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 season(x): if str(x)[5:7] in ('01', '02', '10', '11'): return 0 elif str(x)[5:7] in ('03', '04', '05', '06', '09', '12'): return 1 else: return 2 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/绍兴.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['season'] = data.index.map(season) df_eval = data.loc['2023-10'] # data = data.loc[:'2023-8'] df_train = data[450:-1] # df_train = data[450:][:-3] print(df_train) df_train = df_train[['tem_max','tem_min','holiday','24ST','售电量','season']] 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=0.1,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) 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) print(result_eval) # 保存模型 model.save_model('shaoxing.bin') loaded_model = xgb.XGBRegressor() loaded_model.load_model('shaoxing.bin') import numpy as np X_eval = np.array([[25.1,17.1,23,1,0], [25.8,13.5,23,0,0], [26.6,13.5,23,0,0]]) print(model.predict(X_eval))