sample 算子_算子：sample(false, 0.1)抽样数据

抽样示例操作：

scala> import org.apache.spark.sql.hive.HiveContext

import org.apache.spark.sql.hive.HiveContext

scala> val hiveContext = new HiveContext(sc)

17/11/07 17:19:36 WARN SessionState: load mapred-default.xml, HIVE_CONF_DIR env not found!

17/11/07 17:19:37 WARN SessionState: load mapred-default.xml, HIVE_CONF_DIR env not found!

hiveContext: org.apache.spark.sql.hive.HiveContext = org.apache.spark.sql.hive.HiveContext@14cc2fdd

scala> hiveContext.sql("use my_hive_db")

17/11/07 17:19:40 WARN SessionState: METASTORE_FILTER_HOOK will be ignored, since hive.security.authorization.manager is set to instance of HiveAuthorizerFactory.

17/11/07 17:19:40 WARN UserGroupInformation: No groups available for user acount_rc

res20: org.apache.spark.sql.DataFrame = [result: string]

scala> val sampledPairs = hiveContext.sql(