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\衢州数据.xlsx') df['dtdate'] = pd.to_datetime(df['dtdate'],format='%Y-%m-%d').astype('string') df.set_index('dtdate',inplace=True) plt.plot(range(len(df)),df['售电量']) plt.show() print(df.head()) # df_eval = df[(df.index.str[:10]=='2023-08-29')|(df.index.str[:10]=='2023-08-30')|(df.index.str[:10]=='2023-08-31')] # # df_train = df[(df.index.str[:7]!='2023-09')&(df.index.str!='2023-08-29')&(df.index.str!='2023-08-30')&(df.index.str!='2023-08-31')] df_eval = df[df.index.str[:7]=='2023-07'] # df_train = df[(df.index.str[:7]!='2023-08')&(df.index.str[:7]!='2023-09')] df_train = df[450:900] # max_8,min_8 = df_eval['售电量'].max(),df_eval['售电量'].min() 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'] x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_state=102) model = xgb.XGBRegressor(max_depth=6, learning_rate=0.1, 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 eval_pred = model.predict(X_eval) result_eval = pd.DataFrame({'eval':df_eval['售电量'],'pred':eval_pred}) 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) # print((result_eval['eval'].sum()-result_eval['pred'].sum())/result_eval['eval'].sum()) # print((result_eval['eval'].sum()-(result_eval['eval'][:-3].sum()+result_eval['pred'][-3:].sum()))/result_eval['eval'].sum()) # result_eval.to_csv(r'C:\Users\user\Desktop\9月各地市日电量预测结果\衢州.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'衢州月末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('quzhou.bin') # loaded_model = xgb.XGBRegressor() # loaded_model.load_model('quzhou.bin') # model.predict(X_eval) # from sklearn.ensemble import RandomForestRegressor # from sklearn.metrics import mean_squared_error # rf = RandomForestRegressor(n_estimators=150,max_depth=6) # # # 在训练集上训练模型 # rf.fit(x_train, y_train) # # # 在测试集上进行预测 # y_pred = rf.predict(x_test) # eval_pred = rf.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'].sum()-(result_eval['eval'][:-3].sum()+result_eval['pred'][-3:].sum()))/result_eval['eval'].sum()) # import torch # from torch import nn # from torch.utils.data import TensorDataset,DataLoader # # # net = nn.Sequential( # nn.Linear(6,32), # nn.ReLU(), # nn.Linear(32,64), # nn.ReLU(), # nn.Linear(64,64), # nn.ReLU(), # nn.Linear(64,1) # ) # opt = torch.optim.Adam(net.parameters(),lr=0.00005) # loss_fn = nn.MSELoss() # # epochs = 200 # # x_train = torch.from_numpy(x_train.values).type(torch.float32) # x_train = (x_train - x_train.mean())/x_train.std() # # y_train = torch.from_numpy(y_train.values).type(torch.float32) # std1 = y_train.std() # mean1 = y_train.mean() # y_train = (y_train - mean1)/std1 # # X_eval = torch.from_numpy(X_eval.values).type(torch.float32) # X_eval = (X_eval - X_eval.mean())/X_eval.std() # # y_eval= torch.from_numpy(df_eval['售电量'].values).type(torch.float32) # # # train_ds = TensorDataset(x_train,y_train) # train_dl = DataLoader(train_ds,shuffle=True,batch_size=64) # # # for i in range(epochs): # for x,y in train_dl: # y_pred = net(x) # loss = loss_fn(y_pred,y) # # opt.zero_grad() # loss.backward() # opt.step() # print(round(loss.item(),2)) # # predict = (net(X_eval) * std1 + mean1).detach().numpy() # print(y_train.std(),y_train.mean()) # print(net(X_eval)) # print(predict) # print((y_eval.detach().numpy().sum() - predict.sum())/ y_eval.detach().numpy().sum())