Commit f3a3b672 authored by 张彦钊's avatar 张彦钊

增加分区

parent 271a6100
......@@ -65,7 +65,7 @@ object EsmmData {
|where cid_type = 'diary'
|and stat_date >'${stat_date}'
""".stripMargin
)
).repartition(200)
// imp_data.show()
// println("imp_data.count()")
// println(imp_data.count())
......@@ -79,7 +79,7 @@ object EsmmData {
|where cid_type = 'diary'
|and stat_date >'${stat_date}'
""".stripMargin
)
).repartition(200)
// clk_data.show()
// println("clk_data.count()")
// println(clk_data.count())
......@@ -106,7 +106,7 @@ object EsmmData {
|and params['page_name'] = 'welfare_detail'
|and params['referrer'] = 'diary_detail'
""".stripMargin
)
).repartition(200)
val cvr_data_filter = cvr_data.withColumn("y",lit(1)).withColumn("z",lit(1))
// cvr_data_filter.createOrReplaceTempView("cvr_data_filter")
......@@ -268,7 +268,7 @@ object EsmmPredData {
|select device_id,city_id,search_queue as merge_queue from search_queue) as tmp1
|where tmp1.device_id in (select distinct device_id from esmm_train_data)
""".stripMargin
)
).repartition(200)
raw_data.show()
......@@ -286,7 +286,7 @@ object EsmmPredData {
s"""
|select device_id,city_id,merge_queue from raw_data1 limit 10000
""".stripMargin
)
).repartition(200)
raw_data2.createOrReplaceTempView("raw_data2")
println(raw_data2.count())
raw_data2.show()
......@@ -295,7 +295,7 @@ object EsmmPredData {
s"""
|select device_id,city_id as ucity_id,explode(split(merge_queue, ',')) as cid_id from raw_data2
""".stripMargin
)
).repartition(200)
raw_data3.createOrReplaceTempView("raw_data")
println(raw_data3.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