Learn practical skills, build real-world projects, and advance your career
Created 3 years ago
import pandas as pd
df1 = pd.read_excel("C:/Users/Admin/Downloads/jaycopy.xlsx")
df2 = pd.read_excel("C:/Users/Admin/Downloads/shwetacopy.xlsx")
df2.head(44)
pd.merge(df1, df2, on=["Review Comment", "Category Comment"])
---------------------------------------------------------------------------
MemoryError Traceback (most recent call last)
<ipython-input-4-0ce553970213> in <module>
----> 1 pd.merge(df1, df2, on=["Review Comment", "Category Comment"])
D:\softwares\Anaconda\anaconda\lib\site-packages\pandas\core\reshape\merge.py in merge(left, right, how, on, left_on, right_on, left_index, right_index, sort, suffixes, copy, indicator, validate)
87 validate=validate,
88 )
---> 89 return op.get_result()
90
91
D:\softwares\Anaconda\anaconda\lib\site-packages\pandas\core\reshape\merge.py in get_result(self)
666 self.left, self.right = self._indicator_pre_merge(self.left, self.right)
667
--> 668 join_index, left_indexer, right_indexer = self._get_join_info()
669
670 llabels, rlabels = _items_overlap_with_suffix(
D:\softwares\Anaconda\anaconda\lib\site-packages\pandas\core\reshape\merge.py in _get_join_info(self)
882 )
883 else:
--> 884 (left_indexer, right_indexer) = self._get_join_indexers()
885
886 if self.right_index:
D:\softwares\Anaconda\anaconda\lib\site-packages\pandas\core\reshape\merge.py in _get_join_indexers(self)
861 """ return the join indexers """
862 return _get_join_indexers(
--> 863 self.left_join_keys, self.right_join_keys, sort=self.sort, how=self.how
864 )
865
D:\softwares\Anaconda\anaconda\lib\site-packages\pandas\core\reshape\merge.py in _get_join_indexers(left_keys, right_keys, sort, how, **kwargs)
1348 }[how]
1349
-> 1350 return join_func(lkey, rkey, count, **kwargs)
1351
1352
pandas\_libs\join.pyx in pandas._libs.join.inner_join()
MemoryError: Unable to allocate 700. GiB for an array with shape (93923574892,) and data type int64