Regression in make_block_same_class (tests failing for new fastparquet release) (pandas-dev#19434)

Author: minggli

doc/source/io.rst

@@ -4537,7 +4537,7 @@ See the documentation for `pyarrow <http://arrow.apache.org/docs/python/>`__ and
 .. note::
 
    These engines are very similar and should read/write nearly identical parquet format files.
-   Currently ``pyarrow`` does not support timedelta data, and ``fastparquet`` does not support timezone aware datetimes (they are coerced to UTC).
+   Currently ``pyarrow`` does not support timedelta data, ``fastparquet>=0.1.4`` supports timezone aware datetimes.
    These libraries differ by having different underlying dependencies (``fastparquet`` by using ``numba``, while ``pyarrow`` uses a c-library).
 
 .. ipython:: python

pandas/core/internals.py

@@ -224,12 +224,17 @@ def make_block_scalar(self, values):
         """
         return ScalarBlock(values)
 
-    def make_block_same_class(self, values, placement=None, ndim=None):
+    def make_block_same_class(self, values, placement=None, ndim=None,
+                              dtype=None):
         """ Wrap given values in a block of same type as self. """
+        if dtype is not None:
+            # issue 19431 fastparquet is passing this
+            warnings.warn("dtype argument is deprecated, will be removed "
+                          "in a future release.", FutureWarning)
         if placement is None:
             placement = self.mgr_locs
         return make_block(values, placement=placement, ndim=ndim,
-                          klass=self.__class__)
+                          klass=self.__class__, dtype=dtype)
 
     def __unicode__(self):
 

pandas/tests/internals/test_internals.py

@@ -285,6 +285,13 @@ def test_delete(self):
         with pytest.raises(Exception):
             newb.delete(3)
 
+    def test_make_block_same_class(self):
+        # issue 19431
+        block = create_block('M8[ns, US/Eastern]', [3])
+        with tm.assert_produces_warning(FutureWarning,
+                                        check_stacklevel=False):
+            block.make_block_same_class(block.values, dtype=block.values.dtype)
+
 
 class TestDatetimeBlock(object):
 

pandas/tests/io/test_parquet.py

@@ -71,6 +71,15 @@ def fp():
     return 'fastparquet'
 
 
+@pytest.fixture
+def fp_lt_014():
+    if not _HAVE_FASTPARQUET:
+        pytest.skip("fastparquet is not installed")
+    if LooseVersion(fastparquet.__version__) >= LooseVersion('0.1.4'):
+        pytest.skip("fastparquet is >= 0.1.4")
+    return 'fastparquet'
+
+
 @pytest.fixture
 def df_compat():
     return pd.DataFrame({'A': [1, 2, 3], 'B': 'foo'})
@@ -435,8 +444,10 @@ def test_basic(self, fp, df_full):
         df = df_full
 
         # additional supported types for fastparquet
+        if LooseVersion(fastparquet.__version__) >= LooseVersion('0.1.4'):
+            df['datetime_tz'] = pd.date_range('20130101', periods=3,
+                                              tz='US/Eastern')
         df['timedelta'] = pd.timedelta_range('1 day', periods=3)
-
         check_round_trip(df, fp)
 
     @pytest.mark.skip(reason="not supported")
@@ -468,14 +479,15 @@ def test_categorical(self, fp):
         df = pd.DataFrame({'a': pd.Categorical(list('abc'))})
         check_round_trip(df, fp)
 
-    def test_datetime_tz(self, fp):
-        # doesn't preserve tz
+    def test_datetime_tz(self, fp_lt_014):
+
+        # fastparquet<0.1.4 doesn't preserve tz
         df = pd.DataFrame({'a': pd.date_range('20130101', periods=3,
                                               tz='US/Eastern')})
-
         # warns on the coercion
         with catch_warnings(record=True):
-            check_round_trip(df, fp, expected=df.astype('datetime64[ns]'))
+            check_round_trip(df, fp_lt_014,
+                             expected=df.astype('datetime64[ns]'))
 
     def test_filter_row_groups(self, fp):
         d = {'a': list(range(0, 3))}