A_TL_LGB_LGB.py 文件源码

def lgb_feature_selection(fe_name, matrix_x_temp, label_y, th):
    # SelectfromModel
    clf = LGBMClassifier(n_estimators=400)
    clf.fit(matrix_x_temp, label_y)
    sfm = SelectFromModel(clf, prefit=True, threshold=th)
    matrix_x = sfm.transform(matrix_x_temp)

    # ????????????????
    feature_score_dict = {}
    for fn, s in zip(fe_name, clf.feature_importances_):
        feature_score_dict[fn] = s
    m = 0
    for k in feature_score_dict:
        if feature_score_dict[k] == 0.0:
            m += 1
    print 'number of not-zero features:' + str(len(feature_score_dict) - m)

    # ????????
    feature_score_dict_sorted = sorted(feature_score_dict.items(),
                                       key=lambda d: d[1], reverse=True)
    print 'feature_importance:'
    for ii in range(len(feature_score_dict_sorted)):
        print feature_score_dict_sorted[ii][0], feature_score_dict_sorted[ii][1]
    print '\n'

    f = open('../eda/lgb_feature_importance.txt', 'w')
    f.write(th)
    f.write('\nRank\tFeature Name\tFeature Importance\n')
    for i in range(len(feature_score_dict_sorted)):
        f.write(str(i) + '\t' + str(feature_score_dict_sorted[i][0]) + '\t' + str(feature_score_dict_sorted[i][1]) + '\n')
    f.close()

    # ???????????
    how_long = matrix_x.shape[1]  # matrix_x ? ?????? ????
    feature_used_dict_temp = feature_score_dict_sorted[:how_long]
    feature_used_name = []
    for ii in range(len(feature_used_dict_temp)):
        feature_used_name.append(feature_used_dict_temp[ii][0])
    print 'feature_chooesed:'
    for ii in range(len(feature_used_name)):
        print feature_used_name[ii]
    print '\n'

    f = open('../eda/lgb_feature_chose.txt', 'w')
    f.write('Feature Chose Name :\n')
    for i in range(len(feature_used_name)):
        f.write(str(feature_used_name[i]) + '\n')
    f.close()

    # ??????????
    feature_not_used_name = []
    for i in range(len(fe_name)):
        if fe_name[i] not in feature_used_name:
            feature_not_used_name.append(fe_name[i])

    return matrix_x, feature_not_used_name[:], len(feature_used_name)