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.
41 lines
1.3 KiB
Python
41 lines
1.3 KiB
Python
import pandas as pd
|
|
import matplotlib.pyplot as plt
|
|
import xgboost as xgb
|
|
from sklearn.model_selection import train_test_split
|
|
from sklearn.metrics import r2_score
|
|
def normal(x):
|
|
high = x.describe()['75%'] + 1.5*(x.describe()['75%']-x.describe()['25%'])
|
|
low = x.describe()['25%'] - 1.5*(x.describe()['75%']-x.describe()['25%'])
|
|
return x[(x<=high)&(x>=low)]
|
|
|
|
def season(x):
|
|
if str(x)[5:7] in ('04', '05', '06', '11'):
|
|
return 0
|
|
elif str(x)[5:7] in ('01', '02', '03', '09', '10', '12'):
|
|
return 1
|
|
else:
|
|
return 2
|
|
|
|
df = pd.read_excel('../400v入模数据/衢州.xlsx',index_col='stat_date')
|
|
df.index = pd.to_datetime(df.index)
|
|
|
|
|
|
x_train = df.loc['2021-7':'2023-7'][:-3].drop(columns='0.4kv及以下')
|
|
y_train = df.loc['2021-7':'2023-7'][:-3]['0.4kv及以下']
|
|
x_eval = df.loc['2023-7'].drop(columns='0.4kv及以下')
|
|
y_eval = df.loc['2023-7']['0.4kv及以下']
|
|
|
|
x_train,x_test,y_train,y_test = train_test_split(x_train,y_train,test_size=0.2,random_state=142)
|
|
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)
|
|
print(r2_score(y_test,y_pred))
|
|
|
|
predict = model.predict(x_eval)
|
|
result = pd.DataFrame({'eval':y_eval,'pred':predict},index=y_eval.index)
|
|
print(result)
|
|
print((result['eval'][-3:].sum()-result['pred'][-3:].sum())/result['eval'].sum())
|
|
|
|
|
|
|