Repository: spark Updated Branches: refs/heads/master f3a768b7b -> 4f83ca105
[SPARK-15177][.1][R] make SparkR model params and default values consistent with MLlib ## What changes were proposed in this pull request? This PR is a subset of #13023 by yanboliang to make SparkR model param names and default values consistent with MLlib. I tried to avoid other changes from #13023 to keep this PR minimal. I will send a follow-up PR to improve the documentation. Main changes: * `spark.glm`: epsilon -> tol, maxit -> maxIter * `spark.kmeans`: default k -> 2, default maxIter -> 20, default initMode -> "k-means||" * `spark.naiveBayes`: laplace -> smoothing, default 1.0 ## How was this patch tested? Existing unit tests. Author: Xiangrui Meng <m...@databricks.com> Closes #13801 from mengxr/SPARK-15177.1. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/4f83ca10 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/4f83ca10 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/4f83ca10 Branch: refs/heads/master Commit: 4f83ca1059a3b580fca3f006974ff5ac4d5212a1 Parents: f3a768b Author: Xiangrui Meng <m...@databricks.com> Authored: Tue Jun 21 08:31:15 2016 -0700 Committer: Xiangrui Meng <m...@databricks.com> Committed: Tue Jun 21 08:31:15 2016 -0700 ---------------------------------------------------------------------- R/pkg/R/mllib.R | 74 ++++++++++---------- R/pkg/inst/tests/testthat/test_mllib.R | 4 +- .../r/GeneralizedLinearRegressionWrapper.scala | 8 +-- .../apache/spark/ml/r/NaiveBayesWrapper.scala | 4 +- 4 files changed, 44 insertions(+), 46 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/4f83ca10/R/pkg/R/mllib.R ---------------------------------------------------------------------- diff --git a/R/pkg/R/mllib.R b/R/pkg/R/mllib.R index 74dba8f..b83b3b3 100644 --- a/R/pkg/R/mllib.R +++ b/R/pkg/R/mllib.R @@ -64,8 +64,8 @@ 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 #' @export @@ -74,32 +74,30 @@ setClass("KMeansModel", representation(jobj = "jobj")) #' sparkR.session() #' data(iris) #' df <- createDataFrame(iris) -#' model <- spark.glm(df, Sepal_Length ~ Sepal_Width, family="gaussian") +#' model <- spark.glm(df, Sepal_Length ~ Sepal_Width, family = "gaussian") #' summary(model) #' } #' @note spark.glm since 2.0.0 -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$family)) { - print(family) - stop("'family' not recognized") - } +setMethod("spark.glm", signature(data = "SparkDataFrame", formula = "formula"), + function(data, formula, family = gaussian, tol = 1e-6, maxIter = 25) { + if (is.character(family)) { + family <- get(family, mode = "function", envir = parent.frame()) + } + if (is.function(family)) { + family <- family() + } + if (is.null(family$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). #' @@ -122,13 +120,13 @@ setMethod( #' sparkR.session() #' data(iris) #' df <- createDataFrame(iris) -#' model <- glm(Sepal_Length ~ Sepal_Width, df, family="gaussian") +#' model <- glm(Sepal_Length ~ Sepal_Width, df, family = "gaussian") #' summary(model) #' } #' @note glm since 1.5.0 setMethod("glm", signature(formula = "formula", family = "ANY", data = "SparkDataFrame"), - function(formula, family = gaussian, data, epsilon = 1e-06, maxit = 25) { - spark.glm(data, formula, family, epsilon, maxit) + function(formula, family = gaussian, data, epsilon = 1e-6, maxit = 25) { + spark.glm(data, formula, family, tol = epsilon, maxIter = maxit) }) #' Get the summary of a generalized linear model @@ -296,17 +294,17 @@ setMethod("summary", signature(object = "NaiveBayesModel"), #' @export #' @examples #' \dontrun{ -#' model <- spark.kmeans(data, ~ ., k=2, initMode="random") +#' model <- spark.kmeans(data, ~ ., k = 4, initMode = "random") #' } #' @note spark.kmeans since 2.0.0 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("k-means||", "random")) { formula <- paste(deparse(formula), collapse = "") initMode <- match.arg(initMode) jobj <- callJStatic("org.apache.spark.ml.r.KMeansWrapper", "fit", data@sdf, formula, as.integer(k), as.integer(maxIter), initMode) return(new("KMeansModel", jobj = jobj)) - }) + }) #' Get fitted result from a k-means model #' @@ -397,7 +395,7 @@ setMethod("predict", signature(object = "KMeansModel"), #' @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 +#' @param smoothing Smoothing parameter #' @return a fitted naive Bayes model #' @rdname spark.naiveBayes #' @seealso e1071: \url{https://cran.r-project.org/web/packages/e1071/} @@ -405,16 +403,16 @@ setMethod("predict", signature(object = "KMeansModel"), #' @examples #' \dontrun{ #' df <- createDataFrame(infert) -#' model <- spark.naiveBayes(df, education ~ ., laplace = 0) +#' model <- spark.naiveBayes(df, education ~ ., smoothing = 0) #'} #' @note spark.naiveBayes since 2.0.0 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)) - }) + 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)) + }) #' Save fitted MLlib model to the input path #' @@ -431,7 +429,7 @@ setMethod("spark.naiveBayes", signature(data = "SparkDataFrame", formula = "form #' @examples #' \dontrun{ #' df <- createDataFrame(infert) -#' model <- spark.naiveBayes(df, education ~ ., laplace = 0) +#' model <- spark.naiveBayes(df, education ~ ., smoothing = 0) #' path <- "path/to/model" #' write.ml(model, path) #' } http://git-wip-us.apache.org/repos/asf/spark/blob/4f83ca10/R/pkg/inst/tests/testthat/test_mllib.R ---------------------------------------------------------------------- diff --git a/R/pkg/inst/tests/testthat/test_mllib.R b/R/pkg/inst/tests/testthat/test_mllib.R index c8c5ef2..753da81 100644 --- a/R/pkg/inst/tests/testthat/test_mllib.R +++ b/R/pkg/inst/tests/testthat/test_mllib.R @@ -288,7 +288,7 @@ test_that("spark.kmeans", { take(training, 1) - model <- spark.kmeans(data = training, ~ ., k = 2) + model <- spark.kmeans(data = training, ~ ., k = 2, maxIter = 10, initMode = "random") sample <- take(select(predict(model, training), "prediction"), 1) expect_equal(typeof(sample$prediction), "integer") expect_equal(sample$prediction, 1) @@ -363,7 +363,7 @@ test_that("spark.naiveBayes", { t <- as.data.frame(Titanic) t1 <- t[t$Freq > 0, -5] df <- suppressWarnings(createDataFrame(t1)) - m <- spark.naiveBayes(df, Survived ~ .) + m <- spark.naiveBayes(df, Survived ~ ., smoothing = 0.0) s <- summary(m) expect_equal(as.double(s$apriori[1, "Yes"]), 0.5833333, tolerance = 1e-6) expect_equal(sum(s$apriori), 1) http://git-wip-us.apache.org/repos/asf/spark/blob/4f83ca10/mllib/src/main/scala/org/apache/spark/ml/r/GeneralizedLinearRegressionWrapper.scala ---------------------------------------------------------------------- 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 9618a34..5642abc 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) http://git-wip-us.apache.org/repos/asf/spark/blob/4f83ca10/mllib/src/main/scala/org/apache/spark/ml/r/NaiveBayesWrapper.scala ---------------------------------------------------------------------- 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 28925c7..1dac246 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() --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
