import xgboost as xgb
import pandas as pd
import os
from sklearn.metrics import r2_score
from sklearn.model_selection import train_test_split
pd.set_option('display.width',None)

def season(x):
    if str(x)[5:7] in ('01', '02', '04', '10'):
        return 0
    elif str(x)[5:7] in ('03', '05', '06', '09', '11', '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/金华.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)

data = data.loc[:'2023-12']
df_eval = data.loc['2023-12']

df_train = data.iloc[-180:]
print(df_train)

df_train = df_train[['tem_max','tem_min','holiday','24ST','售电量','season']]

X = df_train[['tem_max','tem_min','24ST','holiday','season']]
X_eval = df_eval[['tem_max','tem_min','24ST','holiday','season']]
y = df_train['售电量']


x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.1,random_state=100)
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)

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)
print(result_eval)


import numpy as np
X_eval = np.array([
    [16.3, 2.5, 0, 0, 1],
    [16.9, 3.8, 0, 0, 1],
    [16.5, 6.2, 0, 0, 1],
    [18.8, 7.8, 0, 3, 1],
    [12.5, 2.8, 0, 3, 1]
])
print(model.predict(X_eval))
result = model.predict(X_eval)
result = pd.DataFrame(result, index=['2023-12-27', '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_1228.xlsx', mode='a', if_sheet_exists='replace',
                    engine='openpyxl') as writer:
    result.to_excel(writer, sheet_name='金华')