优化报错警告

This commit is contained in:
沈健
2025-04-14 13:47:06 +08:00
parent 3c77ac061c
commit c45f480a42
@@ -11,6 +11,7 @@ import os
from elasticsearch import helpers from elasticsearch import helpers
import matplotlib.pyplot as plt import matplotlib.pyplot as plt
import sys import sys
from scipy.stats import boxcox
from sklearn.preprocessing import RobustScaler from sklearn.preprocessing import RobustScaler
from sklearn.mixture import GaussianMixture from sklearn.mixture import GaussianMixture
@@ -91,7 +92,11 @@ def calc_consumption_potential(city):
max_estate_charge_fixed = community_summary_df['estate_charge_fixed'].max() max_estate_charge_fixed = community_summary_df['estate_charge_fixed'].max()
max_relative_price_ranking = community_summary_df['relative_price_ranking'].max() max_relative_price_ranking = community_summary_df['relative_price_ranking'].max()
community_summary_df['total_price_fixed'] = 1 - np.log(community_summary_df['total_price_fixed'] + 1) / np.log(max_total_price_fixed + 1) community_summary_df['total_price_fixed'] = 1 - np.log(community_summary_df['total_price_fixed'] + 1) / np.log(max_total_price_fixed + 1)
community_summary_df['avg_cost_fixed'] = 1 - np.log(community_summary_df['avg_cost_fixed'] + 1) / np.log(max_avg_cost_fixed + 1) # 人均消费极大值处理
community_summary_df['avg_cost_fixed'] = np.where(community_summary_df['avg_cost_fixed'] > 250, 250, community_summary_df['avg_cost_fixed'])
community_summary_df['avg_cost_fixed'] = np.log1p(community_summary_df['avg_cost_fixed'])
#community_summary_df['avg_cost_fixed'] = 1 - np.log(community_summary_df['avg_cost_fixed'] + 1) / np.log(max_avg_cost_fixed + 1)
community_summary_df['estate_charge_fixed'] = 1 - np.log(community_summary_df['estate_charge_fixed'] + 1) / np.log(max_estate_charge_fixed + 1) community_summary_df['estate_charge_fixed'] = 1 - np.log(community_summary_df['estate_charge_fixed'] + 1) / np.log(max_estate_charge_fixed + 1)
community_summary_df['relative_price_ranking'] = 1 - np.log(community_summary_df['relative_price_ranking'] + 1) / np.log(max_relative_price_ranking + 1) community_summary_df['relative_price_ranking'] = 1 - np.log(community_summary_df['relative_price_ranking'] + 1) / np.log(max_relative_price_ranking + 1)
@@ -148,6 +153,7 @@ def gmm_train(total_rate, consumption_df, source, target):
reg_covar=1e-6, # 正则化防止奇异矩阵 reg_covar=1e-6, # 正则化防止奇异矩阵
random_state=42 random_state=42
).fit(consumption_df[[source]]) ).fit(consumption_df[[source]])
consumption_df = consumption_df.copy()
consumption_df.loc[:, 'cluster'] = gmm.predict(consumption_df[[source]]) consumption_df.loc[:, 'cluster'] = gmm.predict(consumption_df[[source]])
consumption_df.loc[:, 'price_mean_cluster'] = consumption_df.groupby('cluster')[source].transform('mean') consumption_df.loc[:, 'price_mean_cluster'] = consumption_df.groupby('cluster')[source].transform('mean')
consumption_df.loc[:, target] = consumption_df['price_mean_cluster'].rank(method='dense', ascending=False).astype(int) consumption_df.loc[:, target] = consumption_df['price_mean_cluster'].rank(method='dense', ascending=False).astype(int)
@@ -182,7 +188,8 @@ def calc_consumption_rating(community_summary_df):
score_df = gmm_train(total_rate, df.dropna(subset=['total_price_score']), "total_price_score", "total_price_rating") score_df = gmm_train(total_rate, df.dropna(subset=['total_price_score']), "total_price_score", "total_price_rating")
score_df['robust_total_price_score'] = scaler.fit_transform(score_df[['total_price_score']]) score_df['robust_total_price_score'] = scaler.fit_transform(score_df[['total_price_score']])
score_df = min_max_scale(score_df, 'robust_total_price_score', 'total_price_score_minmax') score_df = min_max_scale(score_df, 'robust_total_price_score', 'total_price_score_minmax')
df = filter_min_max(df) df = df.copy()
df.loc[:, 'normal_consumption_potential'] = QuantileTransformer(output_distribution="normal").fit_transform(df[['consumption_potential']])
if len(df.dropna(subset=['consumption_potential'])) >= total_rate: if len(df.dropna(subset=['consumption_potential'])) >= total_rate:
df = gmm_train(total_rate, df.dropna(subset=['consumption_potential']), source, target) df = gmm_train(total_rate, df.dropna(subset=['consumption_potential']), source, target)
# 新增子因子评级 # 新增子因子评级
@@ -253,6 +260,9 @@ def calc_consumption_rating(community_summary_df):
count += len(actions) count += len(actions)
actions.clear() actions.clear()
log.info("评级完成,共更新: {}".format(count)) log.info("评级完成,共更新: {}".format(count))
#df['avg_cost_score_minmax'].hist(bins=100)
#df['consumption_score'].hist(bins=100)
#plt.show()
return pd.merge(community_summary_df, df, how='left', on=['_id', 'city', 'consumption_potential']) return pd.merge(community_summary_df, df, how='left', on=['_id', 'city', 'consumption_potential'])
@@ -313,12 +323,6 @@ def sync(city=None):
clear_rating(temp_df) clear_rating(temp_df)
sync_by_city(city) sync_by_city(city)
def filter_min_max(community_summary_df):
community_summary_df['normal_consumption_potential'] = QuantileTransformer(output_distribution="normal").fit_transform(community_summary_df[['consumption_potential']])
return community_summary_df
def save_png(community_city): def save_png(community_city):
""" """
生成财力评级图表 生成财力评级图表