百度新手赛：充电桩故障分类与检测<2>

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/f823154/article/details/80536749

由于该数据集比较好，没有缺失值，就没有做数据预处理，直接使用GDBT玄学调参，accuracy_score=1.0，代码如下：

import warnings
import pandas as pd
from sklearn.ensemble import GradientBoostingClassifier
warnings.filterwarnings('ignore')
column_name1 = ['id', 'K1K2驱动信号', '电子锁驱动信号', '急停信号', '门禁信号', 'THDV-M', 'THDI-M', 'label']
column_name2 = ['id', 'K1K2驱动信号', '电子锁驱动信号', '急停信号', '门禁信号', 'THDV-M', 'THDI-M']
train = pd.read_csv("../data/data_train.csv", names=column_name1)
test = pd.read_csv("../data/data_test.csv", names=column_name2)
# x_train,y_train的划分
x_train = train[['K1K2驱动信号', '电子锁驱动信号', '急停信号', '门禁信号', 'THDV-M', 'THDI-M']]
y_train = train[['label']]
x_test = test[['K1K2驱动信号', '电子锁驱动信号', '急停信号', '门禁信号', 'THDV-M', 'THDI-M']]
# GDBT,n_estimators过大容易造成过拟合，默认为100
gdbt = GradientBoostingClassifier(learning_rate=0.1, max_depth=10,min_samples_split=800,
                        n_estimators=400, min_samples_leaf=60, subsample=0.85, random_state=10)
# GradientBoostingClassifier使用fit函数用来训练模型参数
gdbt.fit(x_train, y_train)
gdbt_y_pre = gdbt.predict(x_test)
# 提交结果
lr_submission = pd.DataFrame({'id': test['id'], 'label': gdbt_y_pre})
lr_submission.to_csv('../submit/gdbt_submission.csv', index=False)
print("运行结束")