feat_util.py 文件源码

def create_id_df(cls, df, is_train):
        """
        :rtype: DataFrame
        :return: dataFrame, sorted by id, 
                 columns are ["label", "id0", "id", "id_tr", "id_te"]
        """

        df = df[["id0", "label"]].copy()
        df = df.reset_index(drop=True)
        is_train = np.array(is_train)

        le_tr = LabelEncoder().fit(df.id0[is_train])
        le_te = LabelEncoder().fit(df.id0[~is_train])

        df["id_tr"] = np.nan
        df["id_te"] = np.nan
        df.loc[is_train, "id_tr"] = le_tr.transform(df.id0[is_train])
        df.loc[~is_train, "id_te"] = le_te.transform(df.id0[~is_train])
        df["id"] = np.where(np.isnan(df["id_tr"]), len(le_tr.classes_) + df["id_te"], df["id_tr"])

        df = df.fillna(-1)
        df = df.sort("id")
        df = df[["label", "id0", "id", "id_tr", "id_te"]]

        return df