ensemble.py 文件源码

def parseDict(probas, output_name, valid_file=None):
    df = pd.DataFrame()
    df["row_id"] = probas.keys()
    df["place_id"] = df["row_id"].apply(lambda x: map(itemgetter(0),
                        sorted(probas[x].items(), key=itemgetter(1), reverse=True)[:3]))
    if valid_file is not None:
        df_valid = pd.read_csv(valid_file, usecols=["row_id", "place_id"])
        df_valid.rename(columns={"place_id": "place_id_label"}, inplace=True)
        df_merge = pd.merge(df, df_valid, how="left", on="row_id")
        valid_score = metrics.mapk(df_merge.place_id_label.values[:, None],
                                   df_merge.place_id.values, 3)
        logging.info("total validation score: %f" % valid_score)
        np.savetxt("%s.txt" % output_name, [valid_score], fmt="%f")
        del df_valid
        del df_merge

    df["place_id"] = df["place_id"].apply(lambda x: " ".join(map(str, x)))
    df.to_csv("%s.csv" % output_name, index=False)