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'): return 0 elif str(x)[5:7] in ('03', '04', '05', '06', '09', '10', '11', '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/衢州.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['season'] = data.index.map(season) # data = data.loc[:'2023-8'] df_eval = data.loc['2023-10'] df_train = data.iloc[450:-1] # df_train = data.iloc[450:-3] 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'] x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_state=42) 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) # 保存模型 model.save_model('quzhou.bin') loaded_model = xgb.XGBRegressor() loaded_model.load_model('quzhou.bin') import numpy as np X_eval = np.array([[23.69,16.5,23,1,0], [24.5,15.19,23,0,0], [25.19,13.9,23,0,0]]) print(model.predict(X_eval)) # 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())