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

bug fix

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

@@ -376,3 +376,119 @@ object hospital_gengmei {
 
 }
 
+
+
+
+
+
+object meigou_xiaofei_renshu {
+
+  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_price = sc.sql(
+        s"""
+           |select  md.user_id,sum(md.gengmei_price) as pay_all
+           |from online.ml_meigou_order_detail md left join final_id
+           |on md.device_id = final_id.device_id
+           |where md.status= 2
+           |and final_id.device_id is  null
+           |and md.partition_date = '20181223'
+           |and  md.pay_time  is  not  null
+           |and  md.validate_time>'2018-01-01 00:00:00.0'
+           |group by md.user_id
+           |order by sum(md.gengmei_price)
+       """.stripMargin
+      )
+      meigou_price.show(80)
+
+      GmeiConfig.writeToJDBCTable(meigou_price, "meigou_price", SaveMode.Append)
+
+    }
+
+
+  }
+
+}
+

tensnsorflow/applist.py

@@ -34,7 +34,7 @@ def sort_app():
     df = df.rename(columns={0: "device_id", 1: "app_list"})
     df = df.loc[df["app_list"].apply(is_json)]
 
-    category = {"competitor":{"新氧美容"},
+    category = {"competitor":{"新氧美容","悦美","美呗整形","悦美微整形","如丽美容","医美咖","整形去哪儿","美黛拉","整形思密达","美芽"},
                 "dianshang":{"京东","淘宝","唯品会","天猫","苏宁易购","国美","当当","亚马逊","网易严选","小米有品"},
                 "kuajing_dianshang": {"小红书", "网易考拉", "洋码头", "达令全球好货", "海狐海淘",
                                       "HIG0", "豌豆公主", "尚品网", "丰趣海淘", "比呀比海外购"},
@@ -72,7 +72,7 @@ def sort_app():
     for i in category.keys():
         df[i] = df["app_list"].apply(lambda x: 1 if len(x & category[i]) > 0 else 0)
         print(i)
-        print(df[i].unique())
+        print(df[i].value_counts())
     df = df.drop("app_list",axis=1)
 
     yconnect = create_engine('mysql+pymysql://root:3SYz54LS9#^9sBvC@10.66.157.22:4000/jerry_test?charset=utf8')