TheNeuralBit commented on a change in pull request #16706:
URL: https://github.com/apache/beam/pull/16706#discussion_r797986911
##########
File path: sdks/python/apache_beam/dataframe/frames.py
##########
@@ -3986,29 +3996,73 @@ def apply(self, func, *args, **kwargs):
fn_input = project(self._ungrouped_with_index.proxy().reset_index(
grouping_columns, drop=True))
result = func(fn_input)
- if isinstance(result, pd.core.generic.NDFrame):
- if result.index is fn_input.index:
- proxy = result
+ def index_to_arrays(index):
+ return [index.get_level_values(level)
+ for level in range(index.nlevels)]
+
+
+ # By default do_apply will just call pandas apply()
+ # We override it below if necessary
+ do_apply = lambda gb: gb.apply(func, *args, **kwargs)
+
+ if (isinstance(result, pd.core.generic.NDFrame) and
+ result.index is fn_input.index):
+ # Special case where apply fn is a transform
+ # Note we trust that if the user fn produces a proxy with the identical
+ # index, it will produce results with identical indexes at execution
+ # time too
+ proxy = result
+ elif isinstance(result, pd.DataFrame):
+ # apply fn is not a transform, we need to make sure the original index
+ # values are prepended to the result's index
+ proxy = result[:0]
+
+ # First adjust proxy
+ proxy.index = pd.MultiIndex.from_arrays(
+ index_to_arrays(self._ungrouped.proxy().index) +
+ index_to_arrays(proxy.index),
+ names=self._ungrouped.proxy().index.names + proxy.index.names)
+
+
+ # Then override do_apply function
+ new_index_names = self._ungrouped.proxy().index.names
+ if len(new_index_names) > 1:
+ def add_key_index(key, df):
+ # df is a dataframe or Series representing the result of func for
+ # a single key
+ # key is a tuple with the MultiIndex values for this key
+ df.index = pd.MultiIndex.from_arrays(
+ [[key[i]] * len(df) for i in range(len(new_index_names))] +
index_to_arrays(df.index),
+ names=new_index_names + df.index.names)
+ return df
else:
- proxy = result[:0]
-
- def index_to_arrays(index):
- return [index.get_level_values(level)
- for level in range(index.nlevels)]
-
- # The final result will have the grouped indexes + the indexes from the
- # result
- proxy.index = pd.MultiIndex.from_arrays(
- index_to_arrays(self._ungrouped.proxy().index) +
- index_to_arrays(proxy.index),
- names=self._ungrouped.proxy().index.names + proxy.index.names)
+ def add_key_index(key, df):
+ # df is a dataframe or Series representing the result of func for
+ # a single key
+ df.index = pd.MultiIndex.from_arrays(
+ [[key] * len(df)] + index_to_arrays(df.index),
+ names=new_index_names + df.index.names)
+ return df
+
+
+ do_apply = lambda gb: pd.concat([add_key_index(k, func(gb.get_group(k),
*args, **kwargs)) for k in gb.groups.keys()])
Review comment:
This is the critical change - when transform detection will break us, we
override `do_apply` with a custom implementation that executes `func` over each
group.
##########
File path: sdks/python/apache_beam/dataframe/frames.py
##########
@@ -4117,8 +4172,15 @@ def apply_fn(df):
@property # type: ignore
@frame_base.with_docs_from(DataFrameGroupBy)
def dtypes(self):
- grouping_columns = self._grouping_columns
- return self.apply(lambda df: df.drop(grouping_columns, axis=1).dtypes)
+ return frame_base.DeferredFrame.wrap(
+ expressions.ComputedExpression(
+ 'dtypes',
+ lambda gb: gb.dtypes,
+ [self._expr],
+ requires_partition_by=partitionings.Arbitrary(),
+ preserves_partition_by=partitionings.Arbitrary()
+ )
+ )
Review comment:
It turns out the old implementation was relying on incorrect behavior in
`apply`, so I've updated this not to use `apply`
##########
File path: sdks/python/apache_beam/dataframe/frames.py
##########
@@ -2674,11 +2674,9 @@ def duplicated(self, keep, subset):
by = subset or list(self.columns)
- # Workaround a bug where groupby.apply() that returns a single-element
- # Series moves index label to column
return self.groupby(by).apply(
lambda df: pd.DataFrame(df.duplicated(keep=keep, subset=subset),
- columns=[None]))[None]
+ columns=[None]))[None].droplevel(by)
Review comment:
Similarly here.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
