[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.

Author: wangmiao1981

R/pkg/R/mllib_classification.R

@@ -75,9 +75,9 @@ setClass("NaiveBayesModel", representation(jobj = "jobj"))
 #' @examples
 #' \dontrun{
 #' sparkR.session()
-#' df <- createDataFrame(iris)
-#' training <- df[df$Species %in% c("versicolor", "virginica"), ]
-#' model <- spark.svmLinear(training, Species ~ ., regParam = 0.5)
+#' t <- as.data.frame(Titanic)
+#' training <- createDataFrame(t)
+#' model <- spark.svmLinear(training, Survived ~ ., regParam = 0.5)
 #' summary <- summary(model)
 #'
 #' # fitted values on training data
@@ -220,9 +220,9 @@ function(object, path, overwrite = FALSE) {
 #' \dontrun{
 #' sparkR.session()
 #' # binary logistic regression
-#' df <- createDataFrame(iris)
-#' training <- df[df$Species %in% c("versicolor", "virginica"), ]
-#' model <- spark.logit(training, Species ~ ., regParam = 0.5)
+#' t <- as.data.frame(Titanic)
+#' training <- createDataFrame(t)
+#' model <- spark.logit(training, Survived ~ ., regParam = 0.5)
 #' summary <- summary(model)
 #'
 #' # fitted values on training data
@@ -239,8 +239,7 @@ function(object, path, overwrite = FALSE) {
 #'
 #' # multinomial logistic regression
 #'
-#' df <- createDataFrame(iris)
-#' model <- spark.logit(df, Species ~ ., regParam = 0.5)
+#' model <- spark.logit(training, Class ~ ., regParam = 0.5)
 #' summary <- summary(model)
 #'
 #' }

R/pkg/R/mllib_clustering.R

@@ -72,8 +72,9 @@ setClass("LDAModel", representation(jobj = "jobj"))
 #' @examples
 #' \dontrun{
 #' sparkR.session()
-#' df <- createDataFrame(iris)
-#' model <- spark.bisectingKmeans(df, Sepal_Length ~ Sepal_Width, k = 4)
+#' t <- as.data.frame(Titanic)
+#' df <- createDataFrame(t)
+#' model <- spark.bisectingKmeans(df, Class ~ Survived, k = 4)
 #' summary(model)
 #'
 #' # get fitted result from a bisecting k-means model
@@ -82,7 +83,7 @@ setClass("LDAModel", representation(jobj = "jobj"))
 #'
 #' # fitted values on training data
 #' fitted <- predict(model, df)
-#' head(select(fitted, "Sepal_Length", "prediction"))
+#' head(select(fitted, "Class", "prediction"))
 #'
 #' # save fitted model to input path
 #' path <- "path/to/model"
@@ -338,14 +339,14 @@ setMethod("write.ml", signature(object = "GaussianMixtureModel", path = "charact
 #' @examples
 #' \dontrun{
 #' sparkR.session()
-#' data(iris)
-#' df <- createDataFrame(iris)
-#' model <- spark.kmeans(df, Sepal_Length ~ Sepal_Width, k = 4, initMode = "random")
+#' t <- as.data.frame(Titanic)
+#' df <- createDataFrame(t)
+#' model <- spark.kmeans(df, Class ~ Survived, k = 4, initMode = "random")
 #' summary(model)
 #'
 #' # fitted values on training data
 #' fitted <- predict(model, df)
-#' head(select(fitted, "Sepal_Length", "prediction"))
+#' head(select(fitted, "Class", "prediction"))
 #'
 #' # save fitted model to input path
 #' path <- "path/to/model"

R/pkg/R/mllib_regression.R

@@ -68,14 +68,14 @@ setClass("IsotonicRegressionModel", representation(jobj = "jobj"))
 #' @examples
 #' \dontrun{
 #' sparkR.session()
-#' data(iris)
-#' df <- createDataFrame(iris)
-#' model <- spark.glm(df, Sepal_Length ~ Sepal_Width, family = "gaussian")
+#' t <- as.data.frame(Titanic)
+#' df <- createDataFrame(t)
+#' model <- spark.glm(df, Freq ~ Sex + Age, family = "gaussian")
 #' summary(model)
 #'
 #' # fitted values on training data
 #' fitted <- predict(model, df)
-#' head(select(fitted, "Sepal_Length", "prediction"))
+#' head(select(fitted, "Freq", "prediction"))
 #'
 #' # save fitted model to input path
 #' path <- "path/to/model"
@@ -137,9 +137,9 @@ setMethod("spark.glm", signature(data = "SparkDataFrame", formula = "formula"),
 #' @examples
 #' \dontrun{
 #' sparkR.session()
-#' data(iris)
-#' df <- createDataFrame(iris)
-#' model <- glm(Sepal_Length ~ Sepal_Width, df, family = "gaussian")
+#' t <- as.data.frame(Titanic)
+#' df <- createDataFrame(t)
+#' model <- glm(Freq ~ Sex + Age, df, family = "gaussian")
 #' summary(model)
 #' }
 #' @note glm since 1.5.0

R/pkg/R/mllib_tree.R

@@ -143,14 +143,15 @@ print.summary.treeEnsemble <- function(x) {
 #'
 #' # fit a Gradient Boosted Tree Classification Model
 #' # label must be binary - Only binary classification is supported for GBT.
-#' df <- createDataFrame(iris[iris$Species != "virginica", ])
-#' model <- spark.gbt(df, Species ~ Petal_Length + Petal_Width, "classification")
+#' t <- as.data.frame(Titanic)
+#' df <- createDataFrame(t)
+#' model <- spark.gbt(df, Survived ~ Age + Freq, "classification")
 #'
 #' # numeric label is also supported
-#' iris2 <- iris[iris$Species != "virginica", ]
-#' iris2$NumericSpecies <- ifelse(iris2$Species == "setosa", 0, 1)
-#' df <- createDataFrame(iris2)
-#' model <- spark.gbt(df, NumericSpecies ~ ., type = "classification")
+#' t2 <- as.data.frame(Titanic)
+#' t2$NumericGender <- ifelse(t2$Sex == "Male", 0, 1)
+#' df <- createDataFrame(t2)
+#' model <- spark.gbt(df, NumericGender ~ ., type = "classification")
 #' }
 #' @note spark.gbt since 2.1.0
 setMethod("spark.gbt", signature(data = "SparkDataFrame", formula = "formula"),
@@ -351,8 +352,9 @@ setMethod("write.ml", signature(object = "GBTClassificationModel", path = "chara
 #' summary(savedModel)
 #'
 #' # fit a Random Forest Classification Model
-#' df <- createDataFrame(iris)
-#' model <- spark.randomForest(df, Species ~ Petal_Length + Petal_Width, "classification")
+#' t <- as.data.frame(Titanic)
+#' df <- createDataFrame(t)
+#' model <- spark.randomForest(df, Survived ~ Freq + Age, "classification")
 #' }
 #' @note spark.randomForest since 2.1.0
 setMethod("spark.randomForest", signature(data = "SparkDataFrame", formula = "formula"),

R/pkg/vignettes/sparkr-vignettes.Rmd

@@ -565,11 +565,10 @@ We use a simple example to demonstrate `spark.logit` usage. In general, there ar
 and 3). Obtain the coefficient matrix of the fitted model using `summary` and use the model for prediction with `predict`.
 
 Binomial logistic regression
-```{r, warning=FALSE}
-df <- createDataFrame(iris)
-# Create a DataFrame containing two classes
-training <- df[df$Species %in% c("versicolor", "virginica"), ]
-model <- spark.logit(training, Species ~ ., regParam = 0.00042)
+```{r}
+t <- as.data.frame(Titanic)
+training <- createDataFrame(t)
+model <- spark.logit(training, Survived ~ ., regParam = 0.04741301)
 summary(model)
 ```
 
@@ -579,10 +578,11 @@ fitted <- predict(model, training)
 ```
 
 Multinomial logistic regression against three classes
-```{r, warning=FALSE}
-df <- createDataFrame(iris)
+```{r}
+t <- as.data.frame(Titanic)
+training <- createDataFrame(t)
 # Note in this case, Spark infers it is multinomial logistic regression, so family = "multinomial" is optional.
-model <- spark.logit(df, Species ~ ., regParam = 0.056)
+model <- spark.logit(training, Class ~ ., regParam = 0.07815179)
 summary(model)
 ```
 
@@ -609,11 +609,12 @@ MLPC employs backpropagation for learning the model. We use the logistic loss fu
 
 `spark.mlp` requires at least two columns in `data`: one named `"label"` and the other one `"features"`. The `"features"` column should be in libSVM-format.
 
-We use iris data set to show how to use `spark.mlp` in classification.
-```{r, warning=FALSE}
-df <- createDataFrame(iris)
+We use Titanic data set to show how to use `spark.mlp` in classification.
+```{r}
+t <- as.data.frame(Titanic)
+training <- createDataFrame(t)
 # fit a Multilayer Perceptron Classification Model
-model <- spark.mlp(df, Species ~ ., blockSize = 128, layers = c(4, 3), solver = "l-bfgs", maxIter = 100, tol = 0.5, stepSize = 1, seed = 1, initialWeights = c(0, 0, 0, 0, 0, 5, 5, 5, 5, 5, 9, 9, 9, 9, 9))
+model <- spark.mlp(training, Survived ~ Age + Sex, blockSize = 128, layers = c(2, 3), solver = "l-bfgs", maxIter = 100, tol = 0.5, stepSize = 1, seed = 1, initialWeights = c( 0, 0, 0, 5, 5, 5, 9, 9, 9))
 ```
 
 To avoid lengthy display, we only present partial results of the model summary. You can check the full result from your sparkR shell.
@@ -630,7 +631,7 @@ options(ops)
 ```
 ```{r}
 # make predictions use the fitted model
-predictions <- predict(model, df)
+predictions <- predict(model, training)
 head(select(predictions, predictions$prediction))
 ```
 
@@ -769,12 +770,13 @@ predictions <- predict(rfModel, df)
 
 `spark.bisectingKmeans` is a kind of [hierarchical clustering](https://en.wikipedia.org/wiki/Hierarchical_clustering) using a divisive (or "top-down") approach: all observations start in one cluster, and splits are performed recursively as one moves down the hierarchy.
 
-```{r, warning=FALSE}
-df <- createDataFrame(iris)
-model <- spark.bisectingKmeans(df, Sepal_Length ~ Sepal_Width, k = 4)
+```{r}
+t <- as.data.frame(Titanic)
+training <- createDataFrame(t)
+model <- spark.bisectingKmeans(training, Class ~ Survived, k = 4)
 summary(model)
-fitted <- predict(model, df)
-head(select(fitted, "Sepal_Length", "prediction"))
+fitted <- predict(model, training)
+head(select(fitted, "Class", "prediction"))
 ```
 
 #### Gaussian Mixture Model
@@ -912,9 +914,10 @@ testSummary
 
 ### Model Persistence
 The following example shows how to save/load an ML model by SparkR.
-```{r, warning=FALSE}
-irisDF <- createDataFrame(iris)
-gaussianGLM <- spark.glm(irisDF, Sepal_Length ~ Sepal_Width + Species, family = "gaussian")
+```{r}
+t <- as.data.frame(Titanic)
+training <- createDataFrame(t)
+gaussianGLM <- spark.glm(training, Freq ~ Sex + Age, family = "gaussian")
 
 # Save and then load a fitted MLlib model
 modelPath <- tempfile(pattern = "ml", fileext = ".tmp")
@@ -925,7 +928,7 @@ gaussianGLM2 <- read.ml(modelPath)
 summary(gaussianGLM2)
 
 # Check model prediction
-gaussianPredictions <- predict(gaussianGLM2, irisDF)
+gaussianPredictions <- predict(gaussianGLM2, training)
 head(gaussianPredictions)
 
 unlink(modelPath)

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()

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)

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

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")