统计数据新需求

eda/feededa/src/main/scala/com/gmei/app_list.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
+import java.io._
+
+object app_list {
+
+  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")
+      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("-","")
+
+      //获取策略命中用户device_id
+      val app_list = sc.sql(
+        s"""
+           |select cl_id as device_id,params['installed_app_info'] as app_list
+           |from online.tl_hdfs_maidian_view
+           |where action="user_installed_all_app_info"
+           |partition_date <= '20181118'
+         """.stripMargin
+      )
+      app_list.show()
+      val appsMapResult=app_list.rdd.map(row=>{
+        val rowAppFieldMap:Map[String,Any] = row.getAs[Map[String,Any]]("app_list")
+        if (rowAppFieldMap.nonEmpty){
+          if (rowAppFieldMap.contains("更美")){
+            if (rowAppFieldMap.contains("新氧美容")){
+
+
+            }
+          }
+        }
+      })
+
+
+
+      val result = diary_pv.join(meigou_pv,"stat_date")
+      result.show()
+      GmeiConfig.writeToJDBCTable(result, "diary_pv", SaveMode.Append)
+
+      //      result.select("stat_date","diary_pv","device_num_diary","meigou_pv","device_num_meigou").write.mode(SaveMode.Append).save("/data2/test.txt")
+
+
+
+    }
+
+
+  }
+
+}