aboutsummaryrefslogtreecommitdiff
path: root/examples/src
diff options
context:
space:
mode:
authorYanbo Liang <ybliang8@gmail.com>2017-01-12 00:58:30 -0800
committerYanbo Liang <ybliang8@gmail.com>2017-01-12 00:58:30 -0800
commit2c586f506de9e2ba592afae1f0c73b6ae631bb96 (patch)
treeb46e4b08c3b733c34b23d069714324649fbbad7a /examples/src
parent24100f162dadb80400cb3e0bc94e4282f10f0c84 (diff)
downloadspark-2c586f506de9e2ba592afae1f0c73b6ae631bb96.tar.gz
spark-2c586f506de9e2ba592afae1f0c73b6ae631bb96.tar.bz2
spark-2c586f506de9e2ba592afae1f0c73b6ae631bb96.zip
[SPARK-19158][SPARKR][EXAMPLES] Fix ml.R example fails due to lack of e1071 package.
## What changes were proposed in this pull request? ```ml.R``` example depends on ```e1071``` package, if it's not available in users' environment, it will fail. I think the example should not depends on third-party packages, so I update it to remove the dependency. ## How was this patch tested? Manual test. Author: Yanbo Liang <ybliang8@gmail.com> Closes #16548 from yanboliang/spark-19158.
Diffstat (limited to 'examples/src')
-rw-r--r--examples/src/main/r/ml/ml.R15
1 files changed, 7 insertions, 8 deletions
diff --git a/examples/src/main/r/ml/ml.R b/examples/src/main/r/ml/ml.R
index d601590c22..05f5199aeb 100644
--- a/examples/src/main/r/ml/ml.R
+++ b/examples/src/main/r/ml/ml.R
@@ -49,17 +49,16 @@ unlink(modelPath)
############################ fit models with spark.lapply #####################################
# Perform distributed training of multiple models with spark.lapply
-costs <- exp(seq(from = log(1), to = log(1000), length.out = 5))
-train <- function(cost) {
- stopifnot(requireNamespace("e1071", quietly = TRUE))
- model <- e1071::svm(Species ~ ., data = iris, cost = cost)
- summary(model)
+algorithms <- c("Hartigan-Wong", "Lloyd", "MacQueen")
+train <- function(algorithm) {
+ model <- kmeans(x = iris[1:4], centers = 3, algorithm = algorithm)
+ model$withinss
}
-model.summaries <- spark.lapply(costs, train)
+model.withinss <- spark.lapply(algorithms, train)
-# Print the summary of each model
-print(model.summaries)
+# Print the within-cluster sum of squares for each model
+print(model.withinss)
# Stop the SparkSession now
sparkR.session.stop()