You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
144 lines
4.6 KiB
Python
144 lines
4.6 KiB
Python
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\鸽子\Desktop\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_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
|
|
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)
|
|
print(result_eval)
|
|
target = (result_eval['eval'].sum()-result_eval['pred'].sum())/ df[df.index.str[:7]=='2023-08']['售电量'].sum()
|
|
print(target)
|
|
|
|
|
|
|
|
# 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\鸽子\Desktop\各地市日电量预测结果\衢州.csv')
|
|
#
|
|
# 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())
|
|
|
|
|
|
|