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

修改统计指标

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

+package com.gmei
+
+import java.io.Serializable
+
+import com.gmei.WeafareStat.{defaultParams, parser}
+import org.apache.spark.sql.{SaveMode, TiContext}
+import org.apache.log4j.{Level, Logger}
+import scopt.OptionParser
+import com.gmei.lib.AbstractParams
+
+object strategy_clk_imp_oldUser {
+
+  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(
+      """
+        |For example, the following command runs this app on a tidb dataset:
+        |
+        | spark-submit --class com.gmei.WeafareStat ./target/scala-2.11/feededa-assembly-0.1.jar \
+      """.stripMargin +
+        s"|   --env ${defaultParams.env}"
+    )
+  }
+
+  def main(args: Array[String]): Unit = {
+    parser.parse(args, defaultParams).map { param =>
+      GmeiConfig.setup(param.env)
+      val spark_env = GmeiConfig.getSparkSession()
+      val sc = spark_env._2
+
+      val ti = new TiContext(sc)
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "diary_video")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_click")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "blacklist")
+      ti.tidbMapTable(dbName = "jerry_test", tableName = "bl_device_list")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_exposure")
+
+
+      import sc.implicits._
+      val stat_date = GmeiConfig.getMinusNDate(1)
+      println(stat_date)
+      val partition_date = stat_date.replace("-","")
+      val decive_id_oldUser = sc.sql(
+        s"""
+           |select distinct(device_id) as decive_id
+           |from online.ml_device_day_active_status
+           |where active_type = '4'
+           |and partition_date ='${partition_date}'
+         """.stripMargin
+      )
+      decive_id_oldUser.show()
+      decive_id_oldUser.createOrReplaceTempView("device_id_old")
+
+      val decive_id_newUser = sc.sql(
+        s"""
+           |select distinct(device_id) as decive_id
+           |from online.ml_device_day_active_status
+           |where active_type != '4'
+           |and partition_date ='${partition_date}'
+         """.stripMargin
+      )
+      decive_id_newUser.show()
+      decive_id_newUser.createOrReplaceTempView("device_id_newUser")
+
+      val strategies = Seq("[1|2]$","[3|4]$","[5|6]$","[7|8]$")
+      for (strategy <- strategies){
+        val clk_count_oldUser = sc.sql(
+          s"""
+             |select '${stat_date}' as stat_date, count(cid_id) as get_clk_count_old
+             |from data_feed_click jd inner join device_id_old
+             |on jd.device_id = device_id_old.decive_id
+             |where  (jd.cid_type = 'diary' or jd.cid_type = 'diary_video')
+             |and jd.device_id regexp'${strategy}'
+             |and jd.device_id not in (select device_id from bl_device_list)
+             |and jd.device_id not in (select device_id from blacklist)
+             |and jd.stat_date ='${stat_date}'
+         """.stripMargin
+        )
+        clk_count_oldUser.show()
+
+        val imp_count_oldUser = sc.sql(
+          s"""
+             |select '${stat_date}' as stat_date, count(cid_id) as get_imp_count_old
+             |from data_feed_exposure je inner join device_id_old
+             |on je.device_id = device_id_old.decive_id
+             |where je.cid_type = 'diary'
+             |and je.device_id regexp'${strategy}'
+             |and je.device_id not in (select device_id from bl_device_list)
+             |and je.device_id not in (select device_id from blacklist)
+             |and je.stat_date ='${stat_date}'
+         """.stripMargin
+        )
+        imp_count_oldUser.show()
+
+
+        val clk_count_newUser = sc.sql(
+          s"""
+             |select '${stat_date}' as stat_date, count(cid_id) as get_clk_count_newUser
+             |from data_feed_click jd inner join device_id_newUser
+             |on jd.device_id = device_id_newUser.decive_id
+             |where  (jd.cid_type = 'diary' or jd.cid_type = 'diary_video')
+             |and jd.device_id regexp'${strategy}'
+             |and jd.device_id not in (select device_id from bl_device_list)
+             |and jd.device_id not in (select device_id from blacklist)
+             |and jd.stat_date ='${stat_date}'
+         """.stripMargin
+        )
+        clk_count_newUser.show()
+
+        val imp_count_newUser = sc.sql(
+          s"""
+             |select '${stat_date}' as stat_date, count(cid_id) as get_imp_count_newUser
+             |from data_feed_exposure je inner join device_id_newUser
+             |on je.device_id = device_id_newUser.decive_id
+             |where je.cid_type = 'diary'
+             |and je.device_id regexp'${strategy}'
+             |and je.device_id not in (select device_id from bl_device_list)
+             |and je.device_id not in (select device_id from blacklist)
+             |and je.stat_date ='${stat_date}'
+         """.stripMargin
+        )
+        imp_count_newUser.show()
+
+        val result = clk_count_oldUser.join(imp_count_oldUser,"stat_date")
+          .join(clk_count_newUser,"stat_date")
+          .join(imp_count_newUser,"stat_date")
+        result.show()
+
+
+
+      }
+
+
+
+
+    }
+
+
+  }
+
+}
\ No newline at end of file