sklearn_stages.py 文件源码

def _op(self, df, verbose):
        columns_to_encode = self._columns
        if self._columns is None:
            columns_to_encode = list(set(df.select_dtypes(
                include=['object', 'category']).columns).difference(
                    self._exclude_columns))
        if verbose:
            columns_to_encode = tqdm.tqdm(columns_to_encode)
        inter_df = df
        for colname in columns_to_encode:
            lbl_enc = sklearn.preprocessing.LabelEncoder()
            source_col = df[colname]
            loc = df.columns.get_loc(colname) + 1
            new_name = colname + "_enc"
            if self._drop:
                inter_df = inter_df.drop(colname, axis=1)
                new_name = colname
                loc -= 1
            inter_df = out_of_place_col_insert(
                df=inter_df,
                series=lbl_enc.fit_transform(source_col),
                loc=loc,
                column_name=new_name)
            self.encoders[colname] = lbl_enc
        return inter_df