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

去除机构黑名

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

@@ -175,3 +175,70 @@ object WeafareStat {
 
 
 }
+
+
+
+
+
+object NdDataInput {
+
+  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 date8 = GmeiConfig.getMinusNDate(5)
+      val tidb_inupt = sc.sql(
+        s"""
+           |SELECT
+           | split(service_id,'\\\\|')[1] as sid,split(cid,'\\\\|')[1] as cid
+           |FROM nd_data_meigou_cid
+           |where stat_date > '${date8}'
+     """.stripMargin
+      )
+      tidb_inupt.createOrReplaceTempView("tmp1")
+      tidb_inupt.show()
+      println(tidb_inupt.count())
+
+      val yesteday = GmeiConfig.getMinusNDate(1).replace("-","")
+      val result01 = sc.sql(
+        s"""
+           |select a.sid as sid, a.cid as cid, b.tag_id as ctag_id, c.level1_id as clevel1_id
+           |from tmp1 a
+           |left join online.tl_hdfs_diary_tags_view b on a.cid=b.diary_id
+           |left join online.bl_tag_hierarchy_detail c on b.tag_id=c.id
+           |where b.partition_date='${yesteday}'
+           |and c.partition_date='${yesteday}'
+         """.stripMargin
+      )
+      result01.createOrReplaceTempView("tmp2")
+      result01.show()
+      println(result01.count())
+
+
+    }
+  }
+}