Refactored

Author: TomAugspurger

pandas/_libs/parsers.pyx

@@ -48,7 +48,6 @@ from pandas.core.dtypes.common import (
 from pandas.core.categorical import Categorical, _recode_for_categories
 from pandas.core.algorithms import take_1d
 from pandas.core.dtypes.concat import union_categoricals
-from pandas.core.dtypes.cast import maybe_convert_for_categorical
 from pandas import Index
 
 import pandas.io.common as com

pandas/core/categorical.py

@@ -21,6 +21,8 @@
     _ensure_platform_int,
     is_dtype_equal,
     is_datetimelike,
+    is_datetime64_dtype,
+    is_timedelta64_dtype,
     is_categorical,
     is_categorical_dtype,
     is_integer_dtype,
@@ -528,11 +530,20 @@ def _from_inferred_categories(cls, inferred_categories, inferred_codes,
         -------
         Categorical
         """
-        from pandas.core.dtypes.cast import maybe_convert_for_categorical
-        from pandas import Index
+        from pandas import Index, to_numeric, to_datetime, to_timedelta
 
         cats = Index(inferred_categories)
-        cats = maybe_convert_for_categorical(cats, dtype)
+
+        # Convert to a specialzed type with `dtype` is specified
+        if (isinstance(dtype, CategoricalDtype) and
+                dtype.categories is not None):
+
+            if dtype.categories.is_numeric():
+                cats = to_numeric(inferred_categories, errors='coerce')
+            elif is_datetime64_dtype(dtype.categories):
+                cats = to_datetime(inferred_categories, errors='coerce')
+            elif is_timedelta64_dtype(dtype.categories):
+                cats = to_timedelta(inferred_categories, errors='coerce')
 
         if (isinstance(dtype, CategoricalDtype) and
                 dtype.categories is not None):

pandas/core/dtypes/cast.py

@@ -24,8 +24,7 @@
                      _ensure_int32, _ensure_int64,
                      _NS_DTYPE, _TD_DTYPE, _INT64_DTYPE,
                      _POSSIBLY_CAST_DTYPES)
-from .dtypes import (ExtensionDtype, DatetimeTZDtype, PeriodDtype,
-                     CategoricalDtype)
+from .dtypes import ExtensionDtype, DatetimeTZDtype, PeriodDtype
 from .generic import (ABCDatetimeIndex, ABCPeriodIndex,
                       ABCSeries)
 from .missing import isna, notna
@@ -605,41 +604,6 @@ def conv(r, dtype):
     return [conv(r, dtype) for r, dtype in zip(result, dtypes)]
 
 
-def maybe_convert_for_categorical(categories, dtype):
-    """Convert ``categories`` depending on ``dtype``.
-
-    Converts to numeric, datetime, or timedelta types, when ``dtype`` is
-    a CategoricalDtype with known, non-object categories.
-
-    Parameters
-    ----------
-    categories : array-like
-    type : CategoricalDtype
-
-    Returns
-    -------
-    new_categories : array or Index
-
-    Examples
-    --------
-    >>> maybe_convert_for_categorical(['1', '2'], CategoricalDtype([1, 2]))
-    array([  1,  2])
-    >>> maybe_convert_for_categorical([1, 'a'], CategoricalDtype([1, 2]))
-    array([  1.,  nan])
-    """
-    if isinstance(dtype, CategoricalDtype) and dtype.categories is not None:
-        from pandas import to_numeric, to_datetime, to_timedelta
-
-        if dtype.categories.is_numeric():
-            categories = to_numeric(categories, errors='coerce')
-        elif is_datetime64_dtype(dtype.categories):
-            categories = to_datetime(categories, errors='coerce')
-        elif is_timedelta64_dtype(dtype.categories):
-            categories = to_timedelta(categories, errors='coerce')
-
-    return categories
-
-
 def astype_nansafe(arr, dtype, copy=True):
     """ return a view if copy is False, but
         need to be very careful as the result shape could change! """

pandas/io/parsers.py

@@ -23,8 +23,7 @@
     is_scalar, is_categorical_dtype)
 from pandas.core.dtypes.dtypes import CategoricalDtype
 from pandas.core.dtypes.missing import isna
-from pandas.core.dtypes.cast import (astype_nansafe,
-                                     maybe_convert_for_categorical)
+from pandas.core.dtypes.cast import astype_nansafe
 from pandas.core.index import (Index, MultiIndex, RangeIndex,
                                _ensure_index_from_sequences)
 from pandas.core.series import Series
@@ -1610,15 +1609,15 @@ def _cast_types(self, values, cast_type, column):
             known_cats = (isinstance(cast_type, CategoricalDtype) and
                           cast_type.categories is not None)
 
-            categories = ordered = None
             if known_cats:
-                values = maybe_convert_for_categorical(values, cast_type)
-                categories = cast_type.categories
-                ordered = cast_type.ordered
-            elif not is_object_dtype(values):
-                values = astype_nansafe(values, str)
-            values = Categorical(values, categories=categories,
-                                 ordered=ordered)
+                cats = Index(values).unique()
+                values = Categorical._from_inferred_categories(
+                    cats, cats.get_indexer(values), cast_type
+                )
+            else:
+                if not is_object_dtype(values):
+                    values = astype_nansafe(values, str)
+                values = Categorical(values, categories=None, ordered=False)
         else:
             try:
                 values = astype_nansafe(values, cast_type, copy=True)

pandas/tests/dtypes/test_cast.py

@@ -16,7 +16,6 @@
 from pandas.core.dtypes.cast import (
     maybe_downcast_to_dtype,
     maybe_convert_objects,
-    maybe_convert_for_categorical,
     cast_scalar_to_array,
     infer_dtype_from_scalar,
     infer_dtype_from_array,
@@ -300,44 +299,6 @@ def test_maybe_infer_to_datetimelike(self):
                                      [NaT, 'b', 1]]))
         assert result.size == 6
 
-    def test_maybe_convert_for_categorical_noop(self):
-        expected = ['1', '2']
-        result = maybe_convert_for_categorical(expected, None)
-        assert result == expected
-
-        result = maybe_convert_for_categorical(expected, CategoricalDtype())
-        assert result == expected
-
-        result = maybe_convert_for_categorical(expected, 'category')
-        assert result == expected
-
-    @pytest.mark.parametrize('categories, dtype, expected', [
-        (['1', '2'], [1, 2, 3], np.array([1, 2], dtype='i8')),
-        (['1', '2', 'a'], [1, 2, 3], np.array([1, 2, np.nan], dtype='f8')),
-    ])
-    def test_maybe_convert_for_categorical(self, categories, dtype, expected):
-        dtype = CategoricalDtype(dtype)
-        result = maybe_convert_for_categorical(categories, dtype)
-        tm.assert_numpy_array_equal(result, expected)
-
-    @pytest.mark.parametrize('categories, dtype, expected', [
-        (['2016', '2017'], pd.to_datetime(['2016', '2017']),
-         pd.to_datetime(['2016', '2017'])),
-        (['2016', '2017', 'bad'], pd.to_datetime(['2016', '2017']),
-         pd.to_datetime(['2016', '2017', 'NaT'])),
-
-        (['1H', '2H'], pd.to_timedelta(['1H', '2H']),
-         pd.to_timedelta(['1H', '2H'])),
-        (['1H', '2H', 'bad'], pd.to_timedelta(['1H', '2H']),
-         pd.to_timedelta(['1H', '2H', 'NaT'])),
-
-    ])
-    def test_maybe_convert_for_categorical_dates(self, categories, dtype,
-                                                 expected):
-        dtype = CategoricalDtype(dtype)
-        result = maybe_convert_for_categorical(categories, dtype)
-        tm.assert_index_equal(result, expected)
-
 
 class TestConvert(object):