fix

src/main/scala/com/gmei/data/dq/pvCheker.scala

@@ -4,12 +4,32 @@ import org.apache.spark.sql.{Row, SparkSession}
 import org.apache.spark.mllib.linalg.Vectors
 import org.apache.spark.mllib.stat.{MultivariateStatisticalSummary, Statistics}
 
+// [41BB2B9E-C72C-4124-9650-FDBAEEEE05F8,page_view,ios,7.9.3,bind_phone,1,0,1,1,1,0,0,1,1,1]
+// [B6DA0665-621A-40F1-8823-0B72FAEF3A48,page_view,ios,7.9.3,message_home,1,1,1,1,1,0,1,1,1,1]
+
+// df.printSchema
+/*
+   |-- cl_id: string (nullable = true)
+   |-- action: string (nullable = true)
+   |-- cl_type: string (nullable = true)
+   |-- app_version: string (nullable = true)
+   |-- page_name: string (nullable = true)
+   |-- extra: integer (nullable = false)
+   |-- referrer: integer (nullable = false)
+   |-- is_push: integer (nullable = false)
+   |-- in: integer (nullable = false)
+   |-- out: integer (nullable = false)
+   |-- referrer_id: integer (nullable = false)
+   |-- referrer_tab_name: integer (nullable = false)
+   |-- bz_id: integer (nullable = false)
+   |-- fake: integer (nullable = false)
+   |-- pv: integer (nullable = false)
 case class Record(
-  cl_id: String, action: String, app_version: String, page_name: String,
+  cl_id: String, action: String, cl_type: String, app_version: String, page_name: String,
   extra: Int, referrer: Int, is_push: Int, in: Int, out: Int,
-  referrer_id: Int, referrer_tab_name: Int, bz_id: Int, fake: Int,
-  pv: Int
+  referrer_id: Int, referrer_tab_name: Int, bz_id: Int, fake: Int, pv: Int
 )
+*/
 
 object pvCheker {
 
@@ -51,7 +71,14 @@ object pvCheker {
     import sc.sqlContext.implicits._
 
     val y = df.rdd.map {
-      case r: Record => Seq(r.extra, r.referrer, r.is_push, r.in, r.out, r.referrer_id, r.referrer_tab_name, r.bz_id)
+      case Row(
+        cl_id: String, action: String, cl_type: String, app_version: String, page_name: String,
+        extra: Int, referrer: Int, is_push: Int, in: Int, out: Int,
+        referrer_id: Int, referrer_tab_name: Int, bz_id: Int, fake: Int, pv: Int
+      ) => Seq(
+        extra, referrer, is_push, in,
+        out, referrer_id, referrer_tab_name, bz_id
+      ).map(_ * 1.0)
     }
 
     val z = y map {i => Vectors.dense(i.toArray[Double])}