add feature

feature.py

@@ -61,6 +61,9 @@ user_sparse_conf = [
 'ctx_region',
 'ctx_city',
 # 统计特征_用户
+'u_cycle_bucket_7days',
+'u_cycle_bucket_30days',
+'u_share_bucket_30days',
 'u_1day_exp_cnt',
 'u_1day_click_cnt',
 'u_1day_share_cnt',
@@ -135,7 +138,8 @@ label_col = 'ui_is_out'
 sparse_fea_cols = [
 # 'u_id',
 # 基础特征_场景
-#'ctx_day',
+#'ctx_day','
+'ctx_apptype',
 'ctx_week',
 'ctx_hour',
 # 基础特征_交叉

get_ad_out_sample_v2_item.py

@@ -44,6 +44,7 @@ mid AS u_id
 ,ceil(log2(total_time + 1)) as i_play_len
 ,ceil(log2(i_days_since_upload + 1)) as i_days_since_upload -- 发布时间（距离现在天数）
 -- 基础特征_场景
+,apptype AS ctx_apptype
 ,ctx_day AS ctx_day
 ,ctx_week AS ctx_week
 ,ctx_hour AS ctx_hour
@@ -56,6 +57,9 @@ mid AS u_id
 ,rootmid AS ui_root_id
 ,shareid AS ui_share_id
 -- 统计特征_用户
+,u_cycle_bucket_7days
+,u_cycle_bucket_30days
+,u_share_bucket_30days
 ,ceil(log2(u_1day_exp_cnt + 1)) as u_1day_exp_cnt
 ,ceil(log2(u_1day_click_cnt + 1)) as u_1day_click_cnt
 ,ceil(log2(u_1day_share_cnt + 1)) as u_1day_share_cnt
@@ -129,6 +133,15 @@ and apptype != '13'
 ), candidate_user as (
     SELECT 
     u_id,
+    max(u_brand) as u_brand,
+    max(u_device) as u_device,
+    max(u_system) as u_system,
+    max(u_system_ver) as u_system_ver,
+    max(ctx_region) as ctx_region,
+    max(ctx_city) as ctx_city,
+    max(u_cycle_bucket_7days) as u_cycle_bucket_7days,
+    max(u_cycle_bucket_30days) as u_cycle_bucket_30days,
+    max(u_share_bucket_30days) as u_share_bucket_30days,
     max(u_1day_exp_cnt) as u_1day_exp_cnt,
     max(u_1day_click_cnt) as u_1day_click_cnt,
     max(u_1day_share_cnt) as u_1day_share_cnt,

get_ad_out_sample_v2_user.py

@@ -43,6 +43,7 @@ mid AS u_id
 ,ceil(log2(total_time + 1)) as i_play_len
 ,ceil(log2(i_days_since_upload + 1)) as i_days_since_upload -- 发布时间（距离现在天数）
 -- 基础特征_场景
+,apptype AS ctx_apptype
 ,ctx_day AS ctx_day
 ,ctx_week AS ctx_week
 ,ctx_hour AS ctx_hour
@@ -55,6 +56,9 @@ mid AS u_id
 ,rootmid AS ui_root_id
 ,shareid AS ui_share_id
 -- 统计特征_用户
+,u_cycle_bucket_7days
+,u_cycle_bucket_30days
+,u_share_bucket_30days
 ,ceil(log2(u_1day_exp_cnt + 1)) as u_1day_exp_cnt
 ,ceil(log2(u_1day_click_cnt + 1)) as u_1day_click_cnt
 ,ceil(log2(u_1day_share_cnt + 1)) as u_1day_share_cnt
@@ -134,6 +138,9 @@ and apptype != '13'
     max(u_system_ver) as u_system_ver,
     max(ctx_region) as ctx_region,
     max(ctx_city) as ctx_city,
+    max(u_cycle_bucket_7days) as u_cycle_bucket_7days,
+    max(u_cycle_bucket_30days) as u_cycle_bucket_30days,
+    max(u_share_bucket_30days) as u_share_bucket_30days,
     max(u_1day_exp_cnt) as u_1day_exp_cnt,
     max(u_1day_click_cnt) as u_1day_click_cnt,
     max(u_1day_share_cnt) as u_1day_share_cnt,