优化统计

This commit is contained in:
shenjian@fangjia.com
2023-02-27 10:30:08 +08:00
parent c27e358f3b
commit 37aa051bf9
+20 -34
View File
@@ -2,7 +2,7 @@
统计近三个月、近一年样本量及小区属性
"""
import logging
from goojia_utils import MAIN_MONGO_CLIENT, ElasticSearchClient, dateutils
from goojia_utils import MAIN_MONGO_CLIENT, ElasticSearchClient, dateutils, commutils
import pandas as pd
import datetime
import sys
@@ -24,37 +24,8 @@ seaweed_df = pd.DataFrame(list(seaweed_conn.find({'cat': 'district', 'status': 0
.batch_size(10000)))
seaweed_df = seaweed_df.rename(columns={'mapping_alias': 'alias'})
def sell_stat():
"""
最近一年有样本小区占比 最近3月有样本小区占比
"""
df = pd.read_excel(aim_file_name)
sell_seaweed_df = es206_client.scan_by_sql_to_data_frame(
"select city, region, district_name, p_date from latest_seawater where p_date > " + start_time + " and cat='sell' ")
# 小区别名升级为单独df
actions = list()
for index, item in seaweed_df.iterrows():
if type(item['alias']) == list:
for name in item['alias']:
actions.append({'_id': item['_id'], 'city': item['city'], 'name': name, 'region': item['region']})
alias_df = pd.DataFrame(actions)
sell_seaweed_rename_df = sell_seaweed_df[['city', 'region', 'district_name']]
sell_seaweed_rename_df = sell_seaweed_rename_df.rename(columns={'district_name': 'name'})
sell_seaweed_merge_df = pd.merge(sell_seaweed_rename_df, alias_df, how='left', on=['city', 'region', 'name'])
sell_seaweed_merge_df['count'] = sell_seaweed_merge_df[sell_seaweed_merge_df['_id'].notna()].groupby('_id')[
'_id'].transform('size')
sell_seaweed_merge_df = sell_seaweed_merge_df[['city', 'region', '_id', 'count']]
sell_seaweed_merge_df = sell_seaweed_merge_df.drop_duplicates(subset=['city', 'region', '_id'])
sell_seaweed_ok_df = sell_seaweed_merge_df[sell_seaweed_merge_df['count'] > sell_num]
sell_seaweed_ok_df['city_seaweed_count'] = sell_seaweed_ok_df.groupby('city')['city'].transform('size')
city_seaweed_count_df = sell_seaweed_ok_df[['city', 'city_seaweed_count']].drop_duplicates(
subset=['city', 'city_seaweed_count'])
city_seaweed_count_df = city_seaweed_count_df.rename(columns={'city': '城市', 'city_seaweed_count': '最近3月有样本小区占比'})
df = pd.merge(df, city_seaweed_count_df, how='left', on=['城市'])
df['最近3月有样本小区占比'] = round(df['最近3月有样本小区占比'] * 100 / df['小区量'], 2)
df.to_excel(aim_file_name, index=False)
def get_sell(df, daysBefore=365):
cities = df[['城市']].drop_duplicates(keep='first')['城市'].values.tolist()
city_one_year_count = list()
for city in cities:
@@ -79,8 +50,7 @@ def sell_stat():
names_str = "','".join(names)
names_str = "'" + names_str + "'"
try:
sql = "select count(*) from latest_seawater where city='" + city + "' and region='" + region + "' and cat='sell' and district_name in(" + names_str + ") and p_date > " + one_year_time
num = es206_client.search_by_sql(sql)['hits']['total']['value']
num = commutils.get_sample(city, region, names_str, daysBefore=daysBefore)
if num > sell_num:
count += 1
total_num += num
@@ -92,9 +62,25 @@ def sell_stat():
print(city + "已处理完, 近一年有样本小区数量" + str(count) + " 近一年的样本总量" + str(total_num))
result_df = pd.DataFrame(city_one_year_count)
return result_df
def sell_stat():
"""
最近一年有样本小区占比 最近3月有样本小区占比
"""
df = pd.read_excel(aim_file_name)
result_df = get_sell(df, 365)
result_df = result_df[['城市', '近一年有样本小区数量', '近一年的样本总量']]
df = pd.merge(df, result_df, how='left', on=['城市'])
df['最近一年有样本小区占比'] = round(df['近一年有样本小区数量'] * 100 / df['小区量'], 2)
df['近一年有样本小区占比'] = round(df['近一年有样本小区数量'] * 100 / df['小区量'], 2)
result_df = get_sell(df, 93)
result_df = result_df.rename(columns={'近一年有样本小区数量': '近三月有样本小区数量'})
result_df = result_df[['城市', '近三月有样本小区数量']]
df = pd.merge(df, result_df, how='left', on=['城市'])
df['近三月有样本小区占比'] = round(df['近三月有样本小区数量'] * 100 / df['小区量'], 2)
df.to_excel(aim_file_name, index=False)