Merge remote-tracking branch 'origin/master' into modularize-jdbc-internals

Author: JoshRosen

.gitignore

@@ -23,6 +23,7 @@
 /lib/
 R-unit-tests.log
 R/unit-tests.out
+R/cran-check.out
 build/*.jar
 build/apache-maven*
 build/scala*

.travis.yml

@@ -44,7 +44,7 @@ notifications:
 # 5. Run maven install before running lint-java.
 install:
   - export MAVEN_SKIP_RC=1
-  - build/mvn -T 4 -q -DskipTests -Pyarn -Phadoop-2.3 -Pkinesis-asl -Phive -Phive-thriftserver install
+  - build/mvn -T 4 -q -DskipTests -Pmesos -Pyarn -Phadoop-2.3 -Pkinesis-asl -Phive -Phive-thriftserver install
 
 # 6. Run lint-java.
 script:

LICENSE

@@ -263,7 +263,7 @@ The text of each license is also included at licenses/LICENSE-[project].txt.
      (New BSD license) Protocol Buffer Java API (org.spark-project.protobuf:protobuf-java:2.4.1-shaded - http://code.google.com/p/protobuf)
      (The BSD License) Fortran to Java ARPACK (net.sourceforge.f2j:arpack_combined_all:0.1 - http://f2j.sourceforge.net)
      (The BSD License) xmlenc Library (xmlenc:xmlenc:0.52 - http://xmlenc.sourceforge.net)
-     (The New BSD License) Py4J (net.sf.py4j:py4j:0.10.1 - http://py4j.sourceforge.net/)
+     (The New BSD License) Py4J (net.sf.py4j:py4j:0.10.3 - http://py4j.sourceforge.net/)
      (Two-clause BSD-style license) JUnit-Interface (com.novocode:junit-interface:0.10 - http://github.com/szeiger/junit-interface/)
      (BSD licence) sbt and sbt-launch-lib.bash
      (BSD 3 Clause) d3.min.js (https://github.com/mbostock/d3/blob/master/LICENSE)

R/WINDOWS.md

@@ -4,13 +4,23 @@ To build SparkR on Windows, the following steps are required
 
 1. Install R (>= 3.1) and [Rtools](http://cran.r-project.org/bin/windows/Rtools/). Make sure to
 include Rtools and R in `PATH`.
+
 2. Install
 [JDK7](http://www.oracle.com/technetwork/java/javase/downloads/jdk7-downloads-1880260.html) and set
 `JAVA_HOME` in the system environment variables.
+
 3. Download and install [Maven](http://maven.apache.org/download.html). Also include the `bin`
 directory in Maven in `PATH`.
+
 4. Set `MAVEN_OPTS` as described in [Building Spark](http://spark.apache.org/docs/latest/building-spark.html).
-5. Open a command shell (`cmd`) in the Spark directory and run `mvn -DskipTests -Psparkr package`
+
+5. Open a command shell (`cmd`) in the Spark directory and build Spark with [Maven](http://spark.apache.org/docs/latest/building-spark.html#building-with-buildmvn) and include the `-Psparkr` profile to build the R package. For example to use the default Hadoop versions you can run
+
+    ```bash
+    mvn.cmd -DskipTests -Psparkr package
+    ```
+
+    `.\build\mvn` is a shell script so `mvn.cmd` should be used directly on Windows.
 
 ##  Unit tests
 

R/pkg/DESCRIPTION

@@ -2,7 +2,7 @@ Package: SparkR
 Type: Package
 Title: R Frontend for Apache Spark
 Version: 2.0.0
-Date: 2016-07-07
+Date: 2016-08-27
 Authors@R: c(person("Shivaram", "Venkataraman", role = c("aut", "cre"),
                     email = "[email protected]"),
              person("Xiangrui", "Meng", role = "aut",
@@ -11,7 +11,7 @@ Authors@R: c(person("Shivaram", "Venkataraman", role = c("aut", "cre"),
                     email = "[email protected]"),
              person(family = "The Apache Software Foundation", role = c("aut", "cph")))
 URL: http://www.apache.org/ http://spark.apache.org/
-BugReports: https://issues.apache.org/jira/secure/CreateIssueDetails!init.jspa?pid=12315420&components=12325400&issuetype=4
+BugReports: https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark#ContributingtoSpark-ContributingBugReports
 Depends:
     R (>= 3.0),
     methods
@@ -39,6 +39,7 @@ Collate:
     'deserialize.R'
     'functions.R'
     'install.R'
+    'jvm.R'
     'mllib.R'
     'serialize.R'
     'sparkR.R'

R/pkg/NAMESPACE

@@ -27,6 +27,7 @@ exportMethods("glm",
               "summary",
               "spark.kmeans",
               "fitted",
+              "spark.mlp",
               "spark.naiveBayes",
               "spark.survreg",
               "spark.lda",
@@ -363,4 +364,8 @@ S3method(structField, jobj)
 S3method(structType, jobj)
 S3method(structType, structField)
 
+export("sparkR.newJObject")
+export("sparkR.callJMethod")
+export("sparkR.callJStatic")
+
 export("install.spark")

R/pkg/R/DataFrame.R

@@ -212,9 +212,9 @@ setMethod("showDF",
 
 #' show
 #'
-#' Print the SparkDataFrame column names and types
+#' Print class and type information of a Spark object.
 #'
-#' @param object a SparkDataFrame.
+#' @param object a Spark object. Can be a SparkDataFrame, Column, GroupedData, WindowSpec.
 #'
 #' @family SparkDataFrame functions
 #' @rdname show

R/pkg/R/WindowSpec.R

@@ -203,6 +203,18 @@ setMethod("rangeBetween",
 #' @aliases over,Column,WindowSpec-method
 #' @family colum_func
 #' @export
+#' @examples \dontrun{
+#'   df <- createDataFrame(mtcars)
+#'
+#'   # Partition by am (transmission) and order by hp (horsepower)
+#'   ws <- orderBy(windowPartitionBy("am"), "hp")
+#'
+#'   # Rank on hp within each partition
+#'   out <- select(df, over(rank(), ws), df$hp, df$am)
+#'
+#'   # Lag mpg values by 1 row on the partition-and-ordered table
+#'   out <- select(df, over(lead(df$mpg), ws), df$mpg, df$hp, df$am)
+#' }
 #' @note over since 2.0.0
 setMethod("over",
           signature(x = "Column", window = "WindowSpec"),

R/pkg/R/functions.R

@@ -3121,9 +3121,9 @@ setMethod("ifelse",
 #' @aliases cume_dist,missing-method
 #' @export
 #' @examples \dontrun{
-#'   df <- createDataFrame(iris)
-#'   ws <- orderBy(windowPartitionBy("Species"), "Sepal_Length")
-#'   out <- select(df, over(cume_dist(), ws), df$Sepal_Length, df$Species)
+#'   df <- createDataFrame(mtcars)
+#'   ws <- orderBy(windowPartitionBy("am"), "hp")
+#'   out <- select(df, over(cume_dist(), ws), df$hp, df$am)
 #' }
 #' @note cume_dist since 1.6.0
 setMethod("cume_dist",
@@ -3148,7 +3148,11 @@ setMethod("cume_dist",
 #' @family window_funcs
 #' @aliases dense_rank,missing-method
 #' @export
-#' @examples \dontrun{dense_rank()}
+#' @examples \dontrun{
+#'   df <- createDataFrame(mtcars)
+#'   ws <- orderBy(windowPartitionBy("am"), "hp")
+#'   out <- select(df, over(dense_rank(), ws), df$hp, df$am)
+#' }
 #' @note dense_rank since 1.6.0
 setMethod("dense_rank",
           signature("missing"),
@@ -3168,18 +3172,26 @@ setMethod("dense_rank",
 #' @param x the column as a character string or a Column to compute on.
 #' @param offset the number of rows back from the current row from which to obtain a value.
 #'               If not specified, the default is 1.
-#' @param defaultValue default to use when the offset row does not exist.
+#' @param defaultValue (optional) default to use when the offset row does not exist.
 #' @param ... further arguments to be passed to or from other methods.
 #' @rdname lag
 #' @name lag
 #' @aliases lag,characterOrColumn-method
 #' @family window_funcs
 #' @export
-#' @examples \dontrun{lag(df$c)}
+#' @examples \dontrun{
+#'   df <- createDataFrame(mtcars)
+#'
+#'   # Partition by am (transmission) and order by hp (horsepower)
+#'   ws <- orderBy(windowPartitionBy("am"), "hp")
+#'
+#'   # Lag mpg values by 1 row on the partition-and-ordered table
+#'   out <- select(df, over(lag(df$mpg), ws), df$mpg, df$hp, df$am)
+#' }
 #' @note lag since 1.6.0
 setMethod("lag",
           signature(x = "characterOrColumn"),
-          function(x, offset, defaultValue = NULL) {
+          function(x, offset = 1, defaultValue = NULL) {
             col <- if (class(x) == "Column") {
               x@jc
             } else {
@@ -3194,25 +3206,35 @@ setMethod("lag",
 #' lead
 #'
 #' Window function: returns the value that is \code{offset} rows after the current row, and
-#' NULL if there is less than \code{offset} rows after the current row. For example,
-#' an \code{offset} of one will return the next row at any given point in the window partition.
+#' \code{defaultValue} if there is less than \code{offset} rows after the current row.
+#' For example, an \code{offset} of one will return the next row at any given point
+#' in the window partition.
 #'
 #' This is equivalent to the \code{LEAD} function in SQL.
 #'
-#' @param x Column to compute on
-#' @param offset Number of rows to offset
-#' @param defaultValue (Optional) default value to use
+#' @param x the column as a character string or a Column to compute on.
+#' @param offset the number of rows after the current row from which to obtain a value.
+#'               If not specified, the default is 1.
+#' @param defaultValue (optional) default to use when the offset row does not exist.
 #'
 #' @rdname lead
 #' @name lead
 #' @family window_funcs
 #' @aliases lead,characterOrColumn,numeric-method
 #' @export
-#' @examples \dontrun{lead(df$c)}
+#' @examples \dontrun{
+#'   df <- createDataFrame(mtcars)
+#'
+#'   # Partition by am (transmission) and order by hp (horsepower)
+#'   ws <- orderBy(windowPartitionBy("am"), "hp")
+#'
+#'   # Lead mpg values by 1 row on the partition-and-ordered table
+#'   out <- select(df, over(lead(df$mpg), ws), df$mpg, df$hp, df$am)
+#' }
 #' @note lead since 1.6.0
 setMethod("lead",
           signature(x = "characterOrColumn", offset = "numeric", defaultValue = "ANY"),
-          function(x, offset, defaultValue = NULL) {
+          function(x, offset = 1, defaultValue = NULL) {
             col <- if (class(x) == "Column") {
               x@jc
             } else {
@@ -3239,7 +3261,15 @@ setMethod("lead",
 #' @aliases ntile,numeric-method
 #' @family window_funcs
 #' @export
-#' @examples \dontrun{ntile(1)}
+#' @examples \dontrun{
+#'   df <- createDataFrame(mtcars)
+#'
+#'   # Partition by am (transmission) and order by hp (horsepower)
+#'   ws <- orderBy(windowPartitionBy("am"), "hp")
+#'
+#'   # Get ntile group id (1-4) for hp
+#'   out <- select(df, over(ntile(4), ws), df$hp, df$am)
+#' }
 #' @note ntile since 1.6.0
 setMethod("ntile",
           signature(x = "numeric"),
@@ -3263,7 +3293,11 @@ setMethod("ntile",
 #' @family window_funcs
 #' @aliases percent_rank,missing-method
 #' @export
-#' @examples \dontrun{percent_rank()}
+#' @examples \dontrun{
+#'   df <- createDataFrame(mtcars)
+#'   ws <- orderBy(windowPartitionBy("am"), "hp")
+#'   out <- select(df, over(percent_rank(), ws), df$hp, df$am)
+#' }
 #' @note percent_rank since 1.6.0
 setMethod("percent_rank",
           signature("missing"),
@@ -3288,7 +3322,11 @@ setMethod("percent_rank",
 #' @family window_funcs
 #' @aliases rank,missing-method
 #' @export
-#' @examples \dontrun{rank()}
+#' @examples \dontrun{
+#'   df <- createDataFrame(mtcars)
+#'   ws <- orderBy(windowPartitionBy("am"), "hp")
+#'   out <- select(df, over(rank(), ws), df$hp, df$am)
+#' }
 #' @note rank since 1.6.0
 setMethod("rank",
           signature(x = "missing"),
@@ -3321,7 +3359,11 @@ setMethod("rank",
 #' @aliases row_number,missing-method
 #' @family window_funcs
 #' @export
-#' @examples \dontrun{row_number()}
+#' @examples \dontrun{
+#'   df <- createDataFrame(mtcars)
+#'   ws <- orderBy(windowPartitionBy("am"), "hp")
+#'   out <- select(df, over(row_number(), ws), df$hp, df$am)
+#' }
 #' @note row_number since 1.6.0
 setMethod("row_number",
           signature("missing"),

R/pkg/R/generics.R

@@ -1330,6 +1330,10 @@ setGeneric("spark.kmeans", function(data, formula, ...) { standardGeneric("spark
 #' @export
 setGeneric("fitted")
 
+#' @rdname spark.mlp
+#' @export
+setGeneric("spark.mlp", function(data, ...) { standardGeneric("spark.mlp") })
+
 #' @rdname spark.naiveBayes
 #' @export
 setGeneric("spark.naiveBayes", function(data, formula, ...) { standardGeneric("spark.naiveBayes") })