pandas remove outliers for multiple columns
def cap_data(df): for col in df.columns: print("capping the ",col) if (((df[col].dtype)=='float64') | ((df[col].dtype)=='int64')): percentiles = df[col].quantile([0.01,0.99]).values df[col][df[col] <= percentiles[0]] = percentiles[0] df[col][df[col] >= percentiles[1]] = percentiles[1] else: df[col]=df[col] return df final_df=cap_data(df)
Source: stackoverflow.com