483 lines
22 KiB
Python
483 lines
22 KiB
Python
"""
|
|
写字楼基准价
|
|
"""
|
|
import math
|
|
from datetime import datetime
|
|
|
|
import numpy as np
|
|
import pandas as pd
|
|
# 第一步:计算有样本写字楼的基准价
|
|
# 取近一年,最近100个样本的中位值
|
|
# 第二步:计算无样本写字楼的基准价
|
|
# 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
|
|
# 第三步:根据第一步和第二步有写字楼等级和写字楼类型的写字楼基准化计算出写字楼等级和类型对基准价影响的系数
|
|
# 第四步:根据写字楼等级系数和类型系数计算出没有相同特征写字楼的基准化
|
|
#
|
|
# 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 pymongo import UpdateOne
|
|
|
|
es = ElasticSearchClient(host='192.168.0.206')
|
|
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(**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', None)
|
|
year_month = conf.get('yearmonth', None)
|
|
district = conf.get('district', None)
|
|
office_name = conf.get('name', None)
|
|
if year_month is None:
|
|
year_month = dateutils.format_date(dateutils.add_months(datetime.today(), months=-1), "%Y%m")
|
|
|
|
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
|
|
print(query)
|
|
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 ('alias' in office) and (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_sell' 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)]
|
|
}
|
|
if "p_date" not in sample.columns:
|
|
sample['p_date'] = None
|
|
|
|
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_sell_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_sell_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": "$avg_price" }
|
|
}
|
|
}
|
|
])
|
|
avg_prices = [doc["avg_price"] for doc in avg_price_ret]
|
|
# 计算平均值
|
|
average_price = np.mean(avg_prices) if len(avg_prices) > 0 else 0
|
|
new_avg_price = None
|
|
if average_price > 0:
|
|
new_avg_price = int(average_price)
|
|
elif "avg_price" in sample.columns:
|
|
# 取样本的平均值
|
|
new_avg_price = int(sample['avg_price'].mean())
|
|
if pd.notna(new_avg_price):
|
|
action = UpdateOne(
|
|
{'cat': 'office', 'city': city, 'district': district, 'name': office_name, 'date': curr_date},
|
|
{'$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_sell_stat_conn.bulk_write([action])
|
|
|
|
|
|
def calcByCity(city, year_month):
|
|
"""
|
|
写字楼基准价
|
|
"""
|
|
sql = "select * from latest_seawater where cat='office_sell' "
|
|
if pd.notna(city) and city != "":
|
|
sql += "and city='" + city + "' "
|
|
if pd.notna(year_month):
|
|
last_year_month = dateutils.format_date(
|
|
dateutils.add_months(dateutils.parse_date(str(year_month), '%Y%m'), months=-13), '%Y%m')
|
|
last_month = dateutils.format_date(dateutils.add_months(dateutils.parse_date(str(year_month), '%Y%m'), months=-1), '%Y%m')
|
|
sql += "and p_date >= '" + last_year_month + "01' "
|
|
if isinstance(year_month, str):
|
|
year_month = int(year_month)
|
|
else:
|
|
last_year_month = dateutils.format_date(dateutils.add_months(datetime.now(), months=-13), '%Y%m')
|
|
last_month = dateutils.format_date(dateutils.add_months(datetime.now(), months=-1), '%Y%m')
|
|
sql += "and p_date >= '" + last_year_month + "01' "
|
|
date = dateutils.add_months(datetime.today(), months=-1)
|
|
year_month = int(dateutils.format_date(date, '%Y%m'))
|
|
print("开始计算年" + str(year_month) + "写字楼基准价")
|
|
|
|
sample = es.scan_by_sql_to_data_frame(sql)
|
|
print("样本SQL:" + sql + "样本量:" +str(len(sample)))
|
|
office = getOffice(city)
|
|
|
|
update_office(city, office, sample, 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
|
|
if 'alias' not in office.columns:
|
|
office['alias'] = None
|
|
merge_df = None
|
|
if not sample.empty:
|
|
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(
|
|
'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']
|
|
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'])
|
|
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
|
|
print("有样本数量:" + str(len(merge_df)))
|
|
actions = list()
|
|
for index, item in merge_df.iterrows():
|
|
city = item['city']
|
|
region = item['region']
|
|
name = item['name']
|
|
avg_price = int(item['day_avg_price'])
|
|
location = {
|
|
"type": "Point",
|
|
"coordinates": [item['lng'] / math.pow(10, 10), item['lat'] / math.pow(10, 10)]
|
|
}
|
|
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},
|
|
{'$set': {'city': city, 'cat': 'office', 'date': year_month, 'district': region,
|
|
'name': name,
|
|
'avg_price': avg_price, 'estate_type2': estate_type2, 'bed_kind': bed_kind,
|
|
'location': location,
|
|
'calc_type': 1, 'updated_date': datetime.now()}},
|
|
upsert=True)
|
|
actions.append(action)
|
|
if len(actions) == 1000:
|
|
office_sell_stat_conn.bulk_write(actions)
|
|
actions.clear()
|
|
if len(actions) > 0:
|
|
office_sell_stat_conn.bulk_write(actions)
|
|
actions.clear()
|
|
# 第二步 取周边3公里内同等级、同类型的最近10个有样本写字楼的基准价的平均值
|
|
office_info = office[['city', 'region', 'name', 'lng', 'lat', 'estate_type2', 'bed_kind']].drop_duplicates(
|
|
keep='first')
|
|
combined = office_info
|
|
if merge_df is not None and not merge_df.empty:
|
|
combined = pd.concat([office_info, merge_df])
|
|
diff_df = combined.drop_duplicates(subset=['city', 'region', 'name'], keep=False)
|
|
actions = list()
|
|
for index, item in diff_df[
|
|
(diff_df['estate_type2'].notna()) & (diff_df['bed_kind'].notna()) & (diff_df['lng'].notna())].iterrows():
|
|
location = {
|
|
"type": "Point",
|
|
"coordinates": [item['lng'] / math.pow(10, 10), item['lat'] / math.pow(10, 10)]
|
|
}
|
|
city = item['city']
|
|
region = item['region']
|
|
name = item['name']
|
|
estate_type2 = item['estate_type2']
|
|
bed_kind = item['bed_kind']
|
|
if estate_type2 == '' or bed_kind == '':
|
|
continue
|
|
ret = office_sell_stat_conn.aggregate([
|
|
{
|
|
'$geoNear': {
|
|
'near': location,
|
|
'distanceField': "distance",
|
|
'maxDistance': 3000,
|
|
'spherical': True
|
|
}
|
|
},
|
|
{
|
|
'$match': {
|
|
'estate_type2': estate_type2,
|
|
'bed_kind': bed_kind,
|
|
'calc_type': 1,
|
|
'date': year_month
|
|
}
|
|
},
|
|
{
|
|
'$limit': 5
|
|
}
|
|
]);
|
|
# 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 = int(average_price)
|
|
action = UpdateOne({'cat': 'office', 'city': city, 'district': region, 'name': name, 'date': year_month},
|
|
{'$set': {'city': city, 'cat': 'office', 'date': year_month, 'district': region,
|
|
'name': name,
|
|
'avg_price': avg_price, 'estate_type2': estate_type2, 'bed_kind': bed_kind,
|
|
'location': location,
|
|
'calc_type': 2, 'updated_date': datetime.now()}},
|
|
upsert=True)
|
|
actions.append(action)
|
|
if len(actions) == 1000:
|
|
office_sell_stat_conn.bulk_write(actions)
|
|
actions.clear()
|
|
if len(actions) > 0:
|
|
office_sell_stat_conn.bulk_write(actions)
|
|
actions.clear()
|
|
# 系数计算在Jupyter中
|
|
bed_kind_dict = {'甲级': 1.111888111888112, '丙级': 0.9143356643356645, '乙级': 1}
|
|
radio_dict = {'创业园区': 0.7799999999999999, '商住两用': 1.0466666666666666, '标准写字楼': 1}
|
|
# 根据写字楼等级系数和类型系数计算出没有相同特征写字楼的基准化
|
|
actions.clear()
|
|
for index, item in diff_df[(diff_df['estate_type2'].notna()) | (diff_df['bed_kind'].notna())].iterrows():
|
|
location = {
|
|
"type": "Point",
|
|
"coordinates": [item['lng'] / math.pow(10, 10), item['lat'] / math.pow(10, 10)]
|
|
}
|
|
city = item['city']
|
|
region = item['region']
|
|
name = item['name']
|
|
estate_type2 = item['estate_type2']
|
|
bed_kind = item['bed_kind']
|
|
if estate_type2 == '' or bed_kind == '':
|
|
continue
|
|
if pd.notna(estate_type2) and pd.notna(bed_kind):
|
|
continue
|
|
if pd.notna(estate_type2):
|
|
ret = office_sell_stat_conn.aggregate([
|
|
{
|
|
'$geoNear': {
|
|
'near': location,
|
|
'distanceField': "distance",
|
|
'maxDistance': 3000,
|
|
'spherical': True
|
|
}
|
|
},
|
|
{
|
|
'$match': {
|
|
'estate_type2': estate_type2,
|
|
'date': year_month
|
|
}
|
|
},
|
|
{
|
|
'$limit': 5
|
|
}
|
|
]);
|
|
# 提取 avg_price 的值
|
|
count = 0
|
|
sum_price = 0
|
|
if estate_type2 in radio_dict.keys():
|
|
for doc in ret:
|
|
if doc['estate_type2'] in radio_dict.keys():
|
|
new_price = doc['avg_price'] / radio_dict[doc['estate_type2']] * radio_dict[estate_type2]
|
|
sum_price += new_price
|
|
count += 1
|
|
if count > 0:
|
|
avg_price = int(sum_price / count)
|
|
action = UpdateOne(
|
|
{'cat': 'office', 'city': city, 'district': region, 'name': name, 'date': year_month},
|
|
{'$set': {'city': city, 'cat': 'office', 'date': year_month, 'district': region,
|
|
'name': name,
|
|
'avg_price': avg_price, 'estate_type2': estate_type2, 'bed_kind': None,
|
|
'location': location,
|
|
'calc_type': 3, 'updated_date': datetime.now()}},
|
|
upsert=True)
|
|
actions.append(action)
|
|
elif pd.notna(bed_kind):
|
|
ret = office_sell_stat_conn.aggregate([
|
|
{
|
|
'$geoNear': {
|
|
'near': location,
|
|
'distanceField': "distance",
|
|
'maxDistance': 3000,
|
|
'spherical': True
|
|
}
|
|
},
|
|
{
|
|
'$match': {
|
|
'bed_kind': bed_kind,
|
|
'date': year_month
|
|
}
|
|
},
|
|
{
|
|
'$limit': 5
|
|
}
|
|
]);
|
|
# 提取 avg_price 的值
|
|
count = 0
|
|
sum_price = 0
|
|
if bed_kind in bed_kind_dict.keys():
|
|
for doc in ret:
|
|
if doc['bed_kind'] in bed_kind_dict.keys():
|
|
new_price = doc['avg_price'] / bed_kind_dict[doc['bed_kind']] * bed_kind_dict[bed_kind]
|
|
sum_price += new_price
|
|
count += 1
|
|
if count > 0:
|
|
avg_price = int(sum_price / count)
|
|
action = UpdateOne(
|
|
{'cat': 'office', 'city': city, 'district': region, 'name': name, 'date': year_month},
|
|
{'$set': {'city': city, 'cat': 'office', 'date': year_month, 'district': region,
|
|
'name': name,
|
|
'avg_price': avg_price, 'estate_type2': None, 'bed_kind': bed_kind,
|
|
'location': location,
|
|
'calc_type': 3, 'updated_date': datetime.now()}},
|
|
upsert=True)
|
|
actions.append(action)
|
|
if len(actions) == 1000:
|
|
office_sell_stat_conn.bulk_write(actions)
|
|
actions.clear()
|
|
if len(actions) > 0:
|
|
office_sell_stat_conn.bulk_write(actions)
|
|
actions.clear()
|
|
# 第五步
|
|
query = {'cat': 'office', 'date': year_month, 'calc_type': {'$in': [1, 2, 3]}}
|
|
if pd.notna(city):
|
|
query['city'] = city
|
|
db_df = pd.DataFrame(list(office_sell_stat_conn.find(query)))
|
|
office_info = office[['city', 'region', 'name', 'lng', 'lat', 'estate_type2', 'bed_kind']].drop_duplicates(
|
|
keep='first')
|
|
# 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
|
|
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)]
|
|
}
|
|
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_sell_stat_conn.aggregate([
|
|
{
|
|
'$geoNear': {
|
|
'near': location,
|
|
'distanceField': "distance",
|
|
'maxDistance': 3000,
|
|
'spherical': True
|
|
}
|
|
},
|
|
{
|
|
'$match': {
|
|
'date': year_month
|
|
}
|
|
},
|
|
{
|
|
'$limit': 5
|
|
}
|
|
]);
|
|
except Exception as e:
|
|
print("Error occurred:", str(e))
|
|
print(item)
|
|
# 提取 avg_price 的值
|
|
avg_prices = [doc["avg_price"] for doc in ret]
|
|
# 计算平均值
|
|
average_price = np.mean(avg_prices) if len(avg_prices) > 0 else 0
|
|
if average_price > 0:
|
|
avg_price = int(average_price)
|
|
action = UpdateOne({'cat': 'office', 'city': city, 'district': region, 'name': name, 'date': year_month},
|
|
{'$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_sell_stat_conn.bulk_write(actions)
|
|
actions.clear()
|
|
if len(actions) > 0:
|
|
office_sell_stat_conn.bulk_write(actions)
|
|
actions.clear()
|
|
|
|
|
|
def getOffice(city, district=None, name=None):
|
|
"""
|
|
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(name):
|
|
query['name'] = name
|
|
office = pd.DataFrame(list(seaweed_df.find(query).batch_size(10000)))
|
|
for col in ['city', 'region', 'name', 'alias', 'estate_type2', 'bed_kind', 'lng', 'lat']:
|
|
if col not in office:
|
|
office[col] = None
|
|
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': '西安'}})) |