scikit-learn · NicolasHug · Apr 19, 2019 · Mar 4, 2019 · Mar 4, 2019 · Mar 4, 2019
diff --git a/doc/whats_new/v0.21.rst b/doc/whats_new/v0.21.rst
@@ -627,6 +627,15 @@ Support for Python 3.4 and below has been officially dropped.
   affects all ensemble methods using decision trees.
   :issue:`12344` by :user:`Adrin Jalali <adrinjalali>`.
 
+:mod:`sklearn.utils`
+...................
+
+- |API| Deprecated ``warn_on_dtype`` parameter from :func:`utils.check_array`
+  and :func:`utils.check_X_y`. Added explicit warning for dtype conversion
+  in :func:`check_pairwise_arrays` if the ``metric`` being passed is a
+  pairwise boolean metric.
+  :issue:`13382` by :user:`Prathmesh Savale <praths007>`.
+
 Multiple modules
 ................
 

diff --git a/sklearn/metrics/pairwise.py b/sklearn/metrics/pairwise.py
@@ -30,6 +30,7 @@
 from ..utils._joblib import effective_n_jobs
 
 from .pairwise_fast import _chi2_kernel_fast, _sparse_manhattan
+from ..exceptions import DataConversionWarning
 
 
 # Utility Functions
@@ -99,19 +100,18 @@ def check_pairwise_arrays(X, Y, precomputed=False, dtype=None):
     """
     X, Y, dtype_float = _return_float_dtype(X, Y)
 
-    warn_on_dtype = dtype is not None
     estimator = 'check_pairwise_arrays'
     if dtype is None:
         dtype = dtype_float
 
     if Y is X or Y is None:
         X = Y = check_array(X, accept_sparse='csr', dtype=dtype,
-                            warn_on_dtype=warn_on_dtype, estimator=estimator)
+                            estimator=estimator)
     else:
         X = check_array(X, accept_sparse='csr', dtype=dtype,
-                        warn_on_dtype=warn_on_dtype, estimator=estimator)
+                        estimator=estimator)
         Y = check_array(Y, accept_sparse='csr', dtype=dtype,
-                        warn_on_dtype=warn_on_dtype, estimator=estimator)
+                        estimator=estimator)
 
     if precomputed:
         if X.shape[1] != Y.shape[0]:
@@ -1421,6 +1421,11 @@ def pairwise_distances(X, Y=None, metric="euclidean", n_jobs=None, **kwds):
                             " support sparse matrices.")
 
         dtype = bool if metric in PAIRWISE_BOOLEAN_FUNCTIONS else None
+
+        if dtype == bool and (X.dtype != bool or Y.dtype != bool):
+            msg = "Data was converted to boolean for metric %s" % metric
+            warnings.warn(msg, DataConversionWarning)
+
         X, Y = check_pairwise_arrays(X, Y, dtype=dtype)
 
         # precompute data-derived metric params

diff --git a/sklearn/metrics/tests/test_pairwise.py b/sklearn/metrics/tests/test_pairwise.py
@@ -138,6 +138,21 @@ def test_pairwise_boolean_distance(metric):
             res[np.isnan(res)] = 0
             assert np.sum(res != 0) == 0
 
+    # non-boolean arrays are converted to boolean for boolean
+    # distance metrics with a data conversion warning
+    msg = "Data was converted to boolean for metric %s" % metric
+    with pytest.warns(DataConversionWarning, match=msg):
+        pairwise_distances(X, metric=metric)
+
+
+def test_no_data_conversion_warning():
+    # No warnings issued if metric is not a boolean distance function
+    rng = np.random.RandomState(0)
+    X = rng.randn(5, 4)
+    with pytest.warns(None) as records:
+        pairwise_distances(X, metric="minkowski")
+    assert len(records) == 0
+
 
 @pytest.mark.parametrize('func', [pairwise_distances, pairwise_kernels])
 def test_pairwise_precomputed(func):

diff --git a/sklearn/preprocessing/data.py b/sklearn/preprocessing/data.py
@@ -137,8 +137,8 @@ def scale(X, axis=0, with_mean=True, with_std=True, copy=True):
 
     """  # noqa
     X = check_array(X, accept_sparse='csc', copy=copy, ensure_2d=False,
-                    warn_on_dtype=False, estimator='the scale function',
-                    dtype=FLOAT_DTYPES, force_all_finite='allow-nan')
+                    estimator='the scale function', dtype=FLOAT_DTYPES,
+                    force_all_finite='allow-nan')
     if sparse.issparse(X):
         if with_mean:
             raise ValueError(
@@ -348,7 +348,7 @@ def partial_fit(self, X, y=None):
             raise TypeError("MinMaxScaler does no support sparse input. "
                             "You may consider to use MaxAbsScaler instead.")
 
-        X = check_array(X, copy=self.copy, warn_on_dtype=False,
+        X = check_array(X, copy=self.copy,
                         estimator=self, dtype=FLOAT_DTYPES,
                         force_all_finite="allow-nan")
 
@@ -468,7 +468,7 @@ def minmax_scale(X, feature_range=(0, 1), axis=0, copy=True):
     """  # noqa
     # Unlike the scaler object, this function allows 1d input.
     # If copy is required, it will be done inside the scaler object.
-    X = check_array(X, copy=False, ensure_2d=False, warn_on_dtype=False,
+    X = check_array(X, copy=False, ensure_2d=False,
                     dtype=FLOAT_DTYPES, force_all_finite='allow-nan')
     original_ndim = X.ndim
 
@@ -659,8 +659,8 @@ def partial_fit(self, X, y=None):
             Ignored
         """
         X = check_array(X, accept_sparse=('csr', 'csc'), copy=self.copy,
-                        warn_on_dtype=False, estimator=self,
-                        dtype=FLOAT_DTYPES, force_all_finite='allow-nan')
+                        estimator=self, dtype=FLOAT_DTYPES,
+                        force_all_finite='allow-nan')
 
         # Even in the case of `with_mean=False`, we update the mean anyway
         # This is needed for the incremental computation of the var
@@ -753,7 +753,7 @@ def transform(self, X, copy=None):
         check_is_fitted(self, 'scale_')
 
         copy = copy if copy is not None else self.copy
-        X = check_array(X, accept_sparse='csr', copy=copy, warn_on_dtype=False,
+        X = check_array(X, accept_sparse='csr', copy=copy,
                         estimator=self, dtype=FLOAT_DTYPES,
                         force_all_finite='allow-nan')
 

diff --git a/sklearn/utils/tests/test_validation.py b/sklearn/utils/tests/test_validation.py
@@ -387,12 +387,15 @@ def test_check_array_dtype_warning():
         assert_equal(X_checked.dtype, np.float64)
 
     for X in float64_data:
-        X_checked = assert_no_warnings(check_array, X, dtype=np.float64,
-                                       accept_sparse=True, warn_on_dtype=True)
-        assert_equal(X_checked.dtype, np.float64)
-        X_checked = assert_no_warnings(check_array, X, dtype=np.float64,
-                                       accept_sparse=True, warn_on_dtype=False)
-        assert_equal(X_checked.dtype, np.float64)
+        with pytest.warns(None) as record:
+            warnings.simplefilter("ignore", DeprecationWarning)  # 0.23
+            X_checked = check_array(X, dtype=np.float64,
+                                    accept_sparse=True, warn_on_dtype=True)
+            assert_equal(X_checked.dtype, np.float64)
+            X_checked = check_array(X, dtype=np.float64,
+                                    accept_sparse=True, warn_on_dtype=False)
+            assert_equal(X_checked.dtype, np.float64)
+        assert len(record) == 0
 
     for X in float32_data:
         X_checked = assert_no_warnings(check_array, X,
@@ -417,6 +420,17 @@ def test_check_array_dtype_warning():
     assert_equal(X_checked.format, 'csr')
 
 
+def test_check_array_warn_on_dtype_deprecation():
+    X = np.asarray([[0.0], [1.0]])
+    Y = np.asarray([[2.0], [3.0]])
+    with pytest.warns(DeprecationWarning,
+                      match="'warn_on_dtype' is deprecated"):
+        check_array(X, warn_on_dtype=True)
+    with pytest.warns(DeprecationWarning,
+                      match="'warn_on_dtype' is deprecated"):
+        check_X_y(X, Y, warn_on_dtype=True)
+
+
 def test_check_array_accept_sparse_type_exception():
     X = [[1, 2], [3, 4]]
     X_csr = sp.csr_matrix(X)
@@ -690,8 +704,7 @@ def test_suppress_validation():
 def test_check_array_series():
     # regression test that check_array works on pandas Series
     pd = importorskip("pandas")
-    res = check_array(pd.Series([1, 2, 3]), ensure_2d=False,
-                      warn_on_dtype=True)
+    res = check_array(pd.Series([1, 2, 3]), ensure_2d=False)
     assert_array_equal(res, np.array([1, 2, 3]))
 
     # with categorical dtype (not a numpy dtype) (GH12699)
@@ -712,7 +725,10 @@ def test_check_dataframe_warns_on_dtype():
                          check_array, df, dtype=np.float64, warn_on_dtype=True)
     assert_warns(DataConversionWarning, check_array, df,
                  dtype='numeric', warn_on_dtype=True)
-    assert_no_warnings(check_array, df, dtype='object', warn_on_dtype=True)
+    with pytest.warns(None) as record:
+        warnings.simplefilter("ignore", DeprecationWarning)  # 0.23
+        check_array(df, dtype='object', warn_on_dtype=True)
+    assert len(record) == 0
 
     # Also check that it raises a warning for mixed dtypes in a DataFrame.
     df_mixed = pd.DataFrame([['1', 2, 3], ['4', 5, 6]])
@@ -728,8 +744,11 @@ def test_check_dataframe_warns_on_dtype():
     df_mixed_numeric = pd.DataFrame([[1., 2, 3], [4., 5, 6]])
     assert_warns(DataConversionWarning, check_array, df_mixed_numeric,
                  dtype='numeric', warn_on_dtype=True)
-    assert_no_warnings(check_array, df_mixed_numeric.astype(int),
-                       dtype='numeric', warn_on_dtype=True)
+    with pytest.warns(None) as record:
+        warnings.simplefilter("ignore", DeprecationWarning)  # 0.23
+        check_array(df_mixed_numeric.astype(int),
+                    dtype='numeric', warn_on_dtype=True)
+    assert len(record) == 0
 
 
 class DummyMemory:

diff --git a/sklearn/utils/validation.py b/sklearn/utils/validation.py
@@ -332,7 +332,7 @@ def _ensure_no_complex_data(array):
 def check_array(array, accept_sparse=False, accept_large_sparse=True,
                 dtype="numeric", order=None, copy=False, force_all_finite=True,
                 ensure_2d=True, allow_nd=False, ensure_min_samples=1,
-                ensure_min_features=1, warn_on_dtype=False, estimator=None):
+                ensure_min_features=1, warn_on_dtype=None, estimator=None):
 
     """Input validation on an array, list, sparse matrix or similar.
 
@@ -407,19 +407,30 @@ def check_array(array, accept_sparse=False, accept_large_sparse=True,
         dimensions or is originally 1D and ``ensure_2d`` is True. Setting to 0
         disables this check.
 
-    warn_on_dtype : boolean (default=False)
+    warn_on_dtype : boolean or None, optional (default=None)
         Raise DataConversionWarning if the dtype of the input data structure
         does not match the requested dtype, causing a memory copy.
 
+        .. deprecated:: 0.21
+            ``warn_on_dtype`` is deprecated in version 0.21 and will be
+            removed in 0.23.
+
     estimator : str or estimator instance (default=None)
         If passed, include the name of the estimator in warning messages.
 
     Returns
     -------
     array_converted : object
         The converted and validated array.
-
     """
+    # warn_on_dtype deprecation
+    if warn_on_dtype is not None:
+        warnings.warn(
+            "'warn_on_dtype' is deprecated in version 0.21 and will be "
+            "removed in 0.23. Don't set `warn_on_dtype` to remove this "
+            "warning.",
+            DeprecationWarning)
+
     # store reference to original array to check if copy is needed when
     # function returns
     array_orig = array
@@ -590,7 +601,7 @@ def check_X_y(X, y, accept_sparse=False, accept_large_sparse=True,
               dtype="numeric", order=None, copy=False, force_all_finite=True,
               ensure_2d=True, allow_nd=False, multi_output=False,
               ensure_min_samples=1, ensure_min_features=1, y_numeric=False,
-              warn_on_dtype=False, estimator=None):
+              warn_on_dtype=None, estimator=None):
     """Input validation for standard estimators.
 
     Checks X and y for consistent length, enforces X to be 2D and y 1D. By
@@ -675,10 +686,14 @@ def check_X_y(X, y, accept_sparse=False, accept_large_sparse=True,
         it is converted to float64. Should only be used for regression
         algorithms.
 
-    warn_on_dtype : boolean (default=False)
+    warn_on_dtype : boolean or None, optional (default=None)
         Raise DataConversionWarning if the dtype of the input data structure
         does not match the requested dtype, causing a memory copy.
 
+        .. deprecated:: 0.21
+            ``warn_on_dtype`` is deprecated in version 0.21 and will be
+             removed in 0.23.
+
     estimator : str or estimator instance (default=None)
         If passed, include the name of the estimator in warning messages.