clean data function

clean_data.py

def CleanData(df, drop_columns, target_name):
  # this function drops not used features
  # and duplicate rows
  # and empty rows of target(poinst)
  # returns cleaned df
  interim_df = df.drop(columns=drop_columns)
  
  interim_df_2 = (interim_df
                  .drop_duplicates(ignore_index=True))

  cleaned_df = (interim_df_2
                .dropna(subset=[target_name], how="any")
                .reset_index(drop=True))
  
  return cleaned_df