彦钊统计指定城市的ctr

eda/feededa/src/main/scala/com/gmei/temp_count.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 temp_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 ${defaultParams.env}"
+    )
+  }
+
+  def main(args: Array[String]): Unit = {
+    parser.parse(args, defaultParams).map { param =>
+      GmeiConfig.setup(param.env)
+      val spark_env = GmeiConfig.getSparkSession()
+      val sc = spark_env._2
+
+      val ti = new TiContext(sc)
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "diary_video")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_click")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "blacklist")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_exposure")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "merge_queue_table")
+
+
+//      val stat_date = GmeiConfig.getMinusNDate(1)
+      val stat_date = param.date
+      //println(param.date)
+      val partition_date = stat_date.replace("-","")
+      val decive_id_oldUser = sc.sql(
+        s"""
+           |select distinct(device_id) as device_id
+           |from online.ml_device_day_active_status
+           |where active_type = '4'
+           |and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
+           |    ,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
+           |    ,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
+           |    ,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
+           |    ,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
+           |    ,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
+           |    ,'promotion_shike','promotion_julang_jl03','','unknown')
+           |and partition_date ='${partition_date}'
+         """.stripMargin
+      )
+      decive_id_oldUser.createOrReplaceTempView("device_id_old")
+
+
+      val clk_count_oldUser = sc.sql(
+        s"""
+           |select '${stat_date}' as stat_date, count(cid_id) as clk_count_oldUser_Contrast
+           |from data_feed_click jd inner join device_id_old
+           |on jd.device_id = device_id_old.device_id
+           |where  (jd.cid_type = 'diary' or jd.cid_type = 'diary_video')
+           |and jd.device_id not in (select device_id from blacklist)
+           |and jd.city_id in ("huzhou","liuan","zhenjiang","taizhou","jiaxing","weihai","maanshan","changzhou","shantou","nantong","yantai","wuxi","huhehaote","taiyuan","xining","yinchuan")
+           |and jd.stat_date ='${stat_date}'
+         """.stripMargin
+      )
+
+      val imp_count_oldUser = sc.sql(
+        s"""
+           |select '${stat_date}' as stat_date, count(cid_id) as imp_count_oldUser_Contrast
+           |from data_feed_exposure je inner join device_id_old
+           |on je.device_id = device_id_old.device_id
+           |where je.cid_type = 'diary'
+           |and je.device_id not in (select device_id from blacklist)
+           |and je.city_id in ("huzhou","liuan","zhenjiang","taizhou","jiaxing","weihai","maanshan","changzhou","shantou","nantong","yantai","wuxi","huhehaote","taiyuan","xining","yinchuan")
+           |and je.stat_date ='${stat_date}'
+         """.stripMargin
+      )
+
+      val clk_count_all = sc.sql(
+        s"""
+           |select '${stat_date}' as stat_date, count(cid_id) as clk_count_oldUser_all
+           |from data_feed_click
+           |where  (jd.cid_type = 'diary' or jd.cid_type = 'diary_video')
+           |and device_id not in (select device_id from blacklist)
+           |and city_id in ("huzhou","liuan","zhenjiang","taizhou","jiaxing","weihai","maanshan","changzhou","shantou","nantong","yantai","wuxi","huhehaote","taiyuan","xining","yinchuan")
+           |and stat_date ='${stat_date}'
+         """.stripMargin
+      )
+
+      val imp_count__all = sc.sql(
+        s"""
+           |select '${stat_date}' as stat_date, count(cid_id) as imp_count_oldUser_all
+           |from data_feed_exposure
+           |where cid_type = 'diary'
+           |and device_id not in (select device_id from blacklist)
+           |and city_id in ("huzhou","liuan","zhenjiang","taizhou","jiaxing","weihai","maanshan","changzhou","shantou","nantong","yantai","wuxi","huhehaote","taiyuan","xining","yinchuan")
+           |and stat_date ='${stat_date}'
+         """.stripMargin
+      )
+
+
+      val result1 = clk_count_oldUser.join(imp_count_oldUser,"stat_date")
+        .join(clk_count_all,"stat_date")
+        .join(imp_count__all,"stat_date")
+      result1.show()
+
+      GmeiConfig.writeToJDBCTable(result1, "ffm_diary_ctr", SaveMode.Append)
+
+
+    }
+
+
+  }
+
+}
\ No newline at end of file