MAINT: Remove np.in1d and np.trapz usages (scikit-learn#27140)

Co-authored-by: Loïc Estève <loic.esteve@ymail.com>

Author: mtsokol

examples/semi_supervised/plot_label_propagation_digits_active_learning.py

@@ -79,7 +79,7 @@
     # select up to 5 digit examples that the classifier is most uncertain about
     uncertainty_index = np.argsort(pred_entropies)[::-1]
     uncertainty_index = uncertainty_index[
-        np.in1d(uncertainty_index, unlabeled_indices)
+        np.isin(uncertainty_index, unlabeled_indices)
     ][:5]
 
     # keep track of indices that we get labels for

sklearn/datasets/_twenty_newsgroups.py

@@ -319,7 +319,7 @@ def fetch_20newsgroups(
         # Sort the categories to have the ordering of the labels
         labels.sort()
         labels, categories = zip(*labels)
-        mask = np.in1d(data.target, labels)
+        mask = np.isin(data.target, labels)
         data.filenames = data.filenames[mask]
         data.target = data.target[mask]
         # searchsorted to have continuous labels

sklearn/feature_extraction/image.py

@@ -76,7 +76,7 @@ def _mask_edges_weights(mask, edges, weights=None):
     """Apply a mask to edges (weighted or not)"""
     inds = np.arange(mask.size)
     inds = inds[mask.ravel()]
-    ind_mask = np.logical_and(np.in1d(edges[0], inds), np.in1d(edges[1], inds))
+    ind_mask = np.logical_and(np.isin(edges[0], inds), np.isin(edges[1], inds))
     edges = edges[:, ind_mask]
     if weights is not None:
         weights = weights[ind_mask]

sklearn/metrics/_plot/tests/test_precision_recall_display.py

@@ -16,6 +16,7 @@
 from sklearn.pipeline import make_pipeline
 from sklearn.preprocessing import StandardScaler
 from sklearn.utils import shuffle
+from sklearn.utils.fixes import trapezoid
 
 # TODO: Remove when https://github.com/numpy/numpy/issues/14397 is resolved
 pytestmark = pytest.mark.filterwarnings(
@@ -289,7 +290,7 @@ def test_plot_precision_recall_pos_label(pyplot, constructor_name, response_meth
     # we should obtain the statistics of the "cancer" class
     avg_prec_limit = 0.65
     assert display.average_precision < avg_prec_limit
-    assert -np.trapz(display.precision, display.recall) < avg_prec_limit
+    assert -trapezoid(display.precision, display.recall) < avg_prec_limit
 
     # otherwise we should obtain the statistics of the "not cancer" class
     if constructor_name == "from_estimator":
@@ -308,7 +309,7 @@ def test_plot_precision_recall_pos_label(pyplot, constructor_name, response_meth
         )
     avg_prec_limit = 0.95
     assert display.average_precision > avg_prec_limit
-    assert -np.trapz(display.precision, display.recall) > avg_prec_limit
+    assert -trapezoid(display.precision, display.recall) > avg_prec_limit
 
 
 @pytest.mark.parametrize("constructor_name", ["from_estimator", "from_predictions"])

sklearn/metrics/_plot/tests/test_roc_curve_display.py

@@ -11,6 +11,7 @@
 from sklearn.pipeline import make_pipeline
 from sklearn.preprocessing import StandardScaler
 from sklearn.utils import shuffle
+from sklearn.utils.fixes import trapezoid
 
 
 @pytest.fixture(scope="module")
@@ -293,7 +294,7 @@ def test_plot_roc_curve_pos_label(pyplot, response_method, constructor_name):
     roc_auc_limit = 0.95679
 
     assert display.roc_auc == pytest.approx(roc_auc_limit)
-    assert np.trapz(display.tpr, display.fpr) == pytest.approx(roc_auc_limit)
+    assert trapezoid(display.tpr, display.fpr) == pytest.approx(roc_auc_limit)
 
     if constructor_name == "from_estimator":
         display = RocCurveDisplay.from_estimator(
@@ -311,4 +312,4 @@ def test_plot_roc_curve_pos_label(pyplot, response_method, constructor_name):
         )
 
     assert display.roc_auc == pytest.approx(roc_auc_limit)
-    assert np.trapz(display.tpr, display.fpr) == pytest.approx(roc_auc_limit)
+    assert trapezoid(display.tpr, display.fpr) == pytest.approx(roc_auc_limit)

sklearn/metrics/_ranking.py

@@ -38,6 +38,7 @@
 from ..utils._encode import _encode, _unique
 from ..utils._param_validation import Interval, StrOptions, validate_params
 from ..utils.extmath import stable_cumsum
+from ..utils.fixes import trapezoid
 from ..utils.multiclass import type_of_target
 from ..utils.sparsefuncs import count_nonzero
 from ..utils.validation import _check_pos_label_consistency, _check_sample_weight
@@ -104,9 +105,9 @@ def auc(x, y):
         else:
             raise ValueError("x is neither increasing nor decreasing : {}.".format(x))
 
-    area = direction * np.trapz(y, x)
+    area = direction * trapezoid(y, x)
     if isinstance(area, np.memmap):
-        # Reductions such as .sum used internally in np.trapz do not return a
+        # Reductions such as .sum used internally in trapezoid do not return a
         # scalar by default for numpy.memmap instances contrary to
         # regular numpy.ndarray instances.
         area = area.dtype.type(area)

sklearn/model_selection/_split.py

@@ -1973,8 +1973,8 @@ def _iter_indices(self, X, y, groups):
             # these are the indices of classes in the partition
             # invert them into data indices
 
-            train = np.flatnonzero(np.in1d(group_indices, group_train))
-            test = np.flatnonzero(np.in1d(group_indices, group_test))
+            train = np.flatnonzero(np.isin(group_indices, group_train))
+            test = np.flatnonzero(np.isin(group_indices, group_test))
 
             yield train, test
 

sklearn/model_selection/tests/test_search.py

@@ -1418,7 +1418,7 @@ def test_grid_search_correct_score_results():
         expected_keys = ("mean_test_score", "rank_test_score") + tuple(
             "split%d_test_score" % cv_i for cv_i in range(n_splits)
         )
-        assert all(np.in1d(expected_keys, result_keys))
+        assert all(np.isin(expected_keys, result_keys))
 
         cv = StratifiedKFold(n_splits=n_splits)
         n_splits = grid_search.n_splits_

sklearn/model_selection/tests/test_split.py

@@ -987,8 +987,8 @@ def test_group_shuffle_split():
             # First test: no train group is in the test set and vice versa
             l_train_unique = np.unique(l[train])
             l_test_unique = np.unique(l[test])
-            assert not np.any(np.in1d(l[train], l_test_unique))
-            assert not np.any(np.in1d(l[test], l_train_unique))
+            assert not np.any(np.isin(l[train], l_test_unique))
+            assert not np.any(np.isin(l[test], l_train_unique))
 
             # Second test: train and test add up to all the data
             assert l[train].size + l[test].size == l.size

sklearn/naive_bayes.py

@@ -467,7 +467,7 @@ def _partial_fit(self, X, y, classes=None, _refit=False, sample_weight=None):
         classes = self.classes_
 
         unique_y = np.unique(y)
-        unique_y_in_classes = np.in1d(unique_y, classes)
+        unique_y_in_classes = np.isin(unique_y, classes)
 
         if not np.all(unique_y_in_classes):
             raise ValueError(