ENH: Add PeriodBlock

Author: sinhrks

pandas/core/algorithms.py

@@ -285,18 +285,18 @@ def factorize(values, sort=False, order=None, na_sentinel=-1, size_hint=None):
     note: an array of Periods will ignore sort as it returns an always sorted
     PeriodIndex
     """
-    from pandas import Index, Series, DatetimeIndex
+    from pandas import Index, Series, DatetimeIndex, PeriodIndex
 
     vals = np.asarray(values)
 
-    # localize to UTC
     is_datetimetz_type = is_datetimetz(values)
-    if is_datetimetz_type:
-        values = DatetimeIndex(values)
-        vals = values.asi8
+    is_period_type = is_period_dtype(values)
+    if is_datetimetz_type or is_period_type:
+        vals = values.view('i8')
 
     is_datetime = is_datetime64_dtype(vals)
     is_timedelta = is_timedelta64_dtype(vals)
+
     (hash_klass, vec_klass), vals = _get_data_algo(vals, _hashtables)
 
     table = hash_klass(size_hint or len(vals))
@@ -318,6 +318,8 @@ def factorize(values, sort=False, order=None, na_sentinel=-1, size_hint=None):
         uniques = uniques.astype('M8[ns]')
     elif is_timedelta:
         uniques = uniques.astype('m8[ns]')
+    elif is_period_type:
+        uniques = PeriodIndex(uniques, freq=values.freq)
     if isinstance(values, Index):
         uniques = values._shallow_copy(uniques, name=None)
     elif isinstance(values, Series):
@@ -362,7 +364,8 @@ def value_counts(values, sort=True, ascending=False, normalize=False,
             raise TypeError("bins argument only works with numeric data.")
         values = cat.codes
 
-    if is_extension_type(values) and not is_datetimetz(values):
+    if (is_extension_type(values) and
+       not (is_datetimetz(values) or is_period(values))):
         # handle Categorical and sparse,
         # datetime tz can be handeled in ndarray path
         result = Series(values).values.value_counts(dropna=dropna)
@@ -394,25 +397,14 @@ def value_counts(values, sort=True, ascending=False, normalize=False,
 
 def _value_counts_arraylike(values, dropna=True):
     is_datetimetz_type = is_datetimetz(values)
-    is_period_type = (is_period_dtype(values) or
-                      is_period_arraylike(values))
-
+    is_period_type = is_period_dtype(values)
     orig = values
 
     from pandas.core.series import Series
-    values = Series(values).values
+    values = Series(values)._values
     dtype = values.dtype
 
-    if needs_i8_conversion(dtype) or is_period_type:
-
-        from pandas.tseries.index import DatetimeIndex
-        from pandas.tseries.period import PeriodIndex
-
-        if is_period_type:
-            # values may be an object
-            values = PeriodIndex(values)
-            freq = values.freq
-
+    if needs_i8_conversion(dtype):
         values = values.view(np.int64)
         keys, counts = htable.value_count_int64(values, dropna)
 
@@ -421,13 +413,14 @@ def _value_counts_arraylike(values, dropna=True):
             keys, counts = keys[msk], counts[msk]
 
         # convert the keys back to the dtype we came in
-        keys = keys.astype(dtype)
-
-        # dtype handling
         if is_datetimetz_type:
+            from pandas.tseries.index import DatetimeIndex
             keys = DatetimeIndex._simple_new(keys, tz=orig.dtype.tz)
-        if is_period_type:
-            keys = PeriodIndex._simple_new(keys, freq=freq)
+        elif is_period_type:
+            from pandas.tseries.period import PeriodIndex
+            keys = PeriodIndex._simple_new(keys, freq=orig.dtype.freq)
+        else:
+            keys = keys.astype(dtype)
 
     elif is_integer_dtype(dtype):
         values = _ensure_int64(values)
@@ -471,9 +464,6 @@ def duplicated(values, keep='first'):
     # no need to revert to original type
     if needs_i8_conversion(dtype):
         values = values.view(np.int64)
-    elif is_period_arraylike(values):
-        from pandas.tseries.period import PeriodIndex
-        values = PeriodIndex(values).asi8
     elif is_categorical_dtype(dtype):
         values = values.values.codes
     elif isinstance(values, (ABCSeries, ABCIndex)):
@@ -1010,8 +1000,9 @@ def take_nd(arr, indexer, axis=0, out=None, fill_value=np.nan, mask_info=None,
     if is_categorical(arr):
         return arr.take_nd(indexer, fill_value=fill_value,
                            allow_fill=allow_fill)
-    elif is_datetimetz(arr):
-        return arr.take(indexer, fill_value=fill_value, allow_fill=allow_fill)
+    elif is_extension_type(arr):
+        return arr.take(indexer, fill_value=fill_value,
+                        allow_fill=allow_fill)
 
     if indexer is None:
         indexer = np.arange(arr.shape[axis], dtype=np.int64)

pandas/core/frame.py

@@ -263,8 +263,10 @@ def __init__(self, data=None, index=None, columns=None, dtype=None,
         if isinstance(data, BlockManager):
             mgr = self._init_mgr(data, axes=dict(index=index, columns=columns),
                                  dtype=dtype, copy=copy)
+
         elif isinstance(data, dict):
             mgr = self._init_dict(data, index, columns, dtype=dtype)
+
         elif isinstance(data, ma.MaskedArray):
             import numpy.ma.mrecords as mrecords
             # masked recarray
@@ -2952,7 +2954,7 @@ def reset_index(self, level=None, drop=False, inplace=False, col_level=0,
 
         def _maybe_casted_values(index, labels=None):
             if isinstance(index, PeriodIndex):
-                values = index.asobject.values
+                values = index
             elif isinstance(index, DatetimeIndex) and index.tz is not None:
                 values = index
             else: