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

add app list

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

@@ -433,7 +433,7 @@ object EsmmPredData {
 }
 
 
-object GetPortrait {
+object GetDiaryPortrait {
 
   Logger.getLogger("org.apache.spark").setLevel(Level.WARN)
   Logger.getLogger("org.apache.eclipse.jetty.server").setLevel(Level.OFF)
@@ -496,6 +496,80 @@ object GetPortrait {
       GmeiConfig.writeToJDBCTable(diary_tag,"diary_feat",SaveMode.Overwrite)
 
 
+      sc.stop()
+
+    }
+  }
+
+}
+
+object GetDevicePortrait {
+
+  Logger.getLogger("org.apache.spark").setLevel(Level.WARN)
+  Logger.getLogger("org.apache.eclipse.jetty.server").setLevel(Level.OFF)
+
+  case class Params(env: String = "dev",
+                    date: String = GmeiConfig.getMinusNDate(1)
+                   ) extends AbstractParams[Params] with Serializable
+
+  val defaultParams = Params()
+
+  val parser = new OptionParser[Params]("Feed_EDA") {
+    head("EsmmData")
+    opt[String]("env")
+      .text(s"the databases environment you used")
+      .action((x, c) => c.copy(env = x))
+    opt[String]("date")
+      .text(s"the date you used")
+      .action((x,c) => c.copy(date = x))
+    note(
+      """
+        |For example, the following command runs this app on a tidb dataset:
+        |
+        | spark-submit --class com.gmei.EsmmData ./target/scala-2.11/feededa-assembly-0.1.jar \
+      """.stripMargin +
+        s"|   --env ${defaultParams.env}"
+    )
+  }
+
+
+
+  def main(args: Array[String]): Unit = {
+    parser.parse(args, defaultParams).map { param =>
+      GmeiConfig.setup(param.env)
+      val spark_env = GmeiConfig.getSparkSession()
+      val sc = spark_env._2
+
+      val ti = new TiContext(sc)
+      ti.tidbMapTable(dbName = "jerry_prod",tableName = "data_feed_click")
+      ti.tidbMapTable(dbName = "jerry_prod",tableName = "diary_feat")
+
+      val stat_date = param.date.replace("-","")
+
+      val device_search_tag = sc.sql(
+        s"""
+           |select a.cl_id as device_id,COALESCE(a.params['diary_id'], a.params['business_id'], 0) as cid_id,split(c.level1_ids,',')[0] as level1_id
+           |from online.tl_hdfs_maidian_view as a
+           |left join
+           |	(select cl_id as device_id,max(partition_date) as stat_date
+           |	from online.tl_hdfs_maidian_view
+           |	where action = 'on_click_diary_card'
+           |	and (params['page_name']='search_result_diary' or params['page_name']='search_result_more')
+           |	and partition_date > '20180601' group by cl_id) b
+           |on a.cl_id = b.device_id and a.partition_date=b.stat_date
+           |left join diary_feat c
+           |on COALESCE(a.params['diary_id'], a.params['business_id'], 0) = c.diary_id
+           |where a.partition_date > '20180601'
+           |and b.params['business_id'] != 0
+           |and c.level1_ids != ""
+         """.stripMargin
+      )
+      device_search_tag.show()
+      println(device_search_tag.count())
+
+//      GmeiConfig.writeToJDBCTable(diary_tag,"diary_feat",SaveMode.Overwrite)
+
+
       sc.stop()
 
     }