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

mpl.rcParams['font.sans-serif'] = ['kaiti']
pd.set_option('display.width', None)


def season(x):
    if str(x)[5:7] in ('01', '02', '03', '04', '05', '06', '09', '10', '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/舟山.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}'
#     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.iloc[450:]

df_train = df_train[['tem_max', 'tem_min', 'holiday', '24ST', '售电量', 'season', 'year']]
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=0.1, 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)

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([
    [12.3, 8.4, 0, 0, 1, 2023],
    [13.3, 7.9, 0, 0, 1, 2023],
    [13.0, 10.6, 0, 3, 1, 2023],
    [10.5, 6.1, 0, 3, 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='舟山')