You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

68 lines
2.3 KiB
Python

import pandas as pd
import os
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)]
fir_dir = './浙江各地市分电压日电量数据'
qw_dir = 'C:\python-project\p1031\入模数据'
result = pd.DataFrame({})
for excel,qw_excel in zip(os.listdir(fir_dir),os.listdir(qw_dir)):
df_city = pd.read_excel(os.path.join(fir_dir,excel))
df_city = df_city[['stat_date','0.4kv及以下']]
df_city['0.4kv及以下'] = df_city['0.4kv及以下']/10000
df_city = df_city.loc[normal(df_city['0.4kv及以下']).index]
df_city['stat_date'] = df_city['stat_date'].map(lambda x:x.strip())
df_city['stat_date'] = pd.to_datetime(df_city['stat_date'])
df_qw = pd.read_excel(os.path.join(qw_dir,qw_excel))
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_city,df_qw,left_on='stat_date',right_on='dtdate',how='left')
df.drop(columns='dtdate',inplace=True)
df.set_index('stat_date',inplace=True)
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)
def season(x):
if str(x)[5:7] in list0:
return 0
elif str(x)[5:7] in list1:
return 1
else:
return 2
print(f'{excel[:2]}',list0)
df['season'] = df.index.map(season)
df.to_excel(f'./400v入模数据/{excel[:2]}.xlsx')
# dict1 = {'杭州':0,'湖州':1,'嘉兴':2,'金华':3,'丽水':4,'宁波':5,'衢州':6,'绍兴':7,'台州':8,'温州':9,'舟山':10}
# df['city'] = dict1[excel[:2]]
# df.reset_index(inplace=True)
# result = pd.concat([result,df])