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

add app list

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

@@ -558,7 +558,7 @@ object GetDevicePortrait {
            |	on COALESCE(a.params['diary_id'], a.params['business_id'], 0) = b.diary_id
            |	where
            |    b.level1_ids is not null and
-           |		a.partition_date = '20181224'
+           |		a.partition_date = '${stat_date}'
            |		and (a.action = 'on_click_diary_card' or (a.action="full_stack_click_video_card_full_screen_play" and a.params["card_type"]="diary"))) c
            |group by c.device_id,c.level1_id,c.stat_date
          """.stripMargin

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

@@ -3,11 +3,12 @@ package com.gmei
 
 import java.util.Properties
 import java.io.Serializable
+import java.sql.{Connection, DriverManager}
 import java.text.SimpleDateFormat
-import java.util.{Calendar}
+import java.util.Calendar
 
 import com.typesafe.config._
-import org.apache.spark.{SparkConf,SparkContext}
+import org.apache.spark.{SparkConf, SparkContext}
 import org.apache.spark.sql.execution.datasources.jdbc.JDBCOptions
 import org.apache.spark.sql.{DataFrame, SaveMode, SparkSession}
 
@@ -77,6 +78,28 @@ object GmeiConfig extends Serializable {
   }
 
 
+
+  def updateDeviceFeat(iterator: Iterator[(String,String,String,String)]): Unit ={
+    var conn: Connection= null
+    var ps:java.sql.PreparedStatement=null
+    val sql=s"replace into device_feat(device_id,stat_date,level1_id,level1_count) values(?,?,?,?)"
+    conn=DriverManager.getConnection("jdbc:mysql://10.66.157.22:4000/jerry_prod","root","3SYz54LS9#^9sBvC")
+    ps = conn.prepareStatement(sql)
+    try{
+      iterator.foreach(x => {
+        ps.setString(1,x._1)
+        ps.setString(2,x._2)
+        ps.setString(3,x._3)
+        ps.setString(4,x._4)
+        ps.executeUpdate()
+      })
+      println("update device feat done")
+    }catch {
+      case _ => println("update failed")
+    }
+  }
+
+
   def getMinusNDate(n: Int):String={
     var  dateFormat:SimpleDateFormat = new SimpleDateFormat("yyyy-MM-dd")
     var cal:Calendar=Calendar.getInstance()

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

@@ -526,3 +526,154 @@ object meigou_xiaofei_renshu {
 
 }
 
+
+
+
+object smart_rank_count {
+
+  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 = "2018-08-01"
+                   ) 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.WeafareStat ./target/scala-2.11/feededa-assembly-0.1.jar \
+      """.stripMargin +
+        s"|   --env ${defaultParams.env}"
+    )
+  }
+
+  def main(args: Array[String]): Unit = {
+    parser.parse(args, defaultParams).map { param =>
+      GmeiConfig.setup(param.env)
+      val spark_env = GmeiConfig.getSparkSession()
+      val sc = spark_env._2
+
+      val ti = new TiContext(sc)
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "diary_video")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_click")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "blacklist")
+      ti.tidbMapTable(dbName = "jerry_test", tableName = "bl_device_list")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_exposure")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "merge_queue_table")
+
+
+      import sc.implicits._
+      val stat_date = GmeiConfig.getMinusNDate(1)
+      //println(param.date)
+      val partition_date = stat_date.replace("-","")
+
+      val agency_id = sc.sql(
+        s"""
+           |SELECT DISTINCT(cl_id) as device_id
+           |FROM online.ml_hospital_spam_pv_day
+           |WHERE partition_date >= '20180402'
+           |AND partition_date <= '${partition_date}'
+           |AND pv_ratio >= 0.95
+           |UNION ALL
+           |SELECT DISTINCT(cl_id) as device_id
+           |FROM online.ml_hospital_spam_pv_month
+           |WHERE partition_date >= '20171101'
+           |AND partition_date <= '${partition_date}'
+           |AND pv_ratio >= 0.95
+         """.stripMargin
+      )
+      agency_id.createOrReplaceTempView("agency_id")
+
+      val blacklist_id = sc.sql(
+        s"""
+           |SELECT device_id
+           |from blacklist
+         """.stripMargin
+      )
+      blacklist_id.createOrReplaceTempView("blacklist_id")
+
+      val final_id = sc.sql(
+        s"""
+           |select device_id
+           |from agency_id
+           |UNION ALL
+           |select device_id
+           |from blacklist_id
+         """.stripMargin
+      )
+      final_id.createOrReplaceTempView("final_id")
+
+
+      val meigou_pv = sc.sql(
+        s"""
+           |select *
+           |from online.tl_hdfs_maidian_view
+           |where action = "page_view"
+           |and params['page_name']="welfare_detail"
+           |and partition_date ='20181201'
+           |LIMIT 3
+       """.stripMargin
+      )
+       meigou_pv.show(80)
+
+//      val zixun_pv = sc.sql(
+//        s"""
+//           |select cl_id,city_id,params['service_id'] as meigou_id
+//           |from online.tl_hdfs_maidian_view
+//           |where partition_date > '20171118'
+//           |and action = 'welfare_detail_click_message'
+//       """.stripMargin
+//      )
+//      zixun_pv.show(80)
+
+
+
+//      val meigou_price = sc.sql(
+//        s"""
+//           |select  md.user_id,sum(md.gengmei_price) as pay_all
+//           |from online.ml_meigou_order_detail md
+//           |left join
+//           |(
+//           |        SELECT
+//           |        order_id
+//           |        FROM mining.ml_order_spam_recognize
+//           |        WHERE partition_date='20181223' AND
+//           |        self_support=0 AND dayBitsGetW1(predict_result,'20181223')=0
+//           |)spam
+//           |on md.order_id = spam.order_id
+//           |where md.status= 2
+//           |and  spam.order_id is null
+//           |and md.partition_date = '20181223'
+//           |and  md.pay_time  is  not  null
+//           |and  md.validate_time>'2017-01-01 00:00:00.0'
+//           |group by md.user_id
+//           |order by sum(md.gengmei_price)
+//       """.stripMargin
+//      )
+
+      //      GmeiConfig.writeToJDBCTable(meigou_price, "meigou_price", SaveMode.Overwrite)
+
+    }
+
+
+  }
+
+}
+
+
+
+
+
+
+