Merge pull request #3003 from jreback/value_counts_3002

BUG: fixed value_counts with datetime64[ns], GH 3002

Author: jreback

RELEASE.rst

@@ -136,6 +136,8 @@ pandas 0.11.0
 
   - Bug on in-place putmasking on an ``integer`` series that needs to be converted to ``float`` (GH2746_)
   - Bug in argsort of ``datetime64[ns]`` Series with ``NaT`` (GH2967_)
+  - Bug in value_counts of ``datetime64[ns]`` Series (GH3002_)
+  - Fixed printing of ``NaT` in an index
   - Bug in idxmin/idxmax of ``datetime64[ns]`` Series with ``NaT`` (GH2982__)
   - Bug in ``icol`` with negative indicies was incorrect producing incorrect return values (see GH2922_)
 
@@ -162,6 +164,7 @@ pandas 0.11.0
 .. _GH2967: https://github.com/pydata/pandas/issues/2967
 .. _GH2982: https://github.com/pydata/pandas/issues/2982
 .. _GH2989: https://github.com/pydata/pandas/issues/2989
+.. _GH3002: https://github.com/pydata/pandas/issues/3002
 
 
 pandas 0.10.1

pandas/core/algorithms.py

@@ -170,6 +170,14 @@ def value_counts(values, sort=True, ascending=False):
     if com.is_integer_dtype(values.dtype):
         values = com._ensure_int64(values)
         keys, counts = htable.value_count_int64(values)
+    elif issubclass(values.dtype.type, (np.datetime64,np.timedelta64)):
+
+        dtype = values.dtype
+        values = values.view(np.int64)
+        keys, counts = htable.value_count_int64(values)
+
+        # convert the keys back to the dtype we came in
+        keys = Series(keys,dtype=dtype)
     else:
         mask = com.isnull(values)
         values = com._ensure_object(values)

pandas/core/index.py

@@ -13,6 +13,7 @@
 from pandas.lib import Timestamp
 
 from pandas.util.decorators import cache_readonly
+from pandas.core.common import isnull
 import pandas.core.common as com
 from pandas.util import py3compat
 from pandas.core.config import get_option
@@ -94,6 +95,8 @@ def __new__(cls, data, dtype=None, copy=False, name=None):
                     return Index(result.to_pydatetime(), dtype=_o_dtype)
                 else:
                     return result
+            elif issubclass(data.dtype.type, np.timedelta64):
+                return Int64Index(data, copy=copy, name=name)
 
             if dtype is not None:
                 try:
@@ -435,9 +438,12 @@ def format(self, name=False, formatter=None):
             zero_time = time(0, 0)
             result = []
             for dt in self:
-                if dt.time() != zero_time or dt.tzinfo is not None:
-                    return header + [u'%s' % x for x in self]
-                result.append(u'%d-%.2d-%.2d' % (dt.year, dt.month, dt.day))
+                if isnull(dt):
+                    result.append(u'NaT')
+                else:
+                    if dt.time() != zero_time or dt.tzinfo is not None:
+                        return header + [u'%s' % x for x in self]
+                    result.append(u'%d-%.2d-%.2d' % (dt.year, dt.month, dt.day))
             return header + result
 
         values = self.values

pandas/tests/test_format.py

@@ -1226,6 +1226,18 @@ def test_float_trim_zeros(self):
             else:
                 self.assert_('+10' in line)
 
+    def test_datetimeindex(self):
+
+        from pandas import date_range, NaT, Timestamp
+        index = date_range('20130102',periods=6)
+        s = Series(1,index=index)
+        result = s.to_string()
+        self.assertTrue('2013-01-02' in result)
+
+        s = Series(2, index=[ Timestamp('20130111'), NaT ]).append(s)
+        result = s.to_string()
+        self.assertTrue('NaT' in result)
+
     def test_timedelta64(self):
 
         from pandas import date_range

pandas/tests/test_series.py

@@ -2396,6 +2396,27 @@ def test_value_counts_nunique(self):
         expected = Series([], dtype=np.int64)
         assert_series_equal(hist, expected)
 
+        # GH 3002, datetime64[ns]
+        import StringIO
+        import pandas as pd
+        f = StringIO.StringIO("xxyyzz20100101PIE\nxxyyzz20100101GUM\nxxyyww20090101EGG\nfoofoo20080909PIE")
+        df = pd.read_fwf(f, widths=[6,8,3], names=["person_id", "dt", "food"], parse_dates=["dt"])
+        s = df.dt.copy()
+        result = s.value_counts()
+        self.assert_(result.index.dtype == 'datetime64[ns]')
+
+        # with NaT
+        s = s.append(Series({ 4 : pd.NaT }))
+        result = s.value_counts()
+        self.assert_(result.index.dtype == 'datetime64[ns]')
+
+        # timedelta64[ns]
+        from datetime import timedelta
+        td = df.dt-df.dt+timedelta(1)
+        result = td.value_counts()
+        #self.assert_(result.index.dtype == 'timedelta64[ns]')
+        self.assert_(result.index.dtype == 'int64')
+
     def test_unique(self):
 
         # 714 also, dtype=float