import xgboost as xgb import pandas as pd import numpy as np 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 season(x): if str(x)[5:7] in ('04', '10'): return 0 elif str(x)[5:7] in ('01', '02', '03', '05', '06', '09', '11', '12'): return 1 else: return 2 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)] parent_dir = os.path.abspath(os.path.join(os.getcwd(),os.pardir)) data = pd.read_excel(os.path.join(parent_dir,'入模数据/杭州.xlsx'),index_col='dtdate') data.index = pd.to_datetime(data.index,format='%Y-%m-%d') data = data.loc[normal(data['售电量']).index] # list2 = [] # list0 = [] # list1 = [] # for i in ('01','02','03','04','05','06','07','08','09','10','11','12'): # month_index = data.index.strftime('%Y-%m-%d').str[5:7] == f'{i}' # if data.loc[month_index]['售电量'].mean() >= data['售电量'].describe()['75%']: # list2.append(i) # elif data.loc[month_index]['售电量'].mean() <= data['售电量'].describe()['25%']: # list0.append(i) # else: # list1.append(i) # print(list0,list1,list2) # data['month'] = data.index.strftime('%Y-%m-%d').str[6] # data['month'] = data['month'].astype('int') data['season'] = data.index.map(season) # df_train = df[500:850] df_train = data.loc['2021-01':'2023-08'] df_eval = data.loc['2023-9'] 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'] # 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=142) 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:',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)) # # # result_eval.to_csv('asda.csv',encoding='gbk') # # 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') # X_eval = df_eval[['tem_max','tem_min','24ST','holiday','season']] # df_eval = pd.read_excel(r'C:\Users\user\Desktop\浙江气象1027.xlsx') # df_eval.columns = df_eval.columns.map(lambda x:x.strip()) # df_eval = df_eval[['city_name','dtdate','tem_max','tem_min']] # df_eval['city_name'] = df_eval['city_name'].map(lambda x:x.strip()) # df_hangzhou = df_eval[df_eval['city_name']=='金华市'].sort_values(by='dtdate') loaded_model = xgb.XGBRegressor() loaded_model.load_model('hangzhou.bin') # X_eval = np.array([[26.1,16.1,23,0,0], # [24.5,14.6,23,1,0], # [24.0,15.2,23,1,0], # [22.7,14.9,23,0,0], # [24.1,13.4,23,0,0]]) # # print(loaded_model.predict(X_eval))