# -*- coding: utf-8 -*-"""@author: Hotil"""import pandas as pd#pandas库操作excel,csvimport os#系统操作库,可以用来获取当前代码路径from sklearn.model_selection import train_test_split#随机分割训练集测试集from sklearn.metrics import r2_score as R2from sklearn.metrics import mean_squared_error as MSE#计算MSE,sklearn没有直接计算RMSE的方法,将MSE开根即可import numpy as np#数组操作import warnings#警示信息from sklearn.multioutput import MultiOutputRegressor#有的模型不支持模拟、期末同时输出，因此需要用到此方法import pydotplus from sklearn.tree import export_graphvizimport graphviz#%%#定义一个函数计算MAPEdef mape(actual, pred): actual, pred = np.array(actual), np.array(pred)return np.mean(np.abs((actual - pred) / actual)) * 100warnings.filterwarnings('ignore')#将代码与两个csv文件放在同意路径下currentPath = os.getcwd()#获取当前代码路径#拼接文件路径filePath1 = currentPath + r'\data.csv'filePath2 = currentPath + r'\data.csv'#读取文件dataBase1 = pd.read_csv(filePath1)dataBase2 = pd.read_csv(filePath2)#将两个csv合并组成一个数据库dataBase = pd.concat([dataBase1,dataBase2])featuresNames = dataBase.columns[:-2].valueslabelsNames = dataBase.columns[-2:].valuestranFeaturesNames = ['num1_hw','num1_test','num2_hw','num3_hw','num4_hw','num2_test','num5_hw','num6_hw','num7_hw','num8_hw', 'num3_test', 'num9_hw', 'num10_hw', 'num4_test']labelsNames = ['model','final']features = dataBase.iloc[:,:-2].valueslabels = dataBase.iloc[:,-2:].values#随机划分训练集和测试集,测试集:训练集 = 2:8xTrain,xTest,yTrain,yTest = train_test_split(features,labels,test_size=0.2)saveBase = pd.DataFrame(columns=dataBase.columns.values)for rowI in range(len(xTest)):saveBase.loc[rowI,:-2] = xTest[rowI]saveBase.iloc[:,-2] = yTest[:,0]saveBase.iloc[:,-1] = yTest[:,1]#============================================================#Decision Tree，ExtraTree，Random Forest，Adaboost，Gradient Boosting，XGBoost#============================================================#1 Decision Treefrom sklearn.tree import DecisionTreeRegressor#从sklearn的数模型中隐入决策树模型DTR = DecisionTreeRegressor(criterion='mse', splitter='best', max_depth=6,random_state=500)#实例化模型并传入参数DTR.fit(xTrain,yTrain)#传入特征和标签,拟合模型DTRPre = DTR.predict(xTest)#调用predict方法用测试集进行预测DTRRMSE = np.sqrt(MSE(yTest,DTRPre))#MSE()计算真实值与预测值的均方误差,np.sqrt进行开方后获得RMSEprint('='*60)print('Decision Tree的评估指标RMSE值为：',DTRRMSE)print('Decision Tree的评估指标MAPE值为：',mape(yTest,DTRPre))print('Decision Tree的评估指标R-square值为：',R2(yTest,DTRPre))DTRBase = saveBase.copy()#复制测试集dataFrame,方便加入各模型的预测值DTRBase.loc[:,'预测模拟'] = DTRPre[:,0]#加入预测模拟的数值DTRBase.loc[:,'预测期末'] = DTRPre[:,1]#加入预测期末的数值DTRBase.to_csv(currentPath +'\Decision Tree预测结果.csv',encoding='gb18030')#保存预测结果#============================================================#2ExtraTreefrom sklearn.tree import ExtraTreeRegressor#从树模型中引入极端树模型ETR = ExtraTreeRegressor(criterion='mse'#实例化模型并传入参数, splitter='random', max_depth=6,random_state=500)ETR.fit(xTrain,yTrain)#传入特征和标签,拟合模型ETRPre = ETR.predict(xTest)#调用predict方法用测试集进行预测ETRRMSE = np.sqrt(MSE(yTest,ETRPre))#MSE()计算真实值与预测值的均方误差,np.sqrt进行开方后获得RMSEprint('='*60)print('ExtraTree的评估指标RMSE值为：',ETRRMSE)print('ExtraTree的评估指标MAPE值为：',mape(yTest,ETRPre))print('ExtraTree的评估指标R-square值为：',R2(yTest,ETRPre))ETRBase = saveBase.copy()#复制测试集dataFrame,方便加入各模型的预测值ETRBase.loc[:,'预测模拟'] = ETRPre[:,0]#加入预测模拟的数值ETRBase.loc[:,'预测期末'] = ETRPre[:,1]#加入预测期末的数值ETRBase.to_csv(currentPath +'\ExtraTree预测结果.csv',encoding='gb18030')#保存预测结果#============================================================#3Random Forestfrom sklearn.ensemble import RandomForestRegressor#从集成模型中引入随机森林模型RFR = RandomForestRegressor(n_estimators=99#实例化模型并传入参数,criterion='squared_error', max_depth=6,random_state=300)RFR.fit(xTrain,yTrain)#传入特征和标签,拟合模型RFRPre = RFR.predict(xTest)#调用predict方法用测试集进行预测RFRRMSE = np.sqrt(MSE(yTest,RFRPre))#MSE()计算真实值与预测值的均方误差,np.sqrt进行开方后获得RMSEprint('='*60)print('Random Forest的评估指标RMSE值为：',RFRRMSE)print('Random Forest的评估指标MAPE值为：',mape(yTest,RFRPre))print('Random Forest的评估指标R-square值为：',R2(yTest,RFRPre))RFRBase = saveBase.copy()#复制测试dataFrame,方便加入各模型的预测值RFRBase.loc[:,'预测模拟'] = RFRPre[:,0]#加入预测模拟的数值RFRBase.loc[:,'预测期末'] = RFRPre[:,1]#加入预测期末的数值RFRBase.to_csv(currentPath +'\Random Forest预测结果.csv',encoding='gb18030')#保存预测结果tree = RFR.estimators_[5]dot_data = export_graphviz(tree, out_file=None,feature_names=tranFeaturesNames,class_names=labelsNames,filled=True, rounded=True,special_characters=True)graph = pydotplus.graph_from_dot_data(dot_data) graph.write_pdf("单颗树可视化.pdf") #============================================================#4Adaboostfrom sklearn.ensemble import AdaBoostRegressor#从集成模型中引入自适应提升模型#由于Adaboost不支持多目标输出,需要调用MultiOutputRegressor,一次可预测多个变量ABR = MultiOutputRegressor(AdaBoostRegressor(n_estimators=99#实例化模型并传入参数,learning_rate=0.2,loss='linear',random_state=500))ABR.fit(xTrain,yTrain)#传入特征和标签,拟合模型ABRPre = ABR.predict(xTest)#调用predict方法用测试集进行预测ABRRMSE = np.sqrt(MSE(yTest,ABRPre))#MSE()计算真实值与预测值的均方误差,np.sqrt进行开方后获得RMSEprint('='*60)print('Adaboost的评估指标RMSE值为：',ABRRMSE)print('Adaboost的评估指标MAPE值为：',mape(yTest,ABRPre))print('Adaboost的评估指标R-square值为：',R2(yTest,ABRPre))ABRBase = saveBase.copy()#复制测试dataFrame,方便加入各模型的预测值ABRBase.loc[:,'预测模拟'] = ABRPre[:,0]#加入预测模拟的数值ABRBase.loc[:,'预测期末'] = ABRPre[:,1]#加入预测期末的数值ABRBase.to_csv(currentPath +'\Adaboost预测结果.csv',encoding='gb18030')#保存预测结果#============================================================#5Gradient Boostingfrom sklearn.ensemble import GradientBoostingRegressor#从集成模型中引入梯度提升模型#由于Gradient Boosting不支持多目标输出,需要调用MultiOutputRegressor,一次可预测多个变量GBR = MultiOutputRegressor(GradientBoostingRegressor(loss='squared_error'#实例化模型并传入参数,learning_rate=0.2,n_estimators=99,criterion='squared_error',random_state=500))GBR.fit(xTrain,yTrain)#传入特征和标签,拟合模型GBRPre = GBR.predict(xTest)#调用predict方法用测试集进行预测GBRRMSE = np.sqrt(MSE(yTest,GBRPre))#MSE()计算真实值与预测值的均方误差,np.sqrt进行开方后获得RMSEprint('='*60)print('Gradient Boosting的评估指标RMSE值为：',GBRRMSE)print('Gradient Boosting的评估指标MAPE值为：',mape(yTest,GBRPre))print('Gradient Boosting的评估指标R-square值为：',R2(yTest,GBRPre))GBRBase = saveBase.copy()#复制测试dataFrame,方便加入各模型的预测值GBRBase.loc[:,'预测模拟'] = GBRPre[:,0]#加入预测模拟的数值GBRBase.loc[:,'预测期末'] = GBRPre[:,1]#加入预测期末的数值GBRBase.to_csv(currentPath +'\Gradient Boosting预测结果.csv',encoding='gb18030')#保存预测结果#============================================================#6XGBOOST# import xgboost as xgb#引入xgboost,xgboost分为原生的独立库xgboost和sklearn里封装好的xgboost,二者本质无太大区别# # from xgboost import XGBRegressor# xgb.set_config(verbosity=0)#隐藏警告信息# fileTrain = xgb.DMatrix(xTrain,yTrain)#要将训练集和测试集使用DMatrix方法封装成xgboost可接受的特殊形式# fileTest = xgb.DMatrix(xTest,yTest)# param = {'silent':True#xgboost原生库需要提前自定参数# ,'objective':'reg:linear'# ,"eta":0.2# ,"max_depth":7# ,"subsample":1# ,"gamma":0# ,"lambda":25# ,"alpha":0# ,"colsample_bytree":1# ,"colsample_bylevel":1# ,"colsample_bynode":1# }# num_round = 99#树的数量# XGBSR=xgb.train(param,fileTrain,num_boost_round=num_round)#训练模型# XGBSRre = XGBSR.predict(fileTest)#调用predict方法用测试集进行预测# XGBRRMSE = np.sqrt(MSE(yTest,XGBSRre))#MSE()计算真实值与预测值的均方误差,np.sqrt进行开方后获得RMSE# print('='*60)# print('XGBOOST的评估指标RMSE值为：',XGBRRMSE)#保存预测结果#============================================================#7SVMfrom sklearn.svm import SVR#引入SVM#由于svm不支持多目标输出,需要调用MultiOutputRegressor,一次可预测多个变量SVRM = MultiOutputRegressor(SVR(kernel='linear'#实例化模型,degree=3,gamma=0.1))SVRM.fit(xTrain,yTrain)#传入特征和标签,拟合模型SVRMPre = SVRM.predict(xTest)#调用predict方法用测试集进行预测SVRMRMSE = np.sqrt(MSE(yTest,SVRMPre))#MSE()计算真实值与预测值的均方误差,np.sqrt进行开方后获得RMSEprint('='*60)print('SVM的评估指标RMSE值为：',SVRMRMSE)print('SVM的评估指标MAPE值为：',mape(yTest,SVRMPre))print('SVM的评估指标R-square值为：',R2(yTest,SVRMPre))SVRMBase = saveBase.copy()SVRMBase.loc[:,'预测模拟'] = SVRMPre[:,0]#加入预测模拟的数值SVRMBase.loc[:,'预测期末'] = SVRMPre[:,1]#加入预测期末的数值SVRMBase.to_csv(currentPath +'\SVM预测结果.csv',encoding='gb18030')#保存预测结果#============================================================#8K Neighborsfrom sklearn.neighbors import KNeighborsRegressor#由于K Neighbors不支持多目标输出,需要调用MultiOutputRegressor,一次可预测多个变量KNNR = MultiOutputRegressor(KNeighborsRegressor(n_neighbors=5#实例化模型,p=2))KNNR.fit(xTrain,yTrain)#传入特征和标签,拟合模型KNNRPre = KNNR.predict(xTest)#调用predict方法用测试集进行预测KNNRRMSE = np.sqrt(MSE(yTest,KNNRPre))#MSE()计算真实值与预测值的均方误差,np.sqrt进行开方后获得RMSEprint('='*60)print('KNNR的评估指标RMSE值为：',KNNRRMSE)print('KNNR的评估指标MAPE值为：',mape(yTest,KNNRPre))print('KNNR的评估指标R-square值为：',R2(yTest,KNNRPre))print('='*60)KNNRBase = saveBase.copy()KNNRBase.loc[:,'预测模拟'] = KNNRPre[:,0]#加入预测模拟的数值KNNRBase.loc[:,'预测期末'] = KNNRPre[:,1]#加入预测期末的数值KNNRBase.to_csv(currentPath +'\K Neighbors预测结果.csv',encoding='gb18030')#保存预测结果#============================================================#各模型平均性能得分为meanScore = np.mean([DTRRMSE,ETRRMSE,RFRRMSE,ABRRMSE,GBRRMSE,SVRMRMSE,KNNRRMSE])print('各模型平均性能得分为:',meanScore)print('='*60)#随机森林性能最好，特征重要性为fIm = RFR.feature_importances_#直接获取模型的重要性print('以下为随机森林各特征重要性：')for i in range(len(dataBase.columns.values[:-2])):print(dataBase.columns.values[:-2][i],'的特征重要性分数为：',fIm[i])#============================================================#优秀模型permutation_importancefrom sklearn.inspection import permutation_importance#引入排序重要性得分PIScore = permutation_importance(RFR, xTrain, yTrain)#拟合时得分情况print(sum(PIScore['importances_mean']))print('以下为随机森林各特征permutation_importance得分：')#调用数组进行打印for i in range(len(dataBase.columns.values[:-2])):print(dataBase.columns.values[:-2][i],'的permutation_importance特征重要性分数为：',PIScore['importances_mean'][i])#============================================================# dot_data = tree.export_graphviz(RFR, out_file=None) #%%
如果觉得《关于Sklearn的SVM XGBOOST 随机森林等算回归预测建模的方法及数据提取》对你有帮助，请点赞、收藏，并留下你的观点哦！
