validate values when converting to boolean array

pandas-dev · jreback · Nov 25, 2019 · Nov 11, 2019 · Nov 12, 2019 · Nov 12, 2019
commit 5ce67e2626b238d2c96becf4663618aec51891d1
diff --git a/pandas/core/arrays/boolean.py b/pandas/core/arrays/boolean.py
@@ -130,11 +130,27 @@ def coerce_to_array(values, mask=None, copy=False):
         if copy:
             values = values.copy()
     else:
+        # TODO conversion from integer/float ndarray can be done more efficiently
+        #  (avoid roundtrip through object)
         values_object = np.asarray(values, dtype=object)
+
+        inferred_dtype = lib.infer_dtype(values_object, skipna=True)
+        integer_like = ("floating", "integer", "mixed-integer-float")
+        if inferred_dtype not in ("boolean", "empty") + integer_like:
+            raise TypeError("Need to pass bool-like values")
+
         mask_values = isna(values_object)
         values = np.zeros(len(values), dtype=bool)
         values[~mask_values] = values_object[~mask_values].astype(bool)
 
+        # if the values were integer-like, validate it were actually 0/1's
+        if inferred_dtype in integer_like:
+            if not np.all(
+                values[~mask_values].astype(float)
+                == values_object[~mask_values].astype(float)
+            ):
+                raise TypeError("Need to pass bool-like values")
+
     if mask is None and mask_values is None:
         mask = np.zeros(len(values), dtype=bool)
     elif mask is None:

diff --git a/pandas/tests/arrays/test_boolean.py b/pandas/tests/arrays/test_boolean.py
@@ -64,6 +64,38 @@ def test_boolean_array_constructor_copy():
     assert result._mask is not mask
 
 
+def test_to_boolean_array():
+    expected = BooleanArray(
+        np.array([True, False, True]), np.array([False, False, False])
+    )
+
+    result = pd.array([True, False, True], dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)
+    result = pd.array(np.array([True, False, True]), dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)
+    result = pd.array(np.array([True, False, True], dtype=object), dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)
+
+    # with missing values
+    expected = BooleanArray(
+        np.array([True, False, True]), np.array([False, False, True])
+    )
+
+    result = pd.array([True, False, None], dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)
+    result = pd.array(np.array([True, False, None], dtype=object), dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_to_boolean_array_all_none():
+    expected = BooleanArray(np.array([True, True, True]), np.array([True, True, True]))
+
+    result = pd.array([None, None, None], dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)
+    result = pd.array(np.array([None, None, None], dtype=object), dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)
+
+
 @pytest.mark.parametrize(
     "a, b",
     [
@@ -79,33 +111,44 @@ def test_to_boolean_array_none_is_nan(a, b):
     tm.assert_extension_array_equal(result, expected)
    
 
-# @pytest.mark.parametrize(
-#     "values",
-#     [
-#         ["foo", "bar"],
-#         ["1", "2"],
-#         "foo",
-#         [1],
-#         [1.0],
-#         pd.date_range("20130101", periods=2),
-#         np.array(["foo"]),
-#         [[1, 2], [3, 4]],
-#         [np.nan, {"a": 1}],
-#     ],
-# )
-# def test_to_boolean_array_error(values):
-#     # error in converting existing arrays to BooleanArray
-#     with pytest.raises(TypeError):
-#         pd.array(values, dtype="boolean")
-
-
-def test_to_boolean_array_integer():
+@pytest.mark.parametrize(
+    "values",
+    [
+        ["foo", "bar"],
+        ["1", "2"],
+        # "foo",
+        [1, 2],
+        [1.0, 2.0],
+        pd.date_range("20130101", periods=2),
+        np.array(["foo"]),
+        [np.nan, {"a": 1}],
+    ],
+)
+def test_to_boolean_array_error(values):
+    # error in converting existing arrays to BooleanArray
+    with pytest.raises(TypeError):
+        pd.array(values, dtype="boolean")
+
+
+def test_to_boolean_array_integer_like():
+    # integers of 0's and 1's
     result = pd.array([1, 0, 1, 0], dtype="boolean")
     expected = pd.array([True, False, True, False], dtype="boolean")
     tm.assert_extension_array_equal(result, expected)
 
-    # with pytest.raises(TypeError, match="cannot safely cast non-equivalent"):
-    #     pd.array([1, 2, 3], dtype="boolean")
+    result = pd.array(np.array([1, 0, 1, 0]), dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)
+
+    result = pd.array(np.array([1.0, 0.0, 1.0, 0.0]), dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)
+
+    # with missing values
+    result = pd.array([1, 0, 1, None], dtype="boolean")
+    expected = pd.array([True, False, True, None], dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)
+
+    result = pd.array(np.array([1.0, 0.0, 1.0, np.nan]), dtype="boolean")
+    tm.assert_extension_array_equal(result, expected)
 
 
 def test_coerce_to_array():