diff options
author | Sun Rui <rui.sun@intel.com> | 2015-10-13 22:31:23 -0700 |
---|---|---|
committer | Shivaram Venkataraman <shivaram@cs.berkeley.edu> | 2015-10-13 22:31:23 -0700 |
commit | 390b22fad69a33eb6daee25b6b858a2e768670a5 (patch) | |
tree | 34a5ada11ef2823c4b082b604b3a9d903647e325 /R/pkg/inst/tests/test_sparkSQL.R | |
parent | 8b32885704502ab2a715cf5142d7517181074428 (diff) | |
download | spark-390b22fad69a33eb6daee25b6b858a2e768670a5.tar.gz spark-390b22fad69a33eb6daee25b6b858a2e768670a5.tar.bz2 spark-390b22fad69a33eb6daee25b6b858a2e768670a5.zip |
[SPARK-10996] [SPARKR] Implement sampleBy() in DataFrameStatFunctions.
Author: Sun Rui <rui.sun@intel.com>
Closes #9023 from sun-rui/SPARK-10996.
Diffstat (limited to 'R/pkg/inst/tests/test_sparkSQL.R')
-rw-r--r-- | R/pkg/inst/tests/test_sparkSQL.R | 10 |
1 files changed, 10 insertions, 0 deletions
diff --git a/R/pkg/inst/tests/test_sparkSQL.R b/R/pkg/inst/tests/test_sparkSQL.R index 46cab7646d..e1b42b0804 100644 --- a/R/pkg/inst/tests/test_sparkSQL.R +++ b/R/pkg/inst/tests/test_sparkSQL.R @@ -1416,6 +1416,16 @@ test_that("freqItems() on a DataFrame", { expect_identical(result[[2]], list(list(-1, -99))) }) +test_that("sampleBy() on a DataFrame", { + l <- lapply(c(0:99), function(i) { as.character(i %% 3) }) + df <- createDataFrame(sqlContext, l, "key") + fractions <- list("0" = 0.1, "1" = 0.2) + sample <- sampleBy(df, "key", fractions, 0) + result <- collect(orderBy(count(groupBy(sample, "key")), "key")) + expect_identical(as.list(result[1, ]), list(key = "0", count = 2)) + expect_identical(as.list(result[2, ]), list(key = "1", count = 10)) +}) + test_that("SQL error message is returned from JVM", { retError <- tryCatch(sql(sqlContext, "select * from blah"), error = function(e) e) expect_equal(grepl("Table Not Found: blah", retError), TRUE) |