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.
101 lines
3.5 KiB
Python
101 lines
3.5 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', '10', '11'):
|
|
return 0
|
|
elif str(x)[5:7] in ('02', '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/丽水.xlsx'))
|
|
data['dtdate'] = pd.to_datetime(data['dtdate'], format='%Y-%m-%d')
|
|
data['year'] = data['dtdate'].dt.year
|
|
data.set_index('dtdate', inplace=True)
|
|
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}'
|
|
# print(data.loc[month_index]['售电量'].max(),data['售电量'].describe()['75%'])
|
|
# 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['2023-12']
|
|
# df_train = data.loc['2021-1':'2023-8']
|
|
|
|
df_train = data[-180:]
|
|
# df_train = data.loc['2022-4':'2023-9'][:-3]
|
|
df_train = df_train[['tem_max', 'tem_min', 'holiday', '24ST', '售电量', 'season', 'year']]
|
|
|
|
print(df_train.corr()['售电量'])
|
|
|
|
X = df_train[['tem_max', 'tem_min', '24ST', 'holiday', 'season', 'year']]
|
|
X_eval = df_eval[['tem_max', 'tem_min', '24ST', 'holiday', 'season', 'year']]
|
|
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=42)
|
|
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_test:',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)
|
|
|
|
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)
|
|
|
|
import numpy as np
|
|
|
|
X_eval = np.array([
|
|
[16.2, 6.5, 0, 0, 1, 2023],
|
|
[15.9, 6.9, 0, 0, 1, 2023],
|
|
[19.1, 7.4, 0, 3, 1, 2023],
|
|
[13.4, 3.2, 0, 3, 1, 2023]
|
|
])
|
|
# X_eval = np.array([[6.2,5.1,0,0,1,2023]])
|
|
print(model.predict(X_eval))
|
|
result = model.predict(X_eval)
|
|
result = pd.DataFrame(result, index=['2023-12-28','2023-12-29','2023-12-30','2023-12-31' ])
|
|
result = pd.concat((result_eval['eval'], result))
|
|
result.index = result.index.map(lambda x: str(x)[:10])
|
|
result.columns = ['预测值']
|
|
print(result)
|
|
|
|
with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\市区日电量预测_1229.xlsx',mode='a',if_sheet_exists='replace',engine='openpyxl') as writer:
|
|
result.to_excel(writer,sheet_name='丽水') |