yaravind
/ spark-duplicates.scala
Created
May 31, 2017 14:39
— forked from crocker/spark-duplicates.scala
Find duplicates in a Spark DataFrame
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| val transactions = spark.read | |
| .option("header", "true") | |
| .option("inferSchema", "true") | |
| .json("s3n://bucket-name/transaction.json") | |
| transactions.groupBy("id", "organization").count.sort($"count".desc).show |
yaravind
/ spark-compare-dataframes.scala
Created
May 31, 2017 14:38
— forked from crocker/spark-compare-dataframes.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| val today = LocalDate.now | |
| val todayTransactions = spark.read | |
| .option("header", "true") | |
| .option("inferSchema", "true") | |
| .json(s"s3n://bucket-name/${today}/transaction.json") | |
| val yesterdayTransactions = spark.read | |
| .option("header", "true") | |
| .option("inferSchema", "true") |
NewerOlder