Merge remote-tracking branch 'upstream/main' into features2

Author: DeaMariaLeon

asv_benchmarks/benchmarks/datasets.py

@@ -1,7 +1,6 @@
 from pathlib import Path
 
 import numpy as np
-import scipy.sparse as sp
 from joblib import Memory
 
 from sklearn.datasets import (
@@ -17,6 +16,7 @@
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import MaxAbsScaler, StandardScaler
+from sklearn.utils.fixes import _sparse_random_array
 
 # memory location for caching datasets
 M = Memory(location=str(Path(__file__).resolve().parent / "cache"))
@@ -100,12 +100,12 @@ def _synth_regression_dataset(n_samples=100000, n_features=100, dtype=np.float32
 def _synth_regression_sparse_dataset(
     n_samples=10000, n_features=10000, density=0.01, dtype=np.float32
 ):
-    X = sp.random(
-        m=n_samples, n=n_features, density=density, format="csr", random_state=0
+    X = _sparse_random_array(
+        (n_samples, n_features), density=density, format="csr", random_state=0
     )
     X.data = np.random.RandomState(0).randn(X.getnnz())
     X = X.astype(dtype, copy=False)
-    coefs = sp.random(m=n_features, n=1, density=0.5, random_state=0)
+    coefs = _sparse_random_array((n_features, 1), density=0.5, random_state=0)
     coefs.data = np.random.RandomState(0).randn(coefs.getnnz())
     y = X.dot(coefs.toarray()).reshape(-1)
     y += 0.2 * y.std() * np.random.randn(n_samples)
@@ -155,9 +155,8 @@ def _random_dataset(
         X = np.random.RandomState(0).random_sample((n_samples, n_features))
         X = X.astype(dtype, copy=False)
     else:
-        X = sp.random(
-            n_samples,
-            n_features,
+        X = _sparse_random_array(
+            (n_samples, n_features),
             density=0.05,
             format="csr",
             dtype=dtype,

benchmarks/bench_feature_expansions.py

@@ -2,9 +2,9 @@
 
 import matplotlib.pyplot as plt
 import numpy as np
-import scipy.sparse as sparse
 
 from sklearn.preprocessing import PolynomialFeatures
+from sklearn.utils.fixes import _sparse_random_array
 
 degree = 2
 trials = 3
@@ -21,7 +21,7 @@
     for density in densities:
         for dim_index, dim in enumerate(dimensionalities):
             print(trial, density, dim)
-            X_csr = sparse.random(num_rows, dim, density).tocsr()
+            X_csr = _sparse_random_array((num_rows, dim), density=density, format="csr")
             X_dense = X_csr.toarray()
             # CSR
             t0 = time()

benchmarks/bench_plot_randomized_svd.py

@@ -188,7 +188,7 @@ def get_data(dataset_name):
         data = np.repeat(data, 10)
         row = np.random.uniform(0, small_size, sparsity)
         col = np.random.uniform(0, small_size, sparsity)
-        X = sp.sparse.csr_matrix((data, (row, col)), shape=(size, small_size))
+        X = sp.sparse.csr_array((data, (row, col)), shape=(size, small_size))
         del data
         del row
         del col

benchmarks/bench_random_projections.py

@@ -70,7 +70,7 @@ def bench_scikit_transformer(X, transformer):
 # Gaussian distributed values
 def make_sparse_random_data(n_samples, n_features, n_nonzeros, random_state=None):
     rng = np.random.RandomState(random_state)
-    data_coo = sp.coo_matrix(
+    data_coo = sp.coo_array(
         (
             rng.randn(n_nonzeros),
             (

doc/modules/impute.rst

@@ -56,11 +56,11 @@ that contain the missing values::
 The :class:`SimpleImputer` class also supports sparse matrices::
 
     >>> import scipy.sparse as sp
-    >>> X = sp.csc_matrix([[1, 2], [0, -1], [8, 4]])
+    >>> X = sp.csc_array([[1, 2], [0, -1], [8, 4]])
     >>> imp = SimpleImputer(missing_values=-1, strategy='mean')
     >>> imp.fit(X)
     SimpleImputer(missing_values=-1)
-    >>> X_test = sp.csc_matrix([[-1, 2], [6, -1], [7, 6]])
+    >>> X_test = sp.csc_array([[-1, 2], [6, -1], [7, 6]])
     >>> print(imp.transform(X_test).toarray())
     [[3. 2.]
      [6. 3.]

doc/modules/multiclass.rst

@@ -169,9 +169,9 @@ Valid :term:`multiclass` representations for
      [1 0 0]
      [0 1 0]]
     >>> from scipy import sparse
-    >>> y_sparse = sparse.csr_matrix(y_dense)
+    >>> y_sparse = sparse.csr_array(y_dense)
     >>> print(y_sparse)
-    <Compressed Sparse Row sparse matrix of dtype 'int64'
+    <Compressed Sparse Row sparse array of dtype 'int64'
       with 4 stored elements and shape (4, 3)>
       Coords Values
       (0, 0) 1
@@ -379,9 +379,9 @@ refer to :ref:`preprocessing_targets`.
 
 An example of the same ``y`` in sparse matrix form:
 
-  >>> y_sparse = sparse.csr_matrix(y)
+  >>> y_sparse = sparse.csr_array(y)
   >>> print(y_sparse)
-  <Compressed Sparse Row sparse matrix of dtype 'int64'
+  <Compressed Sparse Row sparse array of dtype 'int64'
     with 4 stored elements and shape (3, 4)>
     Coords Values
     (0, 0) 1

doc/whats_new/upcoming_changes/many-modules/31177.major-feature.rst

@@ -0,0 +1,9 @@
+- Introduced a new config key: "sparse_interface" to control whether functions
+  return sparse objects using SciPy sparse matrix or SciPy sparse array.
+  Use `sklearn.set_config(sparse_interface="sparray")` to have sklearn
+  return sparse arrays. See more at `the SciPy Sparse Migration Guide.
+  <https://docs.scipy.org/doc/scipy/reference/sparse.migration_to_sparray.html>`_
+  The scikit-learn config "sparse_interface" initially defaults
+  to sparse matrix ("spmatrix"). The plan is to have the default change to
+  sparse array ("sparray") in a few releases.
+  By :user:`Dan Schult <dschult>`

doc/whats_new/upcoming_changes/sklearn.metrics/33405.fix.rst

@@ -0,0 +1,4 @@
+- :meth:`metrics.PrecisionRecallDisplay.from_estimator` and 
+  :meth:`metrics.PrecisionRecallDisplay.from_predictions` now 
+  correctly plot chance level line when `y_true` is a pytorch tensor.
+  By :user:`Lucas Oliveira <lucolivi>`.

doc/whats_new/upcoming_changes/sklearn.preprocessing/33453.api.rst

@@ -0,0 +1,5 @@
+- The `shuffle` and the `random_state` parameters are deprecated on
+  :class:`~preprocessing.TargetEncoder` and will be removed in version 1.11. Pass a
+  cross-validation generator as `cv` argument to specify the shuffling behaviour
+  instead.
+  By :user:`Stefanie Senger <StefanieSenger>`.

examples/applications/plot_tomography_l1_reconstruction.py

@@ -89,7 +89,9 @@ def build_projection_operator(l_x, n_dir):
         weights += list(w[mask])
         camera_inds += list(inds[mask] + i * l_x)
         data_inds += list(data_unravel_indices[mask])
-    proj_operator = sparse.coo_matrix((weights, (camera_inds, data_inds)))
+    camera_inds = np.array(camera_inds, dtype=np.int32)  # lasso needs int32 inds
+    data_inds = np.array(data_inds, dtype=np.int32)
+    proj_operator = sparse.coo_array((weights, (camera_inds, data_inds)))
     return proj_operator