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

rm -r

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

@@ -300,8 +300,75 @@ object ARPU_COM {
       )
       active_num.show(80)
 
+    }
+
+
+  }
+
+}
+
+
+
+
+object hospital_gengmei {
+
+  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 hospital_gengmei = sc.sql(
+        s"""
+           |SELECT id,name,location,city_id
+           |FROM online.tl_hdfs_hospital_view
+           |WHERE partition_date = '20181219'
+         """.stripMargin
+      )
+      hospital_gengmei.show()
+      GmeiConfig.writeToJDBCTable(hospital_gengmei, "hospital_gengmei", SaveMode.Append)
+
     }
 
 

tensnsorflow/ffm.py

@@ -142,7 +142,7 @@ def get_data():
     validate_date = con_sql(db, sql)[0].values.tolist()[0]
     print("validate_date:" + validate_date)
     temp = datetime.datetime.strptime(validate_date, "%Y-%m-%d")
-    start = (temp - datetime.timedelta(days=30)).strftime("%Y-%m-%d")
+    start = (temp - datetime.timedelta(days=6)).strftime("%Y-%m-%d")
     print(start)
     db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
     sql = "select e.y,e.z,e.stat_date,e.ucity_id,e.clevel1_id,e.ccity_name," \
@@ -165,7 +165,7 @@ def get_data():
     df = df.drop(["z","stat_date"], axis=1).fillna(0.0)
     print(df.head(2))
     features = 0
-    for i in ["ucity_id","clevel1_id","ccity_name","device_type","manufacturer","channel"]:
+    for i in ["ucity_id","clevel1_id","ccity_name","device_type","manufacturer","channel","top"]:
         features = features + len(df[i].unique())
     print("fields:{}".format(df.shape[1]-1))
     print("features:{}".format(features))
@@ -261,7 +261,7 @@ if __name__ == "__main__":
     a = time.time()
     df, validate_date, ucity_id,ccity_name = get_data()
     model = transform(df, validate_date)
-    get_predict_set(ucity_id,model,ccity_name)
+    # get_predict_set(ucity_id,model,ccity_name)
     b = time.time()
     print("cost(分钟)")
     print((b-a)/60)