修复重算BUG

This commit is contained in:
沈健
2025-06-12 13:17:16 +08:00
parent 92ce23a11d
commit a6e60819ad
+27 -21
View File
@@ -76,7 +76,10 @@ def calcByOffice(city, district, office_name):
for date in date_range:
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'))]
if len(sample) > 0:
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)
# 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})
@@ -103,7 +106,7 @@ def calcByOffice(city, district, office_name):
average_price = np.mean(avg_prices) if len(avg_prices) > 0 else 0
if average_price > 0:
new_avg_price = round(average_price, 2)
else:
elif len(sample) > 0:
# 取样本的平均值
new_avg_price = round(sample['avg_price'].mean(), 2)
if pd.notna(new_avg_price):
@@ -149,24 +152,27 @@ def calcByCity(city, year_month):
def update_office(city, office, sample, year_month):
sample_new = sample
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(
'count')
sample_new = sample_new[sample_new['sample_count'] >= 5]
sample_new = sample_new[['city', 'region', 'district_name', 'sample_avg_price']].dropna()
sample_new['day_avg_price'] = sample_new['sample_avg_price'] / 30
sample_new = sample_new[['city', 'region', 'district_name', 'day_avg_price']]
sample_new = sample_new.rename(columns={'district_name': 'name'})
sample_new['alias'] = sample_new['name']
# 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])
merge_df = merge_df[merge_df['day_avg_price'].notna()]
merge_df = merge_df.drop_duplicates(subset=['city', 'region', 'name'], keep='first')
if len(sample_new) > 0:
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(
'count')
sample_new = sample_new[sample_new['sample_count'] >= 5]
sample_new = sample_new[['city', 'region', 'district_name', 'sample_avg_price']].dropna()
sample_new['day_avg_price'] = sample_new['sample_avg_price'] / 30
sample_new = sample_new[['city', 'region', 'district_name', 'day_avg_price']]
sample_new = sample_new.rename(columns={'district_name': 'name'})
sample_new['alias'] = sample_new['name']
# 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])
merge_df = merge_df[merge_df['day_avg_price'].notna()]
merge_df = merge_df.drop_duplicates(subset=['city', 'region', 'name'], keep='first')
else:
merge_df = pd.DataFrame()
# 第一步:计算有样本写字楼的基准价
print("有样本数量:" + str(len(merge_df)))
actions = list()
@@ -451,4 +457,4 @@ 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': '上海', 'district': '静安', 'name': '凯迪克大厦'}}))
calc(dag_run=type('DagRun', (), {'conf': {'city': '福州', 'district': '晋安', 'name': '筑源大厦'}}))