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']

def season(x):
    if str(x)[5:7] in ('06','07','08','12','01','02'):
        return 1
    else:
        return 0


pd.set_option('display.width',None)
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'),index_col='dtdate')
data.index = pd.to_datetime(data.index,format='%Y-%m-%d')
data['season'] = data.index.map(season)

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','season']]

# 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)]

# list2 = []
# list0 = []
# list1 = []
# for i in ('01','02','03','04','05','06','07','08','09','10','11','12'):
#     month_index = df.index.strftime('%Y-%m-%d').str[5:7] == f'{i}'
#     if df.loc[month_index]['售电量'].mean() >= df['售电量'].describe()['75%']:
#         list2.append(i)
#     elif df.loc[month_index]['售电量'].mean() <= df['售电量'].describe()['25%']:
#         list0.append(i)
#     else:
#         list1.append(i)
# print(list0,list1,list2)


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(200):


x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.15,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(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)


# 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')
import numpy as np
loaded_model = xgb.XGBRegressor()
loaded_model.load_model('lishui.bin')
X_eval = np.array([
                   [22.5,15.4,23,0,0],
                       [22.3,15.5,23,1,0],
                       [20.0,15.7,23,1,0],
                       [22.0,15.0,23,0,0],
[23.6,13.9,23,0,0]])
print(model.predict(X_eval))