diff options
| author | Dongjoon Hyun <dongjoon@apache.org> | 2016-06-17 16:07:33 -0700 |
|---|---|---|
| committer | Shivaram Venkataraman <shivaram@cs.berkeley.edu> | 2016-06-17 16:07:33 -0700 |
| commit | 7d65a0db4a231882200513836f2720f59b35f364 (patch) | |
| tree | d178328d8cdeeda2078bf371068985891567348d /R/pkg/inst/tests/testthat/test_sparkSQL.R | |
| parent | ef3cc4fc096e831823d62af4fd2a12ae88d434b4 (diff) | |
| download | spark-7d65a0db4a231882200513836f2720f59b35f364.tar.gz spark-7d65a0db4a231882200513836f2720f59b35f364.tar.bz2 spark-7d65a0db4a231882200513836f2720f59b35f364.zip | |
[SPARK-16005][R] Add `randomSplit` to SparkR
## What changes were proposed in this pull request?
This PR adds `randomSplit` to SparkR for API parity.
## How was this patch tested?
Pass the Jenkins tests (with new testcase.)
Author: Dongjoon Hyun <dongjoon@apache.org>
Closes #13721 from dongjoon-hyun/SPARK-16005.
Diffstat (limited to 'R/pkg/inst/tests/testthat/test_sparkSQL.R')
| -rw-r--r-- | R/pkg/inst/tests/testthat/test_sparkSQL.R | 18 |
1 files changed, 18 insertions, 0 deletions
diff --git a/R/pkg/inst/tests/testthat/test_sparkSQL.R b/R/pkg/inst/tests/testthat/test_sparkSQL.R index 7aa03a9048..607bd9c12f 100644 --- a/R/pkg/inst/tests/testthat/test_sparkSQL.R +++ b/R/pkg/inst/tests/testthat/test_sparkSQL.R @@ -2280,6 +2280,24 @@ test_that("createDataFrame sqlContext parameter backward compatibility", { expect_equal(collect(before), collect(after)) }) +test_that("randomSplit", { + num <- 4000 + df <- createDataFrame(data.frame(id = 1:num)) + + weights <- c(2, 3, 5) + df_list <- randomSplit(df, weights) + expect_equal(length(weights), length(df_list)) + counts <- sapply(df_list, count) + expect_equal(num, sum(counts)) + expect_true(all(sapply(abs(counts / num - weights / sum(weights)), function(e) { e < 0.05 }))) + + df_list <- randomSplit(df, weights, 0) + expect_equal(length(weights), length(df_list)) + counts <- sapply(df_list, count) + expect_equal(num, sum(counts)) + expect_true(all(sapply(abs(counts / num - weights / sum(weights)), function(e) { e < 0.05 }))) +}) + unlink(parquetPath) unlink(jsonPath) unlink(jsonPathNa) |