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

修改测试文件

eda/feededa/src/main/scala/com/gmei/Search_keywords_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 Search_keywords_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("Search_keywords_count")
+    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 ${defaultParams.env}"
+    )
+  }
+
+  def main(args: Array[String]): Unit = {
+    parser.parse(args, defaultParams).map { param =>
+      GmeiConfig.setup(param.env)
+      val spark_env = GmeiConfig.getSparkSession()
+      val sc = spark_env._2
+      val stat_date = GmeiConfig.getMinusNDate(1)   //获取昨日日期
+      //println(param.date)
+      val partition_date = stat_date.replace("-","")
+      //搜索关键词提取
+      val search_keywords = sc.sql(
+        s"""
+           |select params['query'] as search_keywords
+           |from online.tl_hdfs_maidian_view
+           |where action = 'search_result_click_search'
+           |and partition_date ='${partition_date}'
+         """.stripMargin
+      )
+      //搜索次数统计
+      val search_count = sc.sql(
+        s"""
+           |select '${stat_date}' as stat_date,count(params['query']) as search_num
+           |from online.tl_hdfs_maidian_view
+           |where action = 'search_result_click_search'
+           |and partition_date ='${partition_date}'
+         """.stripMargin
+      )
+      search_count.show()
+
+      val get_result =search_keywords.rdd.map((_, 1)).reduceByKey(_ + _)
+        .sortBy(_._2,false)
+      val temp=get_result.collect()
+      for (i <- 0 until temp.length ) {
+        println(temp(i))
+      }
+
+
+    }
+
+
+  }
+
+}
\ No newline at end of file