[MRG+1] Fix scikit-learn#10229: check_array should fail if array has …

…strings (scikit-learn#10495) * Add deprecation warning to check_array for flexible array w/ dtype=numeric
ccatalfo · Feb 22, 2018 · 7108d17 · 7108d17
1 parent d9a52cf
commit 7108d17
Show file tree

Hide file tree

Showing 3 changed files with 51 additions and 0 deletions.
diff --git a/doc/whats_new/v0.20.rst b/doc/whats_new/v0.20.rst
@@ -335,6 +335,12 @@ Feature Extraction
   (words or n-grams). :issue:`9147` by :user:`Claes-Fredrik Mannby <mannby>`
   and `Roman Yurchak`_.
 
+Utils
+
+- :func:`utils.validation.check_array` yield a ``FutureWarning`` indicating
+  that arrays of bytes/strings will be interpreted as decimal numbers
+  beginning in version 0.22. :issue:`10229` by :user:`Ryan Lee <rtlee9>`
+
 Preprocessing
 
 - Fixed bugs in :class:`preprocessing.LabelEncoder` which would sometimes throw

diff --git a/sklearn/utils/tests/test_validation.py b/sklearn/utils/tests/test_validation.py
@@ -285,6 +285,42 @@ def test_check_array():
     result = check_array(X_no_array)
     assert_true(isinstance(result, np.ndarray))
 
+    # deprecation warning if string-like array with dtype="numeric"
+    X_str = [['a', 'b'], ['c', 'd']]
+    assert_warns_message(
+        FutureWarning,
+        "arrays of strings will be interpreted as decimal numbers if "
+        "parameter 'dtype' is 'numeric'. It is recommended that you convert "
+        "the array to type np.float64 before passing it to check_array.",
+        check_array, X_str, "numeric")
+    assert_warns_message(
+        FutureWarning,
+        "arrays of strings will be interpreted as decimal numbers if "
+        "parameter 'dtype' is 'numeric'. It is recommended that you convert "
+        "the array to type np.float64 before passing it to check_array.",
+        check_array, np.array(X_str, dtype='U'), "numeric")
+    assert_warns_message(
+        FutureWarning,
+        "arrays of strings will be interpreted as decimal numbers if "
+        "parameter 'dtype' is 'numeric'. It is recommended that you convert "
+        "the array to type np.float64 before passing it to check_array.",
+        check_array, np.array(X_str, dtype='S'), "numeric")
+
+    # deprecation warning if byte-like array with dtype="numeric"
+    X_bytes = [[b'a', b'b'], [b'c', b'd']]
+    assert_warns_message(
+        FutureWarning,
+        "arrays of strings will be interpreted as decimal numbers if "
+        "parameter 'dtype' is 'numeric'. It is recommended that you convert "
+        "the array to type np.float64 before passing it to check_array.",
+        check_array, X_bytes, "numeric")
+    assert_warns_message(
+        FutureWarning,
+        "arrays of strings will be interpreted as decimal numbers if "
+        "parameter 'dtype' is 'numeric'. It is recommended that you convert "
+        "the array to type np.float64 before passing it to check_array.",
+        check_array, np.array(X_bytes, dtype='V1'), "numeric")
+
 
 def test_check_array_pandas_dtype_object_conversion():
     # test that data-frame like objects with dtype object

diff --git a/sklearn/utils/validation.py b/sklearn/utils/validation.py
@@ -516,6 +516,15 @@ def check_array(array, accept_sparse=False, dtype="numeric", order=None,
             # To ensure that array flags are maintained
             array = np.array(array, dtype=dtype, order=order, copy=copy)
 
+        # in the future np.flexible dtypes will be handled like object dtypes
+        if dtype_numeric and np.issubdtype(array.dtype, np.flexible):
+            warnings.warn(
+                "Beginning in version 0.22, arrays of strings will be "
+                "interpreted as decimal numbers if parameter 'dtype' is "
+                "'numeric'. It is recommended that you convert the array to "
+                "type np.float64 before passing it to check_array.",
+                FutureWarning)
+
         # make sure we actually converted to numeric:
         if dtype_numeric and array.dtype.kind == "O":
             array = array.astype(np.float64)