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

增加获取城市列表

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

@@ -34,7 +34,7 @@ object GmeiConfig extends Serializable {
     val sparkConf = new SparkConf
     sparkConf.set("spark.sql.crossJoin.enabled", "true")
     sparkConf.set("spark.debug.maxToStringFields", "100")
-    sparkConf.set("spark.sql.broadcastTimeout",  "1000")
+    sparkConf.set("spark.sql.broadcastTimeout",  "6000")
 
     if (!sparkConf.contains("spark.master")) {
       sparkConf.setMaster("local[3]")

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

@@ -13,8 +13,7 @@ object Recommendation_strategy_all {
   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"
+  case class Params(env: String = "dev"
                    ) extends AbstractParams[Params] with Serializable
 
   val defaultParams = Params()
@@ -24,9 +23,6 @@ object Recommendation_strategy_all {
     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:
@@ -54,6 +50,7 @@ object Recommendation_strategy_all {
 
       import sc.implicits._
       val stat_date = GmeiConfig.getMinusNDate(1)
+      println(stat_date)
       //println(param.date)
       val partition_date = stat_date.replace("-","")
       val decive_id_oldUser = sc.sql(

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

@@ -264,9 +264,61 @@ 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.foreach(println)
 
     }
   }
-}
+}
\ No newline at end of file

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

@@ -179,3 +179,174 @@ object strategy_other {
   }
 
 }
+
+
+
+
+//下边内容开始分析统计推荐系统评价指标
+//使用信息熵描述推荐系统对长尾优质物品(日记本)的挖掘能力
+//使用基尼系数描述推荐系统对日记本推荐是否具有马太效应
+
+object evaluation_indicator_ {
+
+  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 ${defaultParams.env}"
+    )
+  }
+
+  def main(args: Array[String]): Unit = {
+    parser.parse(args, defaultParams).map { param =>
+      GmeiConfig.setup(param.env)
+      val spark_env = GmeiConfig.getSparkSession()
+      val sc = spark_env._2
+
+      import sc.implicits._
+      //val stat_date = GmeiConfig.getMinusNDate(1)
+      //println(param.date)
+      val partition_date = param.date.replace("-","")
+      val devicee_id_oldUser = sc.sql(
+        s"""
+           |select distinct(device_id) as device_id
+           |from online.ml_device_day_active_status
+           |where active_type = '4'
+           |and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
+           |        ,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
+           |        ,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
+           |        ,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
+           |        ,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
+           |        ,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
+           |        ,'promotion_shike','promotion_julang_jl03')
+           |and partition_date ='${partition_date}'
+         """.stripMargin
+      )
+      devicee_id_oldUser.show()
+      devicee_id_oldUser.createOrReplaceTempView("device_id_old")
+
+      //device_id尾号1有点击用户日记本点击数
+      val clk_active_1 = sc.sql(
+        s"""
+           |select '${param.date}' as stat_date, count(jd.cid_id) as clk_active_1
+           |from data_feed_click jd inner join device_id_old
+           |on jd.device_id = device_id_old.device_id
+           |where  (jd.cid_type = 'diary' or jd.cid_type = 'diary_video')
+           |and jd.device_id regexp'1$$'
+           |and jd.device_id not in (select device_id from bl_device_list)
+           |and jd.device_id not in (select device_id from blacklist)
+           |and jd.stat_date ='${param.date}'
+         """.stripMargin
+      )
+
+      //device_id尾号1有点击用户日记本曝光数
+      val imp_active_1 = sc.sql(
+        s"""
+           |select '${param.date}' as stat_date, count(je.cid_id) as imp_active_1
+           |from data_feed_exposure je inner join device_id_old
+           |on je.device_id = device_id_old.device_id
+           |where je.cid_type = 'diary'
+           |and je.device_id in (select distinct(device_id) from data_feed_click where device_id regexp '1$$' and stat_date = '${param.date}')
+           |and je.device_id not in (select device_id from bl_device_list)
+           |and je.device_id not in (select device_id from blacklist)
+           |and je.stat_date ='${param.date}'
+         """.stripMargin
+      )
+
+      //device_id尾号1点击日记本用户数
+      val clk_diary_device = sc.sql(
+        s"""
+           |select '${param.date}' as stat_date, count(distinct(jd.device_id)) as clk_diary_device
+           |from data_feed_click jd inner join device_id_old
+           |on jd.device_id = device_id_old.device_id
+           |where  (jd.cid_type = 'diary' or jd.cid_type = 'diary_video')
+           |and jd.device_id regexp'1$$'
+           |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 ='${param.date}'
+            """.stripMargin
+      )
+
+      //所有有点击用户日记本点击数
+      val clk_active_all = sc.sql(
+        s"""
+           |select '${param.date}' as stat_date, count(jd.cid_id) as clk_active_all
+           |from data_feed_click jd inner join device_id_old
+           |on jd.device_id = device_id_old.device_id
+           |where  (jd.cid_type = 'diary' or jd.cid_type = 'diary_video')
+           |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 ='${param.date}'
+                  """.stripMargin
+      )
+
+      //所有有点击用户日记本曝光数
+      val imp_active_all = sc.sql(
+        s"""
+           |select '${param.date}' as stat_date, count(je.cid_id) as imp_active_all
+           |from data_feed_exposure je inner join device_id_old
+           |on je.device_id = device_id_old.device_id
+           |where je.cid_type = 'diary'
+           |and je.device_id in (select distinct(device_id) from data_feed_click where stat_date = '${param.date}')
+           |and je.device_id not in (select device_id from bl_device_list)
+           |and je.device_id not in (select device_id from blacklist)
+           |and je.stat_date ='${param.date}'
+                  """.stripMargin
+      )
+
+      //策略命中用户点击日记本用户数
+      val clk_diary_device_cover = sc.sql(
+        s"""
+           |select '${param.date}' as stat_date,count(distinct(device_id)) as clk_diary_device_cover
+           |from merge_queue_table
+           |where device_id in (select distinct(device_id) from data_feed_click where stat_date = '${param.date}')
+                  """.stripMargin
+      )
+
+      //策略命中用户总数
+      val device_all_cover = sc.sql(
+        s"""
+           |select '${param.date}' as stat_date,count(distinct(device_id)) as device_all_cover
+           |from merge_queue_table
+                  """.stripMargin
+      )
+
+
+
+      val result = clk_active_1.join(imp_active_1,"stat_date")
+        .join(clk_active_all,"stat_date")
+        .join(imp_active_all,"stat_date")
+        .join(clk_diary_device,"stat_date")
+        .join(clk_diary_device_cover,"stat_date")
+        .join(device_all_cover,"stat_date")
+      result.show()
+
+      GmeiConfig.writeToJDBCTable(result, "strategy_other", SaveMode.Append)
+
+
+    }
+
+
+  }
+
+}
+

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

@@ -54,7 +54,6 @@ object testt {
              |from online.tl_hdfs_maidian_view
              |where action="page_view"
              |and params["page_name"]="diary_detail"
-             |and (params["out"]-params["in"])<7200
              |and partition_date >='20180901'
          """.stripMargin
         )
@@ -71,9 +70,6 @@ object testt {
 
       }
 
-
-
-
     }