Merge pull request #6398 from jreback/index_coerce

API: validate conversions of datetimeindex with tz, and fixup to_series() to handle (GH6032)

Author: jreback

doc/source/api.rst

@@ -1176,7 +1176,7 @@ Conversion
    DatetimeIndex.to_datetime
    DatetimeIndex.to_period
    DatetimeIndex.to_pydatetime
-
+   DatetimeIndex.to_series
 
 GroupBy
 -------

pandas/core/frame.py

@@ -2033,6 +2033,8 @@ def _sanitize_column(self, key, value):
                     value = com._asarray_tuplesafe(value)
             elif isinstance(value, PeriodIndex):
                 value = value.asobject
+            elif isinstance(value, DatetimeIndex):
+                value = value._to_embed(keep_tz=True).copy()
             elif value.ndim == 2:
                 value = value.copy().T
             else:

pandas/core/index.py

@@ -266,13 +266,28 @@ def copy(self, names=None, name=None, dtype=None, deep=False):
             new_index = new_index.astype(dtype)
         return new_index
 
-    def to_series(self):
+    def to_series(self, keep_tz=False):
         """
-        return a series with both index and values equal to the index keys
+        Create a Series with both index and values equal to the index keys
         useful with map for returning an indexer based on an index
+
+        Parameters
+        ----------
+        keep_tz : optional, defaults False.
+                  applies only to a DatetimeIndex
+
+        Returns
+        -------
+        Series : dtype will be based on the type of the Index values.
         """
+
         import pandas as pd
-        return pd.Series(self.values, index=self, name=self.name)
+        values = self._to_embed(keep_tz)
+        return pd.Series(values, index=self, name=self.name)
+
+    def _to_embed(self, keep_tz=False):
+        """ return an array repr of this object, potentially casting to object """
+        return self.values
 
     def astype(self, dtype):
         return Index(self.values.astype(dtype), name=self.name,

pandas/core/series.py

@@ -162,7 +162,8 @@ def __init__(self, data=None, index=None, dtype=None, name=None,
                 # need to copy to avoid aliasing issues
                 if name is None:
                     name = data.name
-                data = data.values
+
+                data = data._to_embed(keep_tz=True)
                 copy = True
             elif isinstance(data, pa.Array):
                 pass

pandas/tests/test_frame.py

@@ -2092,6 +2092,33 @@ def test_set_index_cast_datetimeindex(self):
         idf = df.set_index('A')
         tm.assert_isinstance(idf.index, DatetimeIndex)
 
+        # don't cast a DatetimeIndex WITH a tz, leave as object
+        # GH 6032
+        i = pd.DatetimeIndex(pd.tseries.tools.to_datetime(['2013-1-1 13:00','2013-1-2 14:00'], errors="raise")).tz_localize('US/Pacific')
+        df = DataFrame(np.random.randn(2,1),columns=['A'])
+
+        expected = Series(i)
+        self.assertTrue(expected.dtype == object)
+        self.assertTrue(i.equals(expected.values.values))
+
+        df['B'] = i
+        result = df['B']
+        assert_series_equal(result, expected)
+
+        result = i.to_series(keep_tz=True)
+        assert_series_equal(result.reset_index(drop=True), expected)
+
+        df['C'] = i.to_series().reset_index(drop=True)
+        result = df['C']
+        comp = DatetimeIndex(expected.values).copy()
+        comp.tz = None
+        self.assert_numpy_array_equal(result.values, comp.values)
+
+        # list of datetimes with a tz
+        df['D'] = i.to_pydatetime()
+        result = df['D']
+        assert_series_equal(result, expected)
+
     def test_set_index_multiindexcolumns(self):
         columns = MultiIndex.from_tuples([('foo', 1), ('foo', 2), ('bar', 1)])
         df = DataFrame(np.random.randn(3, 3), columns=columns)

pandas/tseries/index.py

@@ -721,6 +721,38 @@ def _get_time_micros(self):
             values = self._local_timestamps()
         return tslib.get_time_micros(values)
 
+    def to_series(self, keep_tz=False):
+        """
+        Create a Series with both index and values equal to the index keys
+        useful with map for returning an indexer based on an index
+
+        Parameters
+        ----------
+        keep_tz : optional, defaults False.
+                  return the data keeping the timezone.
+
+                  If keep_tz is True:
+
+                    If the timezone is not set or is UTC, the resulting
+                    Series will have a datetime64[ns] dtype.
+                    Otherwise the Series will have an object dtype.
+
+                  If keep_tz is False:
+
+                    Series will have a datetime64[ns] dtype.
+
+        Returns
+        -------
+        Series
+        """
+        return super(DatetimeIndex, self).to_series(keep_tz=keep_tz)
+
+    def _to_embed(self, keep_tz=False):
+        """ return an array repr of this object, potentially casting to object """
+        if keep_tz and self.tz is not None and str(self.tz) != 'UTC':
+            return self.asobject
+        return self.values
+
     @property
     def asobject(self):
         """