scikit-learn · jeremiedbb · Mar 2, 2023 · Mar 1, 2023
diff --git a/benchmarks/bench_20newsgroups.py b/benchmarks/bench_20newsgroups.py
@@ -47,7 +47,7 @@
    print(f"X_train.shape = {X_train.shape}")
    print(f"X_train.format = {X_train.format}")
    print(f"X_train.dtype = {X_train.dtype}")
-    print(f"X_train density = {X_train.nnz / np.product(X_train.shape)}")
+    print(f"X_train density = {X_train.nnz / np.prod(X_train.shape)}")
    print(f"y_train {y_train.shape}")
    print(f"X_test {X_test.shape}")
    print(f"X_test.format = {X_test.format}")

diff --git a/doc/developers/develop.rst b/doc/developers/develop.rst
@@ -533,7 +533,7 @@ general only be determined at runtime.
 The current set of estimator tags are:

 allow_nan (default=False)
-    whether the estimator supports data with missing values encoded as np.NaN
+    whether the estimator supports data with missing values encoded as np.nan

 binary_only (default=False)
    whether estimator supports binary classification but lacks multi-class

diff --git a/doc/modules/grid_search.rst b/doc/modules/grid_search.rst
@@ -660,8 +660,8 @@ Robustness to failure
 Some parameter settings may result in a failure to ``fit`` one or more folds
 of the data.  By default, this will cause the entire search to fail, even if
 some parameter settings could be fully evaluated. Setting ``error_score=0``
-(or `=np.NaN`) will make the procedure robust to such failure, issuing a
-warning and setting the score for that fold to 0 (or `NaN`), but completing
+(or `=np.nan`) will make the procedure robust to such failure, issuing a
+warning and setting the score for that fold to 0 (or `nan`), but completing
 the search.

 .. _alternative_cv:

diff --git a/sklearn/_loss/glm_distribution.py b/sklearn/_loss/glm_distribution.py
@@ -222,7 +222,7 @@ def power(self, power):

        if power <= 0:
            # Extreme Stable or Normal distribution
-            self._lower_bound = DistributionBoundary(-np.Inf, inclusive=False)
+            self._lower_bound = DistributionBoundary(-np.inf, inclusive=False)
        elif 0 < power < 1:
            raise ValueError(
                "Tweedie distribution is only defined for power<=0 and power>=1."

diff --git a/sklearn/decomposition/_nmf.py b/sklearn/decomposition/_nmf.py
@@ -155,7 +155,7 @@ def _beta_divergence(X, W, H, beta, square_root=False):
    # Itakura-Saito divergence
    elif beta == 0:
        div = X_data / WH_data
-        res = np.sum(div) - np.product(X.shape) - np.sum(np.log(div))
+        res = np.sum(div) - np.prod(X.shape) - np.sum(np.log(div))

    # beta-divergence, beta not in (0, 1, 2)
    else:

diff --git a/sklearn/ensemble/_hist_gradient_boosting/tests/test_binning.py b/sklearn/ensemble/_hist_gradient_boosting/tests/test_binning.py
@@ -294,9 +294,9 @@ def test_missing_values_support(n_bins, n_bins_non_missing, X_trans_expected):

    X = [
        [1, 1, 0],
-        [np.NaN, np.NaN, 0],
+        [np.nan, np.nan, 0],
        [2, 1, 0],
-        [np.NaN, 2, 1],
+        [np.nan, 2, 1],
        [3, 2, 1],
        [4, 1, 0],
    ]

diff --git a/sklearn/ensemble/tests/test_bagging.py b/sklearn/ensemble/tests/test_bagging.py
@@ -831,7 +831,7 @@ def test_bagging_regressor_with_missing_inputs():
            [2, None, 6],
            [2, np.nan, 6],
            [2, np.inf, 6],
-            [2, np.NINF, 6],
+            [2, -np.inf, 6],
        ]
    )
    y_values = [
@@ -872,7 +872,7 @@ def test_bagging_classifier_with_missing_inputs():
            [2, None, 6],
            [2, np.nan, 6],
            [2, np.inf, 6],
-            [2, np.NINF, 6],
+            [2, -np.inf, 6],
        ]
    )
    y = np.array([3, 6, 6, 6, 6])

diff --git a/sklearn/feature_selection/tests/test_from_model.py b/sklearn/feature_selection/tests/test_from_model.py
@@ -532,8 +532,8 @@ def test_fit_accepts_nan_inf():
    model = SelectFromModel(estimator=clf)

    nan_data = data.copy()
-    nan_data[0] = np.NaN
-    nan_data[1] = np.Inf
+    nan_data[0] = np.nan
+    nan_data[1] = np.inf

    model.fit(data, y)

@@ -546,8 +546,8 @@ def test_transform_accepts_nan_inf():
    model = SelectFromModel(estimator=clf)
    model.fit(nan_data, y)

-    nan_data[0] = np.NaN
-    nan_data[1] = np.Inf
+    nan_data[0] = np.nan
+    nan_data[1] = np.inf

    model.transform(nan_data)


diff --git a/sklearn/feature_selection/tests/test_rfe.py b/sklearn/feature_selection/tests/test_rfe.py
@@ -505,8 +505,8 @@ def test_rfe_allow_nan_inf_in_x(cv):
    y = iris.target

    # add nan and inf value to X
-    X[0][0] = np.NaN
-    X[0][1] = np.Inf
+    X[0][0] = np.nan
+    X[0][1] = np.inf

    clf = MockClassifier()
    if cv is not None:

diff --git a/sklearn/feature_selection/tests/test_variance_threshold.py b/sklearn/feature_selection/tests/test_variance_threshold.py
@@ -54,9 +54,9 @@ def test_zero_variance_floating_point_error():
 def test_variance_nan():
    arr = np.array(data, dtype=np.float64)
    # add single NaN and feature should still be included
-    arr[0, 0] = np.NaN
+    arr[0, 0] = np.nan
    # make all values in feature NaN and feature should be rejected
-    arr[:, 1] = np.NaN
+    arr[:, 1] = np.nan

    for X in [arr, csr_matrix(arr), csc_matrix(arr), bsr_matrix(arr)]:
        sel = VarianceThreshold().fit(X)

diff --git a/sklearn/mixture/tests/test_bayesian_mixture.py b/sklearn/mixture/tests/test_bayesian_mixture.py
@@ -244,7 +244,7 @@ def test_monotonic_likelihood():
                random_state=rng,
                tol=1e-3,
            )
-            current_lower_bound = -np.infty
+            current_lower_bound = -np.inf
            # Do one training iteration at a time so we can make sure that the
            # training log likelihood increases after each iteration.
            for _ in range(600):

diff --git a/sklearn/mixture/tests/test_gaussian_mixture.py b/sklearn/mixture/tests/test_gaussian_mixture.py
@@ -986,7 +986,7 @@ def test_monotonic_likelihood():
            random_state=rng,
            tol=1e-7,
        )
-        current_log_likelihood = -np.infty
+        current_log_likelihood = -np.inf
        with warnings.catch_warnings():
            warnings.simplefilter("ignore", ConvergenceWarning)
            # Do one training iteration at a time so we can make sure that the

diff --git a/sklearn/model_selection/_search.py b/sklearn/model_selection/_search.py
@@ -151,7 +151,7 @@ def __iter__(self):

    def __len__(self):
        """Number of points on the grid."""
-        # Product function that can handle iterables (np.product can't).
+        # Product function that can handle iterables (np.prod can't).
        product = partial(reduce, operator.mul)
        return sum(
            product(len(v) for v in p.values()) if p else 1 for p in self.param_grid
@@ -184,7 +184,7 @@ def __getitem__(self, ind):
            # Reverse so most frequent cycling parameter comes first
            keys, values_lists = zip(*sorted(sub_grid.items())[::-1])
            sizes = [len(v_list) for v_list in values_lists]
-            total = np.product(sizes)
+            total = np.prod(sizes)

            if ind >= total:
                # Try the next grid

diff --git a/sklearn/utils/sparsefuncs.py b/sklearn/utils/sparsefuncs.py
@@ -452,7 +452,7 @@ def _sparse_min_or_max(X, axis, min_or_max):
        if X.nnz == 0:
            return zero
        m = min_or_max.reduce(X.data.ravel())
-        if X.nnz != np.product(X.shape):
+        if X.nnz != np.prod(X.shape):
            m = min_or_max(zero, m)
        return m
    if axis < 0:

diff --git a/sklearn/utils/tests/test_pprint.py b/sklearn/utils/tests/test_pprint.py
@@ -278,7 +278,7 @@ def test_changed_only():
    expected = """SimpleImputer(missing_values=0)"""
    assert imputer.__repr__() == expected

-    # Defaults to np.NaN, trying with float('NaN')
+    # Defaults to np.nan, trying with float('NaN')
    imputer = SimpleImputer(missing_values=float("NaN"))
    expected = """SimpleImputer()"""
    assert imputer.__repr__() == expected