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) def hf_season(x): list1= [] for i in range(1,13): if x.loc[f'2021-{i}'].mean() >= x.describe()['75%']: list1.append(i) return list1 def season(x): if str(x)[5:7] in ('06','07','08','12','01','02'): return 1 else: return 0 def month(x): if str(x)[5:7] in ('08','09','10','12','01','02'): return 1 else: return 0 def normal(nd): high = nd.describe()['75%'] + 1.5*(nd.describe()['75%']-nd.describe()['25%']) low = nd.describe()['25%'] - 1.5*(nd.describe()['75%']-nd.describe()['25%']) return nd[(ndlow)] data = pd.read_excel(r'C:\python-project\pytorch3\入模数据\杭州数据.xlsx',index_col='dtdate') data.index = pd.to_datetime(data.index,format='%Y-%m-%d') data = data.loc[normal(data['售电量']).index] # for i in range(1,13): # plt.plot(range(len(data['售电量'][f'2022-{i}'])),data['售电量'][f'2022-{i}']) # plt.show() print(data['售电量']['2022-9']) plt.plot(range(len(data['售电量']['2022-7'])),data['售电量']['2022-7']) plt.plot(range(len(data['售电量']['2022-7']),len(data['售电量']['2022-7'])+len(data['售电量']['2023-7'])),data['售电量']['2023-7']) # plt.plot(range(len(data['售电量'][['2022-9','2023-9']])),data['售电量'][['2022-9','2023-9']]) plt.show() # print(hf_season(data.loc['2021']['售电量'])) data['month'] = data.index.strftime('%Y-%m-%d').str[6] data['month'] = data['month'].astype('int') data['season'] = data.index.map(season) print(data.head(50)) df_eval = data.loc['2023-7'] df_train = data.loc['2021-1':'2023-6'] # df_train = df[500:850] print(len(df_eval),len(df_train),len(data)) print(data.drop(columns='city_name').corr(method='pearson')['售电量']) df_train = df_train[['tem_max','tem_min','24ST','rh','rh_max','prs','prs_max','prs_min','售电量','month','holiday','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','24ST','holiday','season']] X_eval = df_eval[['tem_max','tem_min','24ST','holiday','season']] y = df_train['售电量'] print(y.describe()) # 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=0.15,random_state=42) 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['eval'].sum()-result_eval['pred'].sum())/result_eval['eval'].sum()) goal = (result_eval['eval'][-3:].sum()-result_eval['pred'][-3:].sum())/result_eval['eval'].sum() print('goal:',goal) goal2 = (result_eval['eval'][-23:].sum()-result_eval['pred'][-23:].sum())/result_eval['eval'].sum() print('goal2:',goal2) print(result_eval) print('r2:',r2_score(y_test,y_pred)) # 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\杭州.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'杭州月末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('hangzhou.bin') # loaded_model = xgb.XGBRegressor() # loaded_model.load_model('hangzhou.bin') # model.predict(X_eval)