import pandas as pd

df = pd.read_excel(r'C:\Users\鸽子\Desktop\zj20231228.xlsx', sheet_name=2)
df['stat_date'] = pd.to_datetime(df['stat_date'])

# 移动平均
for city in df['city_name'].drop_duplicates():

    print(city)
    df_city = df[df['city_name'] == city].set_index('stat_date').loc['2023-12'].sort_index()
    dict_big = {}
    dict_ok = {}
    resut_df = pd.DataFrame({})
    index_industry = []
    tq_list = []
    pred_list = []
    loss_list = []
    rate_list = []

    for industry in df_city.columns[2:]:
        # index_industry.append(industry)
        df_moving_avg = pd.DataFrame(df_city[industry], index=df_city.index)
        future = pd.date_range(start='2023-12-27', periods=5, freq='D')

        for date in future:
            df_moving_avg.loc[date, industry] = df_moving_avg[-3:].mean().values
        resut_df = pd.concat([resut_df, df_moving_avg], axis=1)
        print(city[4:6])
        print(resut_df)
        # loss = (df_city1[industry].tail(-3).sum() - df_moving_avg.tail(-3).sum()) / df_city1[industry].sum()
        # tq_list.append(df_city1[industry].sum())
        # pred_list.append(df_moving_avg[industry].sum())
        # loss_list.append(df_city1[industry].sum()-df_moving_avg[industry].sum())
        # rate_list.append((df_city1[industry].sum()-df_moving_avg[industry].sum())/df_city1[industry].sum())
    with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\行业电量预测_1228.xlsx', mode='a', if_sheet_exists='replace',
                        engine='openpyxl') as writer:
        resut_df.to_excel(writer, sheet_name=f'{city[4:6]}')

# resut_df = pd.DataFrame({'同期电量':tq_list,'预测电量':pred_list,'偏差':loss_list,'偏差率':rate_list},index=index_industry)
# print(resut_df)
# resut_df.to_excel(r'C:\Users\鸽子\Desktop\移动平均_丽水_行业.xlsx')

#     if loss.values >= 0.005:
#         dict_big[industry] = loss.values[0]
#     else:
#         dict_ok[industry] = loss.values[0]
# print(len(dict_ok))
# print(len(dict_big))