robertwb commented on a change in pull request #13141:
URL: https://github.com/apache/beam/pull/13141#discussion_r513666115
##########
File path: sdks/python/apache_beam/dataframe/frames.py
##########
@@ -575,6 +575,8 @@ def __setitem__(self, key, value):
else:
raise NotImplementedError(key)
+ align = frame_base._elementwise_method('align')
Review comment:
Good call. Done.
##########
File path: sdks/python/apache_beam/dataframe/frames.py
##########
@@ -771,6 +773,62 @@ def fill_matrix(*args):
requires_partition_by=partitionings.Singleton(),
proxy=proxy))
+ @frame_base.args_to_kwargs(pd.DataFrame)
+ @frame_base.populate_defaults(pd.DataFrame)
+ def corrwith(self, other, axis, **kwargs):
+ if axis not in (0, 'index'):
+ raise NotImplementedError('corrwith(axis=%r)' % axis)
+ if not isinstance(other, frame_base.DeferredFrame):
+ other = frame_base.DeferredFrame.wrap(
+ expressions.ConstantExpression(other))
+
+ if isinstance(other, DeferredSeries):
+ proxy = self._expr.proxy().corrwith(other._expr.proxy())
+ self, other = self.align(other, axis=0, join='inner')
+ corrs = [self[col].corr(other, **kwargs) for col in proxy.index]
+ def fill_dataframe(*args):
+ result = proxy.copy(deep=True)
+ for col, value in zip(proxy.index, args):
+ result[col] = value
+ return result
+ with expressions.allow_non_parallel_operations(True):
+ return frame_base.DeferredFrame.wrap(
+ expressions.ComputedExpression(
+ 'fill_dataframe',
+ fill_dataframe,
+ [corr._expr for corr in corrs],
+ requires_partition_by=partitionings.Singleton(),
+ proxy=proxy))
+
+ elif isinstance(other, DeferredDataFrame):
+ proxy = self._expr.proxy().corrwith(other._expr.proxy())
+ self, other = self.align(other, axis=0, join='inner')
+ valid_cols = list(
+ set(self.columns)
+ .intersection(other.columns)
+ .intersection(proxy.index))
+ corrs = [self[col].corr(other[col], **kwargs) for col in valid_cols]
+ def fill_dataframe(*args):
+ result = proxy.copy(deep=True)
+ for col, value in zip(valid_cols, args):
+ result[col] = value
+ return result
+ with expressions.allow_non_parallel_operations(True):
+ return frame_base.DeferredFrame.wrap(
+ expressions.ComputedExpression(
+ 'fill_dataframe',
+ fill_dataframe,
+ [corr._expr for corr in corrs],
+ requires_partition_by=partitionings.Singleton(),
+ proxy=proxy))
Review comment:
I've consolidated them now.
##########
File path: sdks/python/apache_beam/dataframe/frames.py
##########
@@ -771,6 +773,62 @@ def fill_matrix(*args):
requires_partition_by=partitionings.Singleton(),
proxy=proxy))
+ @frame_base.args_to_kwargs(pd.DataFrame)
+ @frame_base.populate_defaults(pd.DataFrame)
+ def corrwith(self, other, axis, **kwargs):
+ if axis not in (0, 'index'):
+ raise NotImplementedError('corrwith(axis=%r)' % axis)
+ if not isinstance(other, frame_base.DeferredFrame):
+ other = frame_base.DeferredFrame.wrap(
+ expressions.ConstantExpression(other))
+
+ if isinstance(other, DeferredSeries):
+ proxy = self._expr.proxy().corrwith(other._expr.proxy())
+ self, other = self.align(other, axis=0, join='inner')
+ corrs = [self[col].corr(other, **kwargs) for col in proxy.index]
Review comment:
Resolved.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
