This commit is contained in:
沈健
2025-06-10 14:04:11 +08:00
parent a09c8b2feb
commit 43e9b5af14
4 changed files with 234 additions and 117 deletions
+5 -4
View File
@@ -1,9 +1,10 @@
"""
写字楼基准价计算
"""
from airflow.operators.bash import BashOperator
from airflow.operators.bash import BashOperator, PythonOperator
import pendulum
from sell.base_price import calc
from airflow import DAG
@@ -14,9 +15,9 @@ with DAG(
catchup=True,
description="写字楼基准价计算"
) as dag:
t1 = BashOperator(
t1 = PythonOperator(
task_id='base_price',
bash_command='python /opt/airflow/dags/repo/dags/office/rent/base_price.py {{dag_run.conf["yearmonth"] if "yearmonth" in dag_run.conf}}',
python_callable=calc,
provide_context=True
)
t1
+202 -99
View File
@@ -10,7 +10,7 @@
#
# 第五步:本身没有等级和类型的写字楼
# 最近10个有样本写字楼的基准价的平均值
from goojia_utils import ElasticSearchClient, dateutils, MAIN_MONGO_CLIENT
from goojia_utils import ElasticSearchClient, dateutils, MAIN_MONGO_CLIENT, commutils
import pandas as pd
from datetime import datetime
from pymongo import UpdateOne
@@ -23,7 +23,103 @@ seaweed_df = MAIN_MONGO_CLIENT.get_collection('fangjia', 'seaweed')
office_rent_stat_conn = MAIN_MONGO_CLIENT.get_collection('fangjia_stat', 'office_rent_stat')
# 计算有样本写字楼的基准价 1. 取近一年,最近100个样本的中位值
def calc(city, year_month):
def calc(**kwargs):
"""
写字楼基准价
"""
# 从 Airflow 的 dag_run.conf 获取参数
conf = kwargs.get('dag_run').conf if kwargs.get('dag_run') else {}
city = conf.get('city', '')
year_month = conf.get('year_month', '')
district = conf.get('district', '')
office_name = conf.get('name', '')
if pd.isna(office_name):
calcByCity(city, year_month)
else:
# 直接重算出最近一年的数据,保证一年有数据
calcByOffice(city, district, office_name)
def calcByOffice(city, district, office_name):
"""
写字楼价格重算
"""
query = {'cat': 'office', 'status': 0}
if pd.notna(city):
query['city'] = city
if pd.notna(district):
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})
names = list()
names.append(office['name'])
if type(office['alias']) == list:
for alias_item in office['alias']:
names.append(alias_item)
names_str = "','".join(names)
names_str = "'" + names_str + "'"
# 只查询该小区的样本
year_time = dateutils.format_date(dateutils.datetime.datetime.now())
one_year_time = dateutils.format_date(dateutils.add_months(dateutils.datetime.datetime.now(), days=-365))
sql = f"select * from latest_seawater where cat='office_rent' and city='{city}' and region='{district}' and district_name in ({names_str}) and p_date > {one_year_time}"
sample = es.scan_by_sql_to_data_frame(sql)
location = {
"type": "Point",
"coordinates": [office['lng'] / math.pow(10, 10), office['lat'] / math.pow(10, 10)]
}
date_range = pd.date_range(start=one_year_time, end=year_time, freq='M')
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'))]
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):
avg_price_ret = office_rent_stat_conn.aggregate([
{
"$match": {
"cat": "office",
"city": city,
"district": district,
"name": office_name,
"date": { "$gte": curr_date - 3, "$lte": curr_date + 3 }
}
},
{
"$group": {
"_id": "$name",
"avg_price": { "$avg": "$avg_price" }
}
}
])
avg_prices = [doc["avg_price"] for doc in avg_price_ret]
# 计算平均值
average_price = np.mean(avg_prices) if len(avg_prices) > 0 else 0
if average_price > 0:
new_avg_price = average_price
else:
# 取样本的平均值
new_avg_price = sample['avg_price'].mean()
if pd.notna(new_avg_price):
action = UpdateOne(
{'cat': 'office', 'city': city, 'district': district, 'name': office_name, 'date': curr_date},
{'$set': {'city': city, 'cat': 'office', 'date': curr_date, 'district': district,
'name': office_name,
'avg_price': new_avg_price, 'estate_type2': office['estate_type2'],
'bed_kind': office['bed_kind'],
'location': location,
'calc_type': 5, 'updated_date': datetime.now()}},
upsert=True)
office_rent_stat_conn.bulk_write([action])
def calcByCity(city, year_month):
"""
写字楼基准价
"""
@@ -46,13 +142,12 @@ def calc(city, year_month):
print("开始计算年" + str(year_month) + "写字楼基准价")
sample = es.scan_by_sql_to_data_frame(sql)
query = {'cat': 'office', 'status': 0}
if pd.notna(city):
query['city'] = city
office = pd.DataFrame(list(seaweed_df.find(query).batch_size(10000)))
office = office[['city', 'region', 'name', 'alias', 'estate_type2', 'bed_kind', 'lng', 'lat']]
office = office.explode('alias')
office = getOffice(city)
update_office(city, office, sample, 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')
@@ -64,7 +159,6 @@ def calc(city, year_month):
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'])
@@ -88,7 +182,8 @@ def calc(city, year_month):
estate_type2 = item['estate_type2'] if pd.notna(item['estate_type2']) else None
bed_kind = item['bed_kind'] if pd.notna(item['bed_kind']) else None
action = UpdateOne({'cat': 'office', 'city': city, 'district': region, 'name': name, 'date': year_month},
{'$set': {'city': city, 'cat': 'office', 'date': year_month, 'district': region, 'name': name,
{'$set': {'city': city, 'cat': 'office', 'date': year_month, 'district': region,
'name': name,
'avg_price': avg_price, 'estate_type2': estate_type2, 'bed_kind': bed_kind,
'location': location,
'calc_type': 1, 'updated_date': datetime.now()}},
@@ -100,13 +195,14 @@ def calc(city, year_month):
if len(actions) > 0:
office_rent_stat_conn.bulk_write(actions)
actions.clear()
# 第二步 取周边3公里内同等级、同类型的最近10个有样本写字楼的基准价的平均值
office_info = office[['city', 'region', 'name', 'lng', 'lat', 'estate_type2', 'bed_kind']].drop_duplicates(keep='first')
office_info = office[['city', 'region', 'name', 'lng', 'lat', 'estate_type2', 'bed_kind']].drop_duplicates(
keep='first')
combined = pd.concat([office_info, merge_df])
diff_df = combined.drop_duplicates(subset=['city', 'region', 'name'], keep=False)
actions = list()
for index, item in diff_df[(diff_df['estate_type2'].notna()) & (diff_df['bed_kind'].notna()) & (diff_df['lng'].notna()) ].iterrows():
for index, item in diff_df[
(diff_df['estate_type2'].notna()) & (diff_df['bed_kind'].notna()) & (diff_df['lng'].notna())].iterrows():
location = {
"type": "Point",
"coordinates": [item['lng'] / math.pow(10, 10), item['lat'] / math.pow(10, 10)]
@@ -159,7 +255,6 @@ def calc(city, year_month):
if len(actions) > 0:
office_rent_stat_conn.bulk_write(actions)
actions.clear()
# 系数计算在Jupyter中
bed_kind_dict = {'甲级': 1.111888111888112, '丙级': 0.9143356643356645, '乙级': 1}
radio_dict = {'创业园区': 0.7799999999999999, '商住两用': 1.0466666666666666, '标准写字楼': 1}
@@ -210,13 +305,14 @@ def calc(city, year_month):
count += 1
if count > 0:
avg_price = round(sum_price / count, 2)
action = UpdateOne({'cat': 'office', 'city': city, 'district': region, 'name': name, 'date': year_month},
{'$set': {'city': city, 'cat': 'office', 'date': year_month, 'district': region,
'name': name,
'avg_price': avg_price, 'estate_type2': estate_type2, 'bed_kind': None,
'location': location,
'calc_type': 3, 'updated_date': datetime.now()}},
upsert=True)
action = UpdateOne(
{'cat': 'office', 'city': city, 'district': region, 'name': name, 'date': year_month},
{'$set': {'city': city, 'cat': 'office', 'date': year_month, 'district': region,
'name': name,
'avg_price': avg_price, 'estate_type2': estate_type2, 'bed_kind': None,
'location': location,
'calc_type': 3, 'updated_date': datetime.now()}},
upsert=True)
actions.append(action)
elif pd.notna(bed_kind):
ret = office_rent_stat_conn.aggregate([
@@ -249,13 +345,14 @@ def calc(city, year_month):
count += 1
if count > 0:
avg_price = round(sum_price / count, 2)
action = UpdateOne({'cat': 'office', 'city': city, 'district': region, 'name': name, 'date': year_month},
{'$set': {'city': city, 'cat': 'office', 'date': year_month, 'district': region,
'name': name,
'avg_price': avg_price, 'estate_type2': None, 'bed_kind': bed_kind,
'location': location,
'calc_type': 3, 'updated_date': datetime.now()}},
upsert=True)
action = UpdateOne(
{'cat': 'office', 'city': city, 'district': region, 'name': name, 'date': year_month},
{'$set': {'city': city, 'cat': 'office', 'date': year_month, 'district': region,
'name': name,
'avg_price': avg_price, 'estate_type2': None, 'bed_kind': bed_kind,
'location': location,
'calc_type': 3, 'updated_date': datetime.now()}},
upsert=True)
actions.append(action)
if len(actions) == 1000:
office_rent_stat_conn.bulk_write(actions)
@@ -273,79 +370,85 @@ def calc(city, year_month):
# 计算价格的写字楼
db_df = db_df.rename(columns={'district': 'region'})
# 使用 merge 操作并结合 indicator 参数
merged = office_info.merge(db_df[['city', 'region', 'name']], on=['city', 'region', 'name'], how='left',
indicator=True)
# 过滤出仅在 office_info 中存在的记录
diff_df = merged[merged['_merge'] == 'left_only'].drop(columns=['_merge'])
# 如果需要保持原始列顺序,可以重新排列列
diff_df = diff_df[office_info.columns]
actions.clear()
for index, item in diff_df.iterrows():
try:
location = {
"type": "Point",
"coordinates": [item['lng'] / math.pow(10, 10), item['lat'] / math.pow(10, 10)]
}
city = item['city']
region = item['region']
name = item['name']
estate_type2 = item['estate_type2'] if pd.notna(item['estate_type2']) else None
bed_kind = item['bed_kind']
ret = office_rent_stat_conn.aggregate([
{
'$geoNear': {
'near': location,
'distanceField': "distance",
'maxDistance': 3000,
'spherical': True
}
},
{
'$match': {
'date': year_month
}
},
{
'$limit': 5
if len(db_df) > 0:
merged = office_info.merge(db_df[['city', 'region', 'name']], on=['city', 'region', 'name'], how='left',
indicator=True)
# 过滤出仅在 office_info 中存在的记录
diff_df = merged[merged['_merge'] == 'left_only'].drop(columns=['_merge'])
# 如果需要保持原始列顺序,可以重新排列列
diff_df = diff_df[office_info.columns]
actions.clear()
for index, item in diff_df.iterrows():
try:
location = {
"type": "Point",
"coordinates": [item['lng'] / math.pow(10, 10), item['lat'] / math.pow(10, 10)]
}
]);
except Exception as e:
print("Error occurred:", str(e))
print(item)
# 提取 avg_price 的值
avg_prices = [doc["avg_price"] for doc in ret]
# 计算平均值
average_price = np.mean(avg_prices) if len(avg_prices) > 0 else 0
if average_price > 0:
avg_price = round(average_price, 2)
action = UpdateOne({'cat': 'office', 'city': city, 'district': region, 'name': name, 'date': year_month},
{'$set': {'city': city, 'cat': 'office', 'date': year_month, 'district': region,
'name': name,
'avg_price': avg_price, 'estate_type2': estate_type2, 'bed_kind': None,
'location': location,
'calc_type': 4, 'updated_date': datetime.now()}},
upsert=True)
actions.append(action)
if len(actions) == 1000:
office_rent_stat_conn.bulk_write(actions)
actions.clear()
city = item['city']
region = item['region']
name = item['name']
estate_type2 = item['estate_type2'] if pd.notna(item['estate_type2']) else None
bed_kind = item['bed_kind']
ret = office_rent_stat_conn.aggregate([
{
'$geoNear': {
'near': location,
'distanceField': "distance",
'maxDistance': 3000,
'spherical': True
}
},
{
'$match': {
'date': year_month
}
},
{
'$limit': 5
}
]);
except Exception as e:
print("Error occurred:", str(e))
print(item)
# 提取 avg_price 的值
avg_prices = [doc["avg_price"] for doc in ret]
# 计算平均值
average_price = np.mean(avg_prices) if len(avg_prices) > 0 else 0
if average_price > 0:
avg_price = round(average_price, 2)
action = UpdateOne({'cat': 'office', 'city': city, 'district': region, 'name': name, 'date': year_month},
{'$set': {'city': city, 'cat': 'office', 'date': year_month, 'district': region,
'name': name,
'avg_price': avg_price, 'estate_type2': estate_type2, 'bed_kind': None,
'location': location,
'calc_type': 4, 'updated_date': datetime.now()}},
upsert=True)
actions.append(action)
if len(actions) == 1000:
office_rent_stat_conn.bulk_write(actions)
actions.clear()
if len(actions) > 0:
office_rent_stat_conn.bulk_write(actions)
actions.clear()
yearmonth = sys.argv[1] if len(sys.argv) > 1 else None
# for yearmonth in [
# "202406",
# "202407",
# "202408",
# "202409",
# "202410",
# "202411",
# "202412",
# "202501"
# ]:
# calc(None, yearmonth)
calc(None, yearmonth)
def getOffice(city, district, name):
"""
获取写字楼
"""
query = {'cat': 'office', 'status': 0}
if pd.notna(city):
query['city'] = city
if pd.notna(district):
query['region'] = district
if pd.notna(city):
query['name'] = name
office = pd.DataFrame(list(seaweed_df.find(query).batch_size(10000)))
office = office[['city', 'region', 'name', 'alias', 'estate_type2', 'bed_kind', 'lng', 'lat']]
office = office.explode('alias')
return office
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'}}))
+16 -3
View File
@@ -23,10 +23,18 @@ seaweed_df = MAIN_MONGO_CLIENT.get_collection('fangjia', 'seaweed')
office_sell_stat_conn = MAIN_MONGO_CLIENT.get_collection('fangjia_stat', 'office_sell_stat')
# 计算有样本写字楼的基准价 1. 取近一年,最近100个样本的中位值
def calc(city, year_month):
def calc(**kwargs):
"""
写字楼基准价
"""
# 从 Airflow 的 dag_run.conf 获取参数
conf = kwargs.get('dag_run').conf if kwargs.get('dag_run') else {}
city = conf.get('city', '')
year_month = conf.get('year_month', '')
district = conf.get('district', '')
office_name = conf.get('name', '')
sql = "select * from latest_seawater where cat='office_sell' "
if pd.notna(city):
sql += "and city='" + city + "' "
@@ -49,6 +57,10 @@ def calc(city, year_month):
query = {'cat': 'office', 'status': 0}
if pd.notna(city):
query['city'] = city
if pd.notna(district):
query['region'] = district
if pd.notna(office_name):
query['name'] = office_name
office = pd.DataFrame(list(seaweed_df.find(query).batch_size(10000)))
office = office[['city', 'region', 'name', 'alias', 'estate_type2', 'bed_kind', 'lng', 'lat']]
office = office.explode('alias')
@@ -353,5 +365,6 @@ def calc(city, year_month):
print("已计算" + str(count) + "条数据")
actions.clear()
yearmonth = sys.argv[1] if len(sys.argv) > 1 else None
calc(None, yearmonth)
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'}}))
+11 -11
View File
@@ -83,16 +83,16 @@ def calc(city, year_month):
print("已处理{}条数据".format(count))
print("处理完毕")
if __name__ == '__main__':
yearmonth = sys.argv[1] if len(sys.argv) > 1 else ''
yearmonth = sys.argv[1] if len(sys.argv) > 1 else ''
if yearmonth == '':
date = dateutils.add_months(datetime.today(), months=-1)
yearmonth = int(dateutils.format_date(date, '%Y%m'))
try:
if type(yearmonth) is str:
yearmonth = int(yearmonth)
calc(None, yearmonth)
except Exception as e:
print(e)
if yearmonth == '':
date = dateutils.add_months(datetime.today(), months=-1)
yearmonth = int(dateutils.format_date(date, '%Y%m'))
try:
if type(yearmonth) is str:
yearmonth = int(yearmonth)
calc(None, yearmonth)
except Exception as e:
print(e)