SPARK-1429: Debian packaging

LICENSE

@@ -249,11 +249,11 @@ The text of each license is also included at licenses/LICENSE-[project].txt.
         (Interpreter classes (all .scala files in repl/src/main/scala
         except for Main.Scala, SparkHelper.scala and ExecutorClassLoader.scala),
         and for SerializableMapWrapper in JavaUtils.scala)
-     (BSD-like) Scala Actors library (org.scala-lang:scala-actors:2.11.7 - http://www.scala-lang.org/)
-     (BSD-like) Scala Compiler (org.scala-lang:scala-compiler:2.11.7 - http://www.scala-lang.org/)
-     (BSD-like) Scala Compiler (org.scala-lang:scala-reflect:2.11.7 - http://www.scala-lang.org/)
-     (BSD-like) Scala Library (org.scala-lang:scala-library:2.11.7 - http://www.scala-lang.org/)
-     (BSD-like) Scalap (org.scala-lang:scalap:2.11.7 - http://www.scala-lang.org/)
+     (BSD-like) Scala Actors library (org.scala-lang:scala-actors:2.11.8 - http://www.scala-lang.org/)
+     (BSD-like) Scala Compiler (org.scala-lang:scala-compiler:2.11.8 - http://www.scala-lang.org/)
+     (BSD-like) Scala Compiler (org.scala-lang:scala-reflect:2.11.8 - http://www.scala-lang.org/)
+     (BSD-like) Scala Library (org.scala-lang:scala-library:2.11.8 - http://www.scala-lang.org/)
+     (BSD-like) Scalap (org.scala-lang:scalap:2.11.8 - http://www.scala-lang.org/)
      (BSD-style) scalacheck (org.scalacheck:scalacheck_2.11:1.10.0 - http://www.scalacheck.org)
      (BSD-style) spire (org.spire-math:spire_2.11:0.7.1 - http://spire-math.org)
      (BSD-style) spire-macros (org.spire-math:spire-macros_2.11:0.7.1 - http://spire-math.org)
@@ -297,3 +297,4 @@ The text of each license is also included at licenses/LICENSE-[project].txt.
      (MIT License) RowsGroup (http://datatables.net/license/mit)
      (MIT License) jsonFormatter (http://www.jqueryscript.net/other/jQuery-Plugin-For-Pretty-JSON-Formatting-jsonFormatter.html)
      (MIT License) modernizr (https://github.com/Modernizr/Modernizr/blob/master/LICENSE)
+     (MIT License) machinist (https://github.com/typelevel/machinist)

R/README.md

@@ -66,11 +66,7 @@ To run one of them, use `./bin/spark-submit <filename> <args>`. For example:
 ```bash
 ./bin/spark-submit examples/src/main/r/dataframe.R
 ```
-You can also run the unit tests for SparkR by running. You need to install the [testthat](http://cran.r-project.org/web/packages/testthat/index.html) package first:
-```bash
-R -e 'install.packages("testthat", repos="http://cran.us.r-project.org")'
-./R/run-tests.sh
-```
+You can run R unit tests by following the instructions under [Running R Tests](http://spark.apache.org/docs/latest/building-spark.html#running-r-tests).
 
 ### Running on YARN
 

R/WINDOWS.md

@@ -34,10 +34,9 @@ To run the SparkR unit tests on Windows, the following steps are required —ass
 
 4. Set the environment variable `HADOOP_HOME` to the full path to the newly created `hadoop` directory.
 
-5. Run unit tests for SparkR by running the command below. You need to install the [testthat](http://cran.r-project.org/web/packages/testthat/index.html) package first:
+5. Run unit tests for SparkR by running the command below. You need to install the needed packages following the instructions under [Running R Tests](http://spark.apache.org/docs/latest/building-spark.html#running-r-tests) first:
 
     ```
-    R -e "install.packages('testthat', repos='http://cran.us.r-project.org')"
     .\bin\spark-submit2.cmd --conf spark.hadoop.fs.defaultFS="file:///" R\pkg\tests\run-all.R
     ```
 

R/pkg/.Rbuildignore

@@ -6,3 +6,4 @@
 ^README\.Rmd$
 ^src-native$
 ^html$
+^tests/fulltests/*

R/pkg/DESCRIPTION

@@ -1,8 +1,8 @@
 Package: SparkR
 Type: Package
-Version: 2.2.0
+Version: 2.2.1
 Title: R Frontend for Apache Spark
-Description: The SparkR package provides an R Frontend for Apache Spark.
+Description: Provides an R Frontend for Apache Spark.
 Authors@R: c(person("Shivaram", "Venkataraman", role = c("aut", "cre"),
                     email = "shivaram@cs.berkeley.edu"),
              person("Xiangrui", "Meng", role = "aut",

R/pkg/NAMESPACE

@@ -122,6 +122,7 @@ exportMethods("arrange",
               "group_by",
               "groupBy",
               "head",
+              "hint",
               "insertInto",
               "intersect",
               "isLocal",

R/pkg/R/DataFrame.R

@@ -591,7 +591,7 @@ setMethod("cache",
 #'
 #' Persist this SparkDataFrame with the specified storage level. For details of the
 #' supported storage levels, refer to
-#' \url{http://spark.apache.org/docs/latest/programming-guide.html#rdd-persistence}.
+#' \url{http://spark.apache.org/docs/latest/rdd-programming-guide.html#rdd-persistence}.
 #'
 #' @param x the SparkDataFrame to persist.
 #' @param newLevel storage level chosen for the persistance. See available options in
@@ -2642,6 +2642,7 @@ generateAliasesForIntersectedCols <- function (x, intersectedColNames, suffix) {
 #' Input SparkDataFrames can have different schemas (names and data types).
 #'
 #' Note: This does not remove duplicate rows across the two SparkDataFrames.
+#' Also as standard in SQL, this function resolves columns by position (not by name).
 #'
 #' @param x A SparkDataFrame
 #' @param y A SparkDataFrame
@@ -3642,3 +3643,33 @@ setMethod("checkpoint",
             df <- callJMethod(x@sdf, "checkpoint", as.logical(eager))
             dataFrame(df)
           })
+
+#' hint
+#'
+#' Specifies execution plan hint and return a new SparkDataFrame.
+#'
+#' @param x a SparkDataFrame.
+#' @param name a name of the hint.
+#' @param ... optional parameters for the hint.
+#' @return A SparkDataFrame.
+#' @family SparkDataFrame functions
+#' @aliases hint,SparkDataFrame,character-method
+#' @rdname hint
+#' @name hint
+#' @export
+#' @examples
+#' \dontrun{
+#' df <- createDataFrame(mtcars)
+#' avg_mpg <- mean(groupBy(createDataFrame(mtcars), "cyl"), "mpg")
+#'
+#' head(join(df, hint(avg_mpg, "broadcast"), df$cyl == avg_mpg$cyl))
+#' }
+#' @note hint since 2.2.0
+setMethod("hint",
+          signature(x = "SparkDataFrame", name = "character"),
+          function(x, name, ...) {
+            parameters <- list(...)
+            stopifnot(all(sapply(parameters, is.character)))
+            jdf <- callJMethod(x@sdf, "hint", name, parameters)
+            dataFrame(jdf)
+          })

R/pkg/R/RDD.R

@@ -227,7 +227,7 @@ setMethod("cacheRDD",
 #'
 #' Persist this RDD with the specified storage level. For details of the
 #' supported storage levels, refer to
-#'\url{http://spark.apache.org/docs/latest/programming-guide.html#rdd-persistence}.
+#'\url{http://spark.apache.org/docs/latest/rdd-programming-guide.html#rdd-persistence}.
 #'
 #' @param x The RDD to persist
 #' @param newLevel The new storage level to be assigned

R/pkg/R/SQLContext.R

@@ -334,7 +334,7 @@ setMethod("toDF", signature(x = "RDD"),
 #'
 #' Loads a JSON file, returning the result as a SparkDataFrame
 #' By default, (\href{http://jsonlines.org/}{JSON Lines text format or newline-delimited JSON}
-#' ) is supported. For JSON (one record per file), set a named property \code{wholeFile} to
+#' ) is supported. For JSON (one record per file), set a named property \code{multiLine} to
 #' \code{TRUE}.
 #' It goes through the entire dataset once to determine the schema.
 #'
@@ -348,7 +348,7 @@ setMethod("toDF", signature(x = "RDD"),
 #' sparkR.session()
 #' path <- "path/to/file.json"
 #' df <- read.json(path)
-#' df <- read.json(path, wholeFile = TRUE)
+#' df <- read.json(path, multiLine = TRUE)
 #' df <- jsonFile(path)
 #' }
 #' @name read.json
@@ -598,7 +598,7 @@ tableToDF <- function(tableName) {
 #' df1 <- read.df("path/to/file.json", source = "json")
 #' schema <- structType(structField("name", "string"),
 #'                      structField("info", "map<string,double>"))
-#' df2 <- read.df(mapTypeJsonPath, "json", schema, wholeFile = TRUE)
+#' df2 <- read.df(mapTypeJsonPath, "json", schema, multiLine = TRUE)
 #' df3 <- loadDF("data/test_table", "parquet", mergeSchema = "true")
 #' }
 #' @name read.df

R/pkg/R/generics.R

@@ -572,6 +572,10 @@ setGeneric("group_by", function(x, ...) { standardGeneric("group_by") })
 #' @export
 setGeneric("groupBy", function(x, ...) { standardGeneric("groupBy") })
 
+#' @rdname hint
+#' @export
+setGeneric("hint", function(x, name, ...) { standardGeneric("hint") })
+
 #' @rdname insertInto
 #' @export
 setGeneric("insertInto", function(x, tableName, ...) { standardGeneric("insertInto") })
@@ -1469,7 +1473,7 @@ setGeneric("write.ml", function(object, path, ...) { standardGeneric("write.ml")
 
 #' @rdname awaitTermination
 #' @export
-setGeneric("awaitTermination", function(x, timeout) { standardGeneric("awaitTermination") })
+setGeneric("awaitTermination", function(x, timeout = NULL) { standardGeneric("awaitTermination") })
 
 #' @rdname isActive
 #' @export

R/pkg/R/install.R

@@ -267,10 +267,14 @@ hadoopVersionName <- function(hadoopVersion) {
 # The implementation refers to appdirs package: https://pypi.python.org/pypi/appdirs and
 # adapt to Spark context
 sparkCachePath <- function() {
-  if (.Platform$OS.type == "windows") {
+  if (is_windows()) {
     winAppPath <- Sys.getenv("LOCALAPPDATA", unset = NA)
     if (is.na(winAppPath)) {
-      stop(paste("%LOCALAPPDATA% not found.",
+      message("%LOCALAPPDATA% not found. Falling back to %USERPROFILE%.")
+      winAppPath <- Sys.getenv("USERPROFILE", unset = NA)
+    }
+    if (is.na(winAppPath)) {
+      stop(paste("%LOCALAPPDATA% and %USERPROFILE% not found.",
                    "Please define the environment variable",
                    "or restart and enter an installation path in localDir."))
     } else {

R/pkg/R/mllib_classification.R

@@ -46,22 +46,25 @@ setClass("MultilayerPerceptronClassificationModel", representation(jobj = "jobj"
 #' @note NaiveBayesModel since 2.0.0
 setClass("NaiveBayesModel", representation(jobj = "jobj"))
 
-#' linear SVM Model
+#' Linear SVM Model
 #'
-#' Fits an linear SVM model against a SparkDataFrame. It is a binary classifier, similar to svm in glmnet package
+#' Fits a linear SVM model against a SparkDataFrame, similar to svm in e1071 package.
+#' Currently only supports binary classification model with linear kernel.
 #' Users can print, make predictions on the produced model and save the 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 regParam The regularization parameter.
+#' @param regParam The regularization parameter. Only supports L2 regularization currently.
 #' @param maxIter Maximum iteration number.
 #' @param tol Convergence tolerance of iterations.
 #' @param standardization Whether to standardize the training features before fitting the model. The coefficients
 #'                        of models will be always returned on the original scale, so it will be transparent for
 #'                        users. Note that with/without standardization, the models should be always converged
 #'                        to the same solution when no regularization is applied.
-#' @param threshold The threshold in binary classification, in range [0, 1].
+#' @param threshold The threshold in binary classification applied to the linear model prediction.
+#'                  This threshold can be any real number, where Inf will make all predictions 0.0
+#'                  and -Inf will make all predictions 1.0.
 #' @param weightCol The weight column name.
 #' @param aggregationDepth The depth for treeAggregate (greater than or equal to 2). If the dimensions of features
 #'                         or the number of partitions are large, this param could be adjusted to a larger size.
@@ -111,10 +114,10 @@ setMethod("spark.svmLinear", signature(data = "SparkDataFrame", formula = "formu
             new("LinearSVCModel", jobj = jobj)
           })
 
-#  Predicted values based on an LinearSVCModel model
+#  Predicted values based on a LinearSVCModel model
 
 #' @param newData a SparkDataFrame for testing.
-#' @return \code{predict} returns the predicted values based on an LinearSVCModel.
+#' @return \code{predict} returns the predicted values based on a LinearSVCModel.
 #' @rdname spark.svmLinear
 #' @aliases predict,LinearSVCModel,SparkDataFrame-method
 #' @export
@@ -124,36 +127,27 @@ setMethod("predict", signature(object = "LinearSVCModel"),
             predict_internal(object, newData)
           })
 
-#  Get the summary of an LinearSVCModel
+#  Get the summary of a LinearSVCModel
 
-#' @param object an LinearSVCModel fitted by \code{spark.svmLinear}.
+#' @param object a LinearSVCModel fitted by \code{spark.svmLinear}.
 #' @return \code{summary} returns summary information of the fitted model, which is a list.
 #'         The list includes \code{coefficients} (coefficients of the fitted model),
-#'         \code{intercept} (intercept of the fitted model), \code{numClasses} (number of classes),
-#'         \code{numFeatures} (number of features).
+#'         \code{numClasses} (number of classes), \code{numFeatures} (number of features).
 #' @rdname spark.svmLinear
 #' @aliases summary,LinearSVCModel-method
 #' @export
 #' @note summary(LinearSVCModel) since 2.2.0
 setMethod("summary", signature(object = "LinearSVCModel"),
           function(object) {
             jobj <- object@jobj
-            features <- callJMethod(jobj, "features")
-            labels <- callJMethod(jobj, "labels")
-            coefficients <- callJMethod(jobj, "coefficients")
-            nCol <- length(coefficients) / length(features)
-            coefficients <- matrix(unlist(coefficients), ncol = nCol)
-            intercept <- callJMethod(jobj, "intercept")
+            features <- callJMethod(jobj, "rFeatures")
+            coefficients <- callJMethod(jobj, "rCoefficients")
+            coefficients <- as.matrix(unlist(coefficients))
+            colnames(coefficients) <- c("Estimate")
+            rownames(coefficients) <- unlist(features)
             numClasses <- callJMethod(jobj, "numClasses")
             numFeatures <- callJMethod(jobj, "numFeatures")
-            if (nCol == 1) {
-              colnames(coefficients) <- c("Estimate")
-            } else {
-              colnames(coefficients) <- unlist(labels)
-            }
-            rownames(coefficients) <- unlist(features)
-            list(coefficients = coefficients, intercept = intercept,
-                 numClasses = numClasses, numFeatures = numFeatures)
+            list(coefficients = coefficients, numClasses = numClasses, numFeatures = numFeatures)
           })
 
 #  Save fitted LinearSVCModel to the input path

R/pkg/R/streaming.R

@@ -169,8 +169,10 @@ setMethod("isActive",
 #' immediately.
 #'
 #' @param x a StreamingQuery.
-#' @param timeout time to wait in milliseconds
-#' @return TRUE if query has terminated within the timeout period.
+#' @param timeout time to wait in milliseconds, if omitted, wait indefinitely until \code{stopQuery}
+#'                is called or an error has occured.
+#' @return TRUE if query has terminated within the timeout period; nothing if timeout is not
+#'         specified.
 #' @rdname awaitTermination
 #' @name awaitTermination
 #' @aliases awaitTermination,StreamingQuery-method
@@ -182,8 +184,12 @@ setMethod("isActive",
 #' @note experimental
 setMethod("awaitTermination",
           signature(x = "StreamingQuery"),
-          function(x, timeout) {
-            handledCallJMethod(x@ssq, "awaitTermination", as.integer(timeout))
+          function(x, timeout = NULL) {
+            if (is.null(timeout)) {
+              invisible(handledCallJMethod(x@ssq, "awaitTermination"))
+            } else {
+              handledCallJMethod(x@ssq, "awaitTermination", as.integer(timeout))
+            }
           })
 
 #' stopQuery

R/pkg/R/utils.R

@@ -899,3 +899,15 @@ basenameSansExtFromUrl <- function(url) {
 isAtomicLengthOne <- function(x) {
   is.atomic(x) && length(x) == 1
 }
+
+is_windows <- function() {
+  .Platform$OS.type == "windows"
+}
+
+hadoop_home_set <- function() {
+  !identical(Sys.getenv("HADOOP_HOME"), "")
+}
+
+windows_with_hadoop <- function() {
+  !is_windows() || hadoop_home_set()
+}