优化分数
This commit is contained in:
@@ -87,22 +87,31 @@ def calc_consumption_potential(city):
|
||||
# community_summary_df['estate_charge_fixed'] = QuantileTransformer(output_distribution="normal").fit_transform(
|
||||
# community_summary_df[['estate_charge_fix']])
|
||||
# 异常值处理
|
||||
total_price_fixed_threshold = community_summary_df['total_price_fixed'].quantile(0.99)
|
||||
community_summary_df['total_price_fixed'] = np.where(community_summary_df['total_price_fixed'] > total_price_fixed_threshold, total_price_fixed_threshold, community_summary_df['total_price_fixed'])
|
||||
max_total_price_fixed = community_summary_df['total_price_fixed'].max()
|
||||
max_avg_cost_fixed = community_summary_df['avg_cost_fixed'].max()
|
||||
max_estate_charge_fixed = community_summary_df['estate_charge_fixed'].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)
|
||||
# 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['total_price_fixed'] = np.log(community_summary_df['total_price_fixed'] + 1) / np.log(max_total_price_fixed + 1)
|
||||
|
||||
# 人均消费极大值处理
|
||||
avg_cost_fixed_threshold = community_summary_df['avg_cost_fixed'].quantile(0.99)
|
||||
community_summary_df['avg_cost_fixed'] = np.where(community_summary_df['avg_cost_fixed'] > avg_cost_fixed_threshold, avg_cost_fixed_threshold, community_summary_df['avg_cost_fixed'])
|
||||
max_avg_cost_fixed = community_summary_df['avg_cost_fixed'].max()
|
||||
try:
|
||||
community_summary_df['avg_cost_fixed'] = np.log1p(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'] = np.log(community_summary_df['avg_cost_fixed'] + 1) / np.log(max_avg_cost_fixed + 1)
|
||||
except Exception:
|
||||
community_summary_df['avg_cost_fixed'] = None
|
||||
pass
|
||||
#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['relative_price_ranking'] = 1 - np.log(community_summary_df['relative_price_ranking'] + 1) / np.log(max_relative_price_ranking + 1)
|
||||
estate_charge_fixed_threshold = community_summary_df['estate_charge_fixed'].quantile(0.99)
|
||||
community_summary_df['estate_charge_fixed'] = np.where(community_summary_df['estate_charge_fixed'] > estate_charge_fixed_threshold, estate_charge_fixed_threshold, community_summary_df['estate_charge_fixed'])
|
||||
max_estate_charge_fixed = community_summary_df['estate_charge_fixed'].max()
|
||||
community_summary_df['estate_charge_fixed'] = np.log(community_summary_df['estate_charge_fixed'] + 1) / np.log(max_estate_charge_fixed + 1)
|
||||
|
||||
#relative_price_ranking_threshold = community_summary_df['relative_price_ranking'].quantile(0.99)
|
||||
#community_summary_df['relative_price_ranking'] = np.where(community_summary_df['relative_price_ranking'] > relative_price_ranking_threshold, relative_price_ranking_threshold, community_summary_df['relative_price_ranking'])
|
||||
max_relative_price_ranking_fixed = community_summary_df['relative_price_ranking'].max()
|
||||
community_summary_df['relative_price_ranking'] = np.log(community_summary_df['relative_price_ranking'] + 1) / np.log(max_relative_price_ranking_fixed + 1)
|
||||
|
||||
community_summary_df['estate_charge_mean'] = community_summary_df.groupby(by=['city'])['estate_charge_fixed'].transform(
|
||||
np.mean)
|
||||
@@ -197,6 +206,9 @@ def calc_consumption_rating(community_summary_df):
|
||||
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')
|
||||
df = df.copy()
|
||||
df_threshold = community_summary_df['consumption_potential'].quantile(0.99)
|
||||
community_summary_df['consumption_potential'] = np.where(community_summary_df['consumption_potential'] > df_threshold, df_threshold, community_summary_df['consumption_potential'])
|
||||
|
||||
df.loc[:, 'normal_consumption_potential'] = QuantileTransformer(output_distribution="normal").fit_transform(df[['consumption_potential']])
|
||||
if len(df.dropna(subset=['consumption_potential'])) >= total_rate:
|
||||
df = gmm_train(total_rate, df.dropna(subset=['consumption_potential']), source, target)
|
||||
@@ -268,9 +280,6 @@ def calc_consumption_rating(community_summary_df):
|
||||
count += len(actions)
|
||||
actions.clear()
|
||||
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'])
|
||||
|
||||
|
||||
@@ -284,6 +293,7 @@ def sync_by_city(city_now):
|
||||
if len(community_summary_df) == 0:
|
||||
log.warning(f"{city_now}无法评级,数量低于5")
|
||||
return
|
||||
#plot_img(community_summary_df)
|
||||
save_png(community_summary_df)
|
||||
nextcloudutils.up_to_nextcloud(save_png_path + "/" + city_now + ".png", nextcloud_aim_file_path + "/" + city_now + ".png")
|
||||
|
||||
@@ -378,6 +388,42 @@ def save_png(community_city):
|
||||
plt.close()
|
||||
|
||||
|
||||
def plot_img(community_city):
|
||||
"""
|
||||
生成财力评级图表
|
||||
"""
|
||||
curr_city = community_city['city'].unique()[0]
|
||||
# 解决中文显示问题
|
||||
plt.rcParams['font.sans-serif'] = ['SimHei']
|
||||
plt.rcParams['axes.unicode_minus'] = False
|
||||
plt.title(curr_city)
|
||||
plt.subplot(3, 1, 1)
|
||||
community_city['consumption_score'].hist(bins=100)
|
||||
plt.xlabel('consumption_rating')
|
||||
plt.tight_layout()
|
||||
|
||||
plt.subplot(3, 2, 3)
|
||||
community_city['total_price_score_minmax'].hist(bins=100)
|
||||
plt.xlabel('total_price')
|
||||
plt.tight_layout()
|
||||
|
||||
plt.subplot(3, 2, 4)
|
||||
community_city['estate_charge_score_minmax'].hist(bins=100)
|
||||
plt.xlabel('estate_charge')
|
||||
plt.tight_layout()
|
||||
|
||||
plt.subplot(3, 2, 5)
|
||||
community_city['avg_cost_score_minmax'].hist(bins=100)
|
||||
plt.xlabel('avg_cost')
|
||||
plt.tight_layout()
|
||||
|
||||
plt.subplot(3, 2, 6)
|
||||
community_city['relative_price_ranking_score_minmax'].hist(bins=100)
|
||||
plt.xlabel('relative_price_ranking')
|
||||
plt.tight_layout()
|
||||
# 关窗口
|
||||
plt.show()
|
||||
|
||||
sys_city = sys.argv[1] if len(sys.argv) > 1 else None
|
||||
if pd.notna(sys_city) and "," in sys_city:
|
||||
cities = sys_city.split(",")
|
||||
|
||||
Reference in New Issue
Block a user