Commit 44cf12a4 authored by 高雅喆's avatar 高雅喆

add esmm data

parent fbe1d20d
...@@ -7,6 +7,7 @@ import org.apache.spark.sql.{SaveMode, TiContext} ...@@ -7,6 +7,7 @@ import org.apache.spark.sql.{SaveMode, TiContext}
import org.apache.log4j.{Level, Logger} import org.apache.log4j.{Level, Logger}
import scopt.OptionParser import scopt.OptionParser
import com.gmei.lib.AbstractParams import com.gmei.lib.AbstractParams
import org.apache.spark.sql.functions.lit
...@@ -62,9 +63,9 @@ object EsmmData { ...@@ -62,9 +63,9 @@ object EsmmData {
|and stat_date >'${stat_date}' |and stat_date >'${stat_date}'
""".stripMargin """.stripMargin
) )
imp_data.show() // imp_data.show()
println("imp_data.count()") // println("imp_data.count()")
println(imp_data.count()) // println(imp_data.count())
val clk_data = sc.sql( val clk_data = sc.sql(
...@@ -76,13 +77,13 @@ object EsmmData { ...@@ -76,13 +77,13 @@ object EsmmData {
|and stat_date >'${stat_date}' |and stat_date >'${stat_date}'
""".stripMargin """.stripMargin
) )
clk_data.show() // clk_data.show()
println("clk_data.count()") // println("clk_data.count()")
println(clk_data.count()) // println(clk_data.count())
val imp_data_filter = imp_data.except(clk_data) val imp_data_filter = imp_data.except(clk_data).withColumn("y",lit(0)).withColumn("z",lit(0))
imp_data_filter.createOrReplaceTempView("imp_data_filter") imp_data_filter.createOrReplaceTempView("imp_data_filter")
imp_data_filter.show() imp_data_filter.show()
println("imp_data_filter.count()") println("imp_data_filter.count()")
...@@ -103,14 +104,16 @@ object EsmmData { ...@@ -103,14 +104,16 @@ object EsmmData {
|and params['referrer'] = 'diary_detail' |and params['referrer'] = 'diary_detail'
""".stripMargin """.stripMargin
) )
cvr_data.createOrReplaceTempView("cvr_data")
cvr_data.show()
println("cvr_data.count()")
println(cvr_data.count())
val cvr_data_filter = cvr_data.withColumn("y",lit(1)).withColumn("z",lit(1))
cvr_data_filter.createOrReplaceTempView("cvr_data_filter")
cvr_data_filter.show()
println("cvr_data_filter.count()")
println(cvr_data_filter.count())
val clk_data_filter =clk_data.except(cvr_data)
val clk_data_filter =clk_data.except(cvr_data).withColumn("y",lit(1)).withColumn("z",lit(0))
clk_data_filter.createOrReplaceTempView("clk_data_filter") clk_data_filter.createOrReplaceTempView("clk_data_filter")
clk_data_filter.show() clk_data_filter.show()
println("clk_data_filter.count()") println("clk_data_filter.count()")
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment