|
|
|
@@ -0,0 +1,68 @@
|
|
|
|
|
"""
|
|
|
|
|
价格异常检测脚本
|
|
|
|
|
"""
|
|
|
|
|
from goojia_utils import dateutils, oracle
|
|
|
|
|
import pandas as pd
|
|
|
|
|
import logging
|
|
|
|
|
|
|
|
|
|
log = logging.getLogger(__name__)
|
|
|
|
|
|
|
|
|
|
month_now = dateutils.format_date(dateutils.add_months(dateutils.datetime.datetime.now()), '%Y%m')
|
|
|
|
|
month_last = dateutils.format_date(dateutils.add_months(dateutils.datetime.datetime.now(), months=-1), '%Y%m')
|
|
|
|
|
month_before = dateutils.format_date(dateutils.add_months(dateutils.datetime.datetime.now(), months=-2), '%Y%m')
|
|
|
|
|
|
|
|
|
|
df = oracle.scan_by_sql_to_data_frame("SELECT id, cityname, distname, commid, commname, calc_type, confidence, avg_price, year_month FROM community_base_price_gj WHERE year_month IN('"+month_now+"', '"+month_last+"') " +
|
|
|
|
|
" ORDER BY cityname, distname, commid, commname, year_month")
|
|
|
|
|
|
|
|
|
|
six_map = dict()
|
|
|
|
|
five_map = dict()
|
|
|
|
|
for index, item in df.iterrows():
|
|
|
|
|
year_month = item['year_month']
|
|
|
|
|
key = item['cityname'] + "," + item['distname'] + "," + item['commid'] + "," + item['commname']
|
|
|
|
|
if year_month == month_last:
|
|
|
|
|
five_map[key] = str(item['avg_price']) + "|" + str(item['calc_type']) + '|' + str(item['confidence'])
|
|
|
|
|
elif year_month == month_now:
|
|
|
|
|
six_map[key] = str(item['avg_price']) + "|" + str(item['calc_type']) + '|' + str(item['confidence'])
|
|
|
|
|
|
|
|
|
|
actions = list()
|
|
|
|
|
city_seaweed_dict = dict()
|
|
|
|
|
for key in six_map:
|
|
|
|
|
if key in five_map and key in six_map:
|
|
|
|
|
try:
|
|
|
|
|
five_price = float(five_map[key].split("|")[0])
|
|
|
|
|
six_price = float(six_map[key].split("|")[0])
|
|
|
|
|
if five_price and six_price:
|
|
|
|
|
info = key.split(",")
|
|
|
|
|
if abs(six_price - five_price) * 100 / five_price > 10:
|
|
|
|
|
actions.append({'city': info[0], 'region': info[1], 'commid': info[2], 'commname': info[3],
|
|
|
|
|
'five_price': five_price,'five_calc_type': five_map[key].split("|")[1],
|
|
|
|
|
'six_price': six_price,'six_calc_type': six_map[key].split("|")[1],
|
|
|
|
|
'涨跌幅': (six_price - five_price) * 100 / five_price, 'confidence': six_map[key].split("|")[2]})
|
|
|
|
|
if info[0] not in city_seaweed_dict:
|
|
|
|
|
city_seaweed_dict[info[0]] = 1
|
|
|
|
|
else:
|
|
|
|
|
city_seaweed_dict[info[0]] += 1
|
|
|
|
|
except Exception as e:
|
|
|
|
|
log.error(e)
|
|
|
|
|
log.error(five_map[key] + ' ' + six_map[key])
|
|
|
|
|
|
|
|
|
|
result_df = pd.DataFrame(actions)
|
|
|
|
|
result_df['confidence'] = result_df['confidence'].astype(float)
|
|
|
|
|
|
|
|
|
|
excel_writer = pd.ExcelWriter('data/'+ month_now +'VS'+ month_last +'月价格波动大于10%小区.xlsx')
|
|
|
|
|
|
|
|
|
|
result_df = result_df.drop_duplicates(subset=['commid'], keep='first')
|
|
|
|
|
result_df = result_df.rename(columns={'city': '城市', 'region': '区域', 'commid': '小区ID', 'commname': '小区名', 'five_price': '上一月价格',
|
|
|
|
|
'five_calc_type': '上一月计算方式', 'six_price': '当月价格', 'six_calc_type': '当月计算方式', 'confidence': '置信度'})
|
|
|
|
|
result_df.to_excel(excel_writer, index=False, sheet_name='价格差异小区')
|
|
|
|
|
|
|
|
|
|
log.info(len(result_df))
|
|
|
|
|
city_count_df = result_df.groupby(by=["城市"])['小区ID'].count().reset_index()
|
|
|
|
|
for index, item in city_count_df.iterrows():
|
|
|
|
|
city_count_df.loc[index, '占比'] = round(item['小区ID'] * 100 / city_seaweed_dict[item['城市']], 2)
|
|
|
|
|
city_count_df = city_count_df.rename(columns={'小区ID': '小区数量'})
|
|
|
|
|
city_count_df.to_excel(excel_writer, index=False, sheet_name='城市维度')
|
|
|
|
|
|
|
|
|
|
excel_writer.save()
|
|
|
|
|
excel_writer.close()
|
|
|
|
|
|