Partial progress

Author: damccorm

sdks/python/apache_beam/dataframe/frames.py

@@ -380,14 +380,12 @@ def groupby(self, by, level, axis, as_index, group_keys, **kwargs):
     """
     if not as_index:
       raise NotImplementedError('groupby(as_index=False)')
-    if not group_keys:
-      raise NotImplementedError('groupby(group_keys=False)')
 
     if axis in (1, 'columns'):
       return _DeferredGroupByCols(
           expressions.ComputedExpression(
               'groupbycols',
-              lambda df: df.groupby(by, axis=axis, **kwargs), [self._expr],
+              lambda df: df.groupby(by, axis=axis, group_keys=group_keys, **kwargs), [self._expr],
               requires_partition_by=partitionings.Arbitrary(),
               preserves_partition_by=partitionings.Arbitrary()))
 
@@ -559,7 +557,7 @@ def prepend_index(df, by):  # type: ignore
         expressions.ComputedExpression(
             'groupbyindex',
             lambda df: df.groupby(
-                level=list(range(df.index.nlevels)), **kwargs), [to_group],
+                level=list(range(df.index.nlevels)), group_keys=group_keys, **kwargs), [to_group],
             requires_partition_by=partitionings.Index(),
             preserves_partition_by=partitionings.Arbitrary()),
         kwargs,

sdks/python/apache_beam/dataframe/pandas_doctests_test.py

@@ -127,10 +127,7 @@ def test_ndframe_tests(self):
             'pandas.core.generic.NDFrame.copy': ['*'],
             'pandas.core.generic.NDFrame.droplevel': ['*'],
             'pandas.core.generic.NDFrame.get': ['*'],
-            'pandas.core.generic.NDFrame.rank': [
-                # Modified dataframe
-                'df'
-            ],
+            'pandas.core.generic.NDFrame.rank': ['*'],
             'pandas.core.generic.NDFrame.rename': [
                 # Seems to be an upstream bug. The actual error has a different
                 # message:
@@ -704,8 +701,11 @@ def test_groupby_tests(self):
     result = doctests.testmod(
         pd.core.groupby.groupby,
         use_beam=False,
+        verbose=True,
         wont_implement_ok={
+            'pandas.core.groupby.groupby.GroupBy.first': ['*'],
             'pandas.core.groupby.groupby.GroupBy.head': ['*'],
+            'pandas.core.groupby.groupby.GroupBy.last': ['*'],
             'pandas.core.groupby.groupby.GroupBy.tail': ['*'],
             'pandas.core.groupby.groupby.GroupBy.nth': ['*'],
             'pandas.core.groupby.groupby.GroupBy.cumcount': ['*'],
@@ -831,6 +831,7 @@ def test_top_level(self):
             'crosstab': ['*'],
             'cut': ['*'],
             'eval': ['*'],
+            'from_dummies': ['*'],
             'get_dummies': ['*'],
             'infer_freq': ['*'],
             'lreshape': ['*'],
@@ -863,7 +864,7 @@ def test_top_level(self):
         },
         skip={
             # error formatting
-            'concat': ['pd.concat([df5, df6], verify_integrity=True)'],
+            'concat': ['pd.concat([df5, df6], verify_integrity=True)', 'pd.concat([df7, new_row.to_frame().T], ignore_index=True)'],
             # doctest DeprecationWarning
             'melt': ['df'],
             # Order-sensitive re-indexing.