diff options
author | Sun Rui <rui.sun@intel.com> | 2015-04-23 16:08:14 -0700 |
---|---|---|
committer | Shivaram Venkataraman <shivaram@cs.berkeley.edu> | 2015-04-23 16:08:14 -0700 |
commit | 73db132bf503341c7a5cf9409351c282a8464175 (patch) | |
tree | 978eecc5d5a1c5d5ab93ae25954b16d892fbd577 | |
parent | 6220d933e5ce4ba890f5d6a50a69b95d319dafb4 (diff) | |
download | spark-73db132bf503341c7a5cf9409351c282a8464175.tar.gz spark-73db132bf503341c7a5cf9409351c282a8464175.tar.bz2 spark-73db132bf503341c7a5cf9409351c282a8464175.zip |
[SPARK-6818] [SPARKR] Support column deletion in SparkR DataFrame API.
Author: Sun Rui <rui.sun@intel.com>
Closes #5655 from sun-rui/SPARK-6818 and squashes the following commits:
7c66570 [Sun Rui] [SPARK-6818][SPARKR] Support column deletion in SparkR DataFrame API.
-rw-r--r-- | R/pkg/R/DataFrame.R | 8 | ||||
-rw-r--r-- | R/pkg/inst/tests/test_sparkSQL.R | 5 |
2 files changed, 12 insertions, 1 deletions
diff --git a/R/pkg/R/DataFrame.R b/R/pkg/R/DataFrame.R index 861fe1c78b..b59b700af5 100644 --- a/R/pkg/R/DataFrame.R +++ b/R/pkg/R/DataFrame.R @@ -790,9 +790,12 @@ setMethod("$", signature(x = "DataFrame"), setMethod("$<-", signature(x = "DataFrame"), function(x, name, value) { - stopifnot(class(value) == "Column") + stopifnot(class(value) == "Column" || is.null(value)) cols <- columns(x) if (name %in% cols) { + if (is.null(value)) { + cols <- Filter(function(c) { c != name }, cols) + } cols <- lapply(cols, function(c) { if (c == name) { alias(value, name) @@ -802,6 +805,9 @@ setMethod("$<-", signature(x = "DataFrame"), }) nx <- select(x, cols) } else { + if (is.null(value)) { + return(x) + } nx <- withColumn(x, name, value) } x@sdf <- nx@sdf diff --git a/R/pkg/inst/tests/test_sparkSQL.R b/R/pkg/inst/tests/test_sparkSQL.R index 25831ae2d9..af7a6c5820 100644 --- a/R/pkg/inst/tests/test_sparkSQL.R +++ b/R/pkg/inst/tests/test_sparkSQL.R @@ -449,6 +449,11 @@ test_that("select operators", { df$age2 <- df$age * 2 expect_equal(columns(df), c("name", "age", "age2")) expect_equal(count(where(df, df$age2 == df$age * 2)), 2) + + df$age2 <- NULL + expect_equal(columns(df), c("name", "age")) + df$age3 <- NULL + expect_equal(columns(df), c("name", "age")) }) test_that("select with column", { |