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.
91 lines
3.0 KiB
Python
91 lines
3.0 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)
|
|
|
|
def season(x):
|
|
if str(x)[5:7] in ('01', '02', '10', '11'):
|
|
return 0
|
|
elif str(x)[5:7] in ('03', '04', '05', '06', '09', '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[(nd<high)&(nd>low)]
|
|
|
|
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/台州.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)
|
|
|
|
df_eval = data.loc['2023-8']
|
|
|
|
df_train = data[500:850]
|
|
|
|
df_train = df_train[['tem_max','tem_min','holiday','24ST','售电量','season']]
|
|
|
|
X = df_train[['tem_max','tem_min','holiday','24ST','season']]
|
|
X_eval = df_eval[['tem_max','tem_min','holiday','24ST','season']]
|
|
y = df_train['售电量']
|
|
# 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=0.2,random_state=158)
|
|
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())
|
|
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)
|
|
# if abs(goal) < best_goal:
|
|
# best_goal = abs(goal)
|
|
# best_i['best_i'] = i
|
|
# print(best_i,best_goal)
|
|
|
|
# 保存模型
|
|
# model.save_model('taizhou.bin')
|
|
import numpy as np
|
|
loaded_model = xgb.XGBRegressor()
|
|
loaded_model.load_model('taizhou.bin')
|
|
X_eval = np.array([
|
|
[22.6,15.3,23,1,0],
|
|
[23.89,13.4,23,0,0],
|
|
[24.69,13.4,23,0,0]])
|
|
print(model.predict(X_eval))
|
|
|