Address comments.

Author: yanboliang

docs/ml-classification-regression.md

@@ -79,7 +79,7 @@ More details on parameters can be found in the [Python API documentation](api/py
 
 More details on parameters can be found in the [R API documentation](api/R/spark.logit.html).
 
-{% include_example r/ml/logit.R %}
+{% include_example binomial r/ml/logit.R %}
 </div>
 
 </div>
@@ -172,6 +172,13 @@ model with elastic net regularization.
 {% include_example python/ml/multiclass_logistic_regression_with_elastic_net.py %}
 </div>
 
+<div data-lang="r" markdown="1">
+
+More details on parameters can be found in the [R API documentation](api/R/spark.logit.html).
+
+{% include_example multinomial r/ml/logit.R %}
+</div>
+
 </div>
 
 

docs/sparkr.md

@@ -516,19 +516,19 @@ head(teenagers)
 
 SparkR supports the following machine learning algorithms currently:
 
-* `spark.glm` or `glm`: `Generalized Linear Model`
-* `spark.survreg`: `Accelerated Failure Time (AFT) Survival Regressio Model`
-* `spark.naiveBayes`: `Naive Bayes Model`
-* `spark.kmeans`: `KMeans Model`
-* `spark.logit`: `Logistic Regression Model`
-* `spark.isoreg`: `Isotonic Regression Model`
-* `spark.gaussianMixture`: `Gaussian Mixture Model`
-* `spark.lda`: `Latent Dirichlet Allocation (LDA) Model`
-* `spark.mlp`: `Multilayer Perceptron Classification Model`
-* `spark.gbt`: `Gradient Boosted Tree Model for Regression and Classification`
-* `spark.randomForest`: `Random Forest Model for Regression and Classification`
-* `spark.als`: `Alternating Least Squares (ALS) matrix factorization Model`
-* `spark.kstest`: `Kolmogorov-Smirnov Test`
+* [`spark.glm`](api/R/spark.glm.html) or [`glm`](api/R/glm.html): [`Generalized Linear Model`](ml-classification-regression.html#generalized-linear-regression)
+* [`spark.survreg`](api/R/spark.survreg.html): [`Accelerated Failure Time (AFT) Survival Regression Model`](ml-classification-regression.html#survival-regression)
+* [`spark.naiveBayes`](api/R/spark.naiveBayes.html): [`Naive Bayes Model`](ml-classification-regression.html#naive-bayes)
+* [`spark.kmeans`](api/R/spark.kmeans.html): [`KMeans Model`](ml-clustering.html#k-means)
+* [`spark.logit`](api/R/spark.logit.html): [`Logistic Regression Model`](ml-classification-regression.html#logistic-regression)
+* [`spark.isoreg`](api/R/spark.isoreg.html): [`Isotonic Regression Model`](ml-classification-regression.html#isotonic-regression)
+* [`spark.gaussianMixture`](api/R/spark.gaussianMixture.html): [`Gaussian Mixture Model`](ml-clustering.html#gaussian-mixture-model-gmm)
+* [`spark.lda`](api/R/spark.lda.html): [`Latent Dirichlet Allocation (LDA) Model`](ml-clustering.html#latent-dirichlet-allocation-lda)
+* [`spark.mlp`](api/R/spark.mlp.html): [`Multilayer Perceptron Classification Model`](ml-classification-regression.html#multilayer-perceptron-classifier)
+* [`spark.gbt`](api/R/spark.gbt.html): `Gradient Boosted Tree Model for` [`Regression`](ml-classification-regression.html#gradient-boosted-tree-regression) `and` [`Classification`](ml-classification-regression.html#gradient-boosted-tree-classifier)
+* [`spark.randomForest`](api/R/spark.randomForest.html): `Random Forest Model for` [`Regression`](ml-classification-regression.html#random-forest-regression) `and` [`Classification`](ml-classification-regression.html#random-forest-classifier)
+* [`spark.als`](api/R/spark.als.html): [`Alternating Least Squares (ALS) matrix factorization Model`](ml-collaborative-filtering.html#collaborative-filtering)
+* [`spark.kstest`](api/R/spark.kstest.html): `Kolmogorov-Smirnov Test`
 
 Under the hood, SparkR uses MLlib to train the model. Please refer to the corresponding section of MLlib user guide for example code.
 Users can call `summary` to print a summary of the fitted model, [predict](api/R/predict.html) to make predictions on new data, and [write.ml](api/R/write.ml.html)/[read.ml](api/R/read.ml.html) to save/load fitted models.

examples/src/main/r/ml/gaussianMixture.R

@@ -39,4 +39,4 @@ summary(model)
 # Prediction
 predictions <- predict(model, test)
 showDF(predictions)
-# $example off$
+# $example off$

examples/src/main/r/ml/isoreg.R

@@ -39,4 +39,4 @@ summary(model)
 # Prediction
 predictions <- predict(model, test)
 showDF(predictions)
-# $example off$
+# $example off$

examples/src/main/r/ml/kmeans.R

@@ -30,7 +30,7 @@ irisDF <- suppressWarnings(createDataFrame(iris))
 kmeansDF <- irisDF
 kmeansTestDF <- irisDF
 kmeansModel <- spark.kmeans(kmeansDF, ~ Sepal_Length + Sepal_Width + Petal_Length + Petal_Width,
-k = 3)
+                            k = 3)
 
 # Model summary
 summary(kmeansModel)

examples/src/main/r/ml/lda.R

@@ -31,7 +31,7 @@ training <- df
 test <- df
 
 # Fit a latent dirichlet allocation model with spark.lda
-model <- spark.lda(training, k=10, maxIter=10)
+model <- spark.lda(training, k = 10, maxIter = 10)
 
 # Model summary
 summary(model)
@@ -43,4 +43,4 @@ showDF(posterior)
 # The log perplexity of the LDA model
 logPerplexity <- spark.perplexity(model, test)
 print(paste0("The upper bound bound on perplexity: ", logPerplexity))
-# $example off$
+# $example off$

examples/src/main/r/ml/logit.R

@@ -24,13 +24,34 @@ library(SparkR)
 # Initialize SparkSession
 sparkR.session(appName = "SparkR-ML-logit-example")
 
-# $example on$
+# Binomial logistic regression
+
+# $example on:binomial$
 # Load training data
 df <- read.df("data/mllib/sample_libsvm_data.txt", source = "libsvm")
 training <- df
 test <- df
 
-# Fit an logistic regression model with spark.logit
+# Fit an binomial logistic regression model with spark.logit
+model <- spark.logit(training, label ~ features, maxIter = 10, regParam = 0.3, elasticNetParam = 0.8)
+
+# Model summary
+summary(model)
+
+# Prediction
+predictions <- predict(model, test)
+showDF(predictions)
+# $example off:binomial$
+
+# Multinomial logistic regression
+
+# $example on:multinomial$
+# Load training data
+df <- read.df("data/mllib/sample_multiclass_classification_data.txt", source = "libsvm")
+training <- df
+test <- df
+
+# Fit a multinomial logistic regression model with spark.logit
 model <- spark.logit(training, label ~ features, maxIter = 10, regParam = 0.3, elasticNetParam = 0.8)
 
 # Model summary
@@ -39,4 +60,4 @@ summary(model)
 # Prediction
 predictions <- predict(model, test)
 showDF(predictions)
-# $example off$
+# $example off:multinomial$

examples/src/main/r/ml/ml.R

@@ -59,6 +59,5 @@ model.summaries <- spark.lapply(families, train)
 # Print the summary of each model
 print(model.summaries)
 
-
 # Stop the SparkSession now
 sparkR.session.stop()

examples/src/main/r/ml/randomForest.R

@@ -33,7 +33,7 @@ training <- df
 test <- df
 
 # Fit a random forest classification model with spark.randomForest
-model <- spark.randomForest(training, label ~ features, "classification", numTrees=10)
+model <- spark.randomForest(training, label ~ features, "classification", numTrees = 10)
 
 # Model summary
 summary(model)
@@ -52,7 +52,7 @@ training <- df
 test <- df
 
 # Fit a random forest regression model with spark.randomForest
-model <- spark.randomForest(training, label ~ features, "regression", numTrees=10)
+model <- spark.randomForest(training, label ~ features, "regression", numTrees = 10)
 
 # Model summary
 summary(model)