[SPARK-31400][ML]The catalogString doesn't distinguish Vectors in ml and mllib

.github/workflows/branch-2.4.yml

@@ -0,0 +1,104 @@
+name: branch-2.4
+
+on:
+  push:
+    branches:
+    - branch-2.4
+  pull_request:
+    branches:
+    - branch-2.4
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        scala: [ '2.11', '2.12' ]
+        hadoop: [ 'hadoop-2.6', 'hadoop-2.7' ]
+    name: Build Spark with Scala ${{ matrix.scala }} / Hadoop ${{ matrix.hadoop }}
+
+    steps:
+    - uses: actions/checkout@master
+    # We split caches because GitHub Action Cache has a 400MB-size limit.
+    - uses: actions/cache@v1
+      with:
+        path: build
+        key: build-${{ hashFiles('**/pom.xml') }}
+        restore-keys: |
+          build-
+    - uses: actions/cache@v1
+      with:
+        path: ~/.m2/repository/com
+        key: ${{ matrix.scala }}-${{ matrix.hadoop }}-maven-com-${{ hashFiles('**/pom.xml') }}
+        restore-keys: |
+          ${{ matrix.scala }}-${{ matrix.hadoop }}-maven-com-
+    - uses: actions/cache@v1
+      with:
+        path: ~/.m2/repository/org
+        key: ${{ matrix.scala }}-${{ matrix.hadoop }}-maven-org-${{ hashFiles('**/pom.xml') }}
+        restore-keys: |
+          ${{ matrix.scala }}-${{ matrix.hadoop }}-maven-org-
+    - name: Set up JDK 8
+      uses: actions/setup-java@v1
+      with:
+        java-version: '1.8'
+    - name: Change to Scala ${{ matrix.scala }}
+      run: |
+        dev/change-scala-version.sh ${{ matrix.scala }}
+    - name: Build with Maven
+      run: |
+        export MAVEN_OPTS="-Xmx2g -XX:ReservedCodeCacheSize=512m -Dorg.slf4j.simpleLogger.defaultLogLevel=WARN"
+        export MAVEN_CLI_OPTS="--no-transfer-progress"
+        mkdir -p ~/.m2
+        ./build/mvn $MAVEN_CLI_OPTS -DskipTests -Pyarn -Pmesos -Pkubernetes -Phive -Phive-thriftserver -Pscala-${{ matrix.scala }} -P${{ matrix.hadoop }} -Phadoop-cloud install
+        rm -rf ~/.m2/repository/org/apache/spark
+
+
+  lint:
+    runs-on: ubuntu-latest
+    name: Linters (Java/Scala/Python), licenses, dependencies
+    steps:
+    - uses: actions/checkout@master
+    - uses: actions/setup-java@v1
+      with:
+        java-version: '1.8'
+    - uses: actions/setup-python@v1
+      with:
+        python-version: '3.7'
+        architecture: 'x64'
+    - name: Scala
+      run: ./dev/lint-scala
+    - name: Java
+      run: ./dev/lint-java
+    - name: Python
+      run: |
+        pip install flake8 sphinx numpy
+        ./dev/lint-python
+    - name: License
+      run: ./dev/check-license
+    - name: Dependencies
+      run: ./dev/test-dependencies.sh
+
+  lintr:
+    runs-on: ubuntu-latest
+    name: Linter (R)
+    steps:
+    - uses: actions/checkout@master
+    - uses: actions/setup-java@v1
+      with:
+        java-version: '1.8'
+    - name: install R
+      run: |
+        echo 'deb https://cloud.r-project.org/bin/linux/ubuntu bionic-cran35/' | sudo tee -a /etc/apt/sources.list
+        curl -sL "https://keyserver.ubuntu.com/pks/lookup?op=get&search=0xE298A3A825C0D65DFD57CBB651716619E084DAB9" | sudo apt-key add
+        sudo apt-get update
+        sudo apt-get install -y r-base r-base-dev libcurl4-openssl-dev
+    - name: install R packages
+      run: |
+        sudo Rscript -e "install.packages(c('curl', 'xml2', 'httr', 'devtools', 'testthat', 'knitr', 'rmarkdown', 'roxygen2', 'e1071', 'survival'), repos='https://cloud.r-project.org/')"
+        sudo Rscript -e "devtools::install_github('jimhester/[email protected]')"
+    - name: package and install SparkR
+      run: ./R/install-dev.sh
+    - name: lint-r
+      run: ./dev/lint-r

.gitignore

@@ -61,6 +61,7 @@ project/plugins/project/build.properties
 project/plugins/src_managed/
 project/plugins/target/
 python/lib/pyspark.zip
+python/.eggs/
 python/deps
 python/test_coverage/coverage_data
 python/test_coverage/htmlcov

LICENSE

@@ -243,7 +243,7 @@ MIT License
 core/src/main/resources/org/apache/spark/ui/static/dagre-d3.min.js
 core/src/main/resources/org/apache/spark/ui/static/*dataTables*
 core/src/main/resources/org/apache/spark/ui/static/graphlib-dot.min.js
-ore/src/main/resources/org/apache/spark/ui/static/jquery*
+core/src/main/resources/org/apache/spark/ui/static/jquery*
 core/src/main/resources/org/apache/spark/ui/static/sorttable.js
 docs/js/vendor/anchor.min.js
 docs/js/vendor/jquery*

LICENSE-binary

@@ -305,7 +305,6 @@ com.google.code.gson:gson
 com.google.inject:guice
 com.google.inject.extensions:guice-servlet
 com.twitter:parquet-hadoop-bundle
-commons-beanutils:commons-beanutils-core
 commons-cli:commons-cli
 commons-dbcp:commons-dbcp
 commons-io:commons-io
@@ -468,6 +467,7 @@ Common Development and Distribution License (CDDL) 1.1
 ------------------------------------------------------
 
 javax.annotation:javax.annotation-api    https://jcp.org/en/jsr/detail?id=250
+javax.el:javax.el-api	https://javaee.github.io/uel-ri/
 javax.servlet:javax.servlet-api   https://javaee.github.io/servlet-spec/
 javax.transaction:jta http://www.oracle.com/technetwork/java/index.html
 javax.ws.rs:javax.ws.rs-api https://github.com/jax-rs

R/pkg/.lintr

@@ -1,2 +1,2 @@
-linters: with_defaults(line_length_linter(100), multiple_dots_linter = NULL, object_name_linter = NULL, camel_case_linter = NULL, open_curly_linter(allow_single_line = TRUE), closed_curly_linter(allow_single_line = TRUE))
+linters: with_defaults(line_length_linter(100), multiple_dots_linter = NULL, object_name_linter = NULL, camel_case_linter = NULL, open_curly_linter(allow_single_line = TRUE), closed_curly_linter(allow_single_line = TRUE), object_usage_linter = NULL, cyclocomp_linter = NULL)
 exclusions: list("inst/profile/general.R" = 1, "inst/profile/shell.R")

R/pkg/DESCRIPTION

@@ -1,8 +1,8 @@
 Package: SparkR
 Type: Package
-Version: 2.4.0
-Title: R Frontend for Apache Spark
-Description: Provides an R Frontend for Apache Spark.
+Version: 2.4.6
+Title: R Front End for 'Apache Spark'
+Description: Provides an R Front end for 'Apache Spark' <https://spark.apache.org>.
 Authors@R: c(person("Shivaram", "Venkataraman", role = c("aut", "cre"),
                     email = "[email protected]"),
              person("Xiangrui", "Meng", role = "aut",
@@ -11,8 +11,8 @@ Authors@R: c(person("Shivaram", "Venkataraman", role = c("aut", "cre"),
                     email = "[email protected]"),
              person(family = "The Apache Software Foundation", role = c("aut", "cph")))
 License: Apache License (== 2.0)
-URL: http://www.apache.org/ http://spark.apache.org/
-BugReports: http://spark.apache.org/contributing.html
+URL: https://www.apache.org/ https://spark.apache.org/
+BugReports: https://spark.apache.org/contributing.html
 SystemRequirements: Java (== 8)
 Depends:
     R (>= 3.0),
@@ -61,3 +61,4 @@ Collate:
 RoxygenNote: 5.0.1
 VignetteBuilder: knitr
 NeedsCompilation: no
+Encoding: UTF-8

R/pkg/NAMESPACE

@@ -313,7 +313,6 @@ exportMethods("%<=>%",
               "lower",
               "lpad",
               "ltrim",
-              "map_entries",
               "map_from_arrays",
               "map_keys",
               "map_values",

R/pkg/R/DataFrame.R

@@ -503,7 +503,6 @@ setMethod("createOrReplaceTempView",
 #' @param x A SparkDataFrame
 #' @param tableName A character vector containing the name of the table
 #'
-#' @family SparkDataFrame functions
 #' @seealso \link{createOrReplaceTempView}
 #' @rdname registerTempTable-deprecated
 #' @name registerTempTable
@@ -2199,7 +2198,7 @@ setMethod("mutate",
 
             # The last column of the same name in the specific columns takes effect
             deDupCols <- list()
-            for (i in 1:length(cols)) {
+            for (i in seq_len(length(cols))) {
               deDupCols[[ns[[i]]]] <- alias(cols[[i]], ns[[i]])
             }
 
@@ -2363,7 +2362,7 @@ setMethod("arrange",
             # builds a list of columns of type Column
             # example: [[1]] Column Species ASC
             #          [[2]] Column Petal_Length DESC
-            jcols <- lapply(seq_len(length(decreasing)), function(i){
+            jcols <- lapply(seq_len(length(decreasing)), function(i) {
               if (decreasing[[i]]) {
                 desc(getColumn(x, by[[i]]))
               } else {
@@ -2695,7 +2694,7 @@ genAliasesForIntersectedCols <- function(x, intersectedColNames, suffix) {
     col <- getColumn(x, colName)
     if (colName %in% intersectedColNames) {
       newJoin <- paste(colName, suffix, sep = "")
-      if (newJoin %in% allColNames){
+      if (newJoin %in% allColNames) {
         stop("The following column name: ", newJoin, " occurs more than once in the 'DataFrame'.",
           "Please use different suffixes for the intersected columns.")
       }
@@ -3394,7 +3393,7 @@ setMethod("str",
             cat(paste0("'", class(object), "': ", length(names), " variables:\n"))
 
             if (nrow(localDF) > 0) {
-              for (i in 1 : ncol(localDF)) {
+              for (i in seq_len(ncol(localDF))) {
                 # Get the first elements for each column
 
                 firstElements <- if (types[i] == "character") {

R/pkg/R/SQLContext.R

@@ -254,7 +254,7 @@ createDataFrame.default <- function(data, schema = NULL, samplingRatio = 1.0,
       as.list(schema)
     }
     if (is.null(names)) {
-      names <- lapply(1:length(row), function(x) {
+      names <- lapply(seq_len(length(row)), function(x) {
         paste("_", as.character(x), sep = "")
       })
     }
@@ -270,7 +270,7 @@ createDataFrame.default <- function(data, schema = NULL, samplingRatio = 1.0,
     })
 
     types <- lapply(row, infer_type)
-    fields <- lapply(1:length(row), function(i) {
+    fields <- lapply(seq_len(length(row)), function(i) {
       structField(names[[i]], types[[i]], TRUE)
     })
     schema <- do.call(structType, fields)
@@ -655,7 +655,8 @@ loadDF <- function(x = NULL, ...) {
 #'
 #' @param url JDBC database url of the form \code{jdbc:subprotocol:subname}
 #' @param tableName the name of the table in the external database
-#' @param partitionColumn the name of a column of integral type that will be used for partitioning
+#' @param partitionColumn the name of a column of numeric, date, or timestamp type
+#'                        that will be used for partitioning.
 #' @param lowerBound the minimum value of \code{partitionColumn} used to decide partition stride
 #' @param upperBound the maximum value of \code{partitionColumn} used to decide partition stride
 #' @param numPartitions the number of partitions, This, along with \code{lowerBound} (inclusive),

R/pkg/R/catalog.R

@@ -69,7 +69,6 @@ createExternalTable <- function(x, ...) {
 #' @param ... additional named parameters as options for the data source.
 #' @return A SparkDataFrame.
 #' @rdname createTable
-#' @seealso \link{createExternalTable}
 #' @examples
 #'\dontrun{
 #' sparkR.session()