fix odd tz hashing issue

pandas-dev · Apr 14, 2017 · e98e89f · e98e89f
1 parent b8d320a
commit e98e89f
Show file tree

Hide file tree

Showing 4 changed files with 24 additions and 4 deletions.
diff --git a/pandas/core/series.py b/pandas/core/series.py
@@ -2844,8 +2844,6 @@ def _sanitize_index(data, index, copy=False):
         data = data.asobject
     elif isinstance(data, DatetimeIndex):
         data = data._to_embed(keep_tz=True)
-        if copy:
-            data = data.copy()
     elif isinstance(data, np.ndarray):
 
         # coerce datetimelike types

diff --git a/pandas/core/typed/dtypes.py b/pandas/core/typed/dtypes.py
@@ -209,8 +209,15 @@ def __new__(cls, unit=None, tz=None):
             raise ValueError("DatetimeTZDtype constructor must have a tz "
                              "supplied")
 
+        # hash with the actual tz if we can
+        # some cannot be hashed, so stringfy
+        try:
+            key = (unit, tz)
+            hash(key)
+        except TypeError:
+            key = (unit, str(tz))
+
         # set/retrieve from cache
-        key = (unit, str(tz))
         try:
             return cls._cache[key]
         except KeyError:

diff --git a/pandas/tests/indexes/datetimes/test_construction.py b/pandas/tests/indexes/datetimes/test_construction.py
@@ -12,21 +12,36 @@
 
 class TestDatetimeIndex(tm.TestCase):
 
+    def test_construction_caching(self):
+
+        df = pd.DataFrame({'dt': pd.date_range('20130101', periods=3),
+                           'dttz': pd.date_range('20130101', periods=3,
+                                                 tz='US/Eastern'),
+                           'dt_with_null': [pd.Timestamp('20130101'), pd.NaT,
+                                            pd.Timestamp('20130103')],
+                           'dtns': pd.date_range('20130101', periods=3,
+                                                 freq='ns')})
+        assert df.dttz.dtype.tz.zone == 'US/Eastern'
+
     def test_construction_with_alt(self):
 
         i = pd.date_range('20130101', periods=5, freq='H', tz='US/Eastern')
         i2 = DatetimeIndex(i, dtype=i.dtype)
         self.assert_index_equal(i, i2)
+        assert i.tz.zone == 'US/Eastern'
 
         i2 = DatetimeIndex(i.tz_localize(None).asi8, tz=i.dtype.tz)
         self.assert_index_equal(i, i2)
+        assert i.tz.zone == 'US/Eastern'
 
         i2 = DatetimeIndex(i.tz_localize(None).asi8, dtype=i.dtype)
         self.assert_index_equal(i, i2)
+        assert i.tz.zone == 'US/Eastern'
 
         i2 = DatetimeIndex(
             i.tz_localize(None).asi8, dtype=i.dtype, tz=i.dtype.tz)
         self.assert_index_equal(i, i2)
+        assert i.tz.zone == 'US/Eastern'
 
         # localize into the provided tz
         i2 = DatetimeIndex(i.tz_localize(None).asi8, tz='UTC')

diff --git a/pandas/tests/io/test_feather.py b/pandas/tests/io/test_feather.py
@@ -53,7 +53,7 @@ def test_basic(self):
                            'dtns': pd.date_range('20130101', periods=3,
                                                  freq='ns')})
 
-        assert df.dttz.dtype.tz.zone is not None
+        assert df.dttz.dtype.tz.zone == 'US/Eastern'
         self.check_round_trip(df)
 
     def test_strided_data_issues(self):