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'):
        return 0
    elif str(x)[5:7] in ('01', '02', '03', '06', '09', '10', '11', '12'):
        return 1
    else:
        return 2

df = pd.read_excel('./浙江各地市分电压日电量数据/杭州 .xlsx')
df = df[['stat_date','0.4kv及以下']]
df['0.4kv及以下'] = df['0.4kv及以下']/10000
df['stat_date'] = df['stat_date'].map(lambda x:x.strip())
df['stat_date'] = pd.to_datetime(df['stat_date'])


df_qw = pd.read_excel(r'C:\python-project\p1031\入模数据\杭州.xlsx')
df_qw.columns = df_qw.columns.map(lambda x:x.strip())

df_qw = df_qw[['dtdate','tem_max','tem_min','holiday','24ST']]
df_qw['dtdate'] = pd.to_datetime(df_qw['dtdate'])


df = pd.merge(df,df_qw,left_on='stat_date',right_on='dtdate',how='left')
df.drop(columns='dtdate',inplace=True)
df.set_index('stat_date',inplace=True)
df['season'] = df.index.map(season)
df = df.loc[normal(df['0.4kv及以下']).index]

print(df.head())

x_train = df.loc['2022-7':'2023-7'].drop(columns='0.4kv及以下')
y_train = df.loc['2022-7':'2023-7']['0.4kv及以下']
x_eval = df.loc['2023-8'].drop(columns='0.4kv及以下')
y_eval = df.loc['2023-8']['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=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)
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())

# 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}'
#     print(df.loc[month_index]['0.4kv及以下'].max(),df['0.4kv及以下'].describe()['75%'])
#     if df.loc[month_index]['0.4kv及以下'].mean() >= df['0.4kv及以下'].describe()['75%']:
#         list2.append(i)
#     elif df.loc[month_index]['0.4kv及以下'].mean() <= df['0.4kv及以下'].describe()['25%']:
#         list0.append(i)
#     else:
#         list1.append(i)
# print(list0,list1,list2)