Asymmetric difference of two pandas Dataframes
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def diff_df(df1, df2, how="left"): | |
""" | |
Find Difference of rows for given two dataframes | |
this function is not symmetric, means | |
diff(x, y) != diff(y, x) | |
however | |
diff(x, y, how='left') == diff(y, x, how='right') | |
Ref: https://stackoverflow.com/questions/18180763/set-difference-for-pandas/40209800#40209800 | |
""" | |
if (df1.columns != df2.columns).any(): | |
raise ValueError("Two dataframe columns must match") | |
if df1.equals(df2): | |
return None | |
elif how == 'right': | |
return pd.concat([df2, df1, df1]).drop_duplicates(keep=False) | |
elif how == 'left': | |
return pd.concat([df1, df2, df2]).drop_duplicates(keep=False) | |
else: | |
raise ValueError('how parameter supports only "left" or "right keywords"') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment