Repository: spark
Updated Branches:
refs/heads/branch-1.5 0eb233507 -> dac83094f
[SPARK-11542] [SPARKR] fix glm with long fomular
Because deparse() will break the long string into multiple lines, the
deserialization will fail
Author: Davies Liu <dav...@databricks.com>
Closes #9510 from davies/fix_glm.
(cherry picked from commit 244010624200eddea6dfd1b2c89f40be45212e96)
Signed-off-by: Davies Liu <davies....@gmail.com>
Conflicts:
R/pkg/R/mllib.R
Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/dac83094
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/dac83094
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/dac83094
Branch: refs/heads/branch-1.5
Commit: dac83094f52edd9ba3a2072b1b7f3186f1a995b7
Parents: 0eb2335
Author: Davies Liu <dav...@databricks.com>
Authored: Thu Nov 5 16:34:10 2015 -0800
Committer: Davies Liu <davies....@gmail.com>
Committed: Thu Nov 5 16:37:57 2015 -0800
----------------------------------------------------------------------
R/pkg/R/mllib.R | 3 ++-
R/pkg/inst/tests/test_mllib.R | 12 ++++++++++++
2 files changed, 14 insertions(+), 1 deletion(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/spark/blob/dac83094/R/pkg/R/mllib.R
----------------------------------------------------------------------
diff --git a/R/pkg/R/mllib.R b/R/pkg/R/mllib.R
index cea3d76..5e5d458 100644
--- a/R/pkg/R/mllib.R
+++ b/R/pkg/R/mllib.R
@@ -46,8 +46,9 @@ setClass("PipelineModel", representation(model = "jobj"))
setMethod("glm", signature(formula = "formula", family = "ANY", data =
"DataFrame"),
function(formula, family = c("gaussian", "binomial"), data, lambda =
0, alpha = 0) {
family <- match.arg(family)
+ formula <- paste(deparse(formula), collapse="")
model <- callJStatic("org.apache.spark.ml.api.r.SparkRWrappers",
- "fitRModelFormula", deparse(formula),
data@sdf, family, lambda,
+ "fitRModelFormula", formula, data@sdf,
family, lambda,
alpha)
return(new("PipelineModel", model = model))
})
http://git-wip-us.apache.org/repos/asf/spark/blob/dac83094/R/pkg/inst/tests/test_mllib.R
----------------------------------------------------------------------
diff --git a/R/pkg/inst/tests/test_mllib.R b/R/pkg/inst/tests/test_mllib.R
index f272de7..18d58ba 100644
--- a/R/pkg/inst/tests/test_mllib.R
+++ b/R/pkg/inst/tests/test_mllib.R
@@ -33,6 +33,18 @@ test_that("glm and predict", {
expect_equal(typeof(take(select(prediction, "prediction"), 1)$prediction),
"double")
})
+test_that("glm should work with long formula", {
+ training <- createDataFrame(sqlContext, iris)
+ training$LongLongLongLongLongName <- training$Sepal_Width
+ training$VeryLongLongLongLonLongName <- training$Sepal_Length
+ training$AnotherLongLongLongLongName <- training$Species
+ model <- glm(LongLongLongLongLongName ~ VeryLongLongLongLonLongName +
AnotherLongLongLongLongName,
+ data = training)
+ vals <- collect(select(predict(model, training), "prediction"))
+ rVals <- predict(glm(Sepal.Width ~ Sepal.Length + Species, data = iris),
iris)
+ expect_true(all(abs(rVals - vals) < 1e-6), rVals - vals)
+})
+
test_that("predictions match with native glm", {
training <- createDataFrame(sqlContext, iris)
model <- glm(Sepal_Width ~ Sepal_Length + Species, data = training)
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org
For additional commands, e-mail: commits-h...@spark.apache.org
