[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.
This commit is contained in:
parent
24100f162d
commit
2c586f506d
|
@ -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()
|
||||
|
|
Loading…
Reference in a new issue