Closed
Description
System information
- OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Ubuntu 18.04
- Modin version: 0.8.1.1
- Python version: 3.8.3
- Exact command to reproduce:
import modin.pandas as pd
import pandas
data = {'a': [0,1,2,3]}
data2 = {'a': [4,5,6,7]}
index = [0,1,0,1]
md_df = pd.DataFrame(data, index=index)
pd_df = pandas.DataFrame(data, index=index)
md_df2 = pd.DataFrame(data2)
pd_df2 = pandas.DataFrame(data2)
print(f'pandas res \n{pd_df.a * pd_df2.a }')
print(f'modin res \n{md_df.a * md_df2.a }')
Describe the problem
Source code / logs
Log
print(f'modin res \n{md_df.a * md_df2.a }')
File "/localdisk/aprutsko/modin/modin/pandas/series.py", line 290, in __mul__
return self.mul(right)
File "/localdisk/aprutsko/modin/modin/pandas/series.py", line 1131, in mul
return super(Series, new_self).mul(
File "/localdisk/aprutsko/modin/modin/pandas/base.py", line 1794, in mul
return self._binary_op(
File "/localdisk/aprutsko/modin/modin/pandas/base.py", line 244, in _binary_op
new_query_compiler = getattr(self._query_compiler, op)(other, **kwargs)
File "/localdisk/aprutsko/modin/modin/data_management/functions/binary_function.py", line 48, in caller
query_compiler._modin_frame._binary_op(
File "/localdisk/aprutsko/modin/modin/engines/base/frame/data.py", line 1735, in _binary_op
left_parts, right_parts, joined_index = self._copartition(
File "/localdisk/aprutsko/modin/modin/engines/base/frame/data.py", line 1666, in _copartition
reindexed_self = self._frame_mgr_cls.map_axis_partitions(
File "/localdisk/aprutsko/modin/modin/engines/base/frame/partition_manager.py", line 323, in map_axis_partitions
return cls.broadcast_axis_partitions(
File "/localdisk/aprutsko/modin/modin/engines/base/frame/partition_manager.py", line 249, in broadcast_axis_partitions
[
File "/localdisk/aprutsko/modin/modin/engines/base/frame/partition_manager.py", line 250, in <listcomp>
part.apply(
File "/localdisk/aprutsko/modin/modin/engines/base/frame/axis_partition.py", line 172, in apply
return self._wrap_partitions(self.deploy_axis_func(*args))
File "/localdisk/aprutsko/modin/modin/engines/base/frame/axis_partition.py", line 218, in deploy_axis_func
result = func(dataframe, **kwargs)
File "/localdisk/aprutsko/modin/modin/engines/base/frame/data.py", line 1667, in <lambda>
axis, self._partitions, lambda df: df.reindex(joined_index, axis=axis)
File "/localdisk/aprutsko/miniconda3/lib/python3.8/site-packages/pandas/util/_decorators.py", line 309, in wrapper
return func(*args, **kwargs)
File "/localdisk/aprutsko/miniconda3/lib/python3.8/site-packages/pandas/core/frame.py", line 4031, in reindex
return super().reindex(**kwargs)
File "/localdisk/aprutsko/miniconda3/lib/python3.8/site-packages/pandas/core/generic.py", line 4458, in reindex
return self._reindex_axes(
File "/localdisk/aprutsko/miniconda3/lib/python3.8/site-packages/pandas/core/frame.py", line 3877, in _reindex_axes
frame = frame._reindex_index(
File "/localdisk/aprutsko/miniconda3/lib/python3.8/site-packages/pandas/core/frame.py", line 3896, in _reindex_index
return self._reindex_with_indexers(
File "/localdisk/aprutsko/miniconda3/lib/python3.8/site-packages/pandas/core/generic.py", line 4521, in _reindex_with_indexers
new_data = new_data.reindex_indexer(
File "/localdisk/aprutsko/miniconda3/lib/python3.8/site-packages/pandas/core/internals/managers.py", line 1276, in reindex_indexer
self.axes[axis]._can_reindex(indexer)
File "/localdisk/aprutsko/miniconda3/lib/python3.8/site-packages/pandas/core/indexes/base.py", line 3285, in _can_reindex
raise ValueError("cannot reindex from a duplicate axis")
ValueError: cannot reindex from a duplicate axis