diff options
author | Dongjoon Hyun <dongjoon@apache.org> | 2016-06-16 20:35:17 -0700 |
---|---|---|
committer | Shivaram Venkataraman <shivaram@cs.berkeley.edu> | 2016-06-16 20:35:17 -0700 |
commit | 513a03e41e27d9c5f70911faccc5d3aecd8bdde9 (patch) | |
tree | 0b030b7d215d09fd12f6ef7274e91923915f2082 /R/pkg/inst | |
parent | 5fd20b66ffe18c05cf257af7f30d32464d2fe8e7 (diff) | |
download | spark-513a03e41e27d9c5f70911faccc5d3aecd8bdde9.tar.gz spark-513a03e41e27d9c5f70911faccc5d3aecd8bdde9.tar.bz2 spark-513a03e41e27d9c5f70911faccc5d3aecd8bdde9.zip |
[SPARK-15908][R] Add varargs-type dropDuplicates() function in SparkR
## What changes were proposed in this pull request?
This PR adds varargs-type `dropDuplicates` function to SparkR for API parity.
Refer to https://issues.apache.org/jira/browse/SPARK-15807, too.
## How was this patch tested?
Pass the Jenkins tests with new testcases.
Author: Dongjoon Hyun <dongjoon@apache.org>
Closes #13684 from dongjoon-hyun/SPARK-15908.
Diffstat (limited to 'R/pkg/inst')
-rw-r--r-- | R/pkg/inst/tests/testthat/test_sparkSQL.R | 8 |
1 files changed, 8 insertions, 0 deletions
diff --git a/R/pkg/inst/tests/testthat/test_sparkSQL.R b/R/pkg/inst/tests/testthat/test_sparkSQL.R index c11930ada6..11d69366df 100644 --- a/R/pkg/inst/tests/testthat/test_sparkSQL.R +++ b/R/pkg/inst/tests/testthat/test_sparkSQL.R @@ -796,6 +796,14 @@ test_that("distinct(), unique() and dropDuplicates() on DataFrames", { result[order(result$key, result$value1, result$value2), ], expected) + result <- collect(dropDuplicates(df, "key", "value1")) + expected <- rbind.data.frame( + c(1, 1, 1), c(1, 2, 1), c(2, 1, 2), c(2, 2, 2)) + names(expected) <- c("key", "value1", "value2") + expect_equivalent( + result[order(result$key, result$value1, result$value2), ], + expected) + result <- collect(dropDuplicates(df, "key")) expected <- rbind.data.frame( c(1, 1, 1), c(2, 1, 2)) |