wassname/ray
1
0
Fork 0
mirror of https://github.com/wassname/ray.git synced 2026-06-27 20:53:14 +08:00
Code Issues Packages Projects Releases Wiki Activity

[DataFrame] Fixing bugs in groupby (#2031)

Browse Source
This commit is contained in:
Devin Petersohn
2018-05-10 11:44:19 -07:00
committed by Robert Nishihara
parent b79912ec74
commit 89e2eef3f3
2 changed files with 5 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/ray/dataframe/dataframe.py
+3
View File
@@ -634,6 +634,9 @@ class DataFrame(object):
elif isinstance(by, compat.string_types):
by = self.__getitem__(by).values.tolist()
elif is_list_like(by):
if isinstance(by, pd.Series):
by = by.values.tolist()
mismatch = len(by) != len(self) if axis == 0 \
else len(by) != len(self.columns)
python/ray/dataframe/groupby.py
+2 -3
View File
@@ -3,7 +3,6 @@ from __future__ import division
from __future__ import print_function
import pandas.core.groupby
import numpy as np
import pandas as pd
from pandas.core.dtypes.common import is_list_like
import ray
@@ -34,7 +33,7 @@ class DataFrameGroupBy(object):
self._index_grouped = pd.Series(self._columns, index=self._index)\
.groupby(by=by, sort=sort)
self._keys_and_values = [(k, np.array(v))
self._keys_and_values = [(k, v)
for k, v in self._index_grouped]
self._grouped_partitions = \
@@ -44,7 +43,7 @@ class DataFrameGroupBy(object):
as_index,
sort,
group_keys,
squeeze) + part,
squeeze) + tuple(part.tolist()),
num_return_vals=len(self))
for part in partitions)))