diff --git a/R/pkg/R/mllib.R b/R/pkg/R/mllib.R
index f46681149d5a..02380900dd63 100644
--- a/R/pkg/R/mllib.R
+++ b/R/pkg/R/mllib.R
@@ -19,11 +19,11 @@
 
 # Integration with R's standard functions.
 # Most of MLlib's argorithms are provided in two flavours:
-# - a specialization of the default R methods (glm). These methods try to respect
+# - a specialization of the default R methods (such as glm). These methods try to respect
 #   the inputs and the outputs of R's method to the largest extent, but some small differences
 #   may exist.
-# - a set of methods that reflect the arguments of the other languages supported by Spark. These
-#   methods are prefixed with the `spark.` prefix: spark.glm, spark.kmeans, etc.
+# - a set of methods that reflect the arguments of other languages supported by Spark. These
+#   methods are prefixed with `spark.`: spark.glm, spark.kmeans, etc.
 
 #' @title S4 class that represents a generalized linear model
 #' @param jobj a Java object reference to the backing Scala GeneralizedLinearRegressionWrapper
@@ -35,7 +35,7 @@ setClass("GeneralizedLinearRegressionModel", representation(jobj = "jobj"))
 #' @export
 setClass("NaiveBayesModel", representation(jobj = "jobj"))
 
-#' @title S4 class that represents a AFTSurvivalRegressionModel
+#' @title S4 class that represents an AFTSurvivalRegressionModel
 #' @param jobj a Java object reference to the backing Scala AFTSurvivalRegressionWrapper
 #' @export
 setClass("AFTSurvivalRegressionModel", representation(jobj = "jobj"))
@@ -45,7 +45,7 @@ setClass("AFTSurvivalRegressionModel", representation(jobj = "jobj"))
 #' @export
 setClass("KMeansModel", representation(jobj = "jobj"))
 
-#' Fits a generalized linear model
+#' Fit a generalized linear model
 #'
 #' Fits a generalized linear model against a Spark DataFrame.
 #'
@@ -56,10 +56,11 @@ setClass("KMeansModel", representation(jobj = "jobj"))
 #'               This can be a character string naming a family function, a family function or
 #'               the result of a call to a family function. Refer R family at
 #'               \url{https://stat.ethz.ch/R-manual/R-devel/library/stats/html/family.html}.
-#' @param epsilon Positive convergence tolerance of iterations.
-#' @param maxit Integer giving the maximal number of IRLS iterations.
+#' @param tol Positive convergence tolerance of iterations.
+#' @param maxIter Integer giving the maximal number of IRLS iterations.
 #' @return a fitted generalized linear model
 #' @rdname spark.glm
+#' @name spark.glm
 #' @export
 #' @examples
 #' \dontrun{
@@ -67,33 +68,31 @@ setClass("KMeansModel", representation(jobj = "jobj"))
 #' sqlContext <- sparkRSQL.init(sc)
 #' data(iris)
 #' df <- createDataFrame(sqlContext, iris)
-#' model <- spark.glm(df, Sepal_Length ~ Sepal_Width, family="gaussian")
+#' model <- spark.glm(df, Sepal_Length ~ Sepal_Width, family = "gaussian")
 #' summary(model)
 #' }
-setMethod(
-    "spark.glm",
-    signature(data = "SparkDataFrame", formula = "formula"),
-    function(data, formula, family = gaussian, epsilon = 1e-06, maxit = 25) {
-        if (is.character(family)) {
-            family <- get(family, mode = "function", envir = parent.frame())
-        }
-        if (is.function(family)) {
-            family <- family()
-        }
-        if (is.null(family$family)) {
-            print(family)
-            stop("'family' not recognized")
-        }
+setMethod("spark.glm", signature(data = "SparkDataFrame", formula = "formula"),
+          function(data, formula, family = gaussian, tol = 1e-06, maxIter = 25) {
+            if (is.character(family)) {
+              family <- get(family, mode = "function", envir = parent.frame())
+            }
+            if (is.function(family)) {
+              family <- family()
+            }
+            if (is.null(family$family)) {
+              print(family)
+              stop("'family' not recognized")
+            }
 
-        formula <- paste(deparse(formula), collapse = "")
+            formula <- paste(deparse(formula), collapse = "")
 
-        jobj <- callJStatic("org.apache.spark.ml.r.GeneralizedLinearRegressionWrapper",
-        "fit", formula, data@sdf, family$family, family$link,
-        epsilon, as.integer(maxit))
-        return(new("GeneralizedLinearRegressionModel", jobj = jobj))
-})
+            jobj <- callJStatic("org.apache.spark.ml.r.GeneralizedLinearRegressionWrapper",
+                                "fit", formula, data@sdf, family$family, family$link,
+                                tol, as.integer(maxIter))
+            return(new("GeneralizedLinearRegressionModel", jobj = jobj))
+          })
 
-#' Fits a generalized linear model (R-compliant).
+#' Fit a generalized linear model (R-compliant)
 #'
 #' Fits a generalized linear model, similarly to R's glm().
 #'
@@ -108,6 +107,7 @@ setMethod(
 #' @param maxit Integer giving the maximal number of IRLS iterations.
 #' @return a fitted generalized linear model
 #' @rdname glm
+#' @name glm
 #' @export
 #' @examples
 #' \dontrun{
@@ -115,7 +115,7 @@ setMethod(
 #' sqlContext <- sparkRSQL.init(sc)
 #' data(iris)
 #' df <- createDataFrame(sqlContext, iris)
-#' model <- glm(Sepal_Length ~ Sepal_Width, df, family="gaussian")
+#' model <- glm(Sepal_Length ~ Sepal_Width, df, family = "gaussian")
 #' summary(model)
 #' }
 setMethod("glm", signature(formula = "formula", family = "ANY", data = "SparkDataFrame"),
@@ -128,8 +128,13 @@ setMethod("glm", signature(formula = "formula", family = "ANY", data = "SparkDat
 #' Returns the summary of a model produced by glm() or spark.glm(), similarly to R's summary().
 #'
 #' @param object A fitted generalized linear model
-#' @return coefficients the model's coefficients, intercept
+#' @return a list with 'deviance.resid', 'coefficients', 'dispersion', 'null.deviance', 'deviance',
+#'         'df.null', 'df.residual', 'aic', 'iter', 'family', 'is.loaded' components.
+#'         The 'coefficients' gives the estimated coefficients, their estimated standard errors,
+#'         t values and p-values. Note 'deviance.resid' in the summary of a saved-loaded model
+#'         is NULL.
 #' @rdname summary
+#' @name summary
 #' @export
 #' @examples
 #' \dontrun{
@@ -168,7 +173,7 @@ setMethod("summary", signature(object = "GeneralizedLinearRegressionModel"),
 
 #' Print the summary of GeneralizedLinearRegressionModel
 #'
-#' @rdname print
+#' @rdname print.summary.GeneralizedLinearRegressionModel
 #' @name print.summary.GeneralizedLinearRegressionModel
 #' @export
 print.summary.GeneralizedLinearRegressionModel <- function(x, ...) {
@@ -195,9 +200,9 @@ print.summary.GeneralizedLinearRegressionModel <- function(x, ...) {
     "Number of Fisher Scoring iterations: ", x$iter, "\n", sep = "")
   cat("\n")
   invisible(x)
-  }
+}
 
-#' Make predictions from a generalized linear model
+#' Make predictions from a fitted MLlib model
 #'
 #' Makes predictions from a generalized linear model produced by glm() or spark.glm(),
 #' similarly to R's predict().
@@ -206,6 +211,7 @@ print.summary.GeneralizedLinearRegressionModel <- function(x, ...) {
 #' @param newData SparkDataFrame for testing
 #' @return SparkDataFrame containing predicted labels in a column named "prediction"
 #' @rdname predict
+#' @name predict
 #' @export
 #' @examples
 #' \dontrun{
@@ -218,29 +224,102 @@ setMethod("predict", signature(object = "GeneralizedLinearRegressionModel"),
             return(dataFrame(callJMethod(object@jobj, "transform", newData@sdf)))
           })
 
-#' Make predictions from a naive Bayes model
+#' Fit an accelerated failure time (AFT) survival regression model
 #'
-#' Makes predictions from a model produced by spark.naiveBayes(),
-#' similarly to R package e1071's predict.
+#' Fits an accelerated failure time (AFT) survival regression model on a Spark DataFrame.
 #'
-#' @param object A fitted naive Bayes model
+#' @param data SparkDataFrame for training.
+#' @param formula A symbolic description of the model to be fitted. Currently only a few formula
+#'                operators are supported, including '~', ':', '+', and '-'.
+#'                Note that operator '.' is not supported currently.
+#' @return a fitted AFT survival regression model
+#' @rdname spark.survreg
+#' @name spark.survreg
+#' @seealso survival: \url{https://cran.r-project.org/web/packages/survival/}
+#' @export
+#' @examples
+#' \dontrun{
+#' df <- createDataFrame(sqlContext, ovarian)
+#' model <- spark.survreg(df, Surv(futime, fustat) ~ ecog_ps + rx)
+#' }
+setMethod("spark.survreg", signature(data = "SparkDataFrame", formula = "formula"),
+          function(data, formula, ...) {
+            formula <- paste(deparse(formula), collapse = "")
+            jobj <- callJStatic("org.apache.spark.ml.r.AFTSurvivalRegressionWrapper",
+                                "fit", formula, data@sdf)
+            return(new("AFTSurvivalRegressionModel", jobj = jobj))
+          })
+
+#' Returns the summary of an AFT survival regression model produced by spark.survreg(),
+#' similarly to R's summary().
+#'
+#' @param object a fitted AFT survival regression model
+#' @return coefficients the model's coefficients, intercept and log(scale).
+#' @rdname summary
+#' @name summary
+#' @export
+#' @examples
+#' \dontrun{
+#' model <- spark.survreg(trainingData, Surv(futime, fustat) ~ ecog_ps + rx)
+#' summary(model)
+#' }
+setMethod("summary", signature(object = "AFTSurvivalRegressionModel"),
+          function(object, ...) {
+            jobj <- object@jobj
+            features <- callJMethod(jobj, "rFeatures")
+            coefficients <- callJMethod(jobj, "rCoefficients")
+            coefficients <- as.matrix(unlist(coefficients))
+            colnames(coefficients) <- c("Value")
+            rownames(coefficients) <- unlist(features)
+            return(list(coefficients = coefficients))
+          })
+
+#' Makes predictions from a model produced by spark.survreg(),
+#' similarly to R package survival's predict.
+#'
+#' @param object A fitted AFT survival regression model
 #' @param newData SparkDataFrame for testing
 #' @return SparkDataFrame containing predicted labels in a column named "prediction"
 #' @rdname predict
+#' @name predict
 #' @export
 #' @examples
 #' \dontrun{
-#' model <- spark.naiveBayes(trainingData, y ~ x)
+#' model <- spark.survreg(trainingData, Surv(futime, fustat) ~ ecog_ps + rx)
 #' predicted <- predict(model, testData)
 #' showDF(predicted)
-#'}
-setMethod("predict", signature(object = "NaiveBayesModel"),
+#' }
+setMethod("predict", signature(object = "AFTSurvivalRegressionModel"),
           function(object, newData) {
             return(dataFrame(callJMethod(object@jobj, "transform", newData@sdf)))
           })
 
-#' Get the summary of a naive Bayes model
+#' Fit a Bernoulli naive Bayes model
 #'
+#' Fits a Bernoulli naive Bayes model on a Spark DataFrame (only categorical data is supported).
+#'
+#' @param data SparkDataFrame for training
+#' @param formula A symbolic description of the model to be fitted. Currently only a few formula
+#'                operators are supported, including '~', '.', ':', '+', and '-'.
+#' @param smoothing Smoothing parameter
+#' @return a fitted naive Bayes model
+#' @rdname spark.naiveBayes
+#' @name spark.naiveBayes
+#' @seealso e1071: \url{https://cran.r-project.org/web/packages/e1071/}
+#' @export
+#' @examples
+#' \dontrun{
+#' df <- createDataFrame(sqlContext, infert)
+#' model <- spark.naiveBayes(df, education ~ ., smoothing = 0)
+#' }
+setMethod("spark.naiveBayes", signature(data = "SparkDataFrame", formula = "formula"),
+          function(data, formula, smoothing = 1.0, ...) {
+            formula <- paste(deparse(formula), collapse = "")
+            jobj <- callJStatic("org.apache.spark.ml.r.NaiveBayesWrapper", "fit",
+                                formula, data@sdf, smoothing)
+            return(new("NaiveBayesModel", jobj = jobj))
+          })
+
 #' Returns the summary of a naive Bayes model produced by spark.naiveBayes(),
 #' similarly to R's summary().
 #'
@@ -248,12 +327,13 @@ setMethod("predict", signature(object = "NaiveBayesModel"),
 #' @return a list containing 'apriori', the label distribution, and 'tables', conditional
 #          probabilities given the target label
 #' @rdname summary
+#' @name summary
 #' @export
 #' @examples
 #' \dontrun{
 #' model <- spark.naiveBayes(trainingData, y ~ x)
 #' summary(model)
-#'}
+#' }
 setMethod("summary", signature(object = "NaiveBayesModel"),
           function(object, ...) {
             jobj <- object@jobj
@@ -269,9 +349,29 @@ setMethod("summary", signature(object = "NaiveBayesModel"),
             return(list(apriori = apriori, tables = tables))
           })
 
+#' Makes predictions from a model produced by spark.naiveBayes(),
+#' similarly to R package e1071's predict.
+#'
+#' @param object A fitted naive Bayes model
+#' @param newData SparkDataFrame for testing
+#' @return SparkDataFrame containing predicted labels in a column named "prediction"
+#' @rdname predict
+#' @name predict
+#' @export
+#' @examples
+#' \dontrun{
+#' model <- spark.naiveBayes(trainingData, y ~ x)
+#' predicted <- predict(model, testData)
+#' showDF(predicted)
+#'}
+setMethod("predict", signature(object = "NaiveBayesModel"),
+          function(object, newData) {
+            return(dataFrame(callJMethod(object@jobj, "transform", newData@sdf)))
+          })
+
 #' Fit a k-means model
 #'
-#' Fit a k-means model, similarly to R's kmeans().
+#' Fits a k-means model, similarly to R's kmeans().
 #'
 #' @param data SparkDataFrame for training
 #' @param formula A symbolic description of the model to be fitted. Currently only a few formula
@@ -282,13 +382,14 @@ setMethod("summary", signature(object = "NaiveBayesModel"),
 #' @param initMode The initialization algorithm choosen to fit the model
 #' @return A fitted k-means model
 #' @rdname spark.kmeans
+#' @name spark.kmeans
 #' @export
 #' @examples
 #' \dontrun{
-#' model <- spark.kmeans(data, ~ ., k=2, initMode="random")
+#' model <- spark.kmeans(data, ~ ., k = 2, initMode = "random")
 #' }
 setMethod("spark.kmeans", signature(data = "SparkDataFrame", formula = "formula"),
-          function(data, formula, k, maxIter = 10, initMode = c("random", "k-means||")) {
+          function(data, formula, k = 2, maxIter = 20, initMode = c("random", "k-means||")) {
             formula <- paste(deparse(formula), collapse = "")
             initMode <- match.arg(initMode)
             jobj <- callJStatic("org.apache.spark.ml.r.KMeansWrapper", "fit", data@sdf, formula,
@@ -298,19 +399,20 @@ setMethod("spark.kmeans", signature(data = "SparkDataFrame", formula = "formula"
 
 #' Get fitted result from a k-means model
 #'
-#' Get fitted result from a k-means model, similarly to R's fitted().
+#' Gets fitted result from a k-means model, similarly to R's fitted().
 #' Note: A saved-loaded model does not support this method.
 #'
 #' @param object A fitted k-means model
 #' @return SparkDataFrame containing fitted values
 #' @rdname fitted
+#' @name fitted
 #' @export
 #' @examples
 #' \dontrun{
-#' model <- spark.kmeans(trainingData, ~ ., 2)
+#' model <- spark.kmeans(trainingData, ~ ., k = 2)
 #' fitted.model <- fitted(model)
 #' showDF(fitted.model)
-#'}
+#' }
 setMethod("fitted", signature(object = "KMeansModel"),
           function(object, method = c("centers", "classes"), ...) {
             method <- match.arg(method)
@@ -323,18 +425,18 @@ setMethod("fitted", signature(object = "KMeansModel"),
             }
           })
 
-#' Get the summary of a k-means model
-#'
 #' Returns the summary of a k-means model produced by spark.kmeans(),
 #' similarly to R's summary().
 #'
 #' @param object a fitted k-means model
-#' @return the model's coefficients, size and cluster
+#' @return the model's 'coefficients', 'size', 'cluster' and 'is.loaded'.
+#'         Note 'cluster' in the summary of a saved-loaded model is NULL.
 #' @rdname summary
+#' @name summary
 #' @export
 #' @examples
 #' \dontrun{
-#' model <- spark.kmeans(trainingData, ~ ., 2)
+#' model <- spark.kmeans(trainingData, ~ ., k = 2)
 #' summary(model)
 #' }
 setMethod("summary", signature(object = "KMeansModel"),
@@ -357,14 +459,13 @@ setMethod("summary", signature(object = "KMeansModel"),
                    cluster = cluster, is.loaded = is.loaded))
           })
 
-#' Make predictions from a k-means model
-#'
-#' Make predictions from a model produced by spark.kmeans().
+#' Makes predictions from a model produced by spark.kmeans().
 #'
 #' @param object A fitted k-means model
 #' @param newData SparkDataFrame for testing
 #' @return SparkDataFrame containing predicted labels in a column named "prediction"
 #' @rdname predict
+#' @name predict
 #' @export
 #' @examples
 #' \dontrun{
@@ -377,32 +478,9 @@ setMethod("predict", signature(object = "KMeansModel"),
             return(dataFrame(callJMethod(object@jobj, "transform", newData@sdf)))
           })
 
-#' Fit a Bernoulli naive Bayes model
-#'
-#' Fit a Bernoulli naive Bayes model on a Spark DataFrame (only categorical data is supported).
+#' Save a fitted MLlib model to the input path
 #'
-#' @param data SparkDataFrame for training
-#' @param formula A symbolic description of the model to be fitted. Currently only a few formula
-#'               operators are supported, including '~', '.', ':', '+', and '-'.
-#' @param laplace Smoothing parameter
-#' @return a fitted naive Bayes model
-#' @rdname spark.naiveBayes
-#' @seealso e1071: \url{https://cran.r-project.org/web/packages/e1071/}
-#' @export
-#' @examples
-#' \dontrun{
-#' df <- createDataFrame(sqlContext, infert)
-#' model <- spark.naiveBayes(df, education ~ ., laplace = 0)
-#'}
-setMethod("spark.naiveBayes", signature(data = "SparkDataFrame", formula = "formula"),
-    function(data, formula, laplace = 0, ...) {
-        formula <- paste(deparse(formula), collapse = "")
-        jobj <- callJStatic("org.apache.spark.ml.r.NaiveBayesWrapper", "fit",
-          formula, data@sdf, laplace)
-        return(new("NaiveBayesModel", jobj = jobj))
-    })
-
-#' Save the Bernoulli naive Bayes model to the input path.
+#' Saves the Bernoulli naive Bayes model to the input path.
 #'
 #' @param object A fitted Bernoulli naive Bayes model
 #' @param path The directory where the model is saved
@@ -415,7 +493,7 @@ setMethod("spark.naiveBayes", signature(data = "SparkDataFrame", formula = "form
 #' @examples
 #' \dontrun{
 #' df <- createDataFrame(sqlContext, infert)
-#' model <- spark.naiveBayes(df, education ~ ., laplace = 0)
+#' model <- spark.naiveBayes(df, education ~ ., smoothing = 0)
 #' path <- "path/to/model"
 #' write.ml(model, path)
 #' }
@@ -428,7 +506,7 @@ setMethod("write.ml", signature(object = "NaiveBayesModel", path = "character"),
             invisible(callJMethod(writer, "save", path))
           })
 
-#' Save the AFT survival regression model to the input path.
+#' Saves the AFT survival regression model to the input path.
 #'
 #' @param object A fitted AFT survival regression model
 #' @param path The directory where the model is saved
@@ -453,7 +531,7 @@ setMethod("write.ml", signature(object = "AFTSurvivalRegressionModel", path = "c
             invisible(callJMethod(writer, "save", path))
           })
 
-#' Save the generalized linear model to the input path.
+#' Saves the generalized linear model to the input path.
 #'
 #' @param object A fitted generalized linear model
 #' @param path The directory where the model is saved
@@ -478,7 +556,7 @@ setMethod("write.ml", signature(object = "GeneralizedLinearRegressionModel", pat
             invisible(callJMethod(writer, "save", path))
           })
 
-#' Save the k-means model to the input path.
+#' Saves the k-means model to the input path.
 #'
 #' @param object A fitted k-means model
 #' @param path The directory where the model is saved
@@ -503,7 +581,7 @@ setMethod("write.ml", signature(object = "KMeansModel", path = "character"),
             invisible(callJMethod(writer, "save", path))
           })
 
-#' Load a fitted MLlib model from the input path.
+#' Load a fitted MLlib model from the input path
 #'
 #' @param path Path of the model to read.
 #' @return a fitted MLlib model
@@ -530,75 +608,3 @@ read.ml <- function(path) {
     stop(paste("Unsupported model: ", jobj))
   }
 }
-
-#' Fit an accelerated failure time (AFT) survival regression model.
-#'
-#' Fit an accelerated failure time (AFT) survival regression model on a Spark DataFrame.
-#'
-#' @param data SparkDataFrame for training.
-#' @param formula A symbolic description of the model to be fitted. Currently only a few formula
-#'                operators are supported, including '~', ':', '+', and '-'.
-#'                Note that operator '.' is not supported currently.
-#' @return a fitted AFT survival regression model
-#' @rdname spark.survreg
-#' @seealso survival: \url{https://cran.r-project.org/web/packages/survival/}
-#' @export
-#' @examples
-#' \dontrun{
-#' df <- createDataFrame(sqlContext, ovarian)
-#' model <- spark.survreg(df, Surv(futime, fustat) ~ ecog_ps + rx)
-#' }
-setMethod("spark.survreg", signature(data = "SparkDataFrame", formula = "formula"),
-          function(data, formula, ...) {
-            formula <- paste(deparse(formula), collapse = "")
-            jobj <- callJStatic("org.apache.spark.ml.r.AFTSurvivalRegressionWrapper",
-                                "fit", formula, data@sdf)
-            return(new("AFTSurvivalRegressionModel", jobj = jobj))
-          })
-
-
-#' Get the summary of an AFT survival regression model
-#'
-#' Returns the summary of an AFT survival regression model produced by spark.survreg(),
-#' similarly to R's summary().
-#'
-#' @param object a fitted AFT survival regression model
-#' @return coefficients the model's coefficients, intercept and log(scale).
-#' @rdname summary
-#' @export
-#' @examples
-#' \dontrun{
-#' model <- spark.survreg(trainingData, Surv(futime, fustat) ~ ecog_ps + rx)
-#' summary(model)
-#' }
-setMethod("summary", signature(object = "AFTSurvivalRegressionModel"),
-          function(object, ...) {
-            jobj <- object@jobj
-            features <- callJMethod(jobj, "rFeatures")
-            coefficients <- callJMethod(jobj, "rCoefficients")
-            coefficients <- as.matrix(unlist(coefficients))
-            colnames(coefficients) <- c("Value")
-            rownames(coefficients) <- unlist(features)
-            return(list(coefficients = coefficients))
-          })
-
-#' Make predictions from an AFT survival regression model
-#'
-#' Make predictions from a model produced by spark.survreg(),
-#' similarly to R package survival's predict.
-#'
-#' @param object A fitted AFT survival regression model
-#' @param newData SparkDataFrame for testing
-#' @return SparkDataFrame containing predicted labels in a column named "prediction"
-#' @rdname predict
-#' @export
-#' @examples
-#' \dontrun{
-#' model <- spark.survreg(trainingData, Surv(futime, fustat) ~ ecog_ps + rx)
-#' predicted <- predict(model, testData)
-#' showDF(predicted)
-#' }
-setMethod("predict", signature(object = "AFTSurvivalRegressionModel"),
-          function(object, newData) {
-            return(dataFrame(callJMethod(object@jobj, "transform", newData@sdf)))
-          })
diff --git a/R/pkg/inst/tests/testthat/test_mllib.R b/R/pkg/inst/tests/testthat/test_mllib.R
index 5f8a27d4e094..ce04de9f0907 100644
--- a/R/pkg/inst/tests/testthat/test_mllib.R
+++ b/R/pkg/inst/tests/testthat/test_mllib.R
@@ -28,7 +28,7 @@ sqlContext <- sparkRSQL.init(sc)
 test_that("formula of spark.glm", {
   training <- suppressWarnings(createDataFrame(sqlContext, iris))
   # directly calling the spark API
-  # dot minus and intercept vs native glm
+  # dot, minus and intercept vs native glm
   model <- spark.glm(training, Sepal_Width ~ . - Species + 0)
   vals <- collect(select(predict(model, training), "prediction"))
   rVals <- predict(glm(Sepal.Width ~ . - Species + 0, data = iris), iris)
@@ -40,7 +40,7 @@ test_that("formula of spark.glm", {
   rVals <- predict(glm(Sepal.Width ~ Species:Sepal.Length, data = iris), iris)
   expect_true(all(abs(rVals - vals) < 1e-6), rVals - vals)
 
-  # glm should work with long formula
+  # spark.glm should work with long formula
   training <- suppressWarnings(createDataFrame(sqlContext, iris))
   training$LongLongLongLongLongName <- training$Sepal_Width
   training$VeryLongLongLongLonLongName <- training$Sepal_Length
@@ -69,7 +69,7 @@ test_that("spark.glm and predict", {
   expect_equal(typeof(take(select(prediction, "prediction"), 1)$prediction), "double")
   vals <- collect(select(prediction, "prediction"))
   rVals <- suppressWarnings(predict(glm(Sepal.Width ~ Sepal.Length + Species,
-  data = iris, family = poisson(link = identity)), iris))
+    data = iris, family = poisson(link = identity)), iris))
   expect_true(all(abs(rVals - vals) < 1e-6), rVals - vals)
 
   # Test stats::predict is working
@@ -120,11 +120,6 @@ test_that("spark.glm summary", {
   expect_equal(stats$df.null, rStats$df.null)
   expect_equal(stats$df.residual, rStats$df.residual)
   expect_equal(stats$aic, rStats$aic)
-
-  # Test summary works on base GLM models
-  baseModel <- stats::glm(Sepal.Width ~ Sepal.Length + Species, data = iris)
-  baseSummary <- summary(baseModel)
-  expect_true(abs(baseSummary$deviance - 12.19313) < 1e-4)
 })
 
 test_that("spark.glm save/load", {
@@ -154,66 +149,21 @@ test_that("spark.glm save/load", {
   unlink(modelPath)
 })
 
-
-
-test_that("formula of glm", {
-  training <- suppressWarnings(createDataFrame(sqlContext, iris))
-  # dot minus and intercept vs native glm
-  model <- glm(Sepal_Width ~ . - Species + 0, data = training)
-  vals <- collect(select(predict(model, training), "prediction"))
-  rVals <- predict(glm(Sepal.Width ~ . - Species + 0, data = iris), iris)
-  expect_true(all(abs(rVals - vals) < 1e-6), rVals - vals)
-
-  # feature interaction vs native glm
-  model <- glm(Sepal_Width ~ Species:Sepal_Length, data = training)
-  vals <- collect(select(predict(model, training), "prediction"))
-  rVals <- predict(glm(Sepal.Width ~ Species:Sepal.Length, data = iris), iris)
-  expect_true(all(abs(rVals - vals) < 1e-6), rVals - vals)
-
-  # glm should work with long formula
-  training <- suppressWarnings(createDataFrame(sqlContext, iris))
-  training$LongLongLongLongLongName <- training$Sepal_Width
-  training$VeryLongLongLongLonLongName <- training$Sepal_Length
-  training$AnotherLongLongLongLongName <- training$Species
-  model <- glm(LongLongLongLongLongName ~ VeryLongLongLongLonLongName + AnotherLongLongLongLongName,
-               data = training)
-  vals <- collect(select(predict(model, training), "prediction"))
-  rVals <- predict(glm(Sepal.Width ~ Sepal.Length + Species, data = iris), iris)
-  expect_true(all(abs(rVals - vals) < 1e-6), rVals - vals)
-})
-
-test_that("glm and predict", {
+test_that("glm, predict and summary", {
+  # Test R-compliant glm() which is another entrance of spark.glm().
   training <- suppressWarnings(createDataFrame(sqlContext, iris))
-  # gaussian family
   model <- glm(Sepal_Width ~ Sepal_Length + Species, data = training)
-  prediction <- predict(model, training)
-  expect_equal(typeof(take(select(prediction, "prediction"), 1)$prediction), "double")
-  vals <- collect(select(prediction, "prediction"))
-  rVals <- predict(glm(Sepal.Width ~ Sepal.Length + Species, data = iris), iris)
-  expect_true(all(abs(rVals - vals) < 1e-6), rVals - vals)
 
-  # poisson family
-  model <- glm(Sepal_Width ~ Sepal_Length + Species, data = training,
-               family = poisson(link = identity))
+  rModel <- glm(Sepal.Width ~ Sepal.Length + Species, data = iris)
+
   prediction <- predict(model, training)
   expect_equal(typeof(take(select(prediction, "prediction"), 1)$prediction), "double")
   vals <- collect(select(prediction, "prediction"))
-  rVals <- suppressWarnings(predict(glm(Sepal.Width ~ Sepal.Length + Species,
-           data = iris, family = poisson(link = identity)), iris))
+  rVals <- predict(rModel, iris)
   expect_true(all(abs(rVals - vals) < 1e-6), rVals - vals)
 
-  # Test stats::predict is working
-  x <- rnorm(15)
-  y <- x + rnorm(15)
-  expect_equal(length(predict(lm(y ~ x))), 15)
-})
-
-test_that("glm summary", {
-  # gaussian family
-  training <- suppressWarnings(createDataFrame(sqlContext, iris))
-  stats <- summary(glm(Sepal_Width ~ Sepal_Length + Species, data = training))
-
-  rStats <- summary(glm(Sepal.Width ~ Sepal.Length + Species, data = iris))
+  stats <- summary(model)
+  rStats <- summary(rModel)
 
   coefs <- unlist(stats$coefficients)
   rCoefs <- unlist(rStats$coefficients)
@@ -228,62 +178,12 @@ test_that("glm summary", {
   expect_equal(stats$df.residual, rStats$df.residual)
   expect_equal(stats$aic, rStats$aic)
 
-  # binomial family
-  df <- suppressWarnings(createDataFrame(sqlContext, iris))
-  training <- df[df$Species %in% c("versicolor", "virginica"), ]
-  stats <- summary(glm(Species ~ Sepal_Length + Sepal_Width, data = training,
-    family = binomial(link = "logit")))
-
-  rTraining <- iris[iris$Species %in% c("versicolor", "virginica"), ]
-  rStats <- summary(glm(Species ~ Sepal.Length + Sepal.Width, data = rTraining,
-    family = binomial(link = "logit")))
-
-  coefs <- unlist(stats$coefficients)
-  rCoefs <- unlist(rStats$coefficients)
-  expect_true(all(abs(rCoefs - coefs) < 1e-4))
-  expect_true(all(
-    rownames(stats$coefficients) ==
-    c("(Intercept)", "Sepal_Length", "Sepal_Width")))
-  expect_equal(stats$dispersion, rStats$dispersion)
-  expect_equal(stats$null.deviance, rStats$null.deviance)
-  expect_equal(stats$deviance, rStats$deviance)
-  expect_equal(stats$df.null, rStats$df.null)
-  expect_equal(stats$df.residual, rStats$df.residual)
-  expect_equal(stats$aic, rStats$aic)
-
   # Test summary works on base GLM models
   baseModel <- stats::glm(Sepal.Width ~ Sepal.Length + Species, data = iris)
   baseSummary <- summary(baseModel)
   expect_true(abs(baseSummary$deviance - 12.19313) < 1e-4)
 })
 
-test_that("glm save/load", {
-  training <- suppressWarnings(createDataFrame(sqlContext, iris))
-  m <- glm(Sepal_Width ~ Sepal_Length + Species, data = training)
-  s <- summary(m)
-
-  modelPath <- tempfile(pattern = "glm", fileext = ".tmp")
-  write.ml(m, modelPath)
-  expect_error(write.ml(m, modelPath))
-  write.ml(m, modelPath, overwrite = TRUE)
-  m2 <- read.ml(modelPath)
-  s2 <- summary(m2)
-
-  expect_equal(s$coefficients, s2$coefficients)
-  expect_equal(rownames(s$coefficients), rownames(s2$coefficients))
-  expect_equal(s$dispersion, s2$dispersion)
-  expect_equal(s$null.deviance, s2$null.deviance)
-  expect_equal(s$deviance, s2$deviance)
-  expect_equal(s$df.null, s2$df.null)
-  expect_equal(s$df.residual, s2$df.residual)
-  expect_equal(s$aic, s2$aic)
-  expect_equal(s$iter, s2$iter)
-  expect_true(!s$is.loaded)
-  expect_true(s2$is.loaded)
-
-  unlink(modelPath)
-})
-
 test_that("spark.kmeans", {
   newIris <- iris
   newIris$Species <- NULL
@@ -366,7 +266,7 @@ test_that("spark.naiveBayes", {
   t <- as.data.frame(Titanic)
   t1 <- t[t$Freq > 0, -5]
   df <- suppressWarnings(createDataFrame(sqlContext, t1))
-  m <- spark.naiveBayes(df, Survived ~ .)
+  m <- spark.naiveBayes(df, Survived ~ ., smoothing = 0.0)
   s <- summary(m)
   expect_equal(as.double(s$apriori[1, "Yes"]), 0.5833333, tolerance = 1e-6)
   expect_equal(sum(s$apriori), 1)
diff --git a/mllib/src/main/scala/org/apache/spark/ml/r/GeneralizedLinearRegressionWrapper.scala b/mllib/src/main/scala/org/apache/spark/ml/r/GeneralizedLinearRegressionWrapper.scala
index 9618a3423e9a..5642abc6450f 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/r/GeneralizedLinearRegressionWrapper.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/r/GeneralizedLinearRegressionWrapper.scala
@@ -67,8 +67,8 @@ private[r] object GeneralizedLinearRegressionWrapper
       data: DataFrame,
       family: String,
       link: String,
-      epsilon: Double,
-      maxit: Int): GeneralizedLinearRegressionWrapper = {
+      tol: Double,
+      maxIter: Int): GeneralizedLinearRegressionWrapper = {
     val rFormula = new RFormula()
       .setFormula(formula)
     val rFormulaModel = rFormula.fit(data)
@@ -82,8 +82,8 @@ private[r] object GeneralizedLinearRegressionWrapper
       .setFamily(family)
       .setLink(link)
       .setFitIntercept(rFormula.hasIntercept)
-      .setTol(epsilon)
-      .setMaxIter(maxit)
+      .setTol(tol)
+      .setMaxIter(maxIter)
     val pipeline = new Pipeline()
       .setStages(Array(rFormulaModel, glr))
       .fit(data)
diff --git a/mllib/src/main/scala/org/apache/spark/ml/r/NaiveBayesWrapper.scala b/mllib/src/main/scala/org/apache/spark/ml/r/NaiveBayesWrapper.scala
index 28925c79da66..1dac246b0332 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/r/NaiveBayesWrapper.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/r/NaiveBayesWrapper.scala
@@ -56,7 +56,7 @@ private[r] object NaiveBayesWrapper extends MLReadable[NaiveBayesWrapper] {
   val PREDICTED_LABEL_INDEX_COL = "pred_label_idx"
   val PREDICTED_LABEL_COL = "prediction"
 
-  def fit(formula: String, data: DataFrame, laplace: Double): NaiveBayesWrapper = {
+  def fit(formula: String, data: DataFrame, smoothing: Double): NaiveBayesWrapper = {
     val rFormula = new RFormula()
       .setFormula(formula)
       .fit(data)
@@ -70,7 +70,7 @@ private[r] object NaiveBayesWrapper extends MLReadable[NaiveBayesWrapper] {
     val features = featureAttrs.map(_.name.get)
     // assemble and fit the pipeline
     val naiveBayes = new NaiveBayes()
-      .setSmoothing(laplace)
+      .setSmoothing(smoothing)
       .setModelType("bernoulli")
       .setPredictionCol(PREDICTED_LABEL_INDEX_COL)
     val idxToStr = new IndexToString()