ensemble.py 文件源码

def folderToDict(model_output_path, c, probas=None):
    logging.info("merge folder %s" % model_output_path)
    files = glob.glob(os.path.join(model_output_path, "*.csv"))
    if probas is None:
        probas = defaultdict(lambda: defaultdict(float))
    for f in files:
        logging.info("loading... %s" % f)
        df = pd.read_csv(f, dtype={"row_id": int, "place_id": int, "proba": float})
        for i in range(len(df)):
            probas[df["row_id"][i]][df["place_id"][i]] += c * df["proba"][i]
    try:
        with open(os.path.join(model_output_path, "map3.txt"), "r") as f_score:
            logging.info("map3=%6.6f" % float(f_score.read()))
    except:
        pass
    return probas