    params = {"groups": groups}
+    cv = GroupKFold(n_splits=splits)
+    cv.set_split_request(groups=True)
+
+    cov = GraphicalLassoCV(cv=cv, alphas=n_alphas, n_refinements=n_refinements).fit(
+        X, **params
+    )
+
+    _assert_graphical_lasso_cv_scores(
+        cov=cov,
+        n_splits=splits,
+        n_refinements=n_refinements,
+        n_alphas=n_alphas,
+    )
+
+
+def _assert_graphical_lasso_cv_scores(cov, n_splits, n_refinements, n_alphas):
+    cv_results = cov.cv_results_
+    # alpha and one for each split
+
+    total_alphas = n_refinements * n_alphas + 1
+    keys = ["alphas"]
+    split_keys = [f"split{i}_test_score" for i in range(n_splits)]
+    for key in keys + split_keys:
+        assert key in cv_results
+        assert len(cv_results[key]) == total_alphas
+
+    cv_scores = np.asarray([cov.cv_results_[key] for key in split_keys])
+    expected_mean = cv_scores.mean(axis=0)
+    expected_std = cv_scores.std(axis=0)
+
+    assert_allclose(cov.cv_results_["mean_test_score"], expected_mean)
+    assert_allclose(cov.cv_results_["std_test_score"], expected_std)

venv/lib/python3.12/site-packages/sklearn/covariance/tests/test_robust_covariance.py

@@ -0,0 +1,171 @@
+# Authors: The scikit-learn developers
+# SPDX-License-Identifier: BSD-3-Clause
+
+import itertools
+
+import numpy as np
+import pytest
+
+from sklearn import datasets
+from sklearn.covariance import MinCovDet, empirical_covariance, fast_mcd
+from sklearn.utils._testing import assert_array_almost_equal
+
+X = datasets.load_iris().data
+X_1d = X[:, 0]
+n_samples, n_features = X.shape
+
+
+def test_mcd(global_random_seed):
+    # Tests the FastMCD algorithm implementation
+    # Small data set
+    # test without outliers (random independent normal data)
+    launch_mcd_on_dataset(100, 5, 0, 0.02, 0.1, 75, global_random_seed)
+    # test with a contaminated data set (medium contamination)
+    launch_mcd_on_dataset(100, 5, 20, 0.3, 0.3, 65, global_random_seed)
+    # test with a contaminated data set (strong contamination)
+    launch_mcd_on_dataset(100, 5, 40, 0.1, 0.1, 50, global_random_seed)
+
+    # Medium data set
+    launch_mcd_on_dataset(1000, 5, 450, 0.1, 0.1, 540, global_random_seed)
+
+    # Large data set
+    launch_mcd_on_dataset(1700, 5, 800, 0.1, 0.1, 870, global_random_seed)
+
+    # 1D data set
+    launch_mcd_on_dataset(500, 1, 100, 0.02, 0.02, 350, global_random_seed)
+
+    # n_samples == n_features
+    launch_mcd_on_dataset(20, 20, 0, 0.1, 0.1, 15, global_random_seed)
+
+
+def test_fast_mcd_on_invalid_input():
+    X = np.arange(100)
+    msg = "Expected 2D array, got 1D array instead"
+    with pytest.raises(ValueError, match=msg):
+        fast_mcd(X)
+
+
+def test_mcd_class_on_invalid_input():
+    X = np.arange(100)
+    mcd = MinCovDet()
+    msg = "Expected 2D array, got 1D array instead"
+    with pytest.raises(ValueError, match=msg):
+        mcd.fit(X)
+
+
+def launch_mcd_on_dataset(
+    n_samples, n_features, n_outliers, tol_loc, tol_cov, tol_support, seed
+):
+    rand_gen = np.random.RandomState(seed)
+    data = rand_gen.randn(n_samples, n_features)
+    # add some outliers
+    outliers_index = rand_gen.permutation(n_samples)[:n_outliers]
+    outliers_offset = 10.0 * (rand_gen.randint(2, size=(n_outliers, n_features)) - 0.5)
+    data[outliers_index] += outliers_offset
+    inliers_mask = np.ones(n_samples).astype(bool)
+    inliers_mask[outliers_index] = False
+
+    pure_data = data[inliers_mask]
+    # compute MCD by fitting an object
+    mcd_fit = MinCovDet(random_state=seed).fit(data)
+    T = mcd_fit.location_
+    S = mcd_fit.covariance_
+    H = mcd_fit.support_
+    # compare with the estimates learnt from the inliers
+    error_location = np.mean((pure_data.mean(0) - T) ** 2)
+    assert error_location < tol_loc
+    error_cov = np.mean((empirical_covariance(pure_data) - S) ** 2)
+    assert error_cov < tol_cov
+    assert np.sum(H) >= tol_support
+    assert_array_almost_equal(mcd_fit.mahalanobis(data), mcd_fit.dist_)
+
+
+def test_mcd_issue1127():
+    # Check that the code does not break with X.shape = (3, 1)
+    # (i.e. n_support = n_samples)
+    rnd = np.random.RandomState(0)
+    X = rnd.normal(size=(3, 1))
+    mcd = MinCovDet()
+    mcd.fit(X)
+
+
+def test_mcd_issue3367(global_random_seed):
+    # Check that MCD completes when the covariance matrix is singular
+    # i.e. one of the rows and columns are all zeros
+    rand_gen = np.random.RandomState(global_random_seed)
+
+    # Think of these as the values for X and Y -> 10 values between -5 and 5
+    data_values = np.linspace(-5, 5, 10).tolist()
+    # Get the cartesian product of all possible coordinate pairs from above set
+    data = np.array(list(itertools.product(data_values, data_values)))
+
+    # Add a third column that's all zeros to make our data a set of point
+    # within a plane, which means that the covariance matrix will be singular
+    data = np.hstack((data, np.zeros((data.shape[0], 1))))
+
+    # The below line of code should raise an exception if the covariance matrix
+    # is singular. As a further test, since we have points in XYZ, the
+    # principle components (Eigenvectors) of these directly relate to the
+    # geometry of the points. Since it's a plane, we should be able to test
+    # that the Eigenvector that corresponds to the smallest Eigenvalue is the
+    # plane normal, specifically [0, 0, 1], since everything is in the XY plane
+    # (as I've set it up above). To do this one would start by:
+    #
+    #     evals, evecs = np.linalg.eigh(mcd_fit.covariance_)
+    #     normal = evecs[:, np.argmin(evals)]
+    #
+    # After which we need to assert that our `normal` is equal to [0, 0, 1].
+    # Do note that there is floating point error associated with this, so it's
+    # best to subtract the two and then compare some small tolerance (e.g.
+    # 1e-12).
+    MinCovDet(random_state=rand_gen).fit(data)
+
+
+def test_mcd_support_covariance_is_zero():
+    # Check that MCD returns a ValueError with informative message when the
+    # covariance of the support data is equal to 0.
+    X_1 = np.array([0.5, 0.1, 0.1, 0.1, 0.957, 0.1, 0.1, 0.1, 0.4285, 0.1])
+    X_1 = X_1.reshape(-1, 1)
+    X_2 = np.array([0.5, 0.3, 0.3, 0.3, 0.957, 0.3, 0.3, 0.3, 0.4285, 0.3])
+    X_2 = X_2.reshape(-1, 1)
+    msg = (
+        "The covariance matrix of the support data is equal to 0, try to "
+        "increase support_fraction"
+    )
+    for X in [X_1, X_2]:
+        with pytest.raises(ValueError, match=msg):
+            MinCovDet().fit(X)
+
+
+def test_mcd_increasing_det_warning(global_random_seed):
+    # Check that a warning is raised if we observe increasing determinants
+    # during the c_step. In theory the sequence of determinants should be
+    # decreasing. Increasing determinants are likely due to ill-conditioned
+    # covariance matrices that result in poor precision matrices.
+
+    X = [
+        [5.1, 3.5, 1.4, 0.2],
+        [4.9, 3.0, 1.4, 0.2],
+        [4.7, 3.2, 1.3, 0.2],
+        [4.6, 3.1, 1.5, 0.2],
+        [5.0, 3.6, 1.4, 0.2],
+        [4.6, 3.4, 1.4, 0.3],
+        [5.0, 3.4, 1.5, 0.2],
+        [4.4, 2.9, 1.4, 0.2],
+        [4.9, 3.1, 1.5, 0.1],
+        [5.4, 3.7, 1.5, 0.2],
+        [4.8, 3.4, 1.6, 0.2],
+        [4.8, 3.0, 1.4, 0.1],
+        [4.3, 3.0, 1.1, 0.1],
+        [5.1, 3.5, 1.4, 0.3],
+        [5.7, 3.8, 1.7, 0.3],
+        [5.4, 3.4, 1.7, 0.2],
+        [4.6, 3.6, 1.0, 0.2],
+        [5.0, 3.0, 1.6, 0.2],
+        [5.2, 3.5, 1.5, 0.2],
+    ]
+
+    mcd = MinCovDet(support_fraction=0.5, random_state=global_random_seed)
+    warn_msg = "Determinant has increased"
+    with pytest.warns(RuntimeWarning, match=warn_msg):
+        mcd.fit(X)