Merge pull request #8146 from jreback/cat_dtype

BUG: comparison of category vs np dtypes buggy (GH8143)

Author: jreback

doc/source/v0.15.0.txt

@@ -347,7 +347,8 @@ Categoricals in Series/DataFrame
 
 :class:`~pandas.Categorical` can now be included in `Series` and `DataFrames` and gained new
 methods to manipulate. Thanks to Jan Schultz for much of this API/implementation. (:issue:`3943`, :issue:`5313`, :issue:`5314`,
-:issue:`7444`, :issue:`7839`, :issue:`7848`, :issue:`7864`, :issue:`7914`, :issue:`7768`, :issue:`8006`, :issue:`3678`, :issue:`8075`, :issue:`8076`).
+:issue:`7444`, :issue:`7839`, :issue:`7848`, :issue:`7864`, :issue:`7914`, :issue:`7768`, :issue:`8006`, :issue:`3678`,
+:issue:`8075`, :issue:`8076`, :issue:`8143`).
 
 For full docs, see the :ref:`Categorical introduction <categorical>` and the
 :ref:`API documentation <api.categorical>`.

pandas/core/ops.py

@@ -522,7 +522,8 @@ def _comp_method_SERIES(op, name, str_rep, masker=False):
     code duplication.
     """
     def na_op(x, y):
-        if com.is_categorical_dtype(x) != com.is_categorical_dtype(y):
+
+        if com.is_categorical_dtype(x) != (not np.isscalar(y) and com.is_categorical_dtype(y)):
             msg = "Cannot compare a Categorical for op {op} with type {typ}. If you want to \n" \
                   "compare values, use 'series <op> np.asarray(cat)'."
             raise TypeError(msg.format(op=op,typ=type(y)))

pandas/lib.pyx

@@ -647,7 +647,21 @@ def scalar_compare(ndarray[object] values, object val, object op):
             if _checknull(x):
                 result[i] = True
             else:
-                result[i] = cpython.PyObject_RichCompareBool(x, val, flag)
+                try:
+                    result[i] = cpython.PyObject_RichCompareBool(x, val, flag)
+                except (TypeError):
+                    result[i] = True
+    elif flag == cpython.Py_EQ:
+        for i in range(n):
+            x = values[i]
+            if _checknull(x):
+                result[i] = False
+            else:
+                try:
+                    result[i] = cpython.PyObject_RichCompareBool(x, val, flag)
+                except (TypeError):
+                    result[i] = False
+
     else:
         for i in range(n):
             x = values[i]

pandas/tests/test_categorical.py

@@ -785,6 +785,25 @@ def f():
         self.assertFalse(dtype == np.str_)
         self.assertFalse(np.str_ == dtype)
 
+        # GH8143
+        index = ['cat','obj','num']
+        cat = pd.Categorical(['a', 'b', 'c'])
+        obj = pd.Series(['a', 'b', 'c'])
+        num = pd.Series([1, 2, 3])
+        df = pd.concat([pd.Series(cat), obj, num], axis=1, keys=index)
+
+        result = df.dtypes == 'object'
+        expected = Series([False,True,False],index=index)
+        tm.assert_series_equal(result, expected)
+
+        result = df.dtypes == 'int64'
+        expected = Series([False,False,True],index=index)
+        tm.assert_series_equal(result, expected)
+
+        result = df.dtypes == 'category'
+        expected = Series([True,False,False],index=index)
+        tm.assert_series_equal(result, expected)
+
     def test_basic(self):
 
         # test basic creation / coercion of categoricals