B_4_find_FR_with_for.py 文件源码

 复制代码def check_log_loss(max_depth, n_splits, test_size):
    model = RandomForestClassifier(max_depth=max_depth, n_jobs=-1, random_state=777)
    trn_scores = []
    vld_scores = []
    sss = StratifiedShuffleSplit(n_splits=n_splits, test_size=test_size, random_state=777)
    for i, (t_ind, v_ind) in enumerate(sss.split(feature_train, trainY)):
        print('# Iter {} / {}'.format(i + 1, n_splits))
        x_trn = feature_train.values[t_ind]
        y_trn = trainY[t_ind]
        x_vld = feature_train.values[v_ind]
        y_vld = trainY[v_ind]

        model.fit(x_trn, y_trn)

        score = log_loss(y_trn, model.predict_proba(x_trn))
        trn_scores.append(score)

        score = log_loss(y_vld, model.predict_proba(x_vld))
        vld_scores.append(score)

    print("max_depth: %d   n_splits: %d    test_size: %f" % (max_depth, n_splits, test_size))
    print('# TRN logloss: {}'.format(np.mean(trn_scores)))
    print('# VLD logloss: {}'.format(np.mean(vld_scores)))