修复重算BUG

This commit is contained in:
沈健
2025-06-16 13:32:02 +08:00
parent e60ec4dfaa
commit b6502d0051
2 changed files with 38 additions and 12 deletions
+20 -7
View File
@@ -52,10 +52,14 @@ def calcByOffice(city, district, office_name):
query['region'] = district
if pd.notna(city):
query['name'] = office_name
office = seaweed_df.find_one(query, {'city': 1, 'region': 1, 'name': 1, 'alias': 1, 'lng': 1, 'lat': 1, 'estate_type2': 1, 'bed_kind': 1})
office = seaweed_df.find_one(query, {'city': 1, 'region': 1, 'name': 1, 'alias': 1, 'lng': 1, 'lat': 1, 'estate_type2': 1, 'bed_kind': 1, '_id': 0})
if 'estate_type2' not in office:
office['estate_type2'] = None
if 'bed_kind' not in office:
office['bed_kind'] = None
names = list()
names.append(office['name'])
if type(office['alias']) == list:
if ('alias' in office) and (type(office['alias']) == list):
for alias_item in office['alias']:
names.append(alias_item)
names_str = "','".join(names)
@@ -80,7 +84,7 @@ def calcByOffice(city, district, office_name):
curr_sample = sample[(sample['p_date']>=int(str(curr_date)+'01')) & (sample['p_date']<=int(str(curr_date)+'31'))]
else:
curr_sample = pd.DataFrame(columns=['city', 'region', 'district_name', 'avg_price'])
update_office(city, pd.DataFrame(office), curr_sample, curr_date)
update_office(city, pd.DataFrame([office]), curr_sample, curr_date)
# 核查当月写字楼是否存在,不存在取最后6个月的平均值
office_db = office_rent_stat_conn.find_one({'cat': 'office', 'city': city, 'district': district, 'name': office_name, 'date': curr_date})
if pd.isna(office_db):
@@ -152,7 +156,13 @@ def calcByCity(city, year_month):
def update_office(city, office, sample, year_month):
if 'bed_kind' not in office.columns:
office['bed_kind'] = None
if 'estate_type2' not in office.columns:
office['estate_type2'] = None
sample_new = sample
if 'alias' not in sample_new.columns:
sample_new['alias'] = None
if len(sample_new) > 0:
sample_new['sample_avg_price'] = sample_new.groupby(by=['city', 'region', 'district_name'])['avg_price'].transform(
'median')
@@ -167,9 +177,12 @@ def update_office(city, office, sample, year_month):
# 使用主名与别名查找样本
merge_df1 = pd.merge(office, sample_new[['city', 'region', 'name', 'day_avg_price']], how='left',
on=['city', 'region', 'name'])
merge_df2 = pd.merge(office, sample_new[['city', 'region', 'alias', 'day_avg_price']], how='left',
on=['city', 'region', 'alias'])
merge_df = pd.concat([merge_df1, merge_df2])
if len(sample_new['alias'].unique()) > 0:
merge_df2 = pd.merge(office, sample_new[['city', 'region', 'alias', 'day_avg_price']], how='left',
on=['city', 'region', 'alias'])
merge_df = pd.concat([merge_df1, merge_df2])
else:
merge_df = merge_df1.copy()
merge_df = merge_df[merge_df['day_avg_price'].notna()]
merge_df = merge_df.drop_duplicates(subset=['city', 'region', 'name'], keep='first')
else:
@@ -458,4 +471,4 @@ def getOffice(city, district, name):
if __name__ == "__main__":
# 测试脚本:直接运行时模拟 Airflow 的上下文
calc(dag_run=type('DagRun', (), {'conf': {'city': '福州', 'district': '晋安', 'name': '筑源大厦'}}))
calc(dag_run=type('DagRun', (), {'conf': {'city': '北京', 'district': '朝阳', 'name': '中核华建大厦'}}))
+18 -5
View File
@@ -53,9 +53,13 @@ def calcByOffice(city, district, office_name):
if pd.notna(city):
query['name'] = office_name
office = seaweed_df.find_one(query, {'city': 1, 'region': 1, 'name': 1, 'alias': 1, 'lng': 1, 'lat': 1, 'estate_type2': 1, 'bed_kind': 1})
if 'estate_type2' not in office:
office['estate_type2'] = None
if 'bed_kind' not in office:
office['bed_kind'] = None
names = list()
names.append(office['name'])
if type(office['alias']) == list:
if ('alias' in office) and (type(office['alias']) == list):
for alias_item in office['alias']:
names.append(alias_item)
names_str = "','".join(names)
@@ -77,7 +81,7 @@ def calcByOffice(city, district, office_name):
curr_date = int(dateutils.format_date(date, fm='%Y%m'))
# 筛选出当前月的样本
curr_sample = sample[(sample['p_date']>=int(str(curr_date)+'01')) & (sample['p_date']<=int(str(curr_date)+'31'))]
update_office(city, pd.DataFrame(office), curr_sample, curr_date)
update_office(city, pd.DataFrame([office]), curr_sample, curr_date)
# 核查当月写字楼是否存在,不存在取最后6个月的平均值
office_db = office_sell_stat_conn.find_one({'cat': 'office', 'city': city, 'district': district, 'name': office_name, 'date': curr_date})
if pd.isna(office_db):
@@ -148,7 +152,13 @@ def calcByCity(city, year_month):
def update_office(city, office, sample, year_month):
if 'bed_kind' not in office.columns:
office['bed_kind'] = None
if 'estate_type2' not in office.columns:
office['estate_type2'] = None
sample_new = sample
if 'alias' not in sample_new.columns:
sample_new['alias'] = None
sample_new['sample_avg_price'] = sample_new.groupby(by=['city', 'region', 'district_name'])['avg_price'].transform(
'median')
sample_new['sample_count'] = sample_new.groupby(by=['city', 'region', 'district_name'])['avg_price'].transform(
@@ -162,9 +172,12 @@ def update_office(city, office, sample, year_month):
# 使用主名与别名查找样本
merge_df1 = pd.merge(office, sample_new[['city', 'region', 'name', 'day_avg_price']], how='left',
on=['city', 'region', 'name'])
merge_df2 = pd.merge(office, sample_new[['city', 'region', 'alias', 'day_avg_price']], how='left',
on=['city', 'region', 'alias'])
merge_df = pd.concat([merge_df1, merge_df2])
if len(sample_new['alias'].unique()) > 0:
merge_df2 = pd.merge(office, sample_new[['city', 'region', 'alias', 'day_avg_price']], how='left',
on=['city', 'region', 'alias'])
merge_df = pd.concat([merge_df1, merge_df2])
else:
merge_df = merge_df1.copy()
merge_df = merge_df[merge_df['day_avg_price'].notna()]
merge_df = merge_df.drop_duplicates(subset=['city', 'region', 'name'], keep='first')
# 第一步:计算有样本写字楼的基准价