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

增加曝光量统计指标

eda/feededa/run.sh

-if [[ $# -ne 2  ]];then
-    echo 'Usage:'$0' <startdate> <enddate>'
-    exit
-fi
-startdate=`date -d "$1" +%Y-%m-%d`
-enddate=`date -d "$2" +%Y-%m-%d`
+ if [[ $# -ne 2 ]];then
+     echo 'Usage:'$0' <startdate> <enddate>'
+     exit
+ fi
 
-while [[ $startdate < $enddate]]
-do
-    /opt/spark/bin/spark-submit --master spark://10.31.242.83:7077  --total-executor-cores 20 --executor-memory 3g  --executor-cores 2 --driver-memory 8g --conf spark.default.parallelism=200  --conf spark.storage.memoryFraction=0.5 --conf spark.shuffle.memoryFraction=0.3 --class com.gmei.jerry.strategy_clk_imp_oldUser /srv/apps/ffm-baseline/eda/feededa/target/scala-2.11/feededa-assembly-0.1.jar --env prod --date $startdate >>ctr1.log
-    startdate=`date -d "+1 day $startdate" +%Y-%m-%d`
-done
+ startdate=`date -d "$1" +%Y-%m-%d`
+ enddate=`date -d "$2" +%Y-%m-%d`
+
+ while [[ $startdate < $enddate  ]]
+ do
+      /opt/spark/bin/spark-submit --master spark://10.31.242.83:7077  --total-executor-cores 10 --executor-memory 3g  --executor-cores 2 --driver-memory 8g --class com.gmei.         strategy_clk_imp_oldUser /srv/apps/ffm-baseline/eda/feededa/target/scala-2.11/feededa-assembly-0.1.jar --env prod --date $startdate >> ctr2.log
+     startdate=`date -d "+1 day $startdate" +%Y-%m-%d`
+ done

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

 package com.gmei
-import java.text.SimpleDateFormat
-import java.util.{Calendar, Date}
-import java.text.SimpleDateFormat
-import java.util.Calendar
-import scala.collection.mutable.ArrayBuffer
+
+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 testt {
 
-  def main(args: Array[String]): Unit ={
-    val dateArray2 = get_date()
-    println(dateArray2(0))
-    for (elem <- dateArray2) {
-      println(elem)
-    }
+  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))
+    //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.testt ./target/scala-2.11/feededa-assembly-0.1.jar \
+      """.stripMargin +
+        s"|   --env ${defaultParams.env}"
+    )
   }
-  def get_date(): ArrayBuffer[String] ={
-    val startTime = "2017-12-01"
-    val endTime = "2017-12-10"
-    val dateFormat = new SimpleDateFormat("yyyy-MM-dd")
-    val dateFiled = Calendar.DAY_OF_MONTH
-    var beginDate = dateFormat.parse(startTime)
-    val endDate = dateFormat.parse(endTime)
-    val calendar = Calendar.getInstance()
-    calendar.setTime(beginDate)
-    val dateArray: ArrayBuffer[String] = ArrayBuffer()
-    while (beginDate.compareTo(endDate) <= 0) {
-      dateArray += dateFormat.format(beginDate)
-      calendar.add(dateFiled, 1)
-      beginDate = calendar.getTime
+
+  def main(args: Array[String]): Unit = {
+    parser.parse(args, defaultParams).map { param =>
+      GmeiConfig.setup(param.env)
+      val spark_env = GmeiConfig.getSparkSession()
+      val sc = spark_env._2
+
+      val ti = new TiContext(sc)
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "diary_video")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_click")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "blacklist")
+      ti.tidbMapTable(dbName = "jerry_test", tableName = "bl_device_list")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_exposure")
+
+      val strategies = Seq("3$","4$","5$","6$","7$","8$","a$","b$","c$","d$","e$","A$","B$","C$","D$")
+      for (strategy <- strategies){
+        println(strategy)
+        val get_data_dura = sc.sql(
+          s"""
+             |select partition_date, sum(params['duration']) as total_dur,count(distinct(cl_id)) as num
+             |from online.tl_hdfs_maidian_view
+             |where  where action="on_app_session_over"
+             |and cl_id regexp '${strategy}'
+             |and params['duration']>=0 and params['duration']<86400
+             |and partition_date >='20180801'
+             |group by partition_date order by partition_date desc
+         """.stripMargin
+        )
+        get_data_dura.show()
+
+
+      }
+
+
     }
-    //println(dateArray)
-    dateArray
-  }
 
 
+  }
 
 }
-