优化全量统计

This commit is contained in:
沈健
2025-04-08 18:03:24 +08:00
parent c1e55c08a4
commit f06263e434
@@ -22,20 +22,7 @@ if not os.path.exists(save_png_path):
nextcloud_aim_file_path = '财力评级/财力评级/财力评级统计报表'
def calculate_confidence(row):
"""计算置信度等级"""
diff = abs(row["consumption_rating"] - row["price_rating"])
if diff == 0:
return "高"
elif diff == 1:
return "中"
else:
return "低"
def stat(community_summary_df):
# 计算置信度
community_summary_df["置信度"] = community_summary_df.apply(calculate_confidence, axis=1)
grouped = community_summary_df.groupby(["city", "region"])
results = []
@@ -58,7 +45,7 @@ def stat(community_summary_df):
rating_6_scores = group[group["consumption_rating"] == 6]["consumption_score"]
# 计算置信度占比
confidence_counts = group["置信度"].value_counts(normalize=True)
confidence_counts = group["credit"].value_counts(normalize=True)
results.append({
"城市": city,
@@ -132,6 +119,7 @@ def detail(city):
"consumption_score",
"sub_factor.total_price_rating"
], index="community_summary")
# 减少重复查询
community_summary_df = data_utils.flatten_json(community_summary_df, 'sub_factor')
community_summary_df = data_utils.flatten_json(community_summary_df, 'credit_detail')
community_summary_df['diff'] = np.abs(community_summary_df['consumption_rating'] - community_summary_df['price_rating'])
@@ -139,6 +127,7 @@ def detail(city):
community_summary_df['estate_charge_type'] = np.where(community_summary_df['estate_charge_flag'] == 1,'周边','自有')
community_summary_df['credit'] = np.where(community_summary_df['total_price_diff'] == 0, '高', np.where(community_summary_df['total_price_diff'] == 1, '中', np.where(community_summary_df['total_price_diff'] >= 2, '低', '-')))
stat(community_summary_df)
community_summary_df = community_summary_df.rename(columns={'city': '城市', 'region': '区域', 'name': '小区名称', 'consumption_score': '财力分数', 'consumption_rating': '财力评级',
'total_price_rating': '户均总价评级', 'total_price_diff': '差值',
'total_price': '户均总价', 'avg_price': '小区均价', 'main_house_area': '典型面积', 'relative_price_ranking': '相对价格排名',
@@ -152,8 +141,7 @@ def detail(city):
community_summary_df.to_csv(save_png_path + '/' + aim_file, index=False, columns=["城市", "区域", "小区名称", "财力分数", "财力评级", "户均总价评级", "差值", "户均总价", "小区均价", "计算方式", "典型面积",
"获取方式", "相对价格排名", "人均消费", "物业费", "物业费获取方式", '置信度'])
nextcloudutils.up_to_nextcloud(save_png_path + "/" + aim_file, nextcloud_aim_file_path + "/" + aim_file)
# 减少重复查询
stat(community_summary_df)
dingutils.send_text("【统计】财力评级统计完毕,请点击 https://nextcloud.fangjia.com/s/nMbzk6ZKJDimapf 查看", "32400b949005817550937f82a82c064fe5be65c23204306442c15e8b485d7ef2")
@@ -163,5 +151,4 @@ if pd.notna(sys_city) and "," in sys_city:
for city in cities:
detail(city)
else:
stat(sys_city)
detail(sys_city)