aboutsummaryrefslogtreecommitdiff
path: root/examples/src/main/r/ml/kmeans.R
diff options
context:
space:
mode:
Diffstat (limited to 'examples/src/main/r/ml/kmeans.R')
-rw-r--r--examples/src/main/r/ml/kmeans.R10
1 files changed, 6 insertions, 4 deletions
diff --git a/examples/src/main/r/ml/kmeans.R b/examples/src/main/r/ml/kmeans.R
index 288e2f9724..824df20644 100644
--- a/examples/src/main/r/ml/kmeans.R
+++ b/examples/src/main/r/ml/kmeans.R
@@ -26,10 +26,12 @@ sparkR.session(appName = "SparkR-ML-kmeans-example")
# $example on$
# Fit a k-means model with spark.kmeans
-irisDF <- suppressWarnings(createDataFrame(iris))
-kmeansDF <- irisDF
-kmeansTestDF <- irisDF
-kmeansModel <- spark.kmeans(kmeansDF, ~ Sepal_Length + Sepal_Width + Petal_Length + Petal_Width,
+t <- as.data.frame(Titanic)
+training <- createDataFrame(t)
+df_list <- randomSplit(training, c(7,3), 2)
+kmeansDF <- df_list[[1]]
+kmeansTestDF <- df_list[[2]]
+kmeansModel <- spark.kmeans(kmeansDF, ~ Class + Sex + Age + Freq,
k = 3)
# Model summary