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 def season(x): if str(x)[5:7] in ('06','07','08','12','01','02'): return 1 else: return 0 mpl.rcParams['font.sans-serif']=['kaiti'] pd.set_option('display.width',None) data = pd.read_excel(r'C:\Users\user\PycharmProjects\pytorch2\入模数据\台州数据(1).xlsx',index_col='dtdate') data.index = pd.to_datetime(data.index,format='%Y-%m-%d') data['season'] = data.index.map(season) # plt.plot(range(len(data)),data['售电量']) # plt.show() print(data.head()) df_eval = data.loc['2023-8'] # df_train = data.loc['2021-1':'2023-7'] df_train = data[500:850] print(len(df_eval),len(df_train),len(data)) df_train = df_train[['tem_max','tem_min','holiday','24ST','rh','prs','售电量','season']] # 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','season']] X_eval = df_eval[['tem_max','tem_min','holiday','24ST','season']] 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=0.2,random_state=163) 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) # print(result_eval) # print((result_eval['eval'].sum()-result_eval['pred'].sum())/result_eval['eval'].sum()) print((result_eval['eval'][-3:].sum()-result_eval['pred'][-3:].sum())/result_eval['eval'].sum()) goal = (result_eval['eval'][-3:].sum()-result_eval['pred'][-3:].sum())/result_eval['eval'].sum() print((result_eval['eval'][-23:].sum()-result_eval['pred'][-23:].sum())/result_eval['eval'].sum()) goal2 = (result_eval['eval'][-23:].sum()-result_eval['pred'][-23:].sum())/result_eval['eval'].sum() # if abs(goal) < best_goal: # best_goal = abs(goal) # best_i['best_i'] = i # print(best_i,best_goal) # # result_eval.to_csv(r'C:\Users\user\Desktop\9月各地市日电量预测结果\台州.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'台州月末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('taizhou.bin') import numpy as np loaded_model = xgb.XGBRegressor() loaded_model.load_model('taizhou.bin') X_eval = np.array([[25.1,16.8,23,0,0], [22.8,16.3,23,1,0], [22.7,14.6,23,1,0], [22.5,14.4,23,0,0], [22.6,15.6,23,0,0]]) print(model.predict(X_eval))