[SPARK-19460][SPARKR] Update dataset used in R documentation, examples to reduce warning noise and confusions

## What changes were proposed in this pull request?

Replace `iris` dataset with `Titanic` or other dataset in example and document.

## How was this patch tested?

Manual and existing test

Author: wm624@hotmail.com <wm624@hotmail.com>

Closes #17032 from wangmiao1981/example.

4 files changed, 28 insertions, 22 deletions

diff --git a/examples/src/main/r/ml/bisectingKmeans.R b/examples/src/main/r/ml/bisectingKmeans.R
index 5fb5bfb0fa..b3eaa6dd86 100644
--- a/examples/src/main/r/ml/bisectingKmeans.R
+++ b/examples/src/main/r/ml/bisectingKmeans.R
@@ -25,20 +25,21 @@ library(SparkR)
 sparkR.session(appName = "SparkR-ML-bisectingKmeans-example")
 
 # $example on$
-irisDF <- createDataFrame(iris)
+t <- as.data.frame(Titanic)
+training <- createDataFrame(t)
 
 # Fit bisecting k-means model with four centers
-model <- spark.bisectingKmeans(df, Sepal_Length ~ Sepal_Width, k = 4)
+model <- spark.bisectingKmeans(training, Class ~ Survived, k = 4)
 
 # get fitted result from a bisecting k-means model
 fitted.model <- fitted(model, "centers")
 
 # Model summary
-summary(fitted.model)
+head(summary(fitted.model))
 
 # fitted values on training data
-fitted <- predict(model, df)
-head(select(fitted, "Sepal_Length", "prediction"))
+fitted <- predict(model, training)
+head(select(fitted, "Class", "prediction"))
 # $example off$
 
 sparkR.session.stop()
diff --git a/examples/src/main/r/ml/glm.R b/examples/src/main/r/ml/glm.R
index e41af97751..ee13910382 100644
--- a/examples/src/main/r/ml/glm.R
+++ b/examples/src/main/r/ml/glm.R
@@ -25,11 +25,12 @@ library(SparkR)
 sparkR.session(appName = "SparkR-ML-glm-example")
 
 # $example on$
-irisDF <- suppressWarnings(createDataFrame(iris))
+training <- read.df("data/mllib/sample_multiclass_classification_data.txt", source = "libsvm")
 # Fit a generalized linear model of family "gaussian" with spark.glm
-gaussianDF <- irisDF
-gaussianTestDF <- irisDF
-gaussianGLM <- spark.glm(gaussianDF, Sepal_Length ~ Sepal_Width + Species, family = "gaussian")
+df_list <- randomSplit(training, c(7,3), 2)
+gaussianDF <- df_list[[1]]
+gaussianTestDF <- df_list[[2]]
+gaussianGLM <- spark.glm(gaussianDF, label ~ features, family = "gaussian")
 
 # Model summary
 summary(gaussianGLM)
@@ -39,14 +40,15 @@ gaussianPredictions <- predict(gaussianGLM, gaussianTestDF)
 head(gaussianPredictions)
 
 # Fit a generalized linear model with glm (R-compliant)
-gaussianGLM2 <- glm(Sepal_Length ~ Sepal_Width + Species, gaussianDF, family = "gaussian")
+gaussianGLM2 <- glm(label ~ features, gaussianDF, family = "gaussian")
 summary(gaussianGLM2)
 
 # Fit a generalized linear model of family "binomial" with spark.glm
-# Note: Filter out "setosa" from label column (two labels left) to match "binomial" family.
-binomialDF <- filter(irisDF, irisDF$Species != "setosa")
-binomialTestDF <- binomialDF
-binomialGLM <- spark.glm(binomialDF, Species ~ Sepal_Length + Sepal_Width, family = "binomial")
+training2 <- read.df("data/mllib/sample_binary_classification_data.txt", source = "libsvm")
+df_list2 <- randomSplit(training2, c(7,3), 2)
+binomialDF <- df_list2[[1]]
+binomialTestDF <- df_list2[[2]]
+binomialGLM <- spark.glm(binomialDF, label ~ features, family = "binomial")
 
 # Model summary
 summary(binomialGLM)
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
diff --git a/examples/src/main/r/ml/ml.R b/examples/src/main/r/ml/ml.R
index b96819418b..41b7867f64 100644
--- a/examples/src/main/r/ml/ml.R
+++ b/examples/src/main/r/ml/ml.R
@@ -26,11 +26,12 @@ sparkR.session(appName = "SparkR-ML-example")
 
 ############################ model read/write ##############################################
 # $example on:read_write$
-irisDF <- suppressWarnings(createDataFrame(iris))
+training <- read.df("data/mllib/sample_multiclass_classification_data.txt", source = "libsvm")
 # Fit a generalized linear model of family "gaussian" with spark.glm
-gaussianDF <- irisDF
-gaussianTestDF <- irisDF
-gaussianGLM <- spark.glm(gaussianDF, Sepal_Length ~ Sepal_Width + Species, family = "gaussian")
+df_list <- randomSplit(training, c(7,3), 2)
+gaussianDF <- df_list[[1]]
+gaussianTestDF <- df_list[[2]]
+gaussianGLM <- spark.glm(gaussianDF, label ~ features, family = "gaussian")
 
 # Save and then load a fitted MLlib model
 modelPath <- tempfile(pattern = "ml", fileext = ".tmp")