import xgboost as xgb
import pandas as pd
import numpy as np
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 ('04', '10'):
        return 0
    elif str(x)[5:7] in ('01', '02', '03', '05', '06', '09', '11', '12'):
        return 1
    else:
        return 2
def month(x):
    if str(x)[5:7] in ('08','09','10','12','01','02'):
        return 1
    else:
        return 0
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/杭州.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['month'] = data.index.strftime('%Y-%m-%d').str[6]
# data['month'] = data['month'].astype('int')
data['season'] = data.index.map(season)


# df_train = df[500:850]

df_train = data.loc['2021-01':'2023-08']
df_eval = data.loc['2023-9']


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']

# 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=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)
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:',goal)

goal2 = (result_eval['eval'][-23:].sum()-result_eval['pred'][-23:].sum())/result_eval['eval'].sum()

print('goal2:',goal2)
print(result_eval)
print('r2:',r2_score(y_test,y_pred))
#
# # result_eval.to_csv('asda.csv',encoding='gbk')
#     # if abs(goal) < best_goal:
#     #     best_goal = abs(goal)
#     #     best_i['best_i'] = i
#     #     x = goal2
# # print(best_i,best_goal,x)
#
#
#
# # result_eval.to_csv(r'C:\Users\user\Desktop\9月各地市日电量预测结果\杭州.csv')
# # 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'杭州月末3天偏差率：{round(goal,5)},9号-月底偏差率：{round(goal2,5)}\n')
# 保存模型
model.save_model('hangzhou.bin')

# X_eval = df_eval[['tem_max','tem_min','24ST','holiday','season']]
# df_eval = pd.read_excel(r'C:\Users\user\Desktop\浙江气象1027.xlsx')
# df_eval.columns = df_eval.columns.map(lambda x:x.strip())
# df_eval = df_eval[['city_name','dtdate','tem_max','tem_min']]
# df_eval['city_name'] = df_eval['city_name'].map(lambda x:x.strip())
# df_hangzhou = df_eval[df_eval['city_name']=='金华市'].sort_values(by='dtdate')




loaded_model = xgb.XGBRegressor()
loaded_model.load_model('hangzhou.bin')
# X_eval = np.array([[26.1,16.1,23,0,0],
#                    [24.5,14.6,23,1,0],
#                        [24.0,15.2,23,1,0],
#                        [22.7,14.9,23,0,0],
#                        [24.1,13.4,23,0,0]])
#
# print(loaded_model.predict(X_eval))