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

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

@@ -264,9 +264,62 @@ object NdDataInput {
       tidb_input.show()
       println(tidb_input.count())
 
+    }
+  }
+}
+
+
+
 
+object ServiceStat {
 
+  Logger.getLogger("org.apache.spark").setLevel(Level.WARN)
+  Logger.getLogger("org.apache.eclipse.jetty.server").setLevel(Level.OFF)
+
+  case class Params(env: String = "dev"
+                   ) extends AbstractParams[Params] with Serializable
+
+  val defaultParams = Params()
+
+  val parser = new OptionParser[Params]("Feed_EDA") {
+    head("WeafareStat")
+    opt[String]("env")
+      .text(s"the databases environment you used")
+      .action((x, c) => c.copy(env = x))
+    note("winter is coming")
+  }
+
+
+  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 = "nd_data_meigou_cid")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_click")
+      ti.tidbMapTable(dbName = "eagle", tableName = "feed_diary_boost")
+
+      val result00 = sc.sql(
+        s"""
+           |select a.cl_id as device_id,
+           |COALESCE(a.params['diary_id'], a.params['business_id'], 0) as diary_id,
+           |c.level1_id as level1_id
+           |from online.tl_hdfs_maidian_view a
+           |left join online.tl_hdfs_diary_tags_view b on COALESCE(a.params['diary_id'], a.params['business_id'], 0)=b.diary_id
+           |left join online.bl_tag_hierarchy_detail c on b.tag_id=c.id
+           |where a.partition_date > "20181112"
+           |and a.action="on_click_diary_card"
+           |and a.params["page_name"]="home"
+           |and a.cl_id != "NULL"
+           |and b.partition_date="20181119"
+           |and c.partition_date="20181119"
+     """.stripMargin
+      )
+      result00.collect()
+      println(result00.count())
 
     }
   }
-}
+}
\ No newline at end of file