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.

95 lines
3.1 KiB
Python

1 year ago
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
1 year ago
def season(x):
if str(x)[5:7] in ('06','07','08','12','01','02'):
return 1
else:
return 0
1 year ago
mpl.rcParams['font.sans-serif']=['kaiti']
pd.set_option('display.width',None)
1 year ago
df = pd.read_excel(r'C:\Users\user\PycharmProjects\pytorch2\入模数据\嘉兴数据.xlsx')
1 year ago
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())
1 year ago
df['season'] = df.index.map(season)
1 year ago
df_eval = df[df.index.str[:7]=='2023-08']
# df_train = df[(df.index.str[:7]!='2023-08')&(df.index.str[:7]!='2023-09')]
df_train = df[500:850]
print(len(df_eval),len(df_train),len(df))
1 year ago
df_train = df_train[['tem_max','tem_min','holiday','24ST','rh','prs','售电量','season']]
1 year ago
# 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)]
1 year ago
X = df_train[['tem_max','tem_min','holiday','24ST','season']]
X_eval = df_eval[['tem_max','tem_min','holiday','24ST','season']]
1 year ago
y = df_train['售电量']
1 year ago
# 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=272)
1 year ago
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)
1 year ago
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()
1 year ago
print(goal,goal2)
1 year ago
# print(goal2)
# if abs(goal) < best_goal :
# best_goal = abs(goal)
# best_i['best_i'] = i
# x = goal2
#
# print(best_i,best_goal,x)
1 year ago
# result_eval.to_csv(r'C:\Users\user\Desktop\8月各地市日电量预测结果\嘉兴.csv')
# with open(r'C:\Users\user\Desktop\8月各地市日电量预测结果\偏差率.txt','a',encoding='utf-8') as f:
# f.write(f'嘉兴月末3天偏差率{round(goal,5)},9号-月底偏差率:{round(goal2,5)}\n')
1 year ago
# 保存模型
1 year ago
# model.save_model('jiaxing.bin')
1 year ago
loaded_model = xgb.XGBRegressor()
loaded_model.load_model('jiaxing.bin')
1 year ago
import numpy as np
X_eval = np.array([[23.4,16.1,23,0,0],
[23.3,16.0,23,1,0],
[22.0,15.8,23,1,0],
[23.8,15.7,23,0,0],
[24.1,15.3,23,0,0]])
print(model.predict(X_eval))