机器学习模型+CATboost（CGB）+greadsearchCV+源码

# 开发者：董书雄 # 开发时间:2022-11-13 23:33 # 开发内容:{} import numpy as np from sklearn.model_selection import train_test_split import pandas as pd import joblib from sklearn import metrics, ensemble from catboost import CatBoostRegressor # 调用模型 import matplotlib.pyplot as plt import seaborn as sns pd.set_option('display.max_columns', None) # 结果显示所有列 pd.set_option('display.max_rows', None) # 结果显示所行行 # 1：TGAN合成数据的训练效果 # data1 = pd.read_csv('traindata928.csv') # data2 = pd.read_csv('testdata.csv') # 2：纯原数据232个的训练效果 #data2 = pd.read_csv('NSGA专用CAT.csv') #data1, data2 = train_test_split(data2, test_size=0.3) data1 = pd.read_csv('CATtraindata.csv') data2 = pd.read_csv('CATtestdata.csv') print('traindata=', data1) print('testdata=', data2) # 记得把测试和训练数据集的特征第一行特征整一样！ # print(data1,type(data1)) x_train = data1.iloc[:, 0:9] y_train = data1.iloc[:, 9] x_test = data2.iloc[:, 0:9] y_test = data2.iloc[:, 9] X = pd.concat([x_train, x_test]) Y = pd.concat([y_train, y_test]) col = data1.columns[:-1] # 训练模型 rfmodel = CatBoostRegressor( learning_rate=0.3, # 学习率 max_depth=5, # n_estimators=120, n_estimators=200 ) # rfmodel.fit(x_train, y_train) # 模型预测 joblib.dump(rfmodel, 'catboost.model') rfmodel = joblib.load('catboost.model') rf_predict_test = rfmodel.predict(x_test) rf_predict_train = rfmodel.predict(x_train) rf_predict_all = rfmodel.predict(X) rf_error = rf_predict_test - y_test # 计算性能指标 rf_R2_rtrain = metrics.r2_score(y_train, rf_predict_train) rf_R2_rtest = metrics.r2_score(y_test, rf_predict_test) rf_R2_rall = metrics.r2_score(Y, rf_predict_all) rf_RMSE_train = metrics.mean_squared_error(y_train, rf_predict_train) ** 0.5 rf_RMSE_test = metrics.mean_squared_error(y_test, rf_predict_test) ** 0.5 rf_RMSE_all = metrics.mean_squared_error(Y, rf_predict_all) ** 0.5 rf_MAPE_train = metrics.mean_absolute_percentage_error(y_train, rf_predict_train) rf_MAPE_test = metrics.mean_absolute_percentage_error(y_test, rf_predict_test) rf_MAPE_all = metrics.mean_absolute_percentage_error(Y, rf_predict_all) rf_performance = (rf_R2_rtrain, rf_R2_rtest, rf_R2_rall, rf_RMSE_train, rf_RMSE_test, rf_RMSE_all, rf_MAPE_train, rf_MAPE_test, rf_MAPE_all) # 绘图数据 data_array = np.array(rf_predict_test) rf_predict_test = data_array.tolist() data_array = np.array(rf_predict_all) rf_predict_all = data_array.tolist() print('y_test=', y_test) print('rf_predict_test=', rf_predict_test, type(rf_predict_test)) print('Y=', Y) print('rf_predict_all=', rf_predict_all) print('rf_R2_rtrain=', rf_R2_rtrain) print('rf_R2_rtest=', rf_R2_rtest) print('rf_R2_rall=', rf_R2_rall) print('rf_RMSE_train=', rf_RMSE_train) print('rf_RMSE_test=', rf_RMSE_test) print('rf_RMSE_all=', rf_RMSE_all) print('rf_MAPE_train=', rf_MAPE_train) print('rf_MAPE_test=', rf_MAPE_test) print('rf_MAPE_all=', rf_MAPE_all) plt.scatter(Y, rf_predict_all, ) plt.show()