roger-mike commented on a change in pull request #15827:
URL: https://github.com/apache/beam/pull/15827#discussion_r756213919
##########
File path: sdks/python/apache_beam/dataframe/frames.py
##########
@@ -1277,6 +1277,90 @@ def align(self, other, join, axis, level, method,
**kwargs):
requires_partition_by=partitionings.Arbitrary(),
preserves_partition_by=partitionings.Singleton())
+ @frame_base.with_docs_from(pd.Series)
+ @frame_base.args_to_kwargs(pd.Series)
+ @frame_base.populate_defaults(pd.Series)
+ def idxmin(self, **kwargs):
+ skipna = kwargs.get('skipna', True)
+
+ def compute_idxmin(s):
+ min_index = s.idxmin(**kwargs)
+ if pd.isna(min_index):
+ return s
+ else:
+ return s.loc[[min_index]]
+
+ # Avoids empty Series error when evaluating proxy
+ index_dtype = self._expr.proxy().index.dtype
+ index = pd.Index([], dtype=index_dtype)
+ proxy = self._expr.proxy().copy()
+ proxy.index = index
+ proxy = proxy.append(
+ pd.Series([np.inf], index=np.asarray(['0']).astype(proxy.index.dtype)))
+
+ if not skipna:
+ proxy = proxy.append(
+ pd.Series([None],
+ index=np.asarray(['1']).astype(proxy.index.dtype)).astype(
+ proxy.dtype))
+
+ idx_min = expressions.ComputedExpression(
+ 'idx_min',
+ compute_idxmin, [self._expr],
+ proxy=proxy,
+ requires_partition_by=partitionings.Index(),
+ preserves_partition_by=partitionings.Singleton())
+
+ with expressions.allow_non_parallel_operations(True):
+ return frame_base.DeferredFrame.wrap(
+ expressions.ComputedExpression(
+ 'idxmin_combine',
+ lambda s: s.idxmin(**kwargs), [idx_min],
+ requires_partition_by=partitionings.Singleton(),
+ preserves_partition_by=partitionings.Singleton()))
+
+ @frame_base.with_docs_from(pd.Series)
+ @frame_base.args_to_kwargs(pd.Series)
+ @frame_base.populate_defaults(pd.Series)
+ def idxmax(self, **kwargs):
+ skipna = kwargs.get('skipna', True)
+
+ def compute_idxmax(s):
+ max_index = s.idxmax(**kwargs)
+ if pd.isna(max_index):
+ return s
+ else:
+ return s.loc[[max_index]]
+
+ # Avoids empty Series error when evaluating proxy
+ index_dtype = self._expr.proxy().index.dtype
+ index = pd.Index([], dtype=index_dtype)
+ proxy = self._expr.proxy().copy()
+ proxy.index = index
+ proxy = proxy.append(
+ pd.Series([-np.inf],
index=np.asarray(['0']).astype(proxy.index.dtype)))
Review comment:
I thought the same but it throws a `ValueError: attempt to get argmin of
an empty sequence`. To solve this I added a value to the proxy which is a
`np.inf` or a `-np.inf` but now I see it could be any other value and it won't
affect the result as long it's the same type as in the input Series.
--
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]
