优化保存图片,无需多次查库

This commit is contained in:
shenjian@fangjia.com
2022-11-22 17:56:32 +08:00
parent ac60fe8900
commit 9acba02dec
+11 -15
View File
@@ -10,7 +10,6 @@ from elasticsearch import helpers
import matplotlib.pyplot as plt
from sklearn.mixture import GaussianMixture
from concurrent.futures import ThreadPoolExecutor
log = logging.getLogger(__name__)
@@ -102,16 +101,15 @@ def calc_consumption_rating(community_summary_df):
"""
计算消费等级
"""
consumption_aim_df = community_summary_df[['_id', 'city', 'consumption_potential']]
consumption_aim_df = consumption_aim_df.dropna(subset=['consumption_potential'])
df = community_summary_df[['_id', 'city', 'consumption_potential']]
df = df.dropna(subset=['consumption_potential'])
source = "consumption_potential"
target = "consumption_rating"
actions = list()
count = 0
df = consumption_aim_df.copy()
if len(df) < 5:
return
return []
df = gmm_train(5, df, source, target)
# 批量更新
for index, item in df.iterrows():
@@ -138,6 +136,7 @@ def calc_consumption_rating(community_summary_df):
count += len(actions)
actions.clear()
log.info("评级完成,共更新: {}".format(count))
return df
def sync_by_city(city_now):
@@ -146,8 +145,11 @@ def sync_by_city(city_now):
if len(community_summary_df) == 0:
log.warning(f"{city_now}无法评级,缺少因子")
return
calc_consumption_rating(community_summary_df)
save_png(city_now)
community_summary_df = calc_consumption_rating(community_summary_df)
if len(community_summary_df) == 0:
log.warning(f"{city_now}无法评级,数量低于5")
return
save_png(community_summary_df)
nextcloudutils.up_to_nextcloud(save_png_path + "/" + city_now + ".png", nextcloud_aim_file_path + "/" + city_now + ".png")
@@ -183,16 +185,10 @@ def filter_min_max(city, community_summary_df):
return community_summary_df
def save_png(city):
def save_png(community_city):
"""
生成财力评级图表
"""
sql = "select id, city, region, name, total_price, estate_charge, avg_cost, relative_price_ranking, consumption_rating from community_summary where city='" + city + "'"
community_summary_df = es206_client.scan_by_sql_to_data_frame(sql)
community_summary_df['total_price'] = community_summary_df['total_price'] / 10000
community_city = filter_min_max(city, community_summary_df).copy()
plt.subplot(3, 1, 1)
community_city['consumption_rating'].hist(bins=100)
plt.xlabel('consumption_rating')
@@ -218,7 +214,7 @@ def save_png(city):
plt.xlabel('relative_price_ranking')
plt.tight_layout()
plt.savefig(save_png_path + "/" + city + ".png")
plt.savefig(save_png_path + "/" + community_city['city'].unique()[0] + ".png")
# 清图
plt.clf()
# 清坐标轴