pytorch/各地级市日电量模型/衢州.py

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())