Merge pull request #8237 from jreback/pi

BUG: Bug in putting a PeriodIndex into a Series would convert to int64

Author: jreback

doc/source/basics.rst

@@ -1125,7 +1125,7 @@ This enables nice expressions like this:
 .. ipython:: python
 
    # period
-   s = Series(period_range('20130101',periods=4,freq='D').asobject)
+   s = Series(period_range('20130101',periods=4,freq='D'))
    s
    s.dt.year
    s.dt.day

doc/source/v0.15.0.txt

@@ -369,7 +369,7 @@ This enables nice expressions like this:
 .. ipython:: python
 
    # period
-   s = Series(period_range('20130101',periods=4,freq='D').asobject)
+   s = Series(period_range('20130101',periods=4,freq='D'))
    s
    s.dt.year
    s.dt.day
@@ -593,7 +593,7 @@ Bug Fixes
 - Bug in Panel when using ``major_xs`` and ``copy=False`` is passed (deprecation warning fails because of missing ``warnings``) (:issue:`8152`).
 - Bug in pickle deserialization that failed for pre-0.14.1 containers with dup items trying to avoid ambiguity
   when matching block and manager items, when there's only one block there's no ambiguity (:issue:`7794`)
-
+- Bug in putting a ``PeriodIndex`` into a ``Series`` would convert to ``int64`` dtype, rather than ``object`` of ``Periods`` (:issue:`7932`)
 - Bug in HDFStore iteration when passing a where (:issue:`8014`)
 - Bug in DataFrameGroupby.transform when transforming with a passed non-sorted key (:issue:`8046`)
 - Bug in repeated timeseries line and area plot may result in ``ValueError`` or incorrect kind (:issue:`7733`)

pandas/core/algorithms.py

@@ -196,8 +196,9 @@ def value_counts(values, sort=True, ascending=False, normalize=False,
     """
     from pandas.core.series import Series
     from pandas.tools.tile import cut
+    from pandas.tseries.period import PeriodIndex
 
-    is_period = getattr(values, 'inferred_type', None) == 'period'
+    is_period = com.is_period_arraylike(values)
     values = Series(values).values
     is_category = com.is_categorical_dtype(values.dtype)
 
@@ -215,6 +216,9 @@ def value_counts(values, sort=True, ascending=False, normalize=False,
     dtype = values.dtype
 
     if issubclass(values.dtype.type, (np.datetime64, np.timedelta64)) or is_period:
+        if is_period:
+            values = PeriodIndex(values)
+
         values = values.view(np.int64)
         keys, counts = htable.value_count_int64(values)
 

pandas/core/common.py

@@ -2327,6 +2327,13 @@ def is_iterator(obj):
 def is_number(obj):
     return isinstance(obj, (numbers.Number, np.number))
 
+def is_period_arraylike(arr):
+    """ return if we are period arraylike / PeriodIndex """
+    if isinstance(arr, pd.PeriodIndex):
+        return True
+    elif isinstance(arr, (np.ndarray, ABCSeries)):
+        return arr.dtype == object and lib.infer_dtype(arr) == 'period'
+    return getattr(arr, 'inferred_type', None) == 'period'
 
 def _coerce_to_dtype(dtype):
     """ coerce a string / np.dtype to a dtype """
@@ -2382,7 +2389,6 @@ def is_datetime64_ns_dtype(arr_or_dtype):
     tipo = _get_dtype(arr_or_dtype)
     return tipo == _NS_DTYPE
 
-
 def is_timedelta64_dtype(arr_or_dtype):
     tipo = _get_dtype_type(arr_or_dtype)
     return issubclass(tipo, np.timedelta64)

pandas/tests/test_series.py

@@ -110,7 +110,7 @@ def get_expected(s, name):
         tm.assert_series_equal(s.dt.second,Series(np.array([0,1,2],dtype='int64'),index=index))
 
         # periodindex
-        for s in [Series(period_range('20130101',periods=5,freq='D').asobject)]:
+        for s in [Series(period_range('20130101',periods=5,freq='D'))]:
 
             for prop in ok_for_period:
                 tm.assert_series_equal(getattr(s.dt,prop),get_expected(s,prop))
@@ -747,6 +747,15 @@ def test_constructor_dtype_datetime64(self):
         s = Series([pd.NaT, np.nan, '2013-08-05 15:30:00.000001'])
         self.assertEqual(s.dtype,'datetime64[ns]')
 
+    def test_constructor_periodindex(self):
+        # GH7932
+        # converting a PeriodIndex when put in a Series
+
+        pi = period_range('20130101',periods=5,freq='D')
+        s = Series(pi)
+        expected = Series(pi.asobject)
+        assert_series_equal(s, expected)
+
     def test_constructor_dict(self):
         d = {'a': 0., 'b': 1., 'c': 2.}
         result = Series(d, index=['b', 'c', 'd', 'a'])

pandas/tseries/common.py

@@ -39,15 +39,9 @@ def maybe_to_datetimelike(data, copy=False):
     if issubclass(data.dtype.type, np.datetime64):
         return DatetimeProperties(DatetimeIndex(data, copy=copy), index)
     else:
-
-        if isinstance(data, PeriodIndex):
+        if com.is_period_arraylike(data):
             return PeriodProperties(PeriodIndex(data, copy=copy), index)
 
-        data = com._values_from_object(data)
-        inferred = lib.infer_dtype(data)
-        if inferred == 'period':
-            return PeriodProperties(PeriodIndex(data), index)
-
     raise TypeError("cannot convert an object of type {0} to a datetimelike index".format(type(data)))
 
 class Properties(PandasDelegate):

pandas/tseries/frequencies.py

@@ -664,9 +664,10 @@ def infer_freq(index, warn=True):
         if not (com.is_datetime64_dtype(index.values) or values.dtype == object):
             raise TypeError("cannot infer freq from a non-convertible dtype on a Series of {0}".format(index.dtype))
         index = values
-    if isinstance(index, pd.PeriodIndex):
+
+    if com.is_period_arraylike(index):
         raise TypeError("PeriodIndex given. Check the `freq` attribute "
-                         "instead of using infer_freq.")
+                        "instead of using infer_freq.")
     if isinstance(index, pd.Index) and not isinstance(index, pd.DatetimeIndex):
         if isinstance(index, (pd.Int64Index, pd.Float64Index)):
             raise TypeError("cannot infer freq from a non-convertible index type {0}".format(type(index)))

pandas/tseries/period.py

@@ -746,6 +746,10 @@ def __contains__(self, key):
     def _box_func(self):
         return lambda x: Period._from_ordinal(ordinal=x, freq=self.freq)
 
+    def _to_embed(self, keep_tz=False):
+        """ return an array repr of this object, potentially casting to object """
+        return self.asobject.values
+
     def asof_locs(self, where, mask):
         """
         where : array of timestamps