Merge branch 'master' of git.wanmeizhensuo.com:ML/ffm-baseline

change ffm encoder

eda/feededa/src/main/scala/com/gmei/testt.scala

@@ -48,39 +48,40 @@ object testt {
 
 
       //机构id
-      val agency_id = sc.sql(
-        s"""
-           |SELECT DISTINCT(cl_id) as device_id
-           |FROM online.ml_hospital_spam_pv_day
-           |WHERE partition_date >= '20180402'
-           |AND partition_date <= '20181203'
-           |AND pv_ratio >= 0.95
-           |UNION ALL
-           |SELECT DISTINCT(cl_id) as device_id
-           |FROM online.ml_hospital_spam_pv_month
-           |WHERE partition_date >= '20171101'
-           |AND partition_date <= '20181203'
-           |AND pv_ratio >= 0.95
-         """.stripMargin
-      )
-//      agency_id.show()
-      agency_id.createOrReplaceTempView("agency_id")
-
-      val diary_pv = sc.sql(
-        s"""
-           |select ov.partition_date, count(params["business_id"]) as diary_pv
-           |from online.tl_hdfs_maidian_view ov left join agency_id
-           |on ov.cl_id = agency_id.device_id
-           |where ov.action="page_view"
-           |and ov.params["page_name"]="diary_detail"
-           |and (ov.params["out"]-ov.params["in"])<7200
-           |and agency_id.device_id is null
-           |and ov.partition_date >='20181120'
-           |and ov.cl_id not in (select distinct(device_id) from blacklist)
-           |group by ov.partition_date order by ov.partition_date
-         """.stripMargin
-      )
-      diary_pv.show()
+//      val agency_id = sc.sql(
+//        s"""
+//           |SELECT DISTINCT(cl_id) as device_id
+//           |FROM online.ml_hospital_spam_pv_day
+//           |WHERE partition_date >= '20180402'
+//           |AND partition_date <= '20181203'
+//           |AND pv_ratio >= 0.95
+//           |UNION ALL
+//           |SELECT DISTINCT(cl_id) as device_id
+//           |FROM online.ml_hospital_spam_pv_month
+//           |WHERE partition_date >= '20171101'
+//           |AND partition_date <= '20181203'
+//           |AND pv_ratio >= 0.95
+//         """.stripMargin
+//      )
+////      agency_id.show()
+//      agency_id.createOrReplaceTempView("agency_id")
+      val a = Array("message_home","my_favor","my_order","order_detail","organization_detail","other_homepage")
+      for (i <- 0 until a.length){
+        val diary_pv = sc.sql(
+          s"""
+             |select partition_date,count(cl_id)
+             |from online.tl_hdfs_maidian_view
+             |where action="page_view"
+             |and params["page_name"]="diary_detail"
+             |and params["referrer"]='${a(i)}'
+             |and partition_date >='20181120'
+             |GROUP BY partition_date
+             |order by partition_date
+           """.stripMargin
+        )
+        diary_pv.show()
+      }
+
 
 
 //      GmeiConfig.writeToJDBCTable(view_count, "avg", SaveMode.Overwrite)