针对财力潜力特征处理

This commit is contained in:
shenjian@fangjia.com
2022-12-14 16:16:55 +08:00
parent 504f4fb89c
commit c4ef8d0dce
+11 -14
View File
@@ -53,15 +53,13 @@ def calc_consumption_potential(city):
# 户均总价计算时候改成万
community_summary_df['total_price'] = round(community_summary_df['total_price'] / 10000, 0)
# 极值设置
community_summary_df = filter_min_max(city, community_summary_df).copy()
community_summary_df['total_price_mean'] = community_summary_df.groupby(by=['city'])['normal_total_price'].transform(
community_summary_df['total_price_mean'] = community_summary_df.groupby(by=['city'])['total_price'].transform(
np.mean)
community_summary_df['total_price_std'] = community_summary_df.groupby(by=['city'])['normal_total_price'].transform(np.std)
community_summary_df['total_price_std'] = community_summary_df.groupby(by=['city'])['total_price'].transform(np.std)
community_summary_df['estate_charge_mean'] = community_summary_df.groupby(by=['city'])['normal_estate_charge'].transform(
community_summary_df['estate_charge_mean'] = community_summary_df.groupby(by=['city'])['estate_charge'].transform(
np.mean)
community_summary_df['estate_charge_std'] = community_summary_df.groupby(by=['city'])['normal_estate_charge'].transform(
community_summary_df['estate_charge_std'] = community_summary_df.groupby(by=['city'])['estate_charge'].transform(
np.std)
community_summary_df['relative_price_ranking_mean'] = community_summary_df.groupby(by=['city'])[
@@ -69,8 +67,8 @@ def calc_consumption_potential(city):
community_summary_df['relative_price_ranking_std'] = community_summary_df.groupby(by=['city'])[
'relative_price_ranking'].transform(np.std)
community_summary_df['avg_cost_mean'] = community_summary_df.groupby(by=['city'])['normal_avg_cost'].transform(np.mean)
community_summary_df['avg_cost_std'] = community_summary_df.groupby(by=['city'])['normal_avg_cost'].transform(np.std)
community_summary_df['avg_cost_mean'] = community_summary_df.groupby(by=['city'])['avg_cost'].transform(np.mean)
community_summary_df['avg_cost_std'] = community_summary_df.groupby(by=['city'])['avg_cost'].transform(np.std)
community_summary_df['total_price_score'] = 286.0134196 * (
community_summary_df['total_price'] - community_summary_df['total_price_mean']) / community_summary_df[
@@ -107,7 +105,7 @@ def calc_consumption_rating(community_summary_df):
"""
df = community_summary_df[['_id', 'city', 'consumption_potential']]
df = df.dropna(subset=['consumption_potential'])
source = "consumption_potential"
source = "normal_consumption_potential"
target = "consumption_rating"
actions = list()
count = 0
@@ -116,6 +114,8 @@ def calc_consumption_rating(community_summary_df):
# 对于样本低于5的直接排名
df[target] = df['consumption_potential'].rank(method='dense', ascending=False).astype(int)
else:
# 极值设置
df = filter_min_max(df)
df = gmm_train(5, df, source, target)
# 批量更新
for index, item in df.iterrows():
@@ -167,11 +167,8 @@ def sync(city=None):
sync_by_city(city)
def filter_min_max(city, community_summary_df):
normal_df = pd.DataFrame(QuantileTransformer(output_distribution="normal").fit_transform(community_summary_df[['total_price', 'estate_charge', 'avg_cost']]), columns=['total_price', 'estate_charge', 'avg_cost'])
community_summary_df['normal_total_price'] = normal_df['total_price']
community_summary_df['normal_estate_charge'] = normal_df['estate_charge']
community_summary_df['normal_avg_cost'] = normal_df['avg_cost']
def filter_min_max(community_summary_df):
community_summary_df['normal_consumption_potential'] = QuantileTransformer(output_distribution="normal").fit_transform(community_summary_df[['consumption_potential']])
# total_price5 = np.percentile(a=community_summary_df['total_price'], q=2, axis=0)
# total_price95 = np.percentile(a=community_summary_df['total_price'], q=98, axis=0)
# community_summary_df.loc[community_summary_df['total_price'] > total_price95, 'total_price'] = total_price95