|
|
|
|
|
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)
|
|
|
|
|
|
|
|
|
|
|
|
data = pd.read_excel(r'C:\Users\user\PycharmProjects\pytorch2\入模数据\丽水数据.xlsx',index_col='dtdate')
|
|
|
|
|
|
data.index = pd.to_datetime(data.index,format='%Y-%m-%d')
|
|
|
|
|
|
|
|
|
|
|
|
plt.plot(range(len(data)),data['售电量'])
|
|
|
|
|
|
plt.show()
|
|
|
|
|
|
print(data.head())
|
|
|
|
|
|
|
|
|
|
|
|
df_eval = data.loc['2023-9']
|
|
|
|
|
|
df_train = data.loc['2021-1':'2023-8']
|
|
|
|
|
|
# df_train = df[500:850]
|
|
|
|
|
|
print(len(df_eval),len(df_train),len(data))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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']
|
|
|
|
|
|
# best_goal = 1
|
|
|
|
|
|
# best_i = {}
|
|
|
|
|
|
# for i in range(200):
|
|
|
|
|
|
|
|
|
|
|
|
x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.15,random_state=176)
|
|
|
|
|
|
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)
|
|
|
|
|
|
# print(result_eval)
|
|
|
|
|
|
# print((result_eval['eval'].sum()-result_eval['pred'].sum())/result_eval['eval'].sum())
|
|
|
|
|
|
print((result_eval['eval'][-3:].sum()-result_eval['pred'][-3:].sum())/result_eval['eval'].sum())
|
|
|
|
|
|
goal = (result_eval['eval'][-3:].sum()-result_eval['pred'][-3:].sum())/result_eval['eval'].sum()
|
|
|
|
|
|
print((result_eval['eval'][-23:].sum()-result_eval['pred'][-23:].sum())/result_eval['eval'].sum())
|
|
|
|
|
|
goal2 = (result_eval['eval'][-23:].sum()-result_eval['pred'][-23:].sum())/result_eval['eval'].sum()
|
|
|
|
|
|
# if abs(goal) < best_goal:
|
|
|
|
|
|
# best_goal = abs(goal)
|
|
|
|
|
|
# best_i['best_i'] = i
|
|
|
|
|
|
# print(best_i,best_goal)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
result_eval.to_csv(r'C:\Users\user\Desktop\9月各地市日电量预测结果\丽水.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'丽水月末3天偏差率：{goal},9号-月底偏差率：{goal2}')
|
|
|
|
|
|
# # 保存模型
|
|
|
|
|
|
# model.save_model('lishui.bin')
|
|
|
|
|
|
# loaded_model = xgb.XGBRegressor()
|
|
|
|
|
|
# loaded_model.load_model('lishui.bin')
|
|
|
|
|
|
# model.predict(X_eval)
|
|
|
|
|
|
|
