import xgboost as xgb import pandas as pd import os from sklearn.metrics import r2_score from sklearn.model_selection import train_test_split import matplotlib as mpl import matplotlib.pyplot as plt mpl.rcParams['font.sans-serif']=['kaiti'] pd.set_option('display.width',None) df = pd.read_excel(r'C:\Users\user\PycharmProjects\pytorch2\入模数据\绍兴数据(1).xlsx',index_col='dtdate') df.index = pd.to_datetime(df.index ,format='%Y-%m-%d') plt.plot(range(len(df)),df['售电量']) plt.show() print(df.head()) df_eval = df.loc['2023-9'] df_train = df.loc['2021-1':'2023-8'] # df_train = df[400:850] print(len(df_eval),len(df_train),len(df)) df_train = df_train[['tem_max','tem_min','holiday','24ST','rh','prs','售电量']] # IQR = df['售电量'].describe()['75%'] - df['售电量'].describe()['25%'] # high = df['售电量'].describe()['75%'] + 1.5*IQR # low = df['售电量'].describe()['25%'] - 1.5*IQR # print('异常值数量:',len(df[(df['售电量'] >= high) | (df['售电量'] <= low)])) # # df_train = df_train[(df['售电量'] <= high) & (df['售电量'] >= low)] X = df_train[['tem_max','tem_min','holiday','24ST','rh','prs']] X_eval = df_eval[['tem_max','tem_min','holiday','24ST','rh','prs']] y = df_train['售电量'] # best_goal = 1 # best_i = {} # for i in range(400): x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.1,random_state=253) model = xgb.XGBRegressor(max_depth=6, learning_rate=0.05, n_estimators=150) model.fit(x_train,y_train) y_pred = model.predict(x_test) result_test = pd.DataFrame({'test':y_test,'pred':y_pred},index=y_test.index) # 指标打印 print(abs(y_test - y_pred).mean() / y_test.mean()) eval_pred = model.predict(X_eval) result_eval = pd.DataFrame({'eval':df_eval['售电量'],'pred':eval_pred},index=df_eval['售电量'].index) goal = (result_eval['eval'][-3:].sum()-result_eval['pred'][-3:].sum())/result_eval['eval'].sum() print(goal) goal2 = (result_eval['eval'][-23:].sum()-result_eval['pred'][-23:].sum())/result_eval['eval'].sum() print(goal2) # if abs(goal) < best_goal : # best_goal = abs(goal) # best_i['best_i'] = i # x = goal2 # print(best_i,best_goal,x) result_eval.to_csv(r'C:\Users\user\Desktop\9月各地市日电量预测结果\绍兴.csv') with open(r'C:\Users\user\Desktop\9月各地市日电量预测结果\偏差率.txt','a',encoding='utf-8') as f: f.write(f'绍兴月末3天偏差率:{round(goal,5)},9号-月底偏差率:{round(goal2,5)}\n') # 保存模型 model.save_model('shaoxing.bin') loaded_model = xgb.XGBRegressor() loaded_model.load_model('shaoxing.bin') model.predict(X_eval)