Separate out restricted and unrestricted tasks (#3736)

* Fix #3730: scikit-learn 0.20 compatibility fix

sklearn.cross_validation has been removed from scikit-learn 0.20,
so replace it with sklearn.model_selection

* Display test names for Python tests for clarity

.clang-tidy

@@ -0,0 +1,21 @@
+Checks: 'modernize-*,-modernize-make-*,-modernize-raw-string-literal,google-*,-google-default-arguments,-clang-diagnostic-#pragma-messages,readability-identifier-naming'
+CheckOptions:
+  - { key: readability-identifier-naming.ClassCase,           value: CamelCase  }
+  - { key: readability-identifier-naming.StructCase,          value: CamelCase  }
+  - { key: readability-identifier-naming.TypeAliasCase,          value: CamelCase  }
+  - { key: readability-identifier-naming.TypedefCase,          value: CamelCase  }
+  - { key: readability-identifier-naming.TypeTemplateParameterCase,          value: CamelCase  }
+  - { key: readability-identifier-naming.MemberCase,          value: lower_case  }
+  - { key: readability-identifier-naming.PrivateMemberSuffix,           value: '_'  }
+  - { key: readability-identifier-naming.ProtectedMemberSuffix,           value: '_'  }
+  - { key: readability-identifier-naming.EnumCase,          value: CamelCase  }
+  - { key: readability-identifier-naming.EnumConstant,          value: CamelCase  }
+  - { key: readability-identifier-naming.EnumConstantPrefix,          value: k  }
+  - { key: readability-identifier-naming.GlobalConstantCase,          value: CamelCase  }
+  - { key: readability-identifier-naming.GlobalConstantPrefix,          value: k  }
+  - { key: readability-identifier-naming.StaticConstantCase,          value: CamelCase  }
+  - { key: readability-identifier-naming.StaticConstantPrefix,          value: k  }
+  - { key: readability-identifier-naming.ConstexprVariableCase,          value: CamelCase  }
+  - { key: readability-identifier-naming.ConstexprVariablePrefix,          value: k  }
+  - { key: readability-identifier-naming.FunctionCase,          value: CamelCase  }
+  - { key: readability-identifier-naming.NamespaceCase,       value: lower_case }

.editorconfig

@@ -0,0 +1,11 @@
+root = true
+
+[*]
+charset=utf-8
+indent_style = space
+indent_size = 2
+insert_final_newline = true
+
+[*.py]
+indent_style = space
+indent_size = 4

.github/ISSUE_TEMPLATE.md

@@ -0,0 +1,7 @@
+Thanks for participating in the XGBoost community! We use https://discuss.xgboost.ai for any general usage questions and discussions. The issue tracker is used for actionable items such as feature proposals discussion, roadmaps, and bug tracking.  You are always welcomed to post on the forum first :)
+
+Issues that are inactive for a period of time may get closed. We adopt this policy so that we won't lose track of actionable issues that may fall at the bottom of the pile. Feel free to reopen a new one if you feel there is an additional problem that needs attention when an old one gets closed.
+
+For bug reports, to help the developer act on the issues, please include a description of your environment, preferably a minimum script to reproduce the problem.
+
+For feature proposals, list clear, small actionable items so we can track the progress of the change.

.gitignore

@@ -15,7 +15,6 @@
 *.Rcheck
 *.rds
 *.tar.gz
-#*txt*
 *conf
 *buffer
 *model
@@ -47,13 +46,12 @@ Debug
 *.cpage.col
 *.cpage
 *.Rproj
-./xgboost
 ./xgboost.mpi
 ./xgboost.mock
 #.Rbuildignore
 R-package.Rproj
 *.cache*
-#java
+# java
 java/xgboost4j/target
 java/xgboost4j/tmp
 java/xgboost4j-demo/target
@@ -68,10 +66,9 @@ nb-configuration*
 .settings/
 build
 config.mk
-xgboost
+/xgboost
 *.data
 build_plugin
-dmlc-core
 .idea
 recommonmark/
 tags

.gitmodules

@@ -4,9 +4,6 @@
 [submodule "rabit"]
 	path = rabit
 	url = https://github.com/dmlc/rabit
-[submodule "nccl"]
-	path = nccl
-	url = https://github.com/dmlc/nccl
 [submodule "cub"]
 	path = cub
 	url = https://github.com/NVlabs/cub

.travis.yml

@@ -26,6 +26,8 @@ env:
     - TASK=cmake_test
     # c++ test
     - TASK=cpp_test
+    # distributed test
+    - TASK=distributed_test
 
 matrix:
   exclude:
@@ -39,15 +41,19 @@ matrix:
       env: TASK=python_lightweight_test
     - os: osx
       env: TASK=cpp_test
+    - os: osx
+      env: TASK=distributed_test
 
 # dependent apt packages
 addons:
   apt:
     sources:
+      - llvm-toolchain-trusty-5.0
       - ubuntu-toolchain-r-test
       - george-edison55-precise-backports
     packages:
-      - cmake
+      - clang
+      - clang-tidy-5.0
       - cmake-data
       - doxygen
       - wget

CMakeLists.txt

@@ -8,14 +8,18 @@ set_default_configuration_release()
 msvc_use_static_runtime()
 
 # Options
-option(USE_CUDA  "Build with GPU acceleration") 
+option(USE_CUDA  "Build with GPU acceleration")
-option(USE_AVX  "Build with AVX instructions. May not produce identical results due to approximate math." OFF) 
+option(USE_AVX  "Build with AVX instructions. May not produce identical results due to approximate math." OFF)
-option(USE_NCCL "Build using NCCL for multi-GPU. Also requires USE_CUDA") 
+option(USE_NCCL "Build using NCCL for multi-GPU. Also requires USE_CUDA")
 option(JVM_BINDINGS "Build JVM bindings" OFF)
 option(GOOGLE_TEST "Build google tests" OFF)
 option(R_LIB "Build shared library for R package" OFF)
-set(GPU_COMPUTE_VER 35;50;52;60;61 CACHE STRING
+option(USE_SANITIZER "Use santizer flags" OFF)
-  "Space separated list of compute versions to be built against")
+set(GPU_COMPUTE_VER "" CACHE STRING
+  "Space separated list of compute versions to be built against, e.g. '35 61'")
+set(ENABLED_SANITIZERS "address" "leak" CACHE STRING
+  "Semicolon separated list of sanitizer names. E.g 'address;leak'. Supported sanitizers are
+address, leak and thread.")
 
 # Deprecation warning
 if(PLUGIN_UPDATER_GPU)
@@ -39,6 +43,15 @@ else()
   # Performance
   set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -funroll-loops")
 endif()
+if(WIN32 AND MINGW)
+  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -static-libstdc++")
+endif()
+
+# Sanitizer
+if(USE_SANITIZER)
+  include(cmake/Sanitizer.cmake)
+  enable_sanitizers("${ENABLED_SANITIZERS}")
+endif(USE_SANITIZER)
 
 # AVX
 if(USE_AVX)
@@ -50,6 +63,12 @@ if(USE_AVX)
   add_definitions(-DXGBOOST_USE_AVX)
 endif()
 
+# dmlc-core
+add_subdirectory(dmlc-core)
+set(LINK_LIBRARIES dmlc rabit)
+
+# enable custom logging
+add_definitions(-DDMLC_LOG_CUSTOMIZE=1)
 
 # compiled code customizations for R package
 if(R_LIB)
@@ -70,7 +89,7 @@ include_directories (
     ${PROJECT_SOURCE_DIR}/rabit/include
 )
 
-file(GLOB_RECURSE SOURCES 
+file(GLOB_RECURSE SOURCES
     src/*.cc
     src/*.h
     include/*.h
@@ -103,47 +122,36 @@ else()
   add_library(rabit STATIC ${RABIT_SOURCES})
 endif()
 
-
-# dmlc-core
-add_subdirectory(dmlc-core)
-set(LINK_LIBRARIES dmlccore rabit)
-
-
 if(USE_CUDA)
   find_package(CUDA 8.0 REQUIRED)
   cmake_minimum_required(VERSION 3.5)
 
   add_definitions(-DXGBOOST_USE_CUDA)
-  
+
   include_directories(cub)
 
   if(USE_NCCL)
-    include_directories(nccl/src)
+    find_package(Nccl REQUIRED)
+    include_directories(${NCCL_INCLUDE_DIR})
     add_definitions(-DXGBOOST_USE_NCCL)
   endif()
 
-  if((CUDA_VERSION_MAJOR EQUAL 9) OR (CUDA_VERSION_MAJOR GREATER 9))
-    message("CUDA 9.0 detected, adding Volta compute capability (7.0).")
-    set(GPU_COMPUTE_VER "${GPU_COMPUTE_VER};70")
-  endif()
-  
   set(GENCODE_FLAGS "")
   format_gencode_flags("${GPU_COMPUTE_VER}" GENCODE_FLAGS)
+  message("cuda architecture flags: ${GENCODE_FLAGS}")
+
   set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS};--expt-extended-lambda;--expt-relaxed-constexpr;${GENCODE_FLAGS};-lineinfo;")
   if(NOT MSVC)
-    set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS};-Xcompiler -fPIC; -std=c++11")
+    set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS};-Xcompiler -fPIC; -Xcompiler -Werror; -std=c++11")
-  endif()
-
-  if(USE_NCCL)
-    add_subdirectory(nccl)
   endif()
 
   cuda_add_library(gpuxgboost ${CUDA_SOURCES} STATIC)
-  
+
   if(USE_NCCL)
-    target_link_libraries(gpuxgboost nccl)
+    link_directories(${NCCL_LIBRARY})
+    target_link_libraries(gpuxgboost ${NCCL_LIB_NAME})
   endif()
-  list(APPEND LINK_LIBRARIES gpuxgboost) 
+  list(APPEND LINK_LIBRARIES gpuxgboost)
 endif()
 
 
@@ -224,12 +232,12 @@ endif()
 
 # Test
 if(GOOGLE_TEST)
-  find_package(GTest REQUIRED)
   enable_testing()
+  find_package(GTest REQUIRED)
 
   file(GLOB_RECURSE TEST_SOURCES "tests/cpp/*.cc")
   auto_source_group("${TEST_SOURCES}")
-  include_directories(${GTEST_INCLUDE_DIR})
+  include_directories(${GTEST_INCLUDE_DIRS})
 
   if(USE_CUDA)
     file(GLOB_RECURSE CUDA_TEST_SOURCES "tests/cpp/*.cu")

CONTRIBUTORS.md

@@ -7,8 +7,8 @@ Committers
 Committers are people who have made substantial contribution to the project and granted write access to the project.
 * [Tianqi Chen](https://github.com/tqchen), University of Washington
   - Tianqi is a PhD working on large-scale machine learning, he is the creator of the project.
-* [Tong He](https://github.com/hetong007), Simon Fraser University
+* [Tong He](https://github.com/hetong007), Amazon AI
-  - Tong is a master student working on data mining, he is the maintainer of xgboost R package.
+  - Tong is an applied scientist in Amazon AI, he is the maintainer of xgboost R package.
 * [Vadim Khotilovich](https://github.com/khotilov)
   - Vadim contributes many improvements in R and core packages.
 * [Bing Xu](https://github.com/antinucleon)
@@ -54,7 +54,8 @@ List of Contributors
 * [Masaaki Horikoshi](https://github.com/sinhrks)
   - Masaaki is the initial creator of xgboost python plotting module.
 * [Hongliang Liu](https://github.com/phunterlau)
-  - Hongliang is the maintainer of xgboost python PyPI package for pip installation.
+* [Hyunsu Cho](http://hyunsu-cho.io/)
+  - Hyunsu is the maintainer of the XGBoost Python package. He is in charge of submitting the Python package to Python Package Index (PyPI). He is also the initial author of the CPU 'hist' updater.
 * [daiyl0320](https://github.com/daiyl0320)
   - daiyl0320 contributed patch to xgboost distributed version more robust, and scales stably on TB scale datasets.
 * [Huayi Zhang](https://github.com/irachex)
@@ -72,3 +73,8 @@ List of Contributors
 * [Gideon Whitehead](https://github.com/gaw89)
 * [Yi-Lin Juang](https://github.com/frankyjuang)
 * [Andrew Hannigan](https://github.com/andrewhannigan)
+* [Andy Adinets](https://github.com/canonizer)
+* [Henry Gouk](https://github.com/henrygouk)
+* [Pierre de Sahb](https://github.com/pdesahb)
+* [liuliang01](https://github.com/liuliang01)
+  - liuliang01 added support for the qid column for LibSVM input format. This makes ranking task easier in distributed setting.

ISSUE_TEMPLATE.md

@@ -1,44 +0,0 @@
-For bugs or installation issues, please provide the following information.
-The more information you provide, the more easily we will be able to offer
-help and advice.
-
-## Environment info
-Operating System:
-
-Compiler:
-
-Package used (python/R/jvm/C++):
-
-`xgboost` version used:
-
-If installing from source, please provide 
-
-1. The commit hash (`git rev-parse HEAD`)
-2. Logs will be helpful (If logs are large, please upload as attachment).
-
-If you are using jvm package, please 
-
-1. add [jvm-packages] in the title to make it quickly be identified
-2. the gcc version and distribution
-
-If you are using python package, please provide
-
-1. The python version and distribution
-2. The command to install `xgboost` if you are not installing from source
-
-If you are using R package, please provide
-
-1. The R `sessionInfo()`
-2. The command to install `xgboost` if you are not installing from source
-
-## Steps to reproduce
-
-1.
-2.
-3.
-
-## What have you tried?
-
-1.
-2.
-3.

Jenkinsfile

@@ -3,13 +3,20 @@
 // Jenkins pipeline
 // See documents at https://jenkins.io/doc/book/pipeline/jenkinsfile/
 
+import groovy.transform.Field
+
+/* Unrestricted tasks: tasks that do NOT generate artifacts */
+
 // Command to run command inside a docker container
-dockerRun = 'tests/ci_build/ci_build.sh'
+def dockerRun = 'tests/ci_build/ci_build.sh'
+// Utility functions
+@Field
+def utils
 
 def buildMatrix = [
-    [ "enabled": true,  "os" : "linux", "withGpu": true,  "withOmp": true, "pythonVersion": "2.7" ],
+    [ "enabled": true,  "os" : "linux", "withGpu": true, "withNccl": true,  "withOmp": true, "pythonVersion": "2.7", "cudaVersion": "9.2" ],
-    [ "enabled": true,  "os" : "linux", "withGpu": false, "withOmp": true, "pythonVersion": "2.7" ],
+    [ "enabled": true,  "os" : "linux", "withGpu": true, "withNccl": true,  "withOmp": true, "pythonVersion": "2.7", "cudaVersion": "8.0" ],
-    [ "enabled": false, "os" : "osx",   "withGpu": false, "withOmp": false, "pythonVersion": "2.7" ],
+    [ "enabled": true,  "os" : "linux", "withGpu": true, "withNccl": false, "withOmp": true, "pythonVersion": "2.7", "cudaVersion": "8.0" ],
 ]
 
 pipeline {
@@ -26,20 +33,25 @@ pipeline {
 
     // Build stages
     stages {
-        stage('Get sources') {
+        stage('Jenkins: Get sources') {
-            agent any
+            agent {
+                label 'unrestricted'
+            }
             steps {
-                checkoutSrcs()
+                script {
+                    utils = load('tests/ci_build/jenkins_tools.Groovy')
+                    utils.checkoutSrcs()
+                }
                 stash name: 'srcs', excludes: '.git/'
                 milestone label: 'Sources ready', ordinal: 1
             }
         }
-        stage('Build & Test') {
+        stage('Jenkins: Build & Test') {
             steps {
                 script {
                     parallel (buildMatrix.findAll{it['enabled']}.collectEntries{ c ->
-                        def buildName = getBuildName(c)
+                        def buildName = utils.getBuildName(c)
-                        buildFactory(buildName, c)
+                        utils.buildFactory(buildName, c, false, this.&buildPlatformCmake)
                     })
                 }
             }
@@ -47,40 +59,17 @@ pipeline {
     }
 }
 
-// initialize source codes
-def checkoutSrcs() {
-  retry(5) {
-    try {
-      timeout(time: 2, unit: 'MINUTES') {
-        checkout scm
-        sh 'git submodule update --init'
-      }
-    } catch (exc) {
-      deleteDir()
-      error "Failed to fetch source codes"
-    }
-  }
-}
-
-/**
- * Creates cmake and make builds
- */
-def buildFactory(buildName, conf) {
-    def os = conf["os"]
-    def nodeReq = conf["withGpu"] ? "${os} && gpu" : "${os}"
-    def dockerTarget = conf["withGpu"] ? "gpu" : "cpu"
-    [ ("cmake_${buildName}") : { buildPlatformCmake("cmake_${buildName}", conf, nodeReq, dockerTarget) },
-      ("make_${buildName}") : { buildPlatformMake("make_${buildName}", conf, nodeReq, dockerTarget) }
-    ]
-}
-
 /**
  * Build platform and test it via cmake.
  */
 def buildPlatformCmake(buildName, conf, nodeReq, dockerTarget) {
-    def opts = cmakeOptions(conf)
+    def opts = utils.cmakeOptions(conf)
     // Destination dir for artifacts
     def distDir = "dist/${buildName}"
+    def dockerArgs = ""
+    if(conf["withGpu"]){
+        dockerArgs = "--build-arg CUDA_VERSION=" + conf["cudaVersion"]
+    }
     // Build node - this is returned result
     node(nodeReq) {
         unstash name: 'srcs'
@@ -92,60 +81,8 @@ def buildPlatformCmake(buildName, conf, nodeReq, dockerTarget) {
         """.stripMargin('|')
         // Invoke command inside docker
         sh """
-        ${dockerRun} ${dockerTarget} tests/ci_build/build_via_cmake.sh ${opts}
+        ${dockerRun} ${dockerTarget} ${dockerArgs} tests/ci_build/build_via_cmake.sh ${opts}
-        ${dockerRun} ${dockerTarget} tests/ci_build/test_${dockerTarget}.sh
+        ${dockerRun} ${dockerTarget} ${dockerArgs} tests/ci_build/test_${dockerTarget}.sh
-        ${dockerRun} ${dockerTarget} bash -c "cd python-package; python setup.py bdist_wheel"
-        rm -rf "${distDir}"; mkdir -p "${distDir}/py"
-        cp xgboost "${distDir}"
-        cp -r lib "${distDir}"
-        cp -r python-package/dist "${distDir}/py"
-        """
-        archiveArtifacts artifacts: "${distDir}/**/*.*", allowEmptyArchive: true
-    }
-}
-
-/**
- * Build platform via make
- */
-def buildPlatformMake(buildName, conf, nodeReq, dockerTarget) {
-    def opts = makeOptions(conf)
-    // Destination dir for artifacts
-    def distDir = "dist/${buildName}"
-    // Build node
-    node(nodeReq) {
-        unstash name: 'srcs'
-        echo """
-        |===== XGBoost Make build =====
-        |  dockerTarget: ${dockerTarget}
-        |  makeOpts    : ${opts}
-        |=========================
-        """.stripMargin('|')
-        // Invoke command inside docker
-        sh """
-        ${dockerRun} ${dockerTarget} tests/ci_build/build_via_make.sh ${opts}
         """
     }
 }
-
-def makeOptions(conf) {
-    return ([
-        conf["withGpu"] ? 'PLUGIN_UPDATER_GPU=ON' : 'PLUGIN_UPDATER_GPU=OFF',
-        conf["withOmp"] ? 'USE_OPENMP=1' : 'USE_OPENMP=0']
-        ).join(" ")
-}
-
-
-def cmakeOptions(conf) {
-    return ([
-        conf["withGpu"] ? '-DPLUGIN_UPDATER_GPU:BOOL=ON' : '',
-        conf["withOmp"] ? '-DOPEN_MP:BOOL=ON' : '']
-        ).join(" ")
-}
-
-def getBuildName(conf) {
-    def gpuLabel = conf['withGpu'] ? "_gpu" : "_cpu"
-    def ompLabel = conf['withOmp'] ? "_omp" : ""
-    def pyLabel = "_py${conf['pythonVersion']}"
-    return "${conf['os']}${gpuLabel}${ompLabel}${pyLabel}"
-}
-

Jenkinsfile-restricted

@@ -0,0 +1,121 @@
+#!/usr/bin/groovy
+// -*- mode: groovy -*-
+// Jenkins pipeline
+// See documents at https://jenkins.io/doc/book/pipeline/jenkinsfile/
+
+import groovy.transform.Field
+
+/* Restricted tasks: tasks generating artifacts, such as binary wheels and
+                     documentation */
+
+// Command to run command inside a docker container
+def dockerRun = 'tests/ci_build/ci_build.sh'
+// Utility functions
+@Field
+def utils
+
+def buildMatrix = [
+    [ "enabled": true,  "os" : "linux", "withGpu": true, "withNccl": true,  "withOmp": true, "pythonVersion": "2.7", "cudaVersion": "9.2" ],
+    [ "enabled": true,  "os" : "linux", "withGpu": true, "withNccl": true,  "withOmp": true, "pythonVersion": "2.7", "cudaVersion": "8.0" ],
+    [ "enabled": true,  "os" : "linux", "withGpu": true, "withNccl": false, "withOmp": true, "pythonVersion": "2.7", "cudaVersion": "8.0" ],
+]
+
+pipeline {
+    // Each stage specify its own agent
+    agent none
+
+    // Setup common job properties
+    options {
+        ansiColor('xterm')
+        timestamps()
+        timeout(time: 120, unit: 'MINUTES')
+        buildDiscarder(logRotator(numToKeepStr: '10'))
+    }
+
+    // Build stages
+    stages {
+        stage('Jenkins: Get sources') {
+            agent {
+                label 'restricted'
+            }
+            steps {
+                script {
+                    utils = load('tests/ci_build/jenkins_tools.Groovy')
+                    utils.checkoutSrcs()
+                }
+                stash name: 'srcs', excludes: '.git/'
+                milestone label: 'Sources ready', ordinal: 1
+            }
+        }
+        stage('Jenkins: Build doc') {
+            agent {
+                label 'linux && cpu && restricted'
+            }
+            steps {
+                unstash name: 'srcs'
+                script {
+                    def commit_id = "${GIT_COMMIT}"
+                    def branch_name = "${GIT_LOCAL_BRANCH}"
+                    echo 'Building doc...'
+                    dir ('jvm-packages') {
+                        sh "bash ./build_doc.sh ${commit_id}"
+                        archiveArtifacts artifacts: "${commit_id}.tar.bz2", allowEmptyArchive: true
+                        echo 'Deploying doc...'
+                        withAWS(credentials:'xgboost-doc-bucket') {
+                            s3Upload file: "${commit_id}.tar.bz2", bucket: 'xgboost-docs', acl: 'PublicRead', path: "${branch_name}.tar.bz2"
+                        }
+                    }
+                }
+            }
+        }
+
+        stage('Jenkins: Build artifacts') {
+            steps {
+                script {
+                    parallel (buildMatrix.findAll{it['enabled']}.collectEntries{ c ->
+                        def buildName = utils.getBuildName(c)
+                        utils.buildFactory(buildName, c, true, this.&buildPlatformCmake)
+                    })
+                }
+            }
+        }
+    }
+}
+
+/**
+ * Build platform and test it via cmake.
+ */
+def buildPlatformCmake(buildName, conf, nodeReq, dockerTarget) {
+    def opts = utils.cmakeOptions(conf)
+    // Destination dir for artifacts
+    def distDir = "dist/${buildName}"
+    def dockerArgs = ""
+    if(conf["withGpu"]){
+        dockerArgs = "--build-arg CUDA_VERSION=" + conf["cudaVersion"]
+    }
+    // Build node - this is returned result
+    node(nodeReq) {
+        unstash name: 'srcs'
+        echo """
+        |===== XGBoost CMake build =====
+        |  dockerTarget: ${dockerTarget}
+        |  cmakeOpts   : ${opts}
+        |=========================
+        """.stripMargin('|')
+        // Invoke command inside docker
+        sh """
+        ${dockerRun} ${dockerTarget} ${dockerArgs} tests/ci_build/build_via_cmake.sh ${opts}
+        ${dockerRun} ${dockerTarget} ${dockerArgs} bash -c "cd python-package; rm -f dist/*; python setup.py bdist_wheel --universal"
+        rm -rf "${distDir}"; mkdir -p "${distDir}/py"
+        cp xgboost "${distDir}"
+        cp -r lib "${distDir}"
+        cp -r python-package/dist "${distDir}/py"
+        # Test the wheel for compatibility on a barebones CPU container
+        ${dockerRun} release ${dockerArgs} bash -c " \
+            auditwheel show xgboost-*-py2-none-any.whl
+            pip install --user python-package/dist/xgboost-*-none-any.whl && \
+            python -m nose tests/python"
+        """
+        archiveArtifacts artifacts: "${distDir}/**/*.*", allowEmptyArchive: true
+    }
+}

Makefile

@@ -68,7 +68,7 @@ endif
 endif
 
 export LDFLAGS= -pthread -lm $(ADD_LDFLAGS) $(DMLC_LDFLAGS) $(PLUGIN_LDFLAGS)
-export CFLAGS=  -std=c++11 -Wall -Wno-unknown-pragmas -Iinclude $(ADD_CFLAGS) $(PLUGIN_CFLAGS)
+export CFLAGS= -DDMLC_LOG_CUSTOMIZE=1 -std=c++11 -Wall -Wno-unknown-pragmas -Iinclude $(ADD_CFLAGS) $(PLUGIN_CFLAGS)
 CFLAGS += -I$(DMLC_CORE)/include -I$(RABIT)/include -I$(GTEST_PATH)/include
 #java include path
 export JAVAINCFLAGS = -I${JAVA_HOME}/include -I./java
@@ -261,13 +261,15 @@ Rpack: clean_all
 	cat R-package/src/Makevars.in|sed '2s/.*/PKGROOT=./' | sed '3s/.*/ENABLE_STD_THREAD=0/' > xgboost/src/Makevars.in
 	cp xgboost/src/Makevars.in xgboost/src/Makevars.win
 	sed -i -e 's/@OPENMP_CXXFLAGS@/$$\(SHLIB_OPENMP_CFLAGS\)/g' xgboost/src/Makevars.win
+	bash R-package/remove_warning_suppression_pragma.sh
+	rm xgboost/remove_warning_suppression_pragma.sh
 
 Rbuild: Rpack
 	R CMD build --no-build-vignettes xgboost
 	rm -rf xgboost
 
 Rcheck: Rbuild
-	R CMD check  xgboost*.tar.gz
+	R CMD check xgboost*.tar.gz
 
 -include build/*.d
 -include build/*/*.d

NEWS.md

@@ -3,6 +3,88 @@ XGBoost Change Log
 
 This file records the changes in xgboost library in reverse chronological order.
 
+## v0.80 (2018.08.13)
+* **JVM packages received a major upgrade**: To consolidate the APIs and improve the user experience, we refactored the design of XGBoost4J-Spark in a significant manner. (#3387)
+  - Consolidated APIs: It is now much easier to integrate XGBoost models into a Spark ML pipeline. Users can control behaviors like output leaf prediction results by setting corresponding column names. Training is now more consistent with other Estimators in Spark MLLIB: there is now one single method `fit()` to train decision trees.
+  - Better user experience: we refactored the parameters relevant modules in XGBoost4J-Spark to provide both camel-case (Spark ML style) and underscore (XGBoost style) parameters
+  - A brand-new tutorial is [available](https://xgboost.readthedocs.io/en/release_0.80/jvm/xgboost4j_spark_tutorial.html) for XGBoost4J-Spark.
+  - Latest API documentation is now hosted at https://xgboost.readthedocs.io/.
+* XGBoost documentation now keeps track of multiple versions:
+  - Latest master: https://xgboost.readthedocs.io/en/latest
+  - 0.80 stable: https://xgboost.readthedocs.io/en/release_0.80
+  - 0.72 stable: https://xgboost.readthedocs.io/en/release_0.72
+* Ranking task now uses instance weights (#3379)
+* Fix inaccurate decimal parsing (#3546)
+* New functionality
+  - Query ID column support in LIBSVM data files (#2749). This is convenient for performing ranking task in distributed setting.
+  - Hinge loss for binary classification (`binary:hinge`) (#3477)
+  - Ability to specify delimiter and instance weight column for CSV files (#3546)
+  - Ability to use 1-based indexing instead of 0-based (#3546)
+* GPU support
+  - Quantile sketch, binning, and index compression are now performed on GPU, eliminating PCIe transfer for 'gpu_hist' algorithm (#3319, #3393)
+  - Upgrade to NCCL2 for multi-GPU training (#3404).
+  - Use shared memory atomics for faster training (#3384).
+  - Dynamically allocate GPU memory, to prevent large allocations for deep trees (#3519)
+  - Fix memory copy bug for large files (#3472)
+* Python package
+  - Importing data from Python datatable (#3272)
+  - Pre-built binary wheels available for 64-bit Linux and Windows (#3424, #3443)
+  - Add new importance measures 'total_gain', 'total_cover' (#3498)
+  - Sklearn API now supports saving and loading models (#3192)
+  - Arbitrary cross validation fold indices (#3353)
+  - `predict()` function in Sklearn API uses `best_ntree_limit` if available, to make early stopping easier to use (#3445)
+  - Informational messages are now directed to Python's `print()` rather than standard output (#3438). This way, messages appear inside Jupyter notebooks.
+* R package
+  - Oracle Solaris support, per CRAN policy (#3372)
+* JVM packages
+  - Single-instance prediction (#3464)
+  - Pre-built JARs are now available from Maven Central (#3401)
+  - Add NULL pointer check (#3021)
+  - Consider `spark.task.cpus` when controlling parallelism (#3530)
+  - Handle missing values in prediction (#3529)
+  - Eliminate outputs of `System.out` (#3572)
+* Refactored C++ DMatrix class for simplicity and de-duplication (#3301)
+* Refactored C++ histogram facilities (#3564)
+* Refactored constraints / regularization mechanism for split finding (#3335, #3429). Users may specify an elastic net (L2 + L1 regularization) on leaf weights as well as monotonic constraints on test nodes. The refactor will be useful for a future addition of feature interaction constraints.
+* Statically link `libstdc++` for MinGW32 (#3430)
+* Enable loading from `group`, `base_margin` and `weight` (see [here](http://xgboost.readthedocs.io/en/latest/tutorials/input_format.html#auxiliary-files-for-additional-information)) for Python, R, and JVM packages (#3431)
+* Fix model saving for `count:possion` so that `max_delta_step` doesn't get truncated (#3515)
+* Fix loading of sparse CSC matrix (#3553)
+* Fix incorrect handling of `base_score` parameter for Tweedie regression (#3295)
+
+## v0.72.1 (2018.07.08)
+This version is only applicable for the Python package. The content is identical to that of v0.72.
+
+## v0.72 (2018.06.01)
+* Starting with this release, we plan to make a new release every two months. See #3252 for more details.
+* Fix a pathological behavior (near-zero second-order gradients) in multiclass objective (#3304)
+* Tree dumps now use high precision in storing floating-point values (#3298)
+* Submodules `rabit` and `dmlc-core` have been brought up to date, bringing bug fixes (#3330, #3221).
+* GPU support
+  - Continuous integration tests for GPU code (#3294, #3309)
+  - GPU accelerated coordinate descent algorithm (#3178)
+  - Abstract 1D vector class now works with multiple GPUs (#3287)
+  - Generate PTX code for most recent architecture (#3316)
+  - Fix a memory bug on NVIDIA K80 cards (#3293)
+  - Address performance instability for single-GPU, multi-core machines (#3324)
+* Python package
+  - FreeBSD support (#3247)
+  - Validation of feature names in `Booster.predict()` is now optional (#3323)
+* Updated Sklearn API
+  - Validation sets now support instance weights (#2354)
+  - `XGBClassifier.predict_proba()` should not support `output_margin` option. (#3343) See BREAKING CHANGES below.
+* R package:
+  - Better handling of NULL in `print.xgb.Booster()` (#3338)
+  - Comply with CRAN policy by removing compiler warning suppression (#3329)
+  - Updated CRAN submission
+* JVM packages
+  - JVM packages will now use the same versioning scheme as other packages (#3253)
+  - Update Spark to 2.3 (#3254)
+  - Add scripts to cross-build and deploy artifacts (#3276, #3307)
+  - Fix a compilation error for Scala 2.10 (#3332)
+* BREAKING CHANGES
+  - `XGBClassifier.predict_proba()` no longer accepts paramter `output_margin`. The paramater makes no sense for `predict_proba()` because the method is to predict class probabilities, not raw margin scores.
+
 ## v0.71 (2018.04.11)
 * This is a minor release, mainly motivated by issues concerning `pip install`, e.g. #2426, #3189, #3118, and #3194.
   With this release, users of Linux and MacOS will be able to run `pip install` for the most part.

R-package/DESCRIPTION

@@ -1,8 +1,8 @@
 Package: xgboost
 Type: Package
 Title: Extreme Gradient Boosting
-Version: 0.71.1
+Version: 0.80.1
-Date: 2018-04-11
+Date: 2018-08-13
 Authors@R: c(
   person("Tianqi", "Chen", role = c("aut"),
          email = "tianqi.tchen@gmail.com"),
@@ -14,7 +14,20 @@ Authors@R: c(
          email = "khotilovich@gmail.com"),
   person("Yuan", "Tang", role = c("aut"),
          email = "terrytangyuan@gmail.com",
-         comment = c(ORCID = "0000-0001-5243-233X"))
+         comment = c(ORCID = "0000-0001-5243-233X")),
+  person("Hyunsu", "Cho", role = c("aut"),
+         email = "chohyu01@cs.washington.edu"),
+  person("Kailong", "Chen", role = c("aut")),
+  person("Rory", "Mitchell", role = c("aut")),
+  person("Ignacio", "Cano", role = c("aut")),
+  person("Tianyi", "Zhou", role = c("aut")),
+  person("Mu", "Li", role = c("aut")),
+  person("Junyuan", "Xie", role = c("aut")),
+  person("Min", "Lin", role = c("aut")),
+  person("Yifeng", "Geng", role = c("aut")),
+  person("Yutian", "Li", role = c("aut")),
+  person("XGBoost contributors", role = c("cph"),
+         comment = "base XGBoost implementation")
   )
 Description: Extreme Gradient Boosting, which is an efficient implementation
     of the gradient boosting framework from Chen & Guestrin (2016) <doi:10.1145/2939672.2939785>.
@@ -28,6 +41,7 @@ Description: Extreme Gradient Boosting, which is an efficient implementation
 License: Apache License (== 2.0) | file LICENSE
 URL: https://github.com/dmlc/xgboost
 BugReports: https://github.com/dmlc/xgboost/issues
+NeedsCompilation: yes
 VignetteBuilder: knitr
 Suggests:
     knitr,
@@ -37,6 +51,7 @@ Suggests:
     Ckmeans.1d.dp (>= 3.3.1),
     vcd (>= 1.3),
     testthat,
+    lintr,
     igraph (>= 1.0.1)
 Depends:
     R (>= 3.3.0)

R-package/R/callbacks.R

@@ -168,7 +168,7 @@ cb.evaluation.log <- function() {
 #' at the beginning of each iteration.
 #' 
 #' Note that when training is resumed from some previous model, and a function is used to 
-#' reset a parameter value, the \code{nround} argument in this function would be the 
+#' reset a parameter value, the \code{nrounds} argument in this function would be the 
 #' the number of boosting rounds in the current training.
 #'
 #' Callback function expects the following values to be set in its calling frame:
@@ -691,11 +691,6 @@ cb.gblinear.history <- function(sparse=FALSE) {
 #' For an \code{xgb.cv} result, a list of such matrices is returned with the elements
 #' corresponding to CV folds.
 #'
-#' @examples
-#' \dontrun{
-#' See \code{\link{cv.gblinear.history}}
-#' }
-#'
 #' @export
 xgb.gblinear.history <- function(model, class_index = NULL) {
 

R-package/R/xgb.Booster.R

@@ -37,11 +37,14 @@ xgb.handleToBooster <- function(handle, raw = NULL) {
 # Check whether xgb.Booster.handle is null
 # internal utility function
 is.null.handle <- function(handle) {
+  if (is.null(handle)) return(TRUE)
+
   if (!identical(class(handle), "xgb.Booster.handle"))
     stop("argument type must be xgb.Booster.handle")
 
-  if (is.null(handle) || .Call(XGCheckNullPtr_R, handle))
+  if (.Call(XGCheckNullPtr_R, handle))
     return(TRUE)
+
   return(FALSE)
 }
 
@@ -537,7 +540,7 @@ xgb.ntree <- function(bst) {
 print.xgb.Booster <- function(x, verbose = FALSE, ...) {
   cat('##### xgb.Booster\n')
 
-  valid_handle <- is.null.handle(x$handle)
+  valid_handle <- !is.null.handle(x$handle)
   if (!valid_handle)
     cat("Handle is invalid! Suggest using xgb.Booster.complete\n")
 

R-package/R/xgb.create.features.R

@@ -52,9 +52,9 @@
 #' dtest <- xgb.DMatrix(data = agaricus.test$data, label = agaricus.test$label)
 #'
 #' param <- list(max_depth=2, eta=1, silent=1, objective='binary:logistic')
-#' nround = 4
+#' nrounds = 4
 #'
-#' bst = xgb.train(params = param, data = dtrain, nrounds = nround, nthread = 2)
+#' bst = xgb.train(params = param, data = dtrain, nrounds = nrounds, nthread = 2)
 #' 
 #' # Model accuracy without new features
 #' accuracy.before <- sum((predict(bst, agaricus.test$data) >= 0.5) == agaricus.test$label) /
@@ -68,7 +68,7 @@
 #' new.dtrain <- xgb.DMatrix(data = new.features.train, label = agaricus.train$label)
 #' new.dtest <- xgb.DMatrix(data = new.features.test, label = agaricus.test$label)
 #' watchlist <- list(train = new.dtrain)
-#' bst <- xgb.train(params = param, data = new.dtrain, nrounds = nround, nthread = 2)
+#' bst <- xgb.train(params = param, data = new.dtrain, nrounds = nrounds, nthread = 2)
 #' 
 #' # Model accuracy with new features
 #' accuracy.after <- sum((predict(bst, new.dtest) >= 0.5) == agaricus.test$label) /

R-package/R/xgb.cv.R

@@ -83,7 +83,7 @@
 #'   \item \code{params} parameters that were passed to the xgboost library. Note that it does not 
 #'         capture parameters changed by the \code{\link{cb.reset.parameters}} callback.
 #'   \item \code{callbacks} callback functions that were either automatically assigned or 
-#'         explicitely passed.
+#'         explicitly passed.
 #'   \item \code{evaluation_log} evaluation history storead as a \code{data.table} with the
 #'         first column corresponding to iteration number and the rest corresponding to the 
 #'         CV-based evaluation means and standard deviations for the training and test CV-sets.

R-package/R/xgb.dump.R

@@ -30,7 +30,8 @@
 #' bst <- xgboost(data = train$data, label = train$label, max_depth = 2, 
 #'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
 #' # save the model in file 'xgb.model.dump'
-#' xgb.dump(bst, 'xgb.model.dump', with_stats = TRUE)
+#' dump_path = file.path(tempdir(), 'model.dump')
+#' xgb.dump(bst, dump_path, with_stats = TRUE)
 #' 
 #' # print the model without saving it to a file
 #' print(xgb.dump(bst, with_stats = TRUE))

R-package/R/xgb.plot.shap.R

@@ -212,6 +212,7 @@ xgb.plot.shap <- function(data, shap_contrib = NULL, features = NULL, top_n = 1,
   }
   if (plot && which == "2d") {
     # TODO
+    warning("Bivariate plotting is currently not available.")
   }
   invisible(list(data = data, shap_contrib = shap_contrib))
 }

R-package/R/xgb.train.R

@@ -22,7 +22,7 @@
 #'   \item \code{gamma} minimum loss reduction required to make a further partition on a leaf node of the tree. the larger, the more conservative the algorithm will be. 
 #'   \item \code{max_depth} maximum depth of a tree. Default: 6
 #'   \item \code{min_child_weight} minimum sum of instance weight (hessian) needed in a child. If the tree partition step results in a leaf node with the sum of instance weight less than min_child_weight, then the building process will give up further partitioning. In linear regression mode, this simply corresponds to minimum number of instances needed to be in each node. The larger, the more conservative the algorithm will be. Default: 1
-#'   \item \code{subsample} subsample ratio of the training instance. Setting it to 0.5 means that xgboost randomly collected half of the data instances to grow trees and this will prevent overfitting. It makes computation shorter (because less data to analyse). It is advised to use this parameter with \code{eta} and increase \code{nround}. Default: 1 
+#'   \item \code{subsample} subsample ratio of the training instance. Setting it to 0.5 means that xgboost randomly collected half of the data instances to grow trees and this will prevent overfitting. It makes computation shorter (because less data to analyse). It is advised to use this parameter with \code{eta} and increase \code{nrounds}. Default: 1 
 #'   \item \code{colsample_bytree} subsample ratio of columns when constructing each tree. Default: 1
 #'   \item \code{num_parallel_tree} Experimental parameter. number of trees to grow per round. Useful to test Random Forest through Xgboost (set \code{colsample_bytree < 1}, \code{subsample  < 1}  and \code{round = 1}) accordingly. Default: 1
 #'   \item \code{monotone_constraints} A numerical vector consists of \code{1}, \code{0} and \code{-1} with its length equals to the number of features in the training data. \code{1} is increasing, \code{-1} is decreasing and \code{0} is no constraint.

R-package/README.md

@@ -30,4 +30,4 @@ Examples
 Development
 -----------
 
-* See the [R Package section](https://xgboost.readthedocs.io/en/latest/how_to/contribute.html#r-package) of the contributiors guide.
+* See the [R Package section](https://xgboost.readthedocs.io/en/latest/how_to/contribute.html#r-package) of the contributors guide.

R-package/demo/basic_walkthrough.R

@@ -99,7 +99,8 @@ err <- as.numeric(sum(as.integer(pred > 0.5) != label))/length(label)
 print(paste("test-error=", err))
 
 # You can dump the tree you learned using xgb.dump into a text file
-xgb.dump(bst, "dump.raw.txt", with_stats = T)
+dump_path = file.path(tempdir(), 'dump.raw.txt')
+xgb.dump(bst, dump_path, with_stats = T)
 
 # Finally, you can check which features are the most important.
 print("Most important features (look at column Gain):")

R-package/demo/cross_validation.R

@@ -5,20 +5,20 @@ data(agaricus.test, package='xgboost')
 dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
 dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 
-nround <- 2
+nrounds <- 2
 param <- list(max_depth=2, eta=1, silent=1, nthread=2, objective='binary:logistic')
 
 cat('running cross validation\n')
 # do cross validation, this will print result out as
 # [iteration]  metric_name:mean_value+std_value
 # std_value is standard deviation of the metric
-xgb.cv(param, dtrain, nround, nfold=5, metrics={'error'})
+xgb.cv(param, dtrain, nrounds, nfold=5, metrics={'error'})
 
 cat('running cross validation, disable standard deviation display\n')
 # do cross validation, this will print result out as
 # [iteration]  metric_name:mean_value+std_value
 # std_value is standard deviation of the metric
-xgb.cv(param, dtrain, nround, nfold=5,
+xgb.cv(param, dtrain, nrounds, nfold=5,
        metrics='error', showsd = FALSE)
 
 ###
@@ -43,9 +43,9 @@ evalerror <- function(preds, dtrain) {
 param <- list(max_depth=2, eta=1, silent=1,
               objective = logregobj, eval_metric = evalerror)
 # train with customized objective
-xgb.cv(params = param, data = dtrain, nrounds = nround, nfold = 5)
+xgb.cv(params = param, data = dtrain, nrounds = nrounds, nfold = 5)
 
 # do cross validation with prediction values for each fold
-res <- xgb.cv(params = param, data = dtrain, nrounds = nround, nfold = 5, prediction = TRUE)
+res <- xgb.cv(params = param, data = dtrain, nrounds = nrounds, nfold = 5, prediction = TRUE)
 res$evaluation_log
 length(res$pred)

R-package/demo/predict_first_ntree.R

@@ -7,10 +7,10 @@ dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 
 param <- list(max_depth=2, eta=1, silent=1, objective='binary:logistic')
 watchlist <- list(eval = dtest, train = dtrain)
-nround = 2
+nrounds = 2
 
 # training the model for two rounds
-bst = xgb.train(param, dtrain, nround, nthread = 2, watchlist)
+bst = xgb.train(param, dtrain, nrounds, nthread = 2, watchlist)
 cat('start testing prediction from first n trees\n')
 labels <- getinfo(dtest,'label')
 

R-package/demo/predict_leaf_indices.R

@@ -11,10 +11,10 @@ dtrain <- xgb.DMatrix(data = agaricus.train$data, label = agaricus.train$label)
 dtest <- xgb.DMatrix(data = agaricus.test$data, label = agaricus.test$label)
 
 param <- list(max_depth=2, eta=1, silent=1, objective='binary:logistic')
-nround = 4
+nrounds = 4
 
 # training the model for two rounds
-bst = xgb.train(params = param, data = dtrain, nrounds = nround, nthread = 2)
+bst = xgb.train(params = param, data = dtrain, nrounds = nrounds, nthread = 2)
 
 # Model accuracy without new features
 accuracy.before <- sum((predict(bst, agaricus.test$data) >= 0.5) == agaricus.test$label) / length(agaricus.test$label)
@@ -43,7 +43,7 @@ new.features.test <- create.new.tree.features(bst, agaricus.test$data)
 new.dtrain <- xgb.DMatrix(data = new.features.train, label = agaricus.train$label)
 new.dtest <- xgb.DMatrix(data = new.features.test, label = agaricus.test$label)
 watchlist <- list(train = new.dtrain)
-bst <- xgb.train(params = param, data = new.dtrain, nrounds = nround, nthread = 2)
+bst <- xgb.train(params = param, data = new.dtrain, nrounds = nrounds, nthread = 2)
 
 # Model accuracy with new features
 accuracy.after <- sum((predict(bst, new.dtest) >= 0.5) == agaricus.test$label) / length(agaricus.test$label)

R-package/man/cb.reset.parameters.Rd

@@ -22,7 +22,7 @@ This is a "pre-iteration" callback function used to reset booster's parameters
 at the beginning of each iteration.
 
 Note that when training is resumed from some previous model, and a function is used to 
-reset a parameter value, the \code{nround} argument in this function would be the 
+reset a parameter value, the \code{nrounds} argument in this function would be the 
 the number of boosting rounds in the current training.
 
 Callback function expects the following values to be set in its calling frame:

R-package/man/xgb.create.features.Rd

@@ -63,9 +63,9 @@ dtrain <- xgb.DMatrix(data = agaricus.train$data, label = agaricus.train$label)
 dtest <- xgb.DMatrix(data = agaricus.test$data, label = agaricus.test$label)
 
 param <- list(max_depth=2, eta=1, silent=1, objective='binary:logistic')
-nround = 4
+nrounds = 4
 
-bst = xgb.train(params = param, data = dtrain, nrounds = nround, nthread = 2)
+bst = xgb.train(params = param, data = dtrain, nrounds = nrounds, nthread = 2)
 
 # Model accuracy without new features
 accuracy.before <- sum((predict(bst, agaricus.test$data) >= 0.5) == agaricus.test$label) /
@@ -79,7 +79,7 @@ new.features.test <- xgb.create.features(model = bst, agaricus.test$data)
 new.dtrain <- xgb.DMatrix(data = new.features.train, label = agaricus.train$label)
 new.dtest <- xgb.DMatrix(data = new.features.test, label = agaricus.test$label)
 watchlist <- list(train = new.dtrain)
-bst <- xgb.train(params = param, data = new.dtrain, nrounds = nround, nthread = 2)
+bst <- xgb.train(params = param, data = new.dtrain, nrounds = nrounds, nthread = 2)
 
 # Model accuracy with new features
 accuracy.after <- sum((predict(bst, new.dtest) >= 0.5) == agaricus.test$label) /

R-package/man/xgb.cv.Rd

@@ -99,7 +99,7 @@ An object of class \code{xgb.cv.synchronous} with the following elements:
   \item \code{params} parameters that were passed to the xgboost library. Note that it does not 
         capture parameters changed by the \code{\link{cb.reset.parameters}} callback.
   \item \code{callbacks} callback functions that were either automatically assigned or 
-        explicitely passed.
+        explicitly passed.
   \item \code{evaluation_log} evaluation history storead as a \code{data.table} with the
         first column corresponding to iteration number and the rest corresponding to the 
         CV-based evaluation means and standard deviations for the training and test CV-sets.

R-package/man/xgb.dump.Rd

@@ -44,7 +44,8 @@ test <- agaricus.test
 bst <- xgboost(data = train$data, label = train$label, max_depth = 2, 
                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
 # save the model in file 'xgb.model.dump'
-xgb.dump(bst, 'xgb.model.dump', with_stats = TRUE)
+dump.path = file.path(tempdir(), 'model.dump')
+xgb.dump(bst, dump.path, with_stats = TRUE)
 
 # print the model without saving it to a file
 print(xgb.dump(bst, with_stats = TRUE))

R-package/man/xgb.gblinear.history.Rd

@@ -27,9 +27,3 @@ A helper function to extract the matrix of linear coefficients' history
 from a gblinear model created while using the \code{cb.gblinear.history()}
 callback.
 }
-\examples{
-\dontrun{
-See \\code{\\link{cv.gblinear.history}}
-}
-
-}

R-package/man/xgb.train.Rd

@@ -35,7 +35,7 @@ xgboost(data = NULL, label = NULL, missing = NA, weight = NULL,
   \item \code{gamma} minimum loss reduction required to make a further partition on a leaf node of the tree. the larger, the more conservative the algorithm will be. 
   \item \code{max_depth} maximum depth of a tree. Default: 6
   \item \code{min_child_weight} minimum sum of instance weight (hessian) needed in a child. If the tree partition step results in a leaf node with the sum of instance weight less than min_child_weight, then the building process will give up further partitioning. In linear regression mode, this simply corresponds to minimum number of instances needed to be in each node. The larger, the more conservative the algorithm will be. Default: 1
-  \item \code{subsample} subsample ratio of the training instance. Setting it to 0.5 means that xgboost randomly collected half of the data instances to grow trees and this will prevent overfitting. It makes computation shorter (because less data to analyse). It is advised to use this parameter with \code{eta} and increase \code{nround}. Default: 1 
+  \item \code{subsample} subsample ratio of the training instance. Setting it to 0.5 means that xgboost randomly collected half of the data instances to grow trees and this will prevent overfitting. It makes computation shorter (because less data to analyse). It is advised to use this parameter with \code{eta} and increase \code{nrounds}. Default: 1 
   \item \code{colsample_bytree} subsample ratio of columns when constructing each tree. Default: 1
   \item \code{num_parallel_tree} Experimental parameter. number of trees to grow per round. Useful to test Random Forest through Xgboost (set \code{colsample_bytree < 1}, \code{subsample  < 1}  and \code{round = 1}) accordingly. Default: 1
   \item \code{monotone_constraints} A numerical vector consists of \code{1}, \code{0} and \code{-1} with its length equals to the number of features in the training data. \code{1} is increasing, \code{-1} is decreasing and \code{0} is no constraint.

R-package/remove_warning_suppression_pragma.sh

@@ -0,0 +1,14 @@
+#!/bin/bash
+# remove all #pragma's that suppress compiler warnings
+set -e
+set -x
+for file in xgboost/src/dmlc-core/include/dmlc/*.h
+do
+  sed -i.bak -e 's/^.*#pragma GCC diagnostic.*$//' -e 's/^.*#pragma clang diagnostic.*$//' -e 's/^.*#pragma warning.*$//' "${file}"
+done
+for file in xgboost/src/dmlc-core/include/dmlc/*.h.bak
+do
+  rm "${file}"
+done
+set +x
+set +e

R-package/tests/testthat/test_dmatrix.R

@@ -77,6 +77,18 @@ test_that("xgb.DMatrix: slice, dim", {
   expect_equal(getinfo(dsub1, 'label'), getinfo(dsub2, 'label'))
 })
 
+test_that("xgb.DMatrix: slice, trailing empty rows", {
+  data(agaricus.train, package='xgboost')
+  train_data <- agaricus.train$data
+  train_label <- agaricus.train$label
+  dtrain <- xgb.DMatrix(data=train_data, label=train_label)
+  slice(dtrain, 6513L)
+  train_data[6513, ] <- 0
+  dtrain <- xgb.DMatrix(data=train_data, label=train_label)
+  slice(dtrain, 6513L)
+  expect_equal(nrow(dtrain), 6513)
+})
+
 test_that("xgb.DMatrix: colnames", {
   dtest <- xgb.DMatrix(test_data, label=test_label)
   expect_equal(colnames(dtest), colnames(test_data))

R-package/tests/testthat/test_gc_safety.R

@@ -9,7 +9,7 @@ test_that("train and prediction when gctorture is on", {
   test <- agaricus.test
   gctorture(TRUE)
   bst <- xgboost(data = train$data, label = train$label, max.depth = 2,
-  eta = 1, nthread = 2, nround = 2, objective = "binary:logistic")
+  eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
   pred <- predict(bst, test$data)
   gctorture(FALSE)
 })

R-package/tests/testthat/test_helpers.R

@@ -7,6 +7,9 @@ require(vcd, quietly = TRUE)
 
 float_tolerance = 5e-6
 
+# disable some tests for Win32
+win32_flag = .Platform$OS.type == "windows" && .Machine$sizeof.pointer != 8
+
 set.seed(1982)
 data(Arthritis)
 df <- data.table(Arthritis, keep.rownames = F)
@@ -41,15 +44,18 @@ mbst.GLM <- xgboost(data = as.matrix(iris[, -5]), label = mlabel, verbose = 0,
 
 
 test_that("xgb.dump works", {
-  expect_length(xgb.dump(bst.Tree), 200)
+  if (!win32_flag)
-  expect_true(xgb.dump(bst.Tree, 'xgb.model.dump', with_stats = T))
+    expect_length(xgb.dump(bst.Tree), 200)
-  expect_true(file.exists('xgb.model.dump'))
+  dump_file = file.path(tempdir(), 'xgb.model.dump')
-  expect_gt(file.size('xgb.model.dump'), 8000)
+  expect_true(xgb.dump(bst.Tree, dump_file, with_stats = T))
+  expect_true(file.exists(dump_file))
+  expect_gt(file.size(dump_file), 8000)
 
   # JSON format
   dmp <- xgb.dump(bst.Tree, dump_format = "json")
   expect_length(dmp, 1)
-  expect_length(grep('nodeid', strsplit(dmp, '\n')[[1]]), 188)
+  if (!win32_flag)
+    expect_length(grep('nodeid', strsplit(dmp, '\n')[[1]]), 188)
 })
 
 test_that("xgb.dump works for gblinear", {
@@ -209,7 +215,8 @@ test_that("xgb.model.dt.tree works with and without feature names", {
   names.dt.trees <- c("Tree", "Node", "ID", "Feature", "Split", "Yes", "No", "Missing", "Quality", "Cover")
   dt.tree <- xgb.model.dt.tree(feature_names = feature.names, model = bst.Tree)
   expect_equal(names.dt.trees, names(dt.tree))
-  expect_equal(dim(dt.tree), c(188, 10))
+  if (!win32_flag)
+    expect_equal(dim(dt.tree), c(188, 10))
   expect_output(str(dt.tree), 'Feature.*\\"Age\\"')
 
   dt.tree.0 <- xgb.model.dt.tree(model = bst.Tree)
@@ -235,7 +242,8 @@ test_that("xgb.model.dt.tree throws error for gblinear", {
 
 test_that("xgb.importance works with and without feature names", {
   importance.Tree <- xgb.importance(feature_names = feature.names, model = bst.Tree)
-  expect_equal(dim(importance.Tree), c(7, 4))
+  if (!win32_flag)
+    expect_equal(dim(importance.Tree), c(7, 4))
   expect_equal(colnames(importance.Tree), c("Feature", "Gain", "Cover", "Frequency"))
   expect_output(str(importance.Tree), 'Feature.*\\"Age\\"')
 

R-package/tests/testthat/test_update.R

@@ -7,6 +7,10 @@ data(agaricus.test, package = 'xgboost')
 dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
 dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 
+# Disable flaky tests for 32-bit Windows.
+# See https://github.com/dmlc/xgboost/issues/3720
+win32_flag = .Platform$OS.type == "windows" && .Machine$sizeof.pointer != 8
+
 test_that("updating the model works", {
   watchlist = list(train = dtrain, test = dtest)
 
@@ -29,7 +33,9 @@ test_that("updating the model works", {
   tr1r <- xgb.model.dt.tree(model = bst1r)
   # all should be the same when no subsampling
   expect_equal(bst1$evaluation_log, bst1r$evaluation_log)
-  expect_equal(tr1, tr1r, tolerance = 0.00001, check.attributes = FALSE)
+  if (!win32_flag) {
+    expect_equal(tr1, tr1r, tolerance = 0.00001, check.attributes = FALSE)
+  }
 
   # the same boosting with subsampling with an extra 'refresh' updater:
   p2r <- modifyList(p2, list(updater = 'grow_colmaker,prune,refresh', refresh_leaf = FALSE))
@@ -38,7 +44,9 @@ test_that("updating the model works", {
   tr2r <- xgb.model.dt.tree(model = bst2r)
   # should be the same evaluation but different gains and larger cover
   expect_equal(bst2$evaluation_log, bst2r$evaluation_log)
-  expect_equal(tr2[Feature == 'Leaf']$Quality, tr2r[Feature == 'Leaf']$Quality)
+  if (!win32_flag) {
+    expect_equal(tr2[Feature == 'Leaf']$Quality, tr2r[Feature == 'Leaf']$Quality)
+  }
   expect_gt(sum(abs(tr2[Feature != 'Leaf']$Quality - tr2r[Feature != 'Leaf']$Quality)), 100)
   expect_gt(sum(tr2r$Cover) / sum(tr2$Cover), 1.5)
 
@@ -61,7 +69,9 @@ test_that("updating the model works", {
   expect_gt(sum(tr2u$Cover) / sum(tr2$Cover), 1.5)
   # the results should be the same as for the model with an extra 'refresh' updater
   expect_equal(bst2r$evaluation_log, bst2u$evaluation_log)
-  expect_equal(tr2r, tr2u, tolerance = 0.00001, check.attributes = FALSE)
+  if (!win32_flag) {
+    expect_equal(tr2r, tr2u, tolerance = 0.00001, check.attributes = FALSE)
+  }
   
   # process type 'update' for no-subsampling model, refreshing only the tree stats from TEST data:
   p1ut <- modifyList(p1, list(process_type = 'update', updater = 'refresh', refresh_leaf = FALSE))

README.md

@@ -6,46 +6,28 @@
 [![GitHub license](http://dmlc.github.io/img/apache2.svg)](./LICENSE)
 [![CRAN Status Badge](http://www.r-pkg.org/badges/version/xgboost)](http://cran.r-project.org/web/packages/xgboost)
 [![PyPI version](https://badge.fury.io/py/xgboost.svg)](https://pypi.python.org/pypi/xgboost/)
-[![Gitter chat for developers at https://gitter.im/dmlc/xgboost](https://badges.gitter.im/Join%20Chat.svg)](https://gitter.im/dmlc/xgboost?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge)
 
+[Community](https://xgboost.ai/community) |
 [Documentation](https://xgboost.readthedocs.org) |
 [Resources](demo/README.md) |
-[Installation](https://xgboost.readthedocs.org/en/latest/build.html) |
+[Contributors](CONTRIBUTORS.md) |
-[Release Notes](NEWS.md) |
+[Release Notes](NEWS.md)
-[RoadMap](https://github.com/dmlc/xgboost/issues/873)
 
 XGBoost is an optimized distributed gradient boosting library designed to be highly ***efficient***, ***flexible*** and ***portable***.
 It implements machine learning algorithms under the [Gradient Boosting](https://en.wikipedia.org/wiki/Gradient_boosting) framework.
 XGBoost provides a parallel tree boosting (also known as GBDT, GBM) that solve many data science problems in a fast and accurate way.
 The same code runs on major distributed environment (Hadoop, SGE, MPI) and can solve problems beyond billions of examples.
 
-What's New
-----------
-* [XGBoost GPU support with fast histogram algorithm](https://github.com/dmlc/xgboost/tree/master/plugin/updater_gpu)
-* [XGBoost4J: Portable Distributed XGboost in Spark, Flink and Dataflow](http://dmlc.ml/2016/03/14/xgboost4j-portable-distributed-xgboost-in-spark-flink-and-dataflow.html), see [JVM-Package](https://github.com/dmlc/xgboost/tree/master/jvm-packages)
-* [Story and Lessons Behind the Evolution of XGBoost](http://homes.cs.washington.edu/~tqchen/2016/03/10/story-and-lessons-behind-the-evolution-of-xgboost.html)
-* [Tutorial: Distributed XGBoost on AWS with YARN](https://xgboost.readthedocs.io/en/latest/tutorials/aws_yarn.html)
-* [XGBoost brick](NEWS.md) Release
-
-Ask a Question
---------------
-* For reporting bugs please use the [xgboost/issues](https://github.com/dmlc/xgboost/issues) page.
-* For generic questions or to share your experience using XGBoost please use the [XGBoost User Group](https://groups.google.com/forum/#!forum/xgboost-user/)
-
-Help to Make XGBoost Better
----------------------------
-XGBoost has been developed and used by a group of active community members. Your help is very valuable to make the package better for everyone.
-- Check out [call for contributions](https://github.com/dmlc/xgboost/issues?q=is%3Aissue+label%3Acall-for-contribution+is%3Aopen) and [Roadmap](https://github.com/dmlc/xgboost/issues/873) to see what can be improved, or open an issue if you want something.
-- Contribute to the [documents and examples](https://github.com/dmlc/xgboost/blob/master/doc/) to share your experience with other users.
-- Add your stories and experience to [Awesome XGBoost](demo/README.md).
-- Please add your name to [CONTRIBUTORS.md](CONTRIBUTORS.md) and after your patch has been merged.
-  - Please also update [NEWS.md](NEWS.md) on changes and improvements in API and docs.
-
 License
 -------
 © Contributors, 2016. Licensed under an [Apache-2](https://github.com/dmlc/xgboost/blob/master/LICENSE) license.
 
+Contribute to XGBoost
+---------------------
+XGBoost has been developed and used by a group of active community members. Your help is very valuable to make the package better for everyone.
+Checkout the [Community Page](https://xgboost.ai/community)
+
 Reference
 ---------
-- Tianqi Chen and Carlos Guestrin. [XGBoost: A Scalable Tree Boosting System](http://arxiv.org/abs/1603.02754). In 22nd SIGKDD Conference on Knowledge Discovery and Data Mining, 2016 
+- Tianqi Chen and Carlos Guestrin. [XGBoost: A Scalable Tree Boosting System](http://arxiv.org/abs/1603.02754). In 22nd SIGKDD Conference on Knowledge Discovery and Data Mining, 2016
-- XGBoost originates from research project at University of Washington, see also the [Project Page at UW](http://dmlc.cs.washington.edu/xgboost.html).
+- XGBoost originates from research project at University of Washington.

amalgamation/dmlc-minimum0.cc

@@ -7,6 +7,8 @@
 #include "../dmlc-core/src/io/recordio_split.cc"
 #include "../dmlc-core/src/io/input_split_base.cc"
 #include "../dmlc-core/src/io/local_filesys.cc"
+#include "../dmlc-core/src/io/filesys.cc"
+#include "../dmlc-core/src/io/indexed_recordio_split.cc"
 #include "../dmlc-core/src/data.cc"
 #include "../dmlc-core/src/io.cc"
 #include "../dmlc-core/src/recordio.cc"

amalgamation/xgboost-all0.cc

@@ -20,6 +20,7 @@
 #include "../src/objective/regression_obj.cc"
 #include "../src/objective/multiclass_obj.cc"
 #include "../src/objective/rank_obj.cc"
+#include "../src/objective/hinge.cc"
 
 // gbms
 #include "../src/gbm/gbm.cc"
@@ -43,6 +44,7 @@
 #endif
 
 // tress
+#include "../src/tree/split_evaluator.cc"
 #include "../src/tree/tree_model.cc"
 #include "../src/tree/tree_updater.cc"
 #include "../src/tree/updater_colmaker.cc"

appveyor.yml

@@ -52,8 +52,10 @@ install:
           Invoke-WebRequest http://raw.github.com/krlmlr/r-appveyor/master/scripts/appveyor-tool.ps1 -OutFile "$Env:TEMP\appveyor-tool.ps1"
           Import-Module "$Env:TEMP\appveyor-tool.ps1"
           Bootstrap
-          $DEPS = "c('data.table','magrittr','stringi','ggplot2','DiagrammeR','Ckmeans.1d.dp','vcd','testthat','igraph','knitr','rmarkdown')"
+          $DEPS = "c('data.table','magrittr','stringi','ggplot2','DiagrammeR','Ckmeans.1d.dp','vcd','testthat','lintr','knitr','rmarkdown')"
-          cmd.exe /c "R.exe -q -e ""install.packages($DEPS, repos='$CRAN', type='win.binary')"" 2>&1"
+          cmd.exe /c "R.exe -q -e ""install.packages($DEPS, repos='$CRAN', type='both')"" 2>&1"
+          $BINARY_DEPS = "c('XML','igraph')"
+          cmd.exe /c "R.exe -q -e ""install.packages($BINARY_DEPS, repos='$CRAN', type='win.binary')"" 2>&1"
         }
 
 build_script:

build.sh

@@ -15,25 +15,21 @@ else
 
     if [[ ! -e ./rabit/Makefile ]]; then
         echo ""
-        echo "Please clone the rabit repository into this directory."
+        echo "Please init the rabit submodule:"
-        echo "Here are the commands:"
+        echo "git submodule update --init --recursive -- rabit"
-        echo "rm -rf rabit"
-        echo "git clone https://github.com/dmlc/rabit.git rabit"
         not_ready=1
     fi
     
     if [[ ! -e ./dmlc-core/Makefile ]]; then
         echo ""
-        echo "Please clone the dmlc-core repository into this directory."
+        echo "Please init the dmlc-core submodule:"
-        echo "Here are the commands:"
+        echo "git submodule update --init --recursive -- dmlc-core"
-        echo "rm -rf dmlc-core"
-        echo "git clone https://github.com/dmlc/dmlc-core.git dmlc-core"
         not_ready=1
     fi
 
     if [[ "${not_ready}" == "1" ]]; then
         echo ""
-        echo "Please fix the errors above and retry the build or reclone the repository with:"
+        echo "Please fix the errors above and retry the build, or reclone the repository with:"
         echo "git clone --recursive https://github.com/dmlc/xgboost.git"
         echo ""
         exit 1

cmake/Sanitizer.cmake

@@ -0,0 +1,58 @@
+# Set appropriate compiler and linker flags for sanitizers.
+#
+# Usage of this module:
+#  enable_sanitizers("address;leak")
+
+# Add flags
+macro(enable_sanitizer santizer)
+  if(${santizer} MATCHES "address")
+    find_package(ASan REQUIRED)
+    set(SAN_COMPILE_FLAGS "${SAN_COMPILE_FLAGS} -fsanitize=address")
+    link_libraries(${ASan_LIBRARY})
+
+  elseif(${santizer} MATCHES "thread")
+    find_package(TSan REQUIRED)
+    set(SAN_COMPILE_FLAGS "${SAN_COMPILE_FLAGS} -fsanitize=thread")
+    link_libraries(${TSan_LIBRARY})
+
+  elseif(${santizer} MATCHES "leak")
+    find_package(LSan REQUIRED)
+    set(SAN_COMPILE_FLAGS "${SAN_COMPILE_FLAGS} -fsanitize=leak")
+    link_libraries(${LSan_LIBRARY})
+
+  else()
+    message(FATAL_ERROR "Santizer ${santizer} not supported.")
+  endif()
+endmacro()
+
+macro(enable_sanitizers SANITIZERS)
+  # Check sanitizers compatibility.
+  # Idealy, we should use if(san IN_LIST SANITIZERS) ... endif()
+  # But I haven't figure out how to make it work.
+  foreach ( _san ${SANITIZERS} )
+    string(TOLOWER ${_san} _san)
+    if (_san MATCHES "thread")
+      if (${_use_other_sanitizers})
+        message(FATAL_ERROR
+          "thread sanitizer is not compatible with ${_san} sanitizer.")
+      endif()
+      set(_use_thread_sanitizer 1)
+    else ()
+      if (${_use_thread_sanitizer})
+        message(FATAL_ERROR
+          "${_san} sanitizer is not compatible with thread sanitizer.")
+      endif()
+      set(_use_other_sanitizers 1)
+    endif()
+  endforeach()
+
+  message("Sanitizers: ${SANITIZERS}")
+
+  foreach( _san ${SANITIZERS} )
+    string(TOLOWER ${_san} _san)
+    enable_sanitizer(${_san})
+  endforeach()
+  message("Sanitizers compile flags: ${SAN_COMPILE_FLAGS}")
+  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${SAN_COMPILE_FLAGS}")
+  set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${SAN_COMPILE_FLAGS}")
+endmacro()

cmake/Utils.cmake

@@ -54,10 +54,25 @@ function(set_default_configuration_release)
 	endif()
 endfunction(set_default_configuration_release)
 
+# Generate nvcc compiler flags given a list of architectures
+# Also generates PTX for the most recent architecture for forwards compatibility
 function(format_gencode_flags flags out)
+  # Set up architecture flags
+  if(NOT flags) 
+    if((CUDA_VERSION_MAJOR EQUAL 9) OR (CUDA_VERSION_MAJOR GREATER 9))
+      set(flags "35;50;52;60;61;70")
+    else()
+      set(flags "35;50;52;60;61")
+    endif()
+  endif()
+  # Generate SASS
   foreach(ver ${flags})
     set(${out} "${${out}}-gencode arch=compute_${ver},code=sm_${ver};")
   endforeach()
+  # Generate PTX for last architecture
+  list(GET flags -1 ver)
+  set(${out} "${${out}}-gencode arch=compute_${ver},code=compute_${ver};")
+  
   set(${out} "${${out}}" PARENT_SCOPE)
 endfunction(format_gencode_flags flags)
 

cmake/modules/FindASan.cmake

@@ -0,0 +1,13 @@
+set(ASan_LIB_NAME ASan)
+
+find_library(ASan_LIBRARY
+  NAMES libasan.so libasan.so.4
+  PATHS /usr/lib64 /usr/lib /usr/local/lib64 /usr/local/lib)
+
+include(FindPackageHandleStandardArgs)
+find_package_handle_standard_args(ASan DEFAULT_MSG
+  ASan_LIBRARY)
+
+mark_as_advanced(
+  ASan_LIBRARY
+  ASan_LIB_NAME)

cmake/modules/FindGTest.cmake

@@ -1,79 +0,0 @@
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-#
-# Tries to find GTest headers and libraries.
-#
-# Usage of this module as follows:
-#
-#  find_package(GTest)
-#
-# Variables used by this module, they can change the default behaviour and need
-# to be set before calling find_package:
-#
-#  GTest_HOME - When set, this path is inspected instead of standard library
-#                locations as the root of the GTest installation.
-#                The environment variable GTEST_HOME overrides this veriable.
-#
-# This module defines
-#  GTEST_INCLUDE_DIR, directory containing headers
-#  GTEST_LIBS, directory containing gtest libraries
-#  GTEST_STATIC_LIB, path to libgtest.a
-#  GTEST_SHARED_LIB, path to libgtest's shared library
-#  GTEST_FOUND, whether gtest has been found
-
-find_path(GTEST_INCLUDE_DIR NAMES gtest/gtest.h gtest.h PATHS ${CMAKE_SOURCE_DIR}/gtest/include NO_DEFAULT_PATH)
-find_library(GTEST_LIBRARIES NAMES gtest PATHS ${CMAKE_SOURCE_DIR}/gtest/lib NO_DEFAULT_PATH)
-
-if (GTEST_INCLUDE_DIR )
-  message(STATUS "Found the GTest includes: ${GTEST_INCLUDE_DIR}")
-endif ()
-
-
-if (GTEST_INCLUDE_DIR AND GTEST_LIBRARIES)
-  set(GTEST_FOUND TRUE)
-  get_filename_component( GTEST_LIBS ${GTEST_LIBRARIES} PATH )
-  set(GTEST_LIB_NAME gtest)
-  set(GTEST_STATIC_LIB ${GTEST_LIBS}/${CMAKE_STATIC_LIBRARY_PREFIX}${GTEST_LIB_NAME}${CMAKE_STATIC_LIBRARY_SUFFIX})
-  set(GTEST_MAIN_STATIC_LIB ${GTEST_LIBS}/${CMAKE_STATIC_LIBRARY_PREFIX}${GTEST_LIB_NAME}_main${CMAKE_STATIC_LIBRARY_SUFFIX})
-  set(GTEST_SHARED_LIB ${GTEST_LIBS}/${CMAKE_SHARED_LIBRARY_PREFIX}${GTEST_LIB_NAME}${CMAKE_SHARED_LIBRARY_SUFFIX})
-else ()
-  set(GTEST_FOUND FALSE)
-endif ()
-
-if (GTEST_FOUND)
-  if (NOT GTest_FIND_QUIETLY)
-    message(STATUS "Found the GTest library: ${GTEST_LIBRARIES}")
-  endif ()
-else ()
-  if (NOT GTest_FIND_QUIETLY)
-    set(GTEST_ERR_MSG "Could not find the GTest library. Looked in ")
-    if ( _gtest_roots )
-      set(GTEST_ERR_MSG "${GTEST_ERR_MSG} in ${_gtest_roots}.")
-    else ()
-      set(GTEST_ERR_MSG "${GTEST_ERR_MSG} system search paths.")
-    endif ()
-    if (GTest_FIND_REQUIRED)
-      message(FATAL_ERROR "${GTEST_ERR_MSG}")
-    else (GTest_FIND_REQUIRED)
-      message(STATUS "${GTEST_ERR_MSG}")
-    endif (GTest_FIND_REQUIRED)
-  endif ()
-endif ()
-
-mark_as_advanced(
-  GTEST_INCLUDE_DIR
-  GTEST_LIBS
-  GTEST_LIBRARIES
-  GTEST_STATIC_LIB
-  GTEST_SHARED_LIB
-)

cmake/modules/FindLSan.cmake

@@ -0,0 +1,13 @@
+set(LSan_LIB_NAME lsan)
+
+find_library(LSan_LIBRARY
+  NAMES liblsan.so liblsan.so.0 liblsan.so.0.0.0
+  PATHS /usr/lib64 /usr/lib /usr/local/lib64 /usr/local/lib)
+
+include(FindPackageHandleStandardArgs)
+find_package_handle_standard_args(LSan DEFAULT_MSG
+  LSan_LIBRARY)
+
+mark_as_advanced(
+  LSan_LIBRARY
+  LSan_LIB_NAME)

cmake/modules/FindNccl.cmake

@@ -0,0 +1,58 @@
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+# Tries to find NCCL headers and libraries.
+#
+# Usage of this module as follows:
+#
+#  find_package(NCCL)
+#
+# Variables used by this module, they can change the default behaviour and need
+# to be set before calling find_package:
+#
+#  NCCL_ROOT - When set, this path is inspected instead of standard library
+#              locations as the root of the NCCL installation.
+#              The environment variable NCCL_ROOT overrides this veriable.
+#
+# This module defines
+#  Nccl_FOUND, whether nccl has been found
+#  NCCL_INCLUDE_DIR, directory containing header
+#  NCCL_LIBRARY, directory containing nccl library
+#  NCCL_LIB_NAME, nccl library name
+#
+# This module assumes that the user has already called find_package(CUDA)
+
+
+set(NCCL_LIB_NAME nccl_static)
+
+find_path(NCCL_INCLUDE_DIR
+  NAMES nccl.h
+  PATHS $ENV{NCCL_ROOT}/include ${NCCL_ROOT}/include ${CUDA_INCLUDE_DIRS} /usr/include)
+
+find_library(NCCL_LIBRARY
+  NAMES ${NCCL_LIB_NAME}
+  PATHS $ENV{NCCL_ROOT}/lib ${NCCL_ROOT}/lib ${CUDA_INCLUDE_DIRS}/../lib /usr/lib)
+
+if (NCCL_INCLUDE_DIR AND NCCL_LIBRARY)
+  get_filename_component(NCCL_LIBRARY ${NCCL_LIBRARY} PATH)
+endif ()
+
+include(FindPackageHandleStandardArgs)
+find_package_handle_standard_args(Nccl DEFAULT_MSG
+                                  NCCL_INCLUDE_DIR NCCL_LIBRARY)
+
+mark_as_advanced(
+  NCCL_INCLUDE_DIR
+  NCCL_LIBRARY
+  NCCL_LIB_NAME
+)

cmake/modules/FindTSan.cmake

@@ -0,0 +1,13 @@
+set(TSan_LIB_NAME tsan)
+
+find_library(TSan_LIBRARY
+  NAMES libtsan.so libtsan.so.0 libtsan.so.0.0.0
+  PATHS /usr/lib64 /usr/lib /usr/local/lib64 /usr/local/lib)
+
+include(FindPackageHandleStandardArgs)
+find_package_handle_standard_args(TSan DEFAULT_MSG
+  TSan_LIBRARY)
+
+mark_as_advanced(
+  TSan_LIBRARY
+  TSan_LIB_NAME)

demo/binary_classification/README.md

@@ -80,12 +80,6 @@ booster = gblinear
 # L2 regularization term on weights, default 0
 lambda = 0.01
 # L1 regularization term on weights, default 0
-If ```agaricus.txt.test.buffer``` exists, and automatically loads from binary buffer if possible, this can speedup training process when you do training many times. You can disable it by setting ```use_buffer=0```.
-  - Buffer file can also be used as standalone input, i.e if buffer file exists, but original agaricus.txt.test was removed, xgboost will still run
-* Deviation from LibSVM input format: xgboost is compatible with LibSVM format, with the following minor differences:
-  - xgboost allows feature index starts from 0
-  - for binary classification, the label is 1 for positive, 0 for negative, instead of +1,-1
-  - the feature indices in each line *do not* need to be sorted
 alpha = 0.01
 # L2 regularization term on bias, default 0
 lambda_bias = 0.01
@@ -102,7 +96,7 @@ After training, we can use the output model to get the prediction of the test da
 For binary classification, the output predictions are probability confidence scores in [0,1], corresponds to the probability of the label to be positive.
 
 #### Dump Model
-This is a preliminary feature, so far only tree model support text dump. XGBoost can display the tree models in text files and we can scan the model in an easy way:
+This is a preliminary feature, so only tree models support text dump. XGBoost can display the tree models in text or JSON files, and we can scan the model in an easy way:
 ```
 ../../xgboost mushroom.conf task=dump model_in=0002.model name_dump=dump.raw.txt
 ../../xgboost mushroom.conf task=dump model_in=0002.model fmap=featmap.txt name_dump=dump.nice.txt

demo/guide-python/custom_objective.py

@@ -33,10 +33,10 @@ def logregobj(preds, dtrain):
 # Take this in mind when you use the customization, and maybe you need write customized evaluation function
 def evalerror(preds, dtrain):
     labels = dtrain.get_label()
-    # return a pair metric_name, result
+    # return a pair metric_name, result. The metric name must not contain a colon (:)
     # since preds are margin(before logistic transformation, cutoff at 0)
     return 'error', float(sum(labels != (preds > 0.0))) / len(labels)
 
 # training with customized objective, we can also do step by step training
 # simply look at xgboost.py's implementation of train
-bst = xgb.train(param, dtrain, num_round, watchlist, logregobj, evalerror)
+bst = xgb.train(param, dtrain, num_round, watchlist, obj=logregobj, feval=evalerror)

demo/kaggle-higgs/higgs-train.R

@@ -24,9 +24,9 @@ param <- list("objective" = "binary:logitraw",
               "silent" = 1,
               "nthread" = 16)
 watchlist <- list("train" = xgmat)
-nround = 120
+nrounds = 120
 print ("loading data end, start to boost trees")
-bst = xgb.train(param, xgmat, nround, watchlist );
+bst = xgb.train(param, xgmat, nrounds, watchlist );
 # save out model
 xgb.save(bst, "higgs.model")
 print ('finish training')

demo/kaggle-higgs/speedtest.R

@@ -39,9 +39,9 @@ for (i in 1:length(threads)){
                   "silent" = 1,
                   "nthread" = thread)
     watchlist <- list("train" = xgmat)
-    nround = 120
+    nrounds = 120
     print ("loading data end, start to boost trees")
-    bst = xgb.train(param, xgmat, nround, watchlist );
+    bst = xgb.train(param, xgmat, nrounds, watchlist );
     # save out model
     xgb.save(bst, "higgs.model")
     print ('finish training')

demo/kaggle-otto/otto_train_pred.R

@@ -23,13 +23,13 @@ param <- list("objective" = "multi:softprob",
               "nthread" = 8)
 
 # Run Cross Validation
-cv.nround = 50
+cv.nrounds = 50
 bst.cv = xgb.cv(param=param, data = x[trind,], label = y, 
-                nfold = 3, nrounds=cv.nround)
+                nfold = 3, nrounds=cv.nrounds)
 
 # Train the model
-nround = 50
+nrounds = 50
-bst = xgboost(param=param, data = x[trind,], label = y, nrounds=nround)
+bst = xgboost(param=param, data = x[trind,], label = y, nrounds=nrounds)
 
 # Make prediction
 pred = predict(bst,x[teind,])

demo/kaggle-otto/understandingXGBoostModel.Rmd

@@ -121,19 +121,19 @@ param <- list("objective" = "multi:softprob",
               "eval_metric" = "mlogloss",
               "num_class" = numberOfClasses)
 
-cv.nround <- 5
+cv.nrounds <- 5
 cv.nfold <- 3
 
 bst.cv = xgb.cv(param=param, data = trainMatrix, label = y,
-                nfold = cv.nfold, nrounds = cv.nround)
+                nfold = cv.nfold, nrounds = cv.nrounds)
 ```
 > As we can see the error rate is low on the test dataset (for a 5mn trained model).
 
 Finally, we are ready to train the real model!!!
 
 ```{r modelTraining}
-nround = 50
+nrounds = 50
-bst = xgboost(param=param, data = trainMatrix, label = y, nrounds=nround)
+bst = xgboost(param=param, data = trainMatrix, label = y, nrounds=nrounds)
 ```
 
 Model understanding
@@ -142,7 +142,7 @@ Model understanding
 Feature importance
 ------------------
 
-So far, we have built a model made of **`r nround`** trees.
+So far, we have built a model made of **`r nrounds`** trees.
 
 To build a tree, the dataset is divided recursively several times. At the end of the process, you get groups of observations (here, these observations are properties regarding **Otto** products).
 

demo/rank/README.md

@@ -14,8 +14,15 @@ For more usage details please refer to the [binary classification demo](../binar
 
 Instructions
 ====
-The dataset for ranking demo is from LETOR04 MQ2008 fold1,
+The dataset for ranking demo is from LETOR04 MQ2008 fold1.
-You can use the following command to run the example
+You can use the following command to run the example:
 
-Get the data: ./wgetdata.sh
+Get the data:
-Run the example: ./runexp.sh
+```
+./wgetdata.sh
+```
+
+Run the example:
+```
+./runexp.sh
+```

demo/rank/wgetdata.sh

@@ -1,4 +1,4 @@
 #!/bin/bash
-wget http://research.microsoft.com/en-us/um/beijing/projects/letor/LETOR4.0/Data/MQ2008.rar
+wget https://s3-us-west-2.amazonaws.com/xgboost-examples/MQ2008.rar
 unrar x MQ2008.rar
 mv -f MQ2008/Fold1/*.txt .

doc/R-package/discoverYourData.md

@@ -222,7 +222,7 @@ The code below is very usual. For more information, you can look at the document
 
 ```r
 bst <- xgboost(data = sparse_matrix, label = output_vector, max.depth = 4,
-               eta = 1, nthread = 2, nround = 10,objective = "binary:logistic")
+               eta = 1, nthread = 2, nrounds = 10,objective = "binary:logistic")
 ```
 
 ```
@@ -244,7 +244,7 @@ A model which fits too well may [overfit](http://en.wikipedia.org/wiki/Overfitti
 
 > Here you can see the numbers decrease until line 7 and then increase.
 >
-> It probably means we are overfitting. To fix that I should reduce the number of rounds to `nround = 4`. I will let things like that because I don't really care for the purpose of this example :-)
+> It probably means we are overfitting. To fix that I should reduce the number of rounds to `nrounds = 4`. I will let things like that because I don't really care for the purpose of this example :-)
 
 Feature importance
 ------------------
@@ -448,7 +448,7 @@ train <- agaricus.train
 test <- agaricus.test
 
 #Random Forest™ - 1000 trees
-bst <- xgboost(data = train$data, label = train$label, max.depth = 4, num_parallel_tree = 1000, subsample = 0.5, colsample_bytree =0.5, nround = 1, objective = "binary:logistic")
+bst <- xgboost(data = train$data, label = train$label, max.depth = 4, num_parallel_tree = 1000, subsample = 0.5, colsample_bytree =0.5, nrounds = 1, objective = "binary:logistic")
 ```
 
 ```
@@ -457,7 +457,7 @@ bst <- xgboost(data = train$data, label = train$label, max.depth = 4, num_parall
 
 ```r
 #Boosting - 3 rounds
-bst <- xgboost(data = train$data, label = train$label, max.depth = 4, nround = 3, objective = "binary:logistic")
+bst <- xgboost(data = train$data, label = train$label, max.depth = 4, nrounds = 3, objective = "binary:logistic")
 ```
 
 ```

doc/R-package/index.md

@@ -1,17 +0,0 @@
-XGBoost R Package
-=================
-[![CRAN Status Badge](http://www.r-pkg.org/badges/version/xgboost)](http://cran.r-project.org/web/packages/xgboost)
-[![CRAN Downloads](http://cranlogs.r-pkg.org/badges/xgboost)](http://cran.rstudio.com/web/packages/xgboost/index.html)
-
-
-You have found the XGBoost R Package!
-
-Get Started
------------
-* Checkout the [Installation Guide](../build.md) contains instructions to install xgboost, and [Tutorials](#tutorials) for examples on how to use xgboost for various tasks.
-* Please visit [walk through example](../../R-package/demo).
-
-Tutorials
----------
-- [Introduction to XGBoost in R](xgboostPresentation.md)
-- [Discover your data with XGBoost in R](discoverYourData.md)

doc/R-package/index.rst

@@ -0,0 +1,28 @@
+#################
+XGBoost R Package
+#################
+
+.. raw:: html
+
+  <a href="http://cran.r-project.org/web/packages/xgboost"><img alt="CRAN Status Badge" src="http://www.r-pkg.org/badges/version/xgboost"></a>
+  <a href="http://cran.rstudio.com/web/packages/xgboost/index.html"><img alt="CRAN Downloads" src="http://cranlogs.r-pkg.org/badges/xgboost"></a>
+
+You have found the XGBoost R Package!
+
+***********
+Get Started
+***********
+* Checkout the :doc:`Installation Guide </build>` contains instructions to install xgboost, and :doc:`Tutorials </tutorials/index>` for examples on how to use XGBoost for various tasks.
+* Read the `API documentation <https://cran.r-project.org/web/packages/xgboost/xgboost.pdf>`_.
+* Please visit `Walk-through Examples <https://github.com/dmlc/xgboost/tree/master/R-package/demo>`_.
+
+*********
+Tutorials
+*********
+
+.. toctree::
+  :maxdepth: 2
+  :titlesonly:
+  
+  Introduction to XGBoost in R <xgboostPresentation>
+  Understanding your dataset with XGBoost <discoverYourData>

doc/R-package/xgboostPresentation.md

@@ -178,11 +178,11 @@ We will train decision tree model using the following parameters:
 * `objective = "binary:logistic"`: we will train a binary classification model ;
 * `max.deph = 2`: the trees won't be deep, because our case is very simple ;
 * `nthread = 2`: the number of cpu threads we are going to use;
-* `nround = 2`: there will be two passes on the data, the second one will enhance the model by further reducing the difference between ground truth and prediction.
+* `nrounds = 2`: there will be two passes on the data, the second one will enhance the model by further reducing the difference between ground truth and prediction.
 
 
 ```r
-bstSparse <- xgboost(data = train$data, label = train$label, max.depth = 2, eta = 1, nthread = 2, nround = 2, objective = "binary:logistic")
+bstSparse <- xgboost(data = train$data, label = train$label, max.depth = 2, eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
 ```
 
 ```
@@ -200,7 +200,7 @@ Alternatively, you can put your dataset in a *dense* matrix, i.e. a basic **R**
 
 
 ```r
-bstDense <- xgboost(data = as.matrix(train$data), label = train$label, max.depth = 2, eta = 1, nthread = 2, nround = 2, objective = "binary:logistic")
+bstDense <- xgboost(data = as.matrix(train$data), label = train$label, max.depth = 2, eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
 ```
 
 ```
@@ -215,7 +215,7 @@ bstDense <- xgboost(data = as.matrix(train$data), label = train$label, max.depth
 
 ```r
 dtrain <- xgb.DMatrix(data = train$data, label = train$label)
-bstDMatrix <- xgboost(data = dtrain, max.depth = 2, eta = 1, nthread = 2, nround = 2, objective = "binary:logistic")
+bstDMatrix <- xgboost(data = dtrain, max.depth = 2, eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
 ```
 
 ```
@@ -232,13 +232,13 @@ One of the simplest way to see the training progress is to set the `verbose` opt
 
 ```r
 # verbose = 0, no message
-bst <- xgboost(data = dtrain, max.depth = 2, eta = 1, nthread = 2, nround = 2, objective = "binary:logistic", verbose = 0)
+bst <- xgboost(data = dtrain, max.depth = 2, eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic", verbose = 0)
 ```
 
 
 ```r
 # verbose = 1, print evaluation metric
-bst <- xgboost(data = dtrain, max.depth = 2, eta = 1, nthread = 2, nround = 2, objective = "binary:logistic", verbose = 1)
+bst <- xgboost(data = dtrain, max.depth = 2, eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic", verbose = 1)
 ```
 
 ```
@@ -249,7 +249,7 @@ bst <- xgboost(data = dtrain, max.depth = 2, eta = 1, nthread = 2, nround = 2, o
 
 ```r
 # verbose = 2, also print information about tree
-bst <- xgboost(data = dtrain, max.depth = 2, eta = 1, nthread = 2, nround = 2, objective = "binary:logistic", verbose = 2)
+bst <- xgboost(data = dtrain, max.depth = 2, eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic", verbose = 2)
 ```
 
 ```
@@ -372,7 +372,7 @@ For the purpose of this example, we use `watchlist` parameter. It is a list of `
 ```r
 watchlist <- list(train=dtrain, test=dtest)
 
-bst <- xgb.train(data=dtrain, max.depth=2, eta=1, nthread = 2, nround=2, watchlist=watchlist, objective = "binary:logistic")
+bst <- xgb.train(data=dtrain, max.depth=2, eta=1, nthread = 2, nrounds=2, watchlist=watchlist, objective = "binary:logistic")
 ```
 
 ```
@@ -380,7 +380,7 @@ bst <- xgb.train(data=dtrain, max.depth=2, eta=1, nthread = 2, nround=2, watchli
 ## [1]	train-error:0.022263	test-error:0.021726
 ```
 
-**XGBoost** has computed at each round the same average error metric than seen above (we set `nround` to 2, that is why we have two lines). Obviously, the `train-error` number is related to the training dataset (the one the algorithm learns from) and the `test-error` number to the test dataset.
+**XGBoost** has computed at each round the same average error metric than seen above (we set `nrounds` to 2, that is why we have two lines). Obviously, the `train-error` number is related to the training dataset (the one the algorithm learns from) and the `test-error` number to the test dataset.
 
 Both training and test error related metrics are very similar, and in some way, it makes sense: what we have learned from the training dataset matches the observations from the test dataset.
 
@@ -390,7 +390,7 @@ For a better understanding of the learning progression, you may want to have som
 
 
 ```r
-bst <- xgb.train(data=dtrain, max.depth=2, eta=1, nthread = 2, nround=2, watchlist=watchlist, eval.metric = "error", eval.metric = "logloss", objective = "binary:logistic")
+bst <- xgb.train(data=dtrain, max.depth=2, eta=1, nthread = 2, nrounds=2, watchlist=watchlist, eval.metric = "error", eval.metric = "logloss", objective = "binary:logistic")
 ```
 
 ```
@@ -407,7 +407,7 @@ Until now, all the learnings we have performed were based on boosting trees. **X
 
 
 ```r
-bst <- xgb.train(data=dtrain, booster = "gblinear", max.depth=2, nthread = 2, nround=2, watchlist=watchlist, eval.metric = "error", eval.metric = "logloss", objective = "binary:logistic")
+bst <- xgb.train(data=dtrain, booster = "gblinear", max.depth=2, nthread = 2, nrounds=2, watchlist=watchlist, eval.metric = "error", eval.metric = "logloss", objective = "binary:logistic")
 ```
 
 ```
@@ -445,7 +445,7 @@ dtrain2 <- xgb.DMatrix("dtrain.buffer")
 ```
 
 ```r
-bst <- xgb.train(data=dtrain2, max.depth=2, eta=1, nthread = 2, nround=2, watchlist=watchlist, objective = "binary:logistic")
+bst <- xgb.train(data=dtrain2, max.depth=2, eta=1, nthread = 2, nrounds=2, watchlist=watchlist, objective = "binary:logistic")
 ```
 
 ```

doc/_static/custom.css

@@ -0,0 +1,23 @@
+div.breathe-sectiondef.container {
+  width: 100%;
+}
+
+div.literal-block-wrapper.container {
+  width: 100%;
+}
+
+.red {
+  color: red;
+}
+
+table {
+  border: 0;
+}
+
+td, th {
+  padding: 1px 8px 1px 5px;
+  border-top: 0;
+  border-bottom: 1px solid #aaa;
+  border-left: 0;
+  border-right: 0;
+}

doc/_static/searchtools-new.js

@@ -1,752 +0,0 @@
-/* 
- * searchtools.js_t
- * ~~~~~~~~~~~~~~~~
- *
- * Sphinx JavaScript utilities for the full-text search.
- *
- * :copyright: Copyright 2007-2016 by the Sphinx team, see AUTHORS.
- * :license: BSD, see LICENSE for details.
- *
- */
-
-
-/* Non-minified version JS is _stemmer.js if file is provided */ 
-/**
- * Porter Stemmer
- */
-var Stemmer = function() {
-
-  var step2list = {
-    ational: 'ate',
-    tional: 'tion',
-    enci: 'ence',
-    anci: 'ance',
-    izer: 'ize',
-    bli: 'ble',
-    alli: 'al',
-    entli: 'ent',
-    eli: 'e',
-    ousli: 'ous',
-    ization: 'ize',
-    ation: 'ate',
-    ator: 'ate',
-    alism: 'al',
-    iveness: 'ive',
-    fulness: 'ful',
-    ousness: 'ous',
-    aliti: 'al',
-    iviti: 'ive',
-    biliti: 'ble',
-    logi: 'log'
-  };
-
-  var step3list = {
-    icate: 'ic',
-    ative: '',
-    alize: 'al',
-    iciti: 'ic',
-    ical: 'ic',
-    ful: '',
-    ness: ''
-  };
-
-  var c = "[^aeiou]";          // consonant
-  var v = "[aeiouy]";          // vowel
-  var C = c + "[^aeiouy]*";    // consonant sequence
-  var V = v + "[aeiou]*";      // vowel sequence
-
-  var mgr0 = "^(" + C + ")?" + V + C;                      // [C]VC... is m>0
-  var meq1 = "^(" + C + ")?" + V + C + "(" + V + ")?$";    // [C]VC[V] is m=1
-  var mgr1 = "^(" + C + ")?" + V + C + V + C;              // [C]VCVC... is m>1
-  var s_v   = "^(" + C + ")?" + v;                         // vowel in stem
-
-  this.stemWord = function (w) {
-    var stem;
-    var suffix;
-    var firstch;
-    var origword = w;
-
-    if (w.length < 3)
-      return w;
-
-    var re;
-    var re2;
-    var re3;
-    var re4;
-
-    firstch = w.substr(0,1);
-    if (firstch == "y")
-      w = firstch.toUpperCase() + w.substr(1);
-
-    // Step 1a
-    re = /^(.+?)(ss|i)es$/;
-    re2 = /^(.+?)([^s])s$/;
-
-    if (re.test(w))
-      w = w.replace(re,"$1$2");
-    else if (re2.test(w))
-      w = w.replace(re2,"$1$2");
-
-    // Step 1b
-    re = /^(.+?)eed$/;
-    re2 = /^(.+?)(ed|ing)$/;
-    if (re.test(w)) {
-      var fp = re.exec(w);
-      re = new RegExp(mgr0);
-      if (re.test(fp[1])) {
-        re = /.$/;
-        w = w.replace(re,"");
-      }
-    }
-    else if (re2.test(w)) {
-      var fp = re2.exec(w);
-      stem = fp[1];
-      re2 = new RegExp(s_v);
-      if (re2.test(stem)) {
-        w = stem;
-        re2 = /(at|bl|iz)$/;
-        re3 = new RegExp("([^aeiouylsz])\\1$");
-        re4 = new RegExp("^" + C + v + "[^aeiouwxy]$");
-        if (re2.test(w))
-          w = w + "e";
-        else if (re3.test(w)) {
-          re = /.$/;
-          w = w.replace(re,"");
-        }
-        else if (re4.test(w))
-          w = w + "e";
-      }
-    }
-
-    // Step 1c
-    re = /^(.+?)y$/;
-    if (re.test(w)) {
-      var fp = re.exec(w);
-      stem = fp[1];
-      re = new RegExp(s_v);
-      if (re.test(stem))
-        w = stem + "i";
-    }
-
-    // Step 2
-    re = /^(.+?)(ational|tional|enci|anci|izer|bli|alli|entli|eli|ousli|ization|ation|ator|alism|iveness|fulness|ousness|aliti|iviti|biliti|logi)$/;
-    if (re.test(w)) {
-      var fp = re.exec(w);
-      stem = fp[1];
-      suffix = fp[2];
-      re = new RegExp(mgr0);
-      if (re.test(stem))
-        w = stem + step2list[suffix];
-    }
-
-    // Step 3
-    re = /^(.+?)(icate|ative|alize|iciti|ical|ful|ness)$/;
-    if (re.test(w)) {
-      var fp = re.exec(w);
-      stem = fp[1];
-      suffix = fp[2];
-      re = new RegExp(mgr0);
-      if (re.test(stem))
-        w = stem + step3list[suffix];
-    }
-
-    // Step 4
-    re = /^(.+?)(al|ance|ence|er|ic|able|ible|ant|ement|ment|ent|ou|ism|ate|iti|ous|ive|ize)$/;
-    re2 = /^(.+?)(s|t)(ion)$/;
-    if (re.test(w)) {
-      var fp = re.exec(w);
-      stem = fp[1];
-      re = new RegExp(mgr1);
-      if (re.test(stem))
-        w = stem;
-    }
-    else if (re2.test(w)) {
-      var fp = re2.exec(w);
-      stem = fp[1] + fp[2];
-      re2 = new RegExp(mgr1);
-      if (re2.test(stem))
-        w = stem;
-    }
-
-    // Step 5
-    re = /^(.+?)e$/;
-    if (re.test(w)) {
-      var fp = re.exec(w);
-      stem = fp[1];
-      re = new RegExp(mgr1);
-      re2 = new RegExp(meq1);
-      re3 = new RegExp("^" + C + v + "[^aeiouwxy]$");
-      if (re.test(stem) || (re2.test(stem) && !(re3.test(stem))))
-        w = stem;
-    }
-    re = /ll$/;
-    re2 = new RegExp(mgr1);
-    if (re.test(w) && re2.test(w)) {
-      re = /.$/;
-      w = w.replace(re,"");
-    }
-
-    // and turn initial Y back to y
-    if (firstch == "y")
-      w = firstch.toLowerCase() + w.substr(1);
-    return w;
-  }
-}
-
-
-
-/**
- * Simple result scoring code.
- */
-var Scorer = {
-  // Implement the following function to further tweak the score for each result
-  // The function takes a result array [filename, title, anchor, descr, score]
-  // and returns the new score.
-  /*
-  score: function(result) {
-    return result[4];
-  },
-  */
-
-  // query matches the full name of an object
-  objNameMatch: 11,
-  // or matches in the last dotted part of the object name
-  objPartialMatch: 6,
-  // Additive scores depending on the priority of the object
-  objPrio: {0:  15,   // used to be importantResults
-            1:  5,   // used to be objectResults
-            2: -5},  // used to be unimportantResults
-  //  Used when the priority is not in the mapping.
-  objPrioDefault: 0,
-
-  // query found in title
-  title: 15,
-  // query found in terms
-  term: 5
-};
-
-
-
-
-
-var splitChars = (function() {
-    var result = {};
-    var singles = [96, 180, 187, 191, 215, 247, 749, 885, 903, 907, 909, 930, 1014, 1648,
-         1748, 1809, 2416, 2473, 2481, 2526, 2601, 2609, 2612, 2615, 2653, 2702,
-         2706, 2729, 2737, 2740, 2857, 2865, 2868, 2910, 2928, 2948, 2961, 2971,
-         2973, 3085, 3089, 3113, 3124, 3213, 3217, 3241, 3252, 3295, 3341, 3345,
-         3369, 3506, 3516, 3633, 3715, 3721, 3736, 3744, 3748, 3750, 3756, 3761,
-         3781, 3912, 4239, 4347, 4681, 4695, 4697, 4745, 4785, 4799, 4801, 4823,
-         4881, 5760, 5901, 5997, 6313, 7405, 8024, 8026, 8028, 8030, 8117, 8125,
-         8133, 8181, 8468, 8485, 8487, 8489, 8494, 8527, 11311, 11359, 11687, 11695,
-         11703, 11711, 11719, 11727, 11735, 12448, 12539, 43010, 43014, 43019, 43587,
-         43696, 43713, 64286, 64297, 64311, 64317, 64319, 64322, 64325, 65141];
-    var i, j, start, end;
-    for (i = 0; i < singles.length; i++) {
-        result[singles[i]] = true;
-    }
-    var ranges = [[0, 47], [58, 64], [91, 94], [123, 169], [171, 177], [182, 184], [706, 709],
-         [722, 735], [741, 747], [751, 879], [888, 889], [894, 901], [1154, 1161],
-         [1318, 1328], [1367, 1368], [1370, 1376], [1416, 1487], [1515, 1519], [1523, 1568],
-         [1611, 1631], [1642, 1645], [1750, 1764], [1767, 1773], [1789, 1790], [1792, 1807],
-         [1840, 1868], [1958, 1968], [1970, 1983], [2027, 2035], [2038, 2041], [2043, 2047],
-         [2070, 2073], [2075, 2083], [2085, 2087], [2089, 2307], [2362, 2364], [2366, 2383],
-         [2385, 2391], [2402, 2405], [2419, 2424], [2432, 2436], [2445, 2446], [2449, 2450],
-         [2483, 2485], [2490, 2492], [2494, 2509], [2511, 2523], [2530, 2533], [2546, 2547],
-         [2554, 2564], [2571, 2574], [2577, 2578], [2618, 2648], [2655, 2661], [2672, 2673],
-         [2677, 2692], [2746, 2748], [2750, 2767], [2769, 2783], [2786, 2789], [2800, 2820],
-         [2829, 2830], [2833, 2834], [2874, 2876], [2878, 2907], [2914, 2917], [2930, 2946],
-         [2955, 2957], [2966, 2968], [2976, 2978], [2981, 2983], [2987, 2989], [3002, 3023],
-         [3025, 3045], [3059, 3076], [3130, 3132], [3134, 3159], [3162, 3167], [3170, 3173],
-         [3184, 3191], [3199, 3204], [3258, 3260], [3262, 3293], [3298, 3301], [3312, 3332],
-         [3386, 3388], [3390, 3423], [3426, 3429], [3446, 3449], [3456, 3460], [3479, 3481],
-         [3518, 3519], [3527, 3584], [3636, 3647], [3655, 3663], [3674, 3712], [3717, 3718],
-         [3723, 3724], [3726, 3731], [3752, 3753], [3764, 3772], [3774, 3775], [3783, 3791],
-         [3802, 3803], [3806, 3839], [3841, 3871], [3892, 3903], [3949, 3975], [3980, 4095],
-         [4139, 4158], [4170, 4175], [4182, 4185], [4190, 4192], [4194, 4196], [4199, 4205],
-         [4209, 4212], [4226, 4237], [4250, 4255], [4294, 4303], [4349, 4351], [4686, 4687],
-         [4702, 4703], [4750, 4751], [4790, 4791], [4806, 4807], [4886, 4887], [4955, 4968],
-         [4989, 4991], [5008, 5023], [5109, 5120], [5741, 5742], [5787, 5791], [5867, 5869],
-         [5873, 5887], [5906, 5919], [5938, 5951], [5970, 5983], [6001, 6015], [6068, 6102],
-         [6104, 6107], [6109, 6111], [6122, 6127], [6138, 6159], [6170, 6175], [6264, 6271],
-         [6315, 6319], [6390, 6399], [6429, 6469], [6510, 6511], [6517, 6527], [6572, 6592],
-         [6600, 6607], [6619, 6655], [6679, 6687], [6741, 6783], [6794, 6799], [6810, 6822],
-         [6824, 6916], [6964, 6980], [6988, 6991], [7002, 7042], [7073, 7085], [7098, 7167],
-         [7204, 7231], [7242, 7244], [7294, 7400], [7410, 7423], [7616, 7679], [7958, 7959],
-         [7966, 7967], [8006, 8007], [8014, 8015], [8062, 8063], [8127, 8129], [8141, 8143],
-         [8148, 8149], [8156, 8159], [8173, 8177], [8189, 8303], [8306, 8307], [8314, 8318],
-         [8330, 8335], [8341, 8449], [8451, 8454], [8456, 8457], [8470, 8472], [8478, 8483],
-         [8506, 8507], [8512, 8516], [8522, 8525], [8586, 9311], [9372, 9449], [9472, 10101],
-         [10132, 11263], [11493, 11498], [11503, 11516], [11518, 11519], [11558, 11567],
-         [11622, 11630], [11632, 11647], [11671, 11679], [11743, 11822], [11824, 12292],
-         [12296, 12320], [12330, 12336], [12342, 12343], [12349, 12352], [12439, 12444],
-         [12544, 12548], [12590, 12592], [12687, 12689], [12694, 12703], [12728, 12783],
-         [12800, 12831], [12842, 12880], [12896, 12927], [12938, 12976], [12992, 13311],
-         [19894, 19967], [40908, 40959], [42125, 42191], [42238, 42239], [42509, 42511],
-         [42540, 42559], [42592, 42593], [42607, 42622], [42648, 42655], [42736, 42774],
-         [42784, 42785], [42889, 42890], [42893, 43002], [43043, 43055], [43062, 43071],
-         [43124, 43137], [43188, 43215], [43226, 43249], [43256, 43258], [43260, 43263],
-         [43302, 43311], [43335, 43359], [43389, 43395], [43443, 43470], [43482, 43519],
-         [43561, 43583], [43596, 43599], [43610, 43615], [43639, 43641], [43643, 43647],
-         [43698, 43700], [43703, 43704], [43710, 43711], [43715, 43738], [43742, 43967],
-         [44003, 44015], [44026, 44031], [55204, 55215], [55239, 55242], [55292, 55295],
-         [57344, 63743], [64046, 64047], [64110, 64111], [64218, 64255], [64263, 64274],
-         [64280, 64284], [64434, 64466], [64830, 64847], [64912, 64913], [64968, 65007],
-         [65020, 65135], [65277, 65295], [65306, 65312], [65339, 65344], [65371, 65381],
-         [65471, 65473], [65480, 65481], [65488, 65489], [65496, 65497]];
-    for (i = 0; i < ranges.length; i++) {
-        start = ranges[i][0];
-        end = ranges[i][1];
-        for (j = start; j <= end; j++) {
-            result[j] = true;
-        }
-    }
-    return result;
-})();
-
-function splitQuery(query) {
-    var result = [];
-    var start = -1;
-    for (var i = 0; i < query.length; i++) {
-        if (splitChars[query.charCodeAt(i)]) {
-            if (start !== -1) {
-                result.push(query.slice(start, i));
-                start = -1;
-            }
-        } else if (start === -1) {
-            start = i;
-        }
-    }
-    if (start !== -1) {
-        result.push(query.slice(start));
-    }
-    return result;
-}
-
-
-
-
-/**
- * Search Module
- */
-var Search = {
-
-  _index : null,
-  _queued_query : null,
-  _pulse_status : -1,
-
-  init : function() {
-      var params = $.getQueryParameters();
-      if (params.q) {
-          var query = params.q[0];
-          $('input[name="q"]')[0].value = query;
-          this.performSearch(query);
-      }
-  },
-
-  loadIndex : function(url) {
-    $.ajax({type: "GET", url: url, data: null,
-            dataType: "script", cache: true,
-            complete: function(jqxhr, textstatus) {
-              if (textstatus != "success") {
-                document.getElementById("searchindexloader").src = url;
-              }
-            }});
-  },
-
-  setIndex : function(index) {
-    var q;
-    this._index = index;
-    if ((q = this._queued_query) !== null) {
-      this._queued_query = null;
-      Search.query(q);
-    }
-  },
-
-  hasIndex : function() {
-      return this._index !== null;
-  },
-
-  deferQuery : function(query) {
-      this._queued_query = query;
-  },
-
-  stopPulse : function() {
-      this._pulse_status = 0;
-  },
-
-  startPulse : function() {
-    if (this._pulse_status >= 0)
-        return;
-    function pulse() {
-      var i;
-      Search._pulse_status = (Search._pulse_status + 1) % 4;
-      var dotString = '';
-      for (i = 0; i < Search._pulse_status; i++)
-        dotString += '.';
-      Search.dots.text(dotString);
-      if (Search._pulse_status > -1)
-        window.setTimeout(pulse, 500);
-    }
-    pulse();
-  },
-
-  /**
-   * perform a search for something (or wait until index is loaded)
-   */
-  performSearch : function(query) {
-    // create the required interface elements
-    this.out = $('#search-results');
-    this.title = $('<h2>' + _('Searching') + '</h2>').appendTo(this.out);
-    this.dots = $('<span></span>').appendTo(this.title);
-    this.status = $('<p style="display: none"></p>').appendTo(this.out);
-    this.output = $('<ul class="search"/>').appendTo(this.out);
-
-    $('#search-progress').text(_('Preparing search...'));
-    this.startPulse();
-
-    // index already loaded, the browser was quick!
-    if (this.hasIndex())
-      this.query(query);
-    else
-      this.deferQuery(query);
-  },
-
-  /**
-   * execute search (requires search index to be loaded)
-   */
-  query : function(query) {
-    var i;
-    var stopwords = ["a","and","are","as","at","be","but","by","for","if","in","into","is","it","near","no","not","of","on","or","such","that","the","their","then","there","these","they","this","to","was","will","with"];
-
-    // stem the searchterms and add them to the correct list
-    var stemmer = new Stemmer();
-    var searchterms = [];
-    var excluded = [];
-    var hlterms = [];
-    var tmp = splitQuery(query);
-    var objectterms = [];
-    for (i = 0; i < tmp.length; i++) {
-      if (tmp[i] !== "") {
-          objectterms.push(tmp[i].toLowerCase());
-      }
-
-      if ($u.indexOf(stopwords, tmp[i].toLowerCase()) != -1 || tmp[i].match(/^\d+$/) ||
-          tmp[i] === "") {
-        // skip this "word"
-        continue;
-      }
-      // stem the word
-      var word = stemmer.stemWord(tmp[i].toLowerCase());
-      var toAppend;
-      // select the correct list
-      if (word[0] == '-') {
-        toAppend = excluded;
-        word = word.substr(1);
-      }
-      else {
-        toAppend = searchterms;
-        hlterms.push(tmp[i].toLowerCase());
-      }
-      // only add if not already in the list
-      if (!$u.contains(toAppend, word))
-        toAppend.push(word);
-    }
-    var highlightstring = '?highlight=' + $.urlencode(hlterms.join(" "));
-
-    // console.debug('SEARCH: searching for:');
-    // console.info('required: ', searchterms);
-    // console.info('excluded: ', excluded);
-
-    // prepare search
-    var terms = this._index.terms;
-    var titleterms = this._index.titleterms;
-
-    // array of [filename, title, anchor, descr, score]
-    var results = [];
-    $('#search-progress').empty();
-
-    // lookup as object
-    for (i = 0; i < objectterms.length; i++) {
-      var others = [].concat(objectterms.slice(0, i),
-                             objectterms.slice(i+1, objectterms.length));
-      results = results.concat(this.performObjectSearch(objectterms[i], others));
-    }
-
-    // lookup as search terms in fulltext
-    results = results.concat(this.performTermsSearch(searchterms, excluded, terms, titleterms));
-
-    // let the scorer override scores with a custom scoring function
-    if (Scorer.score) {
-      for (i = 0; i < results.length; i++)
-        results[i][4] = Scorer.score(results[i]);
-    }
-
-    // now sort the results by score (in opposite order of appearance, since the
-    // display function below uses pop() to retrieve items) and then
-    // alphabetically
-    results.sort(function(a, b) {
-      var left = a[4];
-      var right = b[4];
-      if (left > right) {
-        return 1;
-      } else if (left < right) {
-        return -1;
-      } else {
-        // same score: sort alphabetically
-        left = a[1].toLowerCase();
-        right = b[1].toLowerCase();
-        return (left > right) ? -1 : ((left < right) ? 1 : 0);
-      }
-    });
-
-    // for debugging
-    //Search.lastresults = results.slice();  // a copy
-    //console.info('search results:', Search.lastresults);
-
-    // print the results
-    var resultCount = results.length;
-    function displayNextItem() {
-      // results left, load the summary and display it
-      if (results.length) {
-        var item = results.pop();
-        var listItem = $('<li style="display:none"></li>');
-        if (DOCUMENTATION_OPTIONS.FILE_SUFFIX === '') {
-          // dirhtml builder
-          var dirname = item[0] + '/';
-          if (dirname.match(/\/index\/$/)) {
-            dirname = dirname.substring(0, dirname.length-6);
-          } else if (dirname == 'index/') {
-            dirname = '';
-          }
-          listItem.append($('<a/>').attr('href',
-            DOCUMENTATION_OPTIONS.URL_ROOT + dirname +
-            highlightstring + item[2]).html(item[1]));
-        } else {
-          // normal html builders
-          listItem.append($('<a/>').attr('href',
-            item[0] + DOCUMENTATION_OPTIONS.FILE_SUFFIX +
-            highlightstring + item[2]).html(item[1]));
-        }
-        if (item[3]) {
-          listItem.append($('<span> (' + item[3] + ')</span>'));
-          Search.output.append(listItem);
-          listItem.slideDown(5, function() {
-            displayNextItem();
-          });
-        } else if (DOCUMENTATION_OPTIONS.HAS_SOURCE) {
-          $.ajax({url: DOCUMENTATION_OPTIONS.URL_ROOT + '_sources/' + item[0] + '.md.txt',
-                  dataType: "text",
-                  complete: function(jqxhr, textstatus) {
-                    var data = jqxhr.responseText;
-                    if (data !== '' && data !== undefined) {
-                      listItem.append(Search.makeSearchSummary(data, searchterms, hlterms));
-                    }
-                    Search.output.append(listItem);
-                    listItem.slideDown(5, function() {
-                      displayNextItem();
-                    });
-                  }});
-        } else {
-          // no source available, just display title
-          Search.output.append(listItem);
-          listItem.slideDown(5, function() {
-            displayNextItem();
-          });
-        }
-      }
-      // search finished, update title and status message
-      else {
-        Search.stopPulse();
-        Search.title.text(_('Search Results'));
-        if (!resultCount)
-          Search.status.text(_('Your search did not match any documents. Please make sure that all words are spelled correctly and that you\'ve selected enough categories.'));
-        else
-            Search.status.text(_('Search finished, found %s page(s) matching the search query.').replace('%s', resultCount));
-        Search.status.fadeIn(500);
-      }
-    }
-    displayNextItem();
-  },
-
-  /**
-   * search for object names
-   */
-  performObjectSearch : function(object, otherterms) {
-    var filenames = this._index.docnames;
-    var objects = this._index.objects;
-    var objnames = this._index.objnames;
-    var titles = this._index.titles;
-
-    var i;
-    var results = [];
-
-    for (var prefix in objects) {
-      for (var name in objects[prefix]) {
-        var fullname = (prefix ? prefix + '.' : '') + name;
-        if (fullname.toLowerCase().indexOf(object) > -1) {
-          var score = 0;
-          var parts = fullname.split('.');
-          // check for different match types: exact matches of full name or
-          // "last name" (i.e. last dotted part)
-          if (fullname == object || parts[parts.length - 1] == object) {
-            score += Scorer.objNameMatch;
-          // matches in last name
-          } else if (parts[parts.length - 1].indexOf(object) > -1) {
-            score += Scorer.objPartialMatch;
-          }
-          var match = objects[prefix][name];
-          var objname = objnames[match[1]][2];
-          var title = titles[match[0]];
-          // If more than one term searched for, we require other words to be
-          // found in the name/title/description
-          if (otherterms.length > 0) {
-            var haystack = (prefix + ' ' + name + ' ' +
-                            objname + ' ' + title).toLowerCase();
-            var allfound = true;
-            for (i = 0; i < otherterms.length; i++) {
-              if (haystack.indexOf(otherterms[i]) == -1) {
-                allfound = false;
-                break;
-              }
-            }
-            if (!allfound) {
-              continue;
-            }
-          }
-          var descr = objname + _(', in ') + title;
-
-          var anchor = match[3];
-          if (anchor === '')
-            anchor = fullname;
-          else if (anchor == '-')
-            anchor = objnames[match[1]][1] + '-' + fullname;
-          // add custom score for some objects according to scorer
-          if (Scorer.objPrio.hasOwnProperty(match[2])) {
-            score += Scorer.objPrio[match[2]];
-          } else {
-            score += Scorer.objPrioDefault;
-          }
-          results.push([filenames[match[0]], fullname, '#'+anchor, descr, score]);
-        }
-      }
-    }
-
-    return results;
-  },
-
-  /**
-   * search for full-text terms in the index
-   */
-  performTermsSearch : function(searchterms, excluded, terms, titleterms) {
-    var filenames = this._index.docnames;
-    var titles = this._index.titles;
-
-    var i, j, file;
-    var fileMap = {};
-    var scoreMap = {};
-    var results = [];
-
-    // perform the search on the required terms
-    for (i = 0; i < searchterms.length; i++) {
-      var word = searchterms[i];
-      var files = [];
-      var _o = [
-        {files: terms[word], score: Scorer.term},
-        {files: titleterms[word], score: Scorer.title}
-      ];
-
-      // no match but word was a required one
-      if ($u.every(_o, function(o){return o.files === undefined;})) {
-        break;
-      }
-      // found search word in contents
-      $u.each(_o, function(o) {
-        var _files = o.files;
-        if (_files === undefined)
-          return
-
-        if (_files.length === undefined)
-          _files = [_files];
-        files = files.concat(_files);
-
-        // set score for the word in each file to Scorer.term
-        for (j = 0; j < _files.length; j++) {
-          file = _files[j];
-          if (!(file in scoreMap))
-            scoreMap[file] = {}
-          scoreMap[file][word] = o.score;
-        }
-      });
-
-      // create the mapping
-      for (j = 0; j < files.length; j++) {
-        file = files[j];
-        if (file in fileMap)
-          fileMap[file].push(word);
-        else
-          fileMap[file] = [word];
-      }
-    }
-
-    // now check if the files don't contain excluded terms
-    for (file in fileMap) {
-      var valid = true;
-
-      // check if all requirements are matched
-      if (fileMap[file].length != searchterms.length)
-          continue;
-
-      // ensure that none of the excluded terms is in the search result
-      for (i = 0; i < excluded.length; i++) {
-        if (terms[excluded[i]] == file ||
-            titleterms[excluded[i]] == file ||
-            $u.contains(terms[excluded[i]] || [], file) ||
-            $u.contains(titleterms[excluded[i]] || [], file)) {
-          valid = false;
-          break;
-        }
-      }
-
-      // if we have still a valid result we can add it to the result list
-      if (valid) {
-        // select one (max) score for the file.
-        // for better ranking, we should calculate ranking by using words statistics like basic tf-idf...
-        var score = $u.max($u.map(fileMap[file], function(w){return scoreMap[file][w]}));
-        results.push([filenames[file], titles[file], '', null, score]);
-      }
-    }
-    return results;
-  },
-
-  /**
-   * helper function to return a node containing the
-   * search summary for a given text. keywords is a list
-   * of stemmed words, hlwords is the list of normal, unstemmed
-   * words. the first one is used to find the occurrence, the
-   * latter for highlighting it.
-   */
-  makeSearchSummary : function(text, keywords, hlwords) {
-    var textLower = text.toLowerCase();
-    var start = 0;
-    $.each(keywords, function() {
-      var i = textLower.indexOf(this.toLowerCase());
-      if (i > -1)
-        start = i;
-    });
-    start = Math.max(start - 120, 0);
-    var excerpt = ((start > 0) ? '...' : '') +
-      $.trim(text.substr(start, 240)) +
-      ((start + 240 - text.length) ? '...' : '');
-    var rv = $('<div class="context"></div>').text(excerpt);
-    $.each(hlwords, function() {
-      rv = rv.highlightText(this, 'highlighted');
-    });
-    return rv;
-  }
-};
-
-/* Search initialization removed for Read the Docs */
-$(document).ready(function() {
-  Search.init();
-});

doc/_static/xgboost-theme/footer.html

@@ -1,5 +0,0 @@
-<div class="container">
-<div class="footer">
-  <p> © 2015-2016 DMLC. All rights reserved. </p>
-</div>
-</div>

doc/_static/xgboost-theme/index.html

@@ -1,58 +0,0 @@
-<div class="splash">
-  <div class="container">
-    <div class="row">
-      <div class="col-lg-12">
-        <h1>Scalable and Flexible Gradient Boosting</h1>
-        <div id="social">
-          <span>
-            <iframe src="https://ghbtns.com/github-btn.html?user=dmlc&repo=xgboost&type=star&count=true&v=2"
-                    frameborder="0" scrolling="0" width="120px" height="20px"></iframe>
-            <iframe src="https://ghbtns.com/github-btn.html?user=dmlc&repo=xgboost&type=fork&count=true&v=2"
-                    frameborder="0" scrolling="0" width="100px" height="20px"></iframe>
-          </span>
-        </div> <!-- end of social -->
-        <div class="get_start">
-          <a href="get_started/" class="get_start_btn">Get Started</a>
-        </div> <!-- end of get started button -->
-      </div>
-    </div>
-  </div>
-</div>
-
-<div class="section-tout">
-  <div class="container">
-    <div class="row">
-      <div class="col-lg-4 col-sm-6">
-        <h3><i class="fa fa-flag"></i> Flexible</h3>
-        <p>Supports regression, classification, ranking and user defined objectives.
-        </p>
-      </div>
-      <div class="col-lg-4 col-sm-6">
-        <h3><i class="fa fa-cube"></i> Portable</h3>
-        <p>Runs on Windows, Linux and OS X, as well as various cloud Platforms</p>
-      </div>
-      <div class="col-lg-4 col-sm-6">
-        <h3><i class="fa fa-wrench"></i>Multiple Languages</h3>
-        <p>Supports multiple languages including C++, Python, R, Java, Scala, Julia.</p>
-      </div>
-      <div class="col-lg-4 col-sm-6">
-        <h3><i class="fa fa-cogs"></i> Battle-tested</h3>
-        <p>Wins many data science and machine learning challenges.
-          Used in production by multiple companies.
-        </p>
-      </div>
-      <div class="col-lg-4 col-sm-6">
-        <h3><i class="fa fa-cloud"></i>Distributed on Cloud</h3>
-        <p>Supports distributed training on multiple machines, including AWS,
-          GCE, Azure, and Yarn clusters. Can be integrated with Flink, Spark and other cloud dataflow systems.</p>
-      </div>
-      <div class="col-lg-4 col-sm-6">
-        <h3><i class="fa fa-rocket"></i> Performance</h3>
-        <p>The well-optimized backend system for the best performance with limited resources.
-          The distributed version solves problems beyond billions of examples with same code.
-        </p>
-      </div>
-    </div>
-  </div>
-</div>
-</div>

doc/_static/xgboost-theme/layout.html

@@ -1,156 +0,0 @@
-{%- block doctype -%}
-<!DOCTYPE html>
-{%- endblock %}
-{%- set reldelim1 = reldelim1 is not defined and ' &raquo;' or reldelim1 %}
-{%- set reldelim2 = reldelim2 is not defined and ' |' or reldelim2 %}
-{%- set render_sidebar = (not embedded) and (not theme_nosidebar|tobool) and
-                         (sidebars != []) %}
-{%- set url_root = pathto('', 1) %}
-{%- if url_root == '#' %}{% set url_root = '' %}{% endif %}
-{%- if not embedded and docstitle %}
-  {%- set titlesuffix = " &mdash; "|safe + docstitle|e %}
-{%- else %}
-  {%- set titlesuffix = "" %}
-{%- endif %}
-
-{%- macro searchform(classes, button) %}
-<form class="{{classes}}" role="search" action="{{ pathto('search') }}" method="get">
-  <div class="form-group">
-    <input type="text" name="q" class="form-control" {{ 'placeholder="Search"' if not button }} >
-  </div>
-  <input type="hidden" name="check_keywords" value="yes" />
-  <input type="hidden" name="area" value="default" />
-  {% if button %}
-    <input type="submit" class="btn btn-default" value="search">
-  {% endif %}
-</form>
-{%- endmacro %}
-
-{%- macro sidebarglobal() %}
-<ul class="globaltoc">
-  {{ toctree(maxdepth=2|toint, collapse=False,includehidden=theme_globaltoc_includehidden|tobool) }}
-</ul>
-{%- endmacro %}
-
-{%- macro sidebar() %}
-      {%- if render_sidebar %}
-      <div class="sphinxsidebar" role="navigation" aria-label="main navigation">
-        <div class="sphinxsidebarwrapper">
-          {%- block sidebartoc %}
-          {%- include "localtoc.html" %}
-          {%- endblock %}
-        </div>
-      </div>
-      {%- endif %}
-{%- endmacro %}
-
-
-{%- macro script() %}
-    <script type="text/javascript">
-      var DOCUMENTATION_OPTIONS = {
-        URL_ROOT:    '{{ url_root }}',
-        VERSION:     '{{ release|e }}',
-        COLLAPSE_INDEX: false,
-        FILE_SUFFIX: '{{ '' if no_search_suffix else file_suffix }}',
-        HAS_SOURCE:  {{ has_source|lower }}
-      };
-    </script>
-
-    {% for name in ['jquery.js', 'underscore.js', 'doctools.js', 'searchtools-new.js'] %}
-    <script type="text/javascript" src="{{ pathto('_static/' + name, 1) }}"></script>
-    {% endfor %}
-
-    <script type="text/javascript" src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script>
-
-    <!-- {%- for scriptfile in script_files %} -->
-    <!-- <script type="text/javascript" src="{{ pathto(scriptfile, 1) }}"></script> -->
-    <!-- {%- endfor %} -->
-{%- endmacro %}
-
-{%- macro css() %}
-    <link rel="stylesheet" href="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.6/css/bootstrap.min.css" integrity="sha384-1q8mTJOASx8j1Au+a5WDVnPi2lkFfwwEAa8hDDdjZlpLegxhjVME1fgjWPGmkzs7" crossorigin="anonymous">
-    {% if pagename == 'index' %}
-    <link rel="stylesheet" href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css">
-    {%- else %}
-    <link rel="stylesheet" href="{{ pathto('_static/' + style, 1) }}" type="text/css" />
-    <link rel="stylesheet" href="{{ pathto('_static/pygments.css', 1) }}" type="text/css" />
-    {%- endif %}
-
-    <link rel="stylesheet" href="{{ pathto('_static/xgboost.css', 1) }}">
-{%- endmacro %}
-
-<html lang="en">
-  <head>
-    <meta charset="{{ encoding }}">
-    <meta http-equiv="X-UA-Compatible" content="IE=edge">
-    <meta name="viewport" content="width=device-width, initial-scale=1">
-    {# The above 3 meta tags *must* come first in the head; any other head content
-       must come *after* these tags. #}
-    {{ metatags }}
-    {%- block htmltitle %}
-    {%- if pagename != 'index' %}
-    <title>{{ title|striptags|e }}{{ titlesuffix }}</title>
-    {%- else %}
-    <title>XGBoost Documents</title>
-    {%- endif %}
-    {%- endblock %}
-    {{ css() }}
-    {%- if not embedded %}
-    {{ script() }}
-    {%- if use_opensearch %}
-    <link rel="search" type="application/opensearchdescription+xml"
-          title="{% trans docstitle=docstitle|e %}Search within {{ docstitle }}{% endtrans %}"
-          href="{{ pathto('_static/opensearch.xml', 1) }}"/>
-    {%- endif %}
-    {%- if favicon %}
-    <link rel="shortcut icon" href="{{ pathto('_static/' + favicon, 1) }}"/>
-    {%- endif %}
-    {%- endif %}
-{%- block linktags %}
-    {%- if hasdoc('about') %}
-    <link rel="author" title="{{ _('About these documents') }}" href="{{ pathto('about') }}" />
-    {%- endif %}
-    {%- if hasdoc('genindex') %}
-    <link rel="index" title="{{ _('Index') }}" href="{{ pathto('genindex') }}" />
-    {%- endif %}
-    {%- if hasdoc('search') %}
-    <link rel="search" title="{{ _('Search') }}" href="{{ pathto('search') }}" />
-    {%- endif %}
-    {%- if hasdoc('copyright') %}
-    <link rel="copyright" title="{{ _('Copyright') }}" href="{{ pathto('copyright') }}" />
-    {%- endif %}
-    {%- if parents %}
-    <link rel="up" title="{{ parents[-1].title|striptags|e }}" href="{{ parents[-1].link|e }}" />
-    {%- endif %}
-    {%- if next %}
-    <link rel="next" title="{{ next.title|striptags|e }}" href="{{ next.link|e }}" />
-    {%- endif %}
-    {%- if prev %}
-    <link rel="prev" title="{{ prev.title|striptags|e }}" href="{{ prev.link|e }}" />
-    {%- endif %}
-{%- endblock %}
-{%- block extrahead %} {% endblock %}
-
-    <link rel="icon" type="image/png" href="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/mxnet-icon.png">
-  </head>
-  <body role="document">
-    {%- include "navbar.html" %}
-
-    {% if pagename != 'index' %}
-    <div class="container">
-      <div class="row">
-        {{ sidebar() }}
-        <div class="content">
-          {% block body %} {% endblock %}
-          {%- include "footer.html" %}
-        </div>
-      </div>
-    </div>
-    {%- else %}
-    {%- include "index.html" %}
-    {%- include "footer.html" %}
-    {%- endif %} <!-- pagename != index -->
-
-    <script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.6/js/bootstrap.min.js" integrity="sha384-0mSbJDEHialfmuBBQP6A4Qrprq5OVfW37PRR3j5ELqxss1yVqOtnepnHVP9aJ7xS" crossorigin="anonymous"></script>
-  </body>
-</html>

doc/_static/xgboost-theme/navbar.html

@@ -1,41 +0,0 @@
-<div class="navbar navbar-default navbar-fixed-top">
-  <div class="container">
-    <div class="navbar-header">
-      <button type="button" class="navbar-toggle collapsed" data-toggle="collapse" data-target="#navbar" aria-expanded="false" aria-controls="navbar">
-        <span class="sr-only">Toggle navigation</span>
-        <span class="icon-bar"></span>
-        <span class="icon-bar"></span>
-        <span class="icon-bar"></span>
-      </button>
-    </div>
-    <div id="navbar" class="navbar-collapse collapse">
-      <ul id="navbar" class="navbar navbar-left">
-        <li> <a href="{{url_root}}">XGBoost</a> </li>
-        {% for name in ['Get Started', 'Tutorials', 'How To'] %}
-        <li> <a href="{{url_root}}{{name.lower()|replace(" ", "_")}}/index.html">{{name}}</a> </li>
-        {% endfor %}
-        {% for name in ['Packages'] %}
-        <li class="dropdown">
-          <a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="true">{{name}} <span class="caret"></span></a>
-          <ul class="dropdown-menu">
-            <li><a href="{{url_root}}python/index.html">Python</a></li>
-            <li><a href="{{url_root}}R-package/index.html">R</a></li>
-            <li><a href="{{url_root}}jvm/index.html">JVM</a></li>
-            <li><a href="{{url_root}}julia/index.html">Julia</a></li>
-            <li><a href="{{url_root}}cli/index.html">CLI</a></li>
-            <li><a href="{{url_root}}gpu/index.html">GPU</a></li>
-          </ul>
-        </li>
-        {% endfor %}
-        <li> <a href="{{url_root}}/parameter.html"> Knobs </a> </li>
-        <li> {{searchform('', False)}} </li>
-      </ul>
-      <!--
-      <ul id="navbar" class="navbar navbar-right">
-        <li> <a href="{{url_root}}index.html"><span class="flag-icon flag-icon-us"></span></a> </li>
-        <li> <a href="{{url_root}}/zh/index.html"><span class="flag-icon flag-icon-cn"></span></a> </li>
-      </ul>
-      navbar -->
-    </div>
-  </div>
-</div>

doc/_static/xgboost-theme/theme.conf

@@ -1,2 +0,0 @@
-[theme]
-inherit = basic

doc/_static/xgboost.css

@@ -1,232 +0,0 @@
-/* header section */
-.splash{
-    padding:5em 0 1em 0;
-    background-color:#0079b2;
-    /* background-image:url(../img/bg.jpg); */
-    background-size:cover;
-    background-attachment:fixed;
-    color:#fff;
-    text-align:center
-}
-
-.splash h1{
-    font-size: 40px;
-    margin-bottom: 20px;
-}
-.splash .social{
-    margin:2em 0
-}
-
-.splash .get_start {
-    margin:2em 0
-}
-
-.splash .get_start_btn {
-  border: 2px solid #FFFFFF;
-  border-radius: 5px;
-  color: #FFFFFF;
-  display: inline-block;
-  font-size: 26px;
-  padding: 9px 20px;
-}
-
-.section-tout{
-    padding:3em 0 3em;
-    border-bottom:1px solid rgba(0,0,0,.05);
-    background-color:#eaf1f1
-}
-.section-tout .fa{
-    margin-right:.5em
-}
-
-.section-tout h3{
-    font-size:20px;
-}
-
-.section-tout p {
-    margin-bottom:2em
-}
-
-.section-inst{
-    padding:3em 0 3em;
-    border-bottom:1px solid rgba(0,0,0,.05);
-
-    text-align:center
-}
-
-.section-inst p {
-    margin-bottom:2em
-}
-.section-inst img {
-    -webkit-filter: grayscale(90%); /* Chrome, Safari, Opera */
-    filter: grayscale(90%);
-    margin-bottom:2em
-}
-.section-inst img:hover {
-    -webkit-filter: grayscale(0%); /* Chrome, Safari, Opera */
-    filter: grayscale(0%);
-}
-
-.footer{
-    padding-top: 40px;
-}
-.footer li{
-    float:right;
-    margin-right:1.5em;
-    margin-bottom:1.5em
-}
-.footer p{
-    font-size: 15px;
-    color: #888;
-    clear:right;
-    margin-bottom:0
-}
-
-
-/* sidebar */
-div.sphinxsidebar {
-    margin-top: 20px;
-    margin-left: 0;
-    position: fixed;
-    overflow-y: scroll;
-    width: 250px;
-    top: 52px;
-    bottom: 0;
-    display: none
-}
-div.sphinxsidebar ul { padding: 0 }
-div.sphinxsidebar ul ul { margin-left: 15px }
-
-@media (min-width:1200px) {
-    .content { float: right; width: 66.66666667%; margin-right: 5% }
-    div.sphinxsidebar {display: block}
-}
-
-
-.github-btn { border: 0; overflow: hidden }
-
-.container {
-    margin-right: auto;
-    margin-left: auto;
-    padding-left: 15px;
-    padding-right: 15px
-}
-
-body>.container {
-    padding-top: 80px
-}
-
-body {
-    font-size: 16px;
-}
-
-pre {
-    font-size: 14px;
-}
-
-/* navbar */
-.navbar {
-    background-color:#0079b2;
-    border: 0px;
-    height: 65px;
-}
-.navbar-right li {
-    display:inline-block;
-    vertical-align:top;
-    padding: 22px 4px;
-}
-
-.navbar-left li {
-    display:inline-block;
-    vertical-align:top;
-    padding: 17px 10px;
-    /* margin: 0 5px; */
-}
-
-.navbar-left li a {
-    font-size: 22px;
-    color: #fff;
-}
-
-.navbar-left > li > a:hover{
-    color:#fff;
-}
-.flag-icon {
-  background-size: contain;
-  background-position: 50%;
-  background-repeat: no-repeat;
-  position: relative;
-  display: inline-block;
-  width: 1.33333333em;
-  line-height: 1em;
-}
-
-.flag-icon:before {
-  content: "\00a0";
-}
-
-
-.flag-icon-cn {
-  background-image: url(./cn.svg);
-}
-
-.flag-icon-us {
-  background-image: url(./us.svg);
-}
-
-
-/* .flags { */
-/*    padding: 10px; */
-/* } */
-
-.navbar-brand >img {
-    width: 110px;
-}
-
-.dropdown-menu li  {
-    padding: 0px 0px;
-    width: 100%;
-}
-.dropdown-menu li a {
-    color: #0079b2;
-    font-size: 20px;
-}
-
-.section h1 {
-    padding-top: 90px;
-    margin-top: -60px;
-    padding-bottom: 10px;
-    font-size: 28px;
-}
-
-.section h2 {
-    padding-top: 80px;
-    margin-top: -60px;
-    padding-bottom: 10px;
-    font-size: 22px;
-}
-
-.section h3 {
-    padding-top: 80px;
-    margin-top: -64px;
-    padding-bottom: 8px;
-}
-
-.section h4 {
-    padding-top: 80px;
-    margin-top: -64px;
-    padding-bottom: 8px;
-}
-
-dt {
-    margin-top: -76px;
-    padding-top: 76px;
-}
-
-dt:target, .highlighted {
-    background-color: #fff;
-}
-
-.section code.descname {
-  font-size: 1em;
-}

doc/build.md

@@ -1,377 +0,0 @@
-Installation Guide
-==================
-
-This page gives instructions on how to build and install the xgboost package from
-scratch on various systems. It consists of two steps:
-
-1. First build the shared library from the C++ codes (`libxgboost.so` for Linux/OSX and `xgboost.dll` for Windows).
-   - Exception: for R-package installation please directly refer to the R package section.
-2. Then install the language packages (e.g. Python Package).
-
-***Important*** the newest version of xgboost uses submodule to maintain packages. So when you clone the repo, remember to use the recursive option as follows.
-```bash
-git clone --recursive https://github.com/dmlc/xgboost
-```
-For windows users who use github tools, you can open the git shell, and type the following command.
-```bash
-git submodule init
-git submodule update
-```
-
-Please refer to [Trouble Shooting Section](#trouble-shooting) first if you had any problem
-during installation. If the instructions do not work for you, please feel free
-to ask questions at [xgboost/issues](https://github.com/dmlc/xgboost/issues), or
-even better to send pull request if you can fix the problem.
-
-## Contents
-- [Build the Shared Library](#build-the-shared-library)
-  - [Building on Ubuntu/Debian](#building-on-ubuntu-debian)
-  - [Building on macOS](#building-on-macos)
-  - [Building on Windows](#building-on-windows)
-  - [Building with GPU support](#building-with-gpu-support)
-  - [Windows Binaries](#windows-binaries)
-  - [Customized Building](#customized-building)
-- [Python Package Installation](#python-package-installation)
-- [R Package Installation](#r-package-installation)
-- [Trouble Shooting](#trouble-shooting)
-
-## Build the Shared Library
-
-Our goal is to build the shared library:
-- On Linux/OSX the target library is `libxgboost.so`
-- On Windows the target library is `xgboost.dll`
-
-The minimal building requirement is
-
-- A recent c++ compiler supporting C++ 11 (g++-4.8 or higher)
-
-We can edit `make/config.mk` to change the compile options, and then build by
-`make`. If everything goes well, we can go to the specific language installation section.
-
-### Building on Ubuntu/Debian
-
-On Ubuntu, one builds xgboost by
-
-```bash
-git clone --recursive https://github.com/dmlc/xgboost
-cd xgboost; make -j4
-```
-
-### Building on macOS
-
-**Install with pip - simple method**
-
-First, make sure you obtained *gcc-5* (newer version does not work with this method yet). Note: installation of `gcc` can take a while (~ 30 minutes)
-
-```bash
-brew install gcc5
-```
-
-You might need to run the following command with `sudo` if you run into some permission errors:
-
-```bash
-pip install xgboost
-```
-
-**Build from the source code - advanced method**
-
-First, obtain gcc-7.x.x with brew (https://brew.sh/) if you want multi-threaded version, otherwise, Clang is ok if OpenMP / multi-threaded is not required. Note: installation of `gcc` can take a while (~ 30 minutes)
-
-```bash
-brew install gcc
-```
-
-Now, clone the repository
-
-```bash
-git clone --recursive https://github.com/dmlc/xgboost
-cd xgboost; cp make/config.mk ./config.mk
-```
-
-Open config.mk and uncomment these two lines
-
-```config.mk
-export CC = gcc
-export CXX = g++
-```
-
-and replace these two lines into(5 or 6 or 7; depending on your gcc-version)
-
-```config.mk
-export CC = gcc-7
-export CXX = g++-7
-```
-
-To find your gcc version
-
-```bash
-gcc-version
-```
-
-and build using the following commands
-
-```bash
-make -j4
-```
-head over to `Python Package Installation` for the next steps
-
-### Building on Windows
-You need to first clone the xgboost repo with recursive option clone the submodules.
-If you are using github tools, you can open the git-shell, and type the following command.
-We recommend using [Git for Windows](https://git-for-windows.github.io/)
-because it brings a standard bash shell. This will highly ease the installation process.
-
-```bash
-git submodule init
-git submodule update
-```
-
-XGBoost support both build by MSVC or MinGW. Here is how you can build xgboost library using MinGW.
-
-After installing [Git for Windows](https://git-for-windows.github.io/), you should have a shortcut `Git Bash`.
-All the following steps are in the `Git Bash`.
-
-In MinGW, `make` command comes with the name `mingw32-make`. You can add the following line into the `.bashrc` file.
-```bash
-alias make='mingw32-make'
-```
-(On 64-bit Windows, you should get [mingw64](https://sourceforge.net/projects/mingw-w64/) instead.) Make sure
-that the path to MinGW is in the system PATH.
-
-To build with MinGW, type:
-
-```bash
-cp make/mingw64.mk config.mk; make -j4
-```
-
-To build with Visual Studio 2013 use cmake. Make sure you have a recent version of cmake added to your path and then from the xgboost directory:
-
-```bash
-mkdir build
-cd build
-cmake .. -G"Visual Studio 12 2013 Win64"
-```
-
-This specifies an out of source build using the MSVC 12 64 bit generator. Open the .sln file in the build directory and build with Visual Studio. To use the Python module you can copy `xgboost.dll` into python-package\xgboost.
-
-Other versions of Visual Studio may work but are untested.
-
-### Building with GPU support
-
-XGBoost can be built with GPU support for both Linux and Windows using cmake. GPU support works with the Python package as well as the CLI version. See [Installing R package with GPU support](#installing-r-package-with-gpu-support) for special instructions for R.
-
-An up-to-date version of the CUDA toolkit is required.
-
-From the command line on Linux starting from the xgboost directory:
-
-```bash
-$ mkdir build
-$ cd build
-$ cmake .. -DUSE_CUDA=ON
-$ make -j
-```
-**Windows requirements** for GPU build: only Visual C++ 2015 or 2013 with CUDA v8.0 were fully tested. Either install Visual C++ 2015 Build Tools separately, or as a part of Visual Studio 2015. If you already have Visual Studio 2017, the Visual C++ 2015 Toolchain componenet has to be installed using the VS 2017 Installer. Likely, you would need to use the VS2015 x64 Native Tools command prompt to run the cmake commands given below. In some situations, however, things run just fine from MSYS2 bash command line.
-
-On Windows, using cmake, see what options for Generators you have for cmake, and choose one with [arch] replaced by Win64:
-```bash
-cmake -help
-```
-Then run cmake as:
-```bash
-$ mkdir build
-$ cd build
-$ cmake .. -G"Visual Studio 14 2015 Win64" -DUSE_CUDA=ON
-```
-To speed up compilation, compute version specific to your GPU could be passed to cmake as, e.g., `-DGPU_COMPUTE_VER=50`.
-The above cmake configuration run will create an xgboost.sln solution file in the build directory. Build this solution in release mode as a x64 build, either from Visual studio or from command line:
-```
-cmake --build . --target xgboost --config Release
-```
-If build seems to use only a single process, you might try to append an option like ` -- /m:6` to the above command.
-
-### Windows Binaries
-
-After the build process successfully ends, you will find a `xgboost.dll` library file inside `./lib/` folder, copy this file to the the API package folder like `python-package/xgboost` if you are using *python* API. And you are good to follow the below instructions.
-
-Unofficial windows binaries and instructions on how to use them are hosted on [Guido Tapia's blog](http://www.picnet.com.au/blogs/guido/post/2016/09/22/xgboost-windows-x64-binaries-for-download/)
-
-### Customized Building
-
-The configuration of xgboost can be modified by ```config.mk```
-- modify configuration on various distributed filesystem such as HDFS/Amazon S3/...
-- First copy [make/config.mk](../make/config.mk) to the project root, on which
-  any local modification will be ignored by git, then modify the according flags.
-
-
-
-## Python Package Installation
-
-The python package is located at [python-package](../python-package).
-There are several ways to install the package:
-
-1. Install system-widely, which requires root permission
-
-   ```bash
-   cd python-package; sudo python setup.py install
-   ```
-
-   You will however need Python `distutils` module for this to
-   work. It is often part of the core python package or it can be installed using your
-   package manager, e.g. in Debian use
-
-   ```bash
-   sudo apt-get install python-setuptools
-   ```
-
-   *NOTE: If you recompiled xgboost, then you need to reinstall it again to
-    make the new library take effect*
-
-2. Only set the environment variable `PYTHONPATH` to tell python where to find
-   the library. For example, assume we cloned `xgboost` on the home directory
-   `~`. then we can added the following line in `~/.bashrc`.
-    It is ***recommended for developers*** who may change the codes. The changes will be immediately reflected once you pulled the code and rebuild the project (no need to call ```setup``` again)
-
-    ```bash
-    export PYTHONPATH=~/xgboost/python-package
-    ```
-
-3. Install only for the current user.
-
-    ```bash
-    cd python-package; python setup.py develop --user
-    ```
-
-4. If you are installing the latest xgboost version which requires compilation, add MinGW to the system PATH:
-
-    ```python
-    import os
-    os.environ['PATH'] = os.environ['PATH'] + ';C:\\Program Files\\mingw-w64\\x86_64-5.3.0-posix-seh-rt_v4-rev0\\mingw64\\bin'
-    ```
-
-## R Package Installation
-
-### Installing pre-packaged version
-
-You can install xgboost from CRAN just like any other R package:
-
-```r
-install.packages("xgboost")
-```
-
-Or you can install it from our weekly updated drat repo:
-
-```r
-install.packages("drat", repos="https://cran.rstudio.com")
-drat:::addRepo("dmlc")
-install.packages("xgboost", repos="http://dmlc.ml/drat/", type = "source")
-```
-
-For OSX users, single threaded version will be installed. To install multi-threaded version,
-first follow [Building on OSX](#building-on-osx) to get the OpenMP enabled compiler, then:
-
-- Set the `Makevars` file in highest piority for R.
-
-  The point is, there are three `Makevars` : `~/.R/Makevars`, `xgboost/R-package/src/Makevars`, and `/usr/local/Cellar/r/3.2.0/R.framework/Resources/etc/Makeconf` (the last one obtained by running `file.path(R.home("etc"), "Makeconf")` in R), and `SHLIB_OPENMP_CXXFLAGS` is not set by default!! After trying, it seems that the first one has highest piority (surprise!).
-
-  Then inside R, run
-
-  ```R
-  install.packages("drat", repos="https://cran.rstudio.com")
-  drat:::addRepo("dmlc")
-  install.packages("xgboost", repos="http://dmlc.ml/drat/", type = "source")
-  ```
-
-### Installing the development version
-
-Make sure you have installed git and a recent C++ compiler supporting C++11 (e.g., g++-4.8 or higher).
-On Windows, Rtools must be installed, and its bin directory has to be added to PATH during the installation.
-And see the previous subsection for an OSX tip.
-
-Due to the use of git-submodules, `devtools::install_github` can no longer be used to install the latest version of R package.
-Thus, one has to run git to check out the code first:
-
-```bash
-git clone --recursive https://github.com/dmlc/xgboost
-cd xgboost
-git submodule init
-git submodule update
-cd R-package
-R CMD INSTALL .
-```
-
-If the last line fails because of "R: command not found", it means that R was not set up to run from command line.
-In this case, just start R as you would normally do and run the following:
-
-```r
-setwd('wherever/you/cloned/it/xgboost/R-package/')
-install.packages('.', repos = NULL, type="source")
-```
-
-The package could also be built and installed with cmake (and Visual C++ 2015 on Windows) using instructions from the next section, but without GPU support (omit the `-DUSE_CUDA=ON` cmake parameter).
-
-If all fails, try [building the shared library](#build-the-shared-library) to see whether a problem is specific to R package or not.
-
-### Installing R package with GPU support
-
-The procedure and requirements are similar as in [Building with GPU support](#building-with-gpu-support), so make sure to read it first.
-
-On Linux, starting from the xgboost directory:
-
-```bash
-mkdir build
-cd build
-cmake .. -DUSE_CUDA=ON -DR_LIB=ON
-make install -j
-```
-When default target is used, an R package shared library would be built in the `build` area.
-The `install` target, in addition, assembles the package files with this shared library under `build/R-package`, and runs `R CMD INSTALL`.
-
-On Windows, cmake with Visual C++ Build Tools (or Visual Studio) has to be used to build an R package with GPU support. Rtools must also be installed (perhaps, some other MinGW distributions with `gendef.exe` and `dlltool.exe` would work, but that was not tested).
-```bash
-mkdir build
-cd build
-cmake .. -G"Visual Studio 14 2015 Win64" -DUSE_CUDA=ON -DR_LIB=ON
-cmake --build . --target install --config Release
-```
-When `--target xgboost` is used, an R package dll would be built under `build/Release`.
-The `--target install`, in addition, assembles the package files with this dll under `build/R-package`, and runs `R CMD INSTALL`.
-
-If cmake can't find your R during the configuration step, you might provide the location of its executable to cmake like this: `-DLIBR_EXECUTABLE="C:/Program Files/R/R-3.4.1/bin/x64/R.exe"`.
-
-If on Windows you get a "permission denied" error when trying to write to ...Program Files/R/... during the package installation, create a `.Rprofile` file in your personal home directory (if you don't already have one in there), and add a line to it which specifies the location of your R packages user library, like the following:
-```r
-.libPaths( unique(c("C:/Users/USERNAME/Documents/R/win-library/3.4", .libPaths())))
-```
-You might find the exact location by running `.libPaths()` in R GUI or RStudio.
-
-## Trouble Shooting
-
-1. **Compile failed after `git pull`**
-
-   Please first update the submodules, clean all and recompile:
-
-   ```bash
-   git submodule update && make clean_all && make -j4
-   ```
-
-2. **Compile failed after `config.mk` is modified**
-
-   Need to clean all first:
-
-    ```bash
-    make clean_all && make -j4
-    ```
-
-
-3. **Makefile: dmlc-core/make/dmlc.mk: No such file or directory**
-
-   We need to recursively clone the submodule, you can do:
-
-    ```bash
-    git submodule init
-    git submodule update
-    ```
-    Alternatively, do another clone
-    ```bash
-    git clone https://github.com/dmlc/xgboost --recursive
-    ```

doc/build.rst

@@ -0,0 +1,445 @@
+##################
+Installation Guide
+##################
+
+.. note:: Pre-built binary wheel for Python
+
+  If you are planning to use Python, consider installing XGBoost from a pre-built binary wheel, available from Python Package Index (PyPI). You may download and install it by running
+
+  .. code-block:: bash
+
+    # Ensure that you are downloading one of the following:
+    #   * xgboost-{version}-py2.py3-none-manylinux1_x86_64.whl
+    #   * xgboost-{version}-py2.py3-none-win_amd64.whl
+    pip3 install xgboost
+
+  * The binary wheel will support GPU algorithms (`gpu_exact`, `gpu_hist`) on machines with NVIDIA GPUs. **However, it will not support multi-GPU training; only single GPU will be used.** To enable multi-GPU training, download and install the binary wheel from `this page <https://s3-us-west-2.amazonaws.com/xgboost-wheels/list.html>`_.
+  * Currently, we provide binary wheels for 64-bit Linux and Windows.
+
+****************************
+Building XGBoost from source
+****************************
+This page gives instructions on how to build and install XGBoost from scratch on various systems. It consists of two steps:
+
+1. First build the shared library from the C++ codes (``libxgboost.so`` for Linux/OSX and ``xgboost.dll`` for Windows).
+   (For R-package installation, please directly refer to `R Package Installation`_.)
+2. Then install the language packages (e.g. Python Package).
+
+.. note:: Use of Git submodules
+
+  XGBoost uses Git submodules to manage dependencies. So when you clone the repo, remember to specify ``--recursive`` option:
+  
+  .. code-block:: bash
+
+    git clone --recursive https://github.com/dmlc/xgboost
+
+For windows users who use github tools, you can open the git shell and type the following command:
+
+.. code-block:: batch
+
+  git submodule init
+  git submodule update
+
+Please refer to `Trouble Shooting`_ section first if you have any problem
+during installation. If the instructions do not work for you, please feel free
+to ask questions at `the user forum <https://discuss.xgboost.ai>`_.
+
+**Contents**
+
+* `Building the Shared Library`_
+
+  - `Building on Ubuntu/Debian`_
+  - `Building on OSX`_
+  - `Building on Windows`_
+  - `Building with GPU support`_
+  - `Customized Building`_
+
+* `Python Package Installation`_
+* `R Package Installation`_
+* `Trouble Shooting`_
+
+***************************
+Building the Shared Library
+***************************
+
+Our goal is to build the shared library:
+
+- On Linux/OSX the target library is ``libxgboost.so``
+- On Windows the target library is ``xgboost.dll``
+
+The minimal building requirement is
+
+- A recent C++ compiler supporting C++11 (g++-4.8 or higher)
+
+We can edit ``make/config.mk`` to change the compile options, and then build by
+``make``. If everything goes well, we can go to the specific language installation section.
+
+Building on Ubuntu/Debian
+=========================
+
+On Ubuntu, one builds XGBoost by running
+
+.. code-block:: bash
+
+  git clone --recursive https://github.com/dmlc/xgboost
+  cd xgboost; make -j4
+
+Building on OSX
+===============
+
+Install with pip: simple method
+--------------------------------
+
+First, make sure you obtained ``gcc-5`` (newer version does not work with this method yet). Note: installation of ``gcc`` can take a while (~ 30 minutes).
+
+.. code-block:: bash
+
+  brew install gcc@5
+
+Then install XGBoost with ``pip``:
+
+.. code-block:: bash
+
+  pip3 install xgboost
+
+You might need to run the command with ``sudo`` if you run into permission errors.
+
+Build from the source code - advanced method
+--------------------------------------------
+
+First, obtain ``gcc-7`` with homebrew (https://brew.sh/) if you want multi-threaded version. Clang is okay if multithreading is not required. Note: installation of ``gcc`` can take a while (~ 30 minutes).
+
+.. code-block:: bash
+
+  brew install gcc@7
+
+Now, clone the repository:
+
+.. code-block:: bash
+
+  git clone --recursive https://github.com/dmlc/xgboost
+  cd xgboost; cp make/config.mk ./config.mk
+
+Open ``config.mk`` and uncomment these two lines:
+
+.. code-block:: bash
+
+  export CC = gcc
+  export CXX = g++
+
+and replace these two lines as follows: (specify the GCC version)
+
+.. code-block:: bash
+
+  export CC = gcc-7
+  export CXX = g++-7
+
+Now, you may build XGBoost using the following command:
+
+.. code-block:: bash
+
+  make -j4
+
+You may now continue to `Python Package Installation`_.
+
+Building on Windows
+===================
+You need to first clone the XGBoost repo with ``--recursive`` option, to clone the submodules.
+We recommend you use `Git for Windows <https://git-for-windows.github.io/>`_, as it comes with a standard Bash shell. This will highly ease the installation process.
+
+.. code-block:: bash
+
+  git submodule init
+  git submodule update
+
+XGBoost support compilation with Microsoft Visual Studio and MinGW.
+
+Compile XGBoost using MinGW
+---------------------------
+After installing `Git for Windows <https://git-for-windows.github.io/>`_, you should have a shortcut named ``Git Bash``. You should run all subsequent steps in ``Git Bash``.
+
+In MinGW, ``make`` command comes with the name ``mingw32-make``. You can add the following line into the ``.bashrc`` file:
+
+.. code-block:: bash
+
+  alias make='mingw32-make'
+
+(On 64-bit Windows, you should get `MinGW64 <https://sourceforge.net/projects/mingw-w64/>`_ instead.) Make sure
+that the path to MinGW is in the system PATH.
+
+To build with MinGW, type:
+
+.. code-block:: bash
+
+  cp make/mingw64.mk config.mk; make -j4
+
+Compile XGBoost with Microsoft Visual Studio
+--------------------------------------------
+To build with Visual Studio, we will need CMake. Make sure to install a recent version of CMake. Then run the following from the root of the XGBoost directory:
+
+.. code-block:: bash
+
+  mkdir build
+  cd build
+  cmake .. -G"Visual Studio 12 2013 Win64"
+
+This specifies an out of source build using the MSVC 12 64 bit generator. Open the ``.sln`` file in the build directory and build with Visual Studio. To use the Python module you can copy ``xgboost.dll`` into ``python-package/xgboost``.
+
+After the build process successfully ends, you will find a ``xgboost.dll`` library file inside ``./lib/`` folder, copy this file to the the API package folder like ``python-package/xgboost`` if you are using Python API.
+
+Unofficial windows binaries and instructions on how to use them are hosted on `Guido Tapia's blog <http://www.picnet.com.au/blogs/guido/post/2016/09/22/xgboost-windows-x64-binaries-for-download/>`_.
+
+.. _build_gpu_support:
+
+Building with GPU support
+=========================
+XGBoost can be built with GPU support for both Linux and Windows using CMake. GPU support works with the Python package as well as the CLI version. See `Installing R package with GPU support`_ for special instructions for R.
+
+An up-to-date version of the CUDA toolkit is required.
+
+From the command line on Linux starting from the XGBoost directory:
+
+.. code-block:: bash
+
+  mkdir build
+  cd build
+  cmake .. -DUSE_CUDA=ON
+  make -j
+
+.. note:: Enabling multi-GPU training
+
+  By default, multi-GPU training is disabled and only a single GPU will be used. To enable multi-GPU training, set the option ``USE_NCCL=ON``. Multi-GPU training depends on NCCL2, available at `this link <https://developer.nvidia.com/nccl>`_. Since NCCL2 is only available for Linux machines, **multi-GPU training is available only for Linux**.
+
+  .. code-block:: bash
+
+    mkdir build
+    cd build
+    cmake .. -DUSE_CUDA=ON -DUSE_NCCL=ON
+    make -j
+
+On Windows, see what options for generators you have for CMake, and choose one with ``[arch]`` replaced with Win64:
+
+.. code-block:: bash
+
+  cmake -help
+
+Then run CMake as follows:
+
+.. code-block:: bash
+
+  mkdir build
+  cd build
+  cmake .. -G"Visual Studio 14 2015 Win64" -DUSE_CUDA=ON
+
+.. note:: Visual Studio 2017 Win64 Generator may not work
+
+  Choosing the Visual Studio 2017 generator may cause compilation failure. When it happens, specify the 2015 compiler by adding the ``-T`` option:
+
+  .. code-block:: bash
+
+    make .. -G"Visual Studio 15 2017 Win64" -T v140,cuda=8.0 -DR_LIB=ON -DUSE_CUDA=ON
+
+To speed up compilation, the compute version specific to your GPU could be passed to cmake as, e.g., ``-DGPU_COMPUTE_VER=50``.
+The above cmake configuration run will create an ``xgboost.sln`` solution file in the build directory. Build this solution in release mode as a x64 build, either from Visual studio or from command line:
+
+.. code-block:: bash
+
+  cmake --build . --target xgboost --config Release
+
+To speed up compilation, run multiple jobs in parallel by appending option ``-- /MP``.
+
+Customized Building
+===================
+
+The configuration file ``config.mk`` modifies several compilation flags:
+- Whether to enable support for various distributed filesystems such as HDFS and Amazon S3
+- Which compiler to use
+- And some more
+
+To customize, first copy ``make/config.mk`` to the project root and then modify the copy.
+
+Python Package Installation
+===========================
+
+The python package is located at ``python-package/``.
+There are several ways to install the package:
+
+1. Install system-wide, which requires root permission:
+
+.. code-block:: bash
+
+  cd python-package; sudo python setup.py install
+
+You will however need Python ``distutils`` module for this to
+work. It is often part of the core python package or it can be installed using your
+package manager, e.g. in Debian use
+
+.. code-block:: bash
+
+  sudo apt-get install python-setuptools
+
+.. note:: Re-compiling XGBoost
+
+  If you recompiled XGBoost, then you need to reinstall it again to make the new library take effect.
+
+2. Only set the environment variable ``PYTHONPATH`` to tell python where to find
+   the library. For example, assume we cloned `xgboost` on the home directory
+   `~`. then we can added the following line in `~/.bashrc`.
+   This option is **recommended for developers** who change the code frequently. The changes will be immediately reflected once you pulled the code and rebuild the project (no need to call ``setup`` again)
+
+.. code-block:: bash
+
+  export PYTHONPATH=~/xgboost/python-package
+
+3. Install only for the current user.
+
+.. code-block:: bash
+
+  cd python-package; python setup.py develop --user
+
+4. If you are installing the latest XGBoost version which requires compilation, add MinGW to the system PATH:
+
+.. code-block:: bash
+
+    import os
+    os.environ['PATH'] = os.environ['PATH'] + ';C:\\Program Files\\mingw-w64\\x86_64-5.3.0-posix-seh-rt_v4-rev0\\mingw64\\bin'
+
+R Package Installation
+======================
+
+Installing pre-packaged version
+-------------------------------
+
+You can install xgboost from CRAN just like any other R package:
+
+.. code-block:: R
+
+  install.packages("xgboost")
+
+Or you can install it from our weekly updated drat repo:
+
+.. code-block:: R
+
+  install.packages("drat", repos="https://cran.rstudio.com")
+  drat:::addRepo("dmlc")
+  install.packages("xgboost", repos="http://dmlc.ml/drat/", type = "source")
+
+For OSX users, single threaded version will be installed. To install multi-threaded version,
+first follow `Building on OSX`_ to get the OpenMP enabled compiler. Then
+
+- Set the ``Makevars`` file in highest piority for R.
+
+  The point is, there are three ``Makevars`` : ``~/.R/Makevars``, ``xgboost/R-package/src/Makevars``, and ``/usr/local/Cellar/r/3.2.0/R.framework/Resources/etc/Makeconf`` (the last one obtained by running ``file.path(R.home("etc"), "Makeconf")`` in R), and ``SHLIB_OPENMP_CXXFLAGS`` is not set by default!! After trying, it seems that the first one has highest piority (surprise!).
+
+  Then inside R, run
+
+.. code-block:: R
+
+  install.packages("drat", repos="https://cran.rstudio.com")
+  drat:::addRepo("dmlc")
+  install.packages("xgboost", repos="http://dmlc.ml/drat/", type = "source")
+
+Installing the development version
+----------------------------------
+
+Make sure you have installed git and a recent C++ compiler supporting C++11 (e.g., g++-4.8 or higher).
+On Windows, Rtools must be installed, and its bin directory has to be added to PATH during the installation.
+And see the previous subsection for an OSX tip.
+
+Due to the use of git-submodules, ``devtools::install_github`` can no longer be used to install the latest version of R package.
+Thus, one has to run git to check out the code first:
+
+.. code-block:: bash
+
+  git clone --recursive https://github.com/dmlc/xgboost
+  cd xgboost
+  git submodule init
+  git submodule update
+  cd R-package
+  R CMD INSTALL .
+
+If the last line fails because of the error ``R: command not found``, it means that R was not set up to run from command line.
+In this case, just start R as you would normally do and run the following:
+
+.. code-block:: R
+
+  setwd('wherever/you/cloned/it/xgboost/R-package/')
+  install.packages('.', repos = NULL, type="source")
+
+The package could also be built and installed with cmake (and Visual C++ 2015 on Windows) using instructions from the next section, but without GPU support (omit the ``-DUSE_CUDA=ON`` cmake parameter).
+
+If all fails, try `Building the shared library`_ to see whether a problem is specific to R package or not.
+
+Installing R package with GPU support
+-------------------------------------
+
+The procedure and requirements are similar as in `Building with GPU support`_, so make sure to read it first.
+
+On Linux, starting from the XGBoost directory type:
+
+.. code-block:: bash
+
+  mkdir build
+  cd build
+  cmake .. -DUSE_CUDA=ON -DR_LIB=ON
+  make install -j
+
+When default target is used, an R package shared library would be built in the ``build`` area.
+The ``install`` target, in addition, assembles the package files with this shared library under ``build/R-package``, and runs ``R CMD INSTALL``.
+
+On Windows, cmake with Visual C++ Build Tools (or Visual Studio) has to be used to build an R package with GPU support. Rtools must also be installed (perhaps, some other MinGW distributions with ``gendef.exe`` and ``dlltool.exe`` would work, but that was not tested).
+
+.. code-block:: bash
+
+  mkdir build
+  cd build
+  cmake .. -G"Visual Studio 14 2015 Win64" -DUSE_CUDA=ON -DR_LIB=ON
+  cmake --build . --target install --config Release
+
+When ``--target xgboost`` is used, an R package dll would be built under ``build/Release``.
+The ``--target install``, in addition, assembles the package files with this dll under ``build/R-package``, and runs ``R CMD INSTALL``.
+
+If cmake can't find your R during the configuration step, you might provide the location of its executable to cmake like this: ``-DLIBR_EXECUTABLE="C:/Program Files/R/R-3.4.1/bin/x64/R.exe"``.
+
+If on Windows you get a "permission denied" error when trying to write to ...Program Files/R/... during the package installation, create a ``.Rprofile`` file in your personal home directory (if you don't already have one in there), and add a line to it which specifies the location of your R packages user library, like the following:
+
+.. code-block:: R
+
+  .libPaths( unique(c("C:/Users/USERNAME/Documents/R/win-library/3.4", .libPaths())))
+
+You might find the exact location by running ``.libPaths()`` in R GUI or RStudio.
+
+Trouble Shooting
+================
+
+1. Compile failed after ``git pull``
+
+   Please first update the submodules, clean all and recompile:
+
+   .. code-block:: bash
+
+     git submodule update && make clean_all && make -j4
+
+2. Compile failed after ``config.mk`` is modified
+
+   Need to clean all first:
+
+   .. code-block:: bash
+
+     make clean_all && make -j4
+
+3. ``Makefile: dmlc-core/make/dmlc.mk: No such file or directory``
+
+   We need to recursively clone the submodule:
+
+   .. code-block:: bash
+
+     git submodule init
+     git submodule update
+
+   Alternatively, do another clone
+
+   .. code-block:: bash
+
+     git clone https://github.com/dmlc/xgboost --recursive
+

doc/cli.rst

@@ -0,0 +1,5 @@
+############################
+XGBoost Command Line version
+############################
+
+See `XGBoost Command Line walkthrough <https://github.com/dmlc/xgboost/blob/master/demo/binary_classification/README.md>`_.

doc/cli/index.md

@@ -1,3 +0,0 @@
-# XGBoost Command Line version
-
-See [XGBoost Command Line walkthrough](https://github.com/dmlc/xgboost/blob/master/demo/binary_classification/README.md)

doc/conf.py

@@ -11,9 +11,26 @@
 #
 # All configuration values have a default; values that are commented out
 # serve to show the default.
+from subprocess import call
+from sh.contrib import git
+import urllib.request
+from urllib.error import HTTPError
+from recommonmark.parser import CommonMarkParser
 import sys
+import re
 import os, subprocess
 import shlex
+import guzzle_sphinx_theme
+
+git_branch = [re.sub(r'origin/', '', x.lstrip(' ')) for x in str(git.branch('-r', '--contains', 'HEAD')).rstrip('\n').split('\n')]
+git_branch = [x for x in git_branch if 'HEAD' not in x]
+print('git_branch = {}'.format(git_branch[0]))
+try:
+  filename, _ = urllib.request.urlretrieve('https://s3-us-west-2.amazonaws.com/xgboost-docs/{}.tar.bz2'.format(git_branch[0]))
+  call('if [ -d tmp ]; then rm -rf tmp; fi; mkdir -p tmp/jvm; cd tmp/jvm; tar xvf {}'.format(filename), shell=True)
+except HTTPError:
+  print('JVM doc not found. Skipping...')
+
 # If extensions (or modules to document with autodoc) are in another directory,
 # add these directories to sys.path here. If the directory is relative to the
 # documentation root, use os.path.abspath to make it absolute, like shown here.
@@ -22,13 +39,11 @@ libpath = os.path.join(curr_path, '../python-package/')
 sys.path.insert(0, libpath)
 sys.path.insert(0, curr_path)
 
-from sphinx_util import MarkdownParser, AutoStructify
-
 # -- mock out modules
 import mock
 MOCK_MODULES = ['numpy', 'scipy', 'scipy.sparse', 'sklearn', 'matplotlib', 'pandas', 'graphviz']
 for mod_name in MOCK_MODULES:
-    sys.modules[mod_name] = mock.Mock()
+  sys.modules[mod_name] = mock.Mock()
 
 # -- General configuration ------------------------------------------------
 
@@ -38,11 +53,6 @@ author = u'%s developers' % project
 copyright = u'2016, %s' % author
 github_doc_root = 'https://github.com/dmlc/xgboost/tree/master/doc/'
 
-# add markdown parser
-MarkdownParser.github_doc_root = github_doc_root
-source_parsers = {
-    '.md': MarkdownParser,
-}
 os.environ['XGBOOST_BUILD_DOC'] = '1'
 # Version information.
 import xgboost
@@ -55,14 +65,23 @@ extensions = [
     'sphinx.ext.autodoc',
     'sphinx.ext.napoleon',
     'sphinx.ext.mathjax',
+    'sphinx.ext.intersphinx',
+    'breathe'
 ]
 
+# Breathe extension variables
+breathe_projects = {"xgboost": "doxyxml/"}
+breathe_default_project = "xgboost"
+
 # Add any paths that contain templates here, relative to this directory.
 templates_path = ['_templates']
 
+source_parsers = {
+  '.md': CommonMarkParser,
+}
+
 # The suffix(es) of source filenames.
 # You can specify multiple suffix as a list of string:
-# source_suffix = ['.rst', '.md']
 source_suffix = ['.rst', '.md']
 
 # The encoding of source files.
@@ -89,6 +108,7 @@ autoclass_content = 'both'
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.
 exclude_patterns = ['_build']
+html_extra_path = ['./tmp']
 
 # The reST default role (used for this markup: `text`) to use for all
 # documents.
@@ -119,11 +139,23 @@ todo_include_todos = False
 
 # -- Options for HTML output ----------------------------------------------
 
-html_theme_path = ['_static']
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
-# html_theme = 'alabaster'
+html_theme_path = guzzle_sphinx_theme.html_theme_path()
-html_theme = 'xgboost-theme'
+html_theme = 'guzzle_sphinx_theme'
+
+# Register the theme as an extension to generate a sitemap.xml
+extensions.append("guzzle_sphinx_theme")
+
+# Guzzle theme options (see theme.conf for more information)
+html_theme_options = {
+    # Set the name of the project to appear in the sidebar
+    "project_nav_name": "XGBoost (0.80)"
+}
+
+html_sidebars = {
+  '**': ['logo-text.html', 'globaltoc.html', 'searchbox.html']
+}
 
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
@@ -145,38 +177,27 @@ latex_documents = [
    author, 'manual'),
 ]
 
+intersphinx_mapping = {'python': ('https://docs.python.org/3.6', None),
+                       'numpy': ('http://docs.scipy.org/doc/numpy/', None),
+                       'scipy': ('http://docs.scipy.org/doc/scipy/reference/', None),
+                       'pandas': ('http://pandas-docs.github.io/pandas-docs-travis/', None),
+                       'sklearn': ('http://scikit-learn.org/stable', None)}
+
 # hook for doxygen
 def run_doxygen(folder):
-    """Run the doxygen make command in the designated folder."""
+  """Run the doxygen make command in the designated folder."""
-    try:
+  try:
-        retcode = subprocess.call("cd %s; make doxygen" % folder, shell=True)
+    retcode = subprocess.call("cd %s; make doxygen" % folder, shell=True)
-        if retcode < 0:
+    if retcode < 0:
-            sys.stderr.write("doxygen terminated by signal %s" % (-retcode))
+      sys.stderr.write("doxygen terminated by signal %s" % (-retcode))
-    except OSError as e:
+  except OSError as e:
-        sys.stderr.write("doxygen execution failed: %s" % e)
+    sys.stderr.write("doxygen execution failed: %s" % e)
 
 def generate_doxygen_xml(app):
-    """Run the doxygen make commands if we're on the ReadTheDocs server"""
+  """Run the doxygen make commands if we're on the ReadTheDocs server"""
-    read_the_docs_build = os.environ.get('READTHEDOCS', None) == 'True'
+  read_the_docs_build = os.environ.get('READTHEDOCS', None) == 'True'
-    if read_the_docs_build:
+  if read_the_docs_build:
-        run_doxygen('..')
+    run_doxygen('..')
 
 def setup(app):
-    # Add hook for building doxygen xml when needed
+  app.add_stylesheet('custom.css')
-    # no c++ API for now
-    # app.connect("builder-inited", generate_doxygen_xml)
-
-    # urlretrieve got moved in Python 3.x
-    try:
-      from urllib import urlretrieve
-    except ImportError:
-      from urllib.request import urlretrieve
-    urlretrieve('https://code.jquery.com/jquery-2.2.4.min.js',
-                '_static/jquery.js')
-    app.add_config_value('recommonmark_config', {
-            'url_resolver': lambda url: github_doc_root + url,
-            'enable_eval_rst': True,
-            }, True,
-            )
-    app.add_transform(AutoStructify)
-    app.add_javascript('jquery.js')

doc/contribute.rst

@@ -0,0 +1,256 @@
+#####################
+Contribute to XGBoost
+#####################
+XGBoost has been developed and used by a group of active community members.
+Everyone is more than welcome to contribute. It is a way to make the project better and more accessible to more users.
+
+- Please add your name to `CONTRIBUTORS.md <https://github.com/dmlc/xgboost/blob/master/CONTRIBUTORS.md>`_ after your patch has been merged.
+- Please also update `NEWS.md <https://github.com/dmlc/xgboost/blob/master/NEWS.md>`_ to add note on your changes to the API or XGBoost documentation.
+
+**Guidelines**
+
+* `Submit Pull Request`_
+* `Git Workflow Howtos`_
+
+  - `How to resolve conflict with master`_
+  - `How to combine multiple commits into one`_
+  - `What is the consequence of force push`_
+
+* `Documents`_
+* `Testcases`_
+* `Sanitizers`_
+* `Examples`_
+* `Core Library`_
+* `Python Package`_
+* `R Package`_
+
+*******************
+Submit Pull Request
+*******************
+
+* Before submit, please rebase your code on the most recent version of master, you can do it by
+
+  .. code-block:: bash
+
+    git remote add upstream https://github.com/dmlc/xgboost
+    git fetch upstream
+    git rebase upstream/master
+
+* If you have multiple small commits,
+  it might be good to merge them together(use git rebase then squash) into more meaningful groups.
+* Send the pull request!
+
+  - Fix the problems reported by automatic checks
+  - If you are contributing a new module, consider add a testcase in `tests <https://github.com/dmlc/xgboost/tree/master/tests>`_.
+
+*******************
+Git Workflow Howtos
+*******************
+
+How to resolve conflict with master
+===================================
+- First rebase to most recent master
+
+  .. code-block:: bash
+
+    # The first two steps can be skipped after you do it once.
+    git remote add upstream https://github.com/dmlc/xgboost
+    git fetch upstream
+    git rebase upstream/master
+
+- The git may show some conflicts it cannot merge, say ``conflicted.py``.
+
+  - Manually modify the file to resolve the conflict.
+  - After you resolved the conflict, mark it as resolved by
+
+    .. code-block:: bash
+
+      git add conflicted.py
+
+- Then you can continue rebase by
+
+  .. code-block:: bash
+
+    git rebase --continue
+
+- Finally push to your fork, you may need to force push here.
+
+  .. code-block:: bash
+
+    git push --force
+
+How to combine multiple commits into one
+========================================
+Sometimes we want to combine multiple commits, especially when later commits are only fixes to previous ones,
+to create a PR with set of meaningful commits. You can do it by following steps.
+
+- Before doing so, configure the default editor of git if you haven't done so before.
+
+  .. code-block:: bash
+
+    git config core.editor the-editor-you-like
+
+- Assume we want to merge last 3 commits, type the following commands
+
+  .. code-block:: bash
+
+    git rebase -i HEAD~3
+
+- It will pop up an text editor. Set the first commit as ``pick``, and change later ones to ``squash``.
+- After you saved the file, it will pop up another text editor to ask you modify the combined commit message.
+- Push the changes to your fork, you need to force push.
+
+  .. code-block:: bash
+
+    git push --force
+
+What is the consequence of force push
+=====================================
+The previous two tips requires force push, this is because we altered the path of the commits.
+It is fine to force push to your own fork, as long as the commits changed are only yours.
+
+*********
+Documents
+*********
+* Documentation is built using sphinx.
+* Each document is written in `reStructuredText <http://www.sphinx-doc.org/en/master/usage/restructuredtext/basics.html>`_.
+* You can build document locally to see the effect.
+
+*********
+Testcases
+*********
+* All the testcases are in `tests <https://github.com/dmlc/xgboost/tree/master/tests>`_.
+* We use python nose for python test cases.
+
+**********
+Sanitizers
+**********
+
+By default, sanitizers are bundled in GCC and Clang/LLVM. One can enable
+sanitizers with GCC >= 4.8 or LLVM >= 3.1, But some distributions might package
+sanitizers separately.  Here is a list of supported sanitizers with
+corresponding library names:
+
+- Address sanitizer: libasan
+- Leak sanitizer:    liblsan
+- Thread sanitizer:  libtsan
+
+Memory sanitizer is exclusive to LLVM, hence not supported in XGBoost.
+
+How to build XGBoost with sanitizers
+====================================
+One can build XGBoost with sanitizer support by specifying -DUSE_SANITIZER=ON.
+By default, address sanitizer and leak sanitizer are used when you turn the
+USE_SANITIZER flag on.  You can always change the default by providing a
+semicolon separated list of sanitizers to ENABLED_SANITIZERS.  Note that thread
+sanitizer is not compatible with the other two sanitizers.
+
+  .. code-block:: bash
+
+    cmake -DUSE_SANITIZER=ON -DENABLED_SANITIZERS="address;leak" /path/to/xgboost
+
+How to use sanitizers with CUDA support
+=======================================
+Runing XGBoost on CUDA with address sanitizer (asan) will raise memory error.
+To use asan with CUDA correctly, you need to configure asan via ASAN_OPTIONS
+environment variable:
+
+  .. code-block:: bash
+
+    ASAN_OPTIONS=protect_shadow_gap=0 ../testxgboost
+
+For details, please consult `official documentation <https://github.com/google/sanitizers/wiki>`_ for sanitizers.
+
+
+********
+Examples
+********
+* Usecases and examples will be in `demo <https://github.com/dmlc/xgboost/tree/master/demo>`_.
+* We are super excited to hear about your story, if you have blogposts,
+  tutorials code solutions using XGBoost, please tell us and we will add
+  a link in the example pages.
+
+************
+Core Library
+************
+- Follow `Google style for C++ <https://google.github.io/styleguide/cppguide.html>`_.
+- Use C++11 features such as smart pointers, braced initializers, lambda functions, and ``std::thread``.
+- We use Doxygen to document all the interface code.
+- You can reproduce the linter checks by running ``make lint``
+
+**************
+Python Package
+**************
+- Always add docstring to the new functions in numpydoc format.
+- You can reproduce the linter checks by typing ``make lint``
+
+*********
+R Package
+*********
+
+Code Style
+==========
+- We follow Google's C++ Style guide for C++ code.
+
+  - This is mainly to be consistent with the rest of the project.
+  - Another reason is we will be able to check style automatically with a linter.
+
+- You can check the style of the code by typing the following command at root folder.
+
+  .. code-block:: bash
+
+    make rcpplint
+
+- When needed, you can disable the linter warning of certain line with ```// NOLINT(*)``` comments.
+- We use `roxygen <https://cran.r-project.org/web/packages/roxygen2/vignettes/roxygen2.html>`_ for documenting the R package.
+
+Rmarkdown Vignettes
+===================
+Rmarkdown vignettes are placed in `R-package/vignettes <https://github.com/dmlc/xgboost/tree/master/R-package/vignettes>`_.
+These Rmarkdown files are not compiled. We host the compiled version on `doc/R-package <https://github.com/dmlc/xgboost/tree/master/doc/R-package>`_.
+
+The following steps are followed to add a new Rmarkdown vignettes:
+
+- Add the original rmarkdown to ``R-package/vignettes``.
+- Modify ``doc/R-package/Makefile`` to add the markdown files to be build.
+- Clone the `dmlc/web-data <https://github.com/dmlc/web-data>`_ repo to folder ``doc``.
+- Now type the following command on ``doc/R-package``:
+
+  .. code-block:: bash
+
+    make the-markdown-to-make.md
+
+- This will generate the markdown, as well as the figures in ``doc/web-data/xgboost/knitr``.
+- Modify the ``doc/R-package/index.md`` to point to the generated markdown.
+- Add the generated figure to the ``dmlc/web-data`` repo.
+
+  - If you already cloned the repo to doc, this means ``git add``
+
+- Create PR for both the markdown  and ``dmlc/web-data``.
+- You can also build the document locally by typing the following command at the ``doc`` directory:
+
+  .. code-block:: bash
+
+    make html
+
+The reason we do this is to avoid exploded repo size due to generated images.
+
+R package versioning
+====================
+Since version 0.6.4.3, we have adopted a versioning system that uses x.y.z (or ``core_major.core_minor.cran_release``)
+format for CRAN releases and an x.y.z.p (or ``core_major.core_minor.cran_release.patch``) format for development patch versions.
+This approach is similar to the one described in Yihui Xie's
+`blog post on R Package Versioning <https://yihui.name/en/2013/06/r-package-versioning/>`_,
+except we need an additional field to accomodate the x.y core library version.
+
+Each new CRAN release bumps up the 3rd field, while developments in-between CRAN releases
+would be marked by an additional 4th field on the top of an existing CRAN release version.
+Some additional consideration is needed when the core library version changes.
+E.g., after the core changes from 0.6 to 0.7, the R package development version would become 0.7.0.1, working towards
+a 0.7.1 CRAN release. The 0.7.0 would not be released to CRAN, unless it would require almost no additional development.
+
+Registering native routines in R
+================================
+According to `R extension manual <https://cran.r-project.org/doc/manuals/r-release/R-exts.html#Registering-native-routines>`_,
+it is good practice to register native routines and to disable symbol search. When any changes or additions are made to the
+C++ interface of the R package, please make corresponding changes in ``src/init.c`` as well.

doc/faq.rst

@@ -1,46 +1,50 @@
+##########################
 Frequently Asked Questions
-========================
+##########################
-This document contains frequently asked questions about xgboost.
 
+This document contains frequently asked questions about XGBoost.
+
+**********************
 How to tune parameters
-----------------------
+**********************
-See [Parameter Tunning Guide](how_to/param_tuning.md)
+See :doc:`Parameter Tuning Guide </tutorials/param_tuning>`.
 
+************************
 Description on the model
-------------------------
+************************
-See [Introduction to Boosted Trees](model.md)
+See :doc:`Introduction to Boosted Trees </tutorials/model>`.
-
 
+********************
 I have a big dataset
---------------------
+********************
-XGBoost is designed to be memory efficient. Usually it can handle problems as long as the data fit into your memory
+XGBoost is designed to be memory efficient. Usually it can handle problems as long as the data fit into your memory.
-(This usually means millions of instances).
+(This usually means millions of instances)
-If you are running out of memory, checkout [external memory version](how_to/external_memory.md) or
+If you are running out of memory, checkout :doc:`external memory version </tutorials/external_memory>` or
-[distributed version](../demo/distributed-training) of xgboost.
+:doc:`distributed version </tutorials/aws_yarn>` of XGBoost.
 
-
+**************************************************
-Running xgboost on Platform X (Hadoop/Yarn, Mesos)
+Running XGBoost on Platform X (Hadoop/Yarn, Mesos)
---------------------------------------------------
+**************************************************
 The distributed version of XGBoost is designed to be portable to various environment.
-Distributed XGBoost can be ported to any platform that supports [rabit](https://github.com/dmlc/rabit).
+Distributed XGBoost can be ported to any platform that supports `rabit <https://github.com/dmlc/rabit>`_.
-You can directly run xgboost on Yarn. In theory Mesos and other resource allocation engines can be easily supported as well.
+You can directly run XGBoost on Yarn. In theory Mesos and other resource allocation engines can be easily supported as well.
 
-
+*****************************************************************
-Why not implement distributed xgboost on top of X (Spark, Hadoop)
+Why not implement distributed XGBoost on top of X (Spark, Hadoop)
------------------------------------------------------------------
+*****************************************************************
 The first fact we need to know is going distributed does not necessarily solve all the problems.
 Instead, it creates more problems such as more communication overhead and fault tolerance.
 The ultimate question will still come back to how to push the limit of each computation node
 and use less resources to complete the task (thus with less communication and chance of failure).
 
-To achieve these, we decide to reuse the optimizations in the single node xgboost and build distributed version on top of it.
+To achieve these, we decide to reuse the optimizations in the single node XGBoost and build distributed version on top of it.
 The demand of communication in machine learning is rather simple, in the sense that we can depend on a limited set of API (in our case rabit).
 Such design allows us to reuse most of the code, while being portable to major platforms such as Hadoop/Yarn, MPI, SGE.
 Most importantly, it pushes the limit of the computation resources we can use.
 
-
+*****************************************
 How can I port the model to my own system
------------------------------------------
+*****************************************
 The model and data format of XGBoost is exchangeable,
 which means the model trained by one language can be loaded in another.
 This means you can train the model using R, while running prediction using
@@ -48,26 +52,26 @@ Java or C++, which are more common in production systems.
 You can also train the model using distributed versions,
 and load them in from Python to do some interactive analysis.
 
-
+*************************
 Do you support LambdaMART
--------------------------
+*************************
-Yes, xgboost implements LambdaMART. Checkout the objective section in [parameters](parameter.md)
+Yes, XGBoost implements LambdaMART. Checkout the objective section in :doc:`parameters </parameter>`.
-
 
+******************************
 How to deal with Missing Value
-------------------------------
+******************************
-xgboost supports missing value by default.
+XGBoost supports missing value by default.
 In tree algorithms, branch directions for missing values are learned during training.
 Note that the gblinear booster treats missing values as zeros.
 
-
+**************************************
 Slightly different result between runs
---------------------------------------
+**************************************
 This could happen, due to non-determinism in floating point summation order and multi-threading.
 Though the general accuracy will usually remain the same.
 
-
+**********************************************************
 Why do I see different results with sparse and dense data?
---------------------------------------------------------
+**********************************************************
 "Sparse" elements are treated as if they were "missing" by the tree booster, and as zeros by the linear booster.
-For tree models, it is important to use consistent data formats during training and scoring.
+For tree models, it is important to use consistent data formats during training and scoring.

doc/get_started.rst

@@ -0,0 +1,94 @@
+########################
+Get Started with XGBoost
+########################
+
+This is a quick start tutorial showing snippets for you to quickly try out XGBoost
+on the demo dataset on a binary classification task.
+
+********************************
+Links to Other Helpful Resources
+********************************
+- See :doc:`Installation Guide </build>` on how to install XGBoost.
+- See :doc:`Text Input Format </tutorials/input_format>` on using text format for specifying training/testing data.
+- See :doc:`Tutorials </tutorials/index>` for tips and tutorials.
+- See `Learning to use XGBoost by Examples <https://github.com/dmlc/xgboost/tree/master/demo>`_ for more code examples.
+
+******
+Python
+******
+
+.. code-block:: python
+
+  import xgboost as xgb
+  # read in data
+  dtrain = xgb.DMatrix('demo/data/agaricus.txt.train')
+  dtest = xgb.DMatrix('demo/data/agaricus.txt.test')
+  # specify parameters via map
+  param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'binary:logistic' }
+  num_round = 2
+  bst = xgb.train(param, dtrain, num_round)
+  # make prediction
+  preds = bst.predict(dtest)
+
+***
+R
+***
+
+.. code-block:: R
+
+  # load data
+  data(agaricus.train, package='xgboost')
+  data(agaricus.test, package='xgboost')
+  train <- agaricus.train
+  test <- agaricus.test
+  # fit model
+  bst <- xgboost(data = train$data, label = train$label, max.depth = 2, eta = 1, nrounds = 2,
+                 nthread = 2, objective = "binary:logistic")
+  # predict
+  pred <- predict(bst, test$data)
+
+*****
+Julia
+*****
+
+.. code-block:: julia
+
+  using XGBoost
+  # read data
+  train_X, train_Y = readlibsvm("demo/data/agaricus.txt.train", (6513, 126))
+  test_X, test_Y = readlibsvm("demo/data/agaricus.txt.test", (1611, 126))
+  # fit model
+  num_round = 2
+  bst = xgboost(train_X, num_round, label=train_Y, eta=1, max_depth=2)
+  # predict
+  pred = predict(bst, test_X)
+
+*****
+Scala
+*****
+
+.. code-block:: scala
+
+  import ml.dmlc.xgboost4j.scala.DMatrix
+  import ml.dmlc.xgboost4j.scala.XGBoost
+  
+  object XGBoostScalaExample {
+    def main(args: Array[String]) {
+      // read trainining data, available at xgboost/demo/data
+      val trainData =
+        new DMatrix("/path/to/agaricus.txt.train")
+      // define parameters
+      val paramMap = List(
+        "eta" -> 0.1,
+        "max_depth" -> 2,
+        "objective" -> "binary:logistic").toMap
+      // number of iterations
+      val round = 2
+      // train the model
+      val model = XGBoost.train(trainData, paramMap, round)
+      // run prediction
+      val predTrain = model.predict(trainData)
+      // save model to the file.
+      model.saveModel("/local/path/to/model")
+    }
+  }

doc/get_started/index.md

@@ -1,79 +0,0 @@
-# Get Started with XGBoost
-
-This is a quick start tutorial showing snippets for you to quickly try out xgboost
-on the demo dataset on a binary classification task.
-
-## Links to Helpful Other Resources
-- See [Installation Guide](../build.md) on how to install xgboost.
-- See [How to pages](../how_to/index.md) on various tips on using xgboost.
-- See [Tutorials](../tutorials/index.md) on tutorials on specific tasks.
-- See [Learning to use XGBoost by Examples](../../demo) for more code examples.
-
-## Python
-```python
-import xgboost as xgb
-# read in data
-dtrain = xgb.DMatrix('demo/data/agaricus.txt.train')
-dtest = xgb.DMatrix('demo/data/agaricus.txt.test')
-# specify parameters via map
-param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'binary:logistic' }
-num_round = 2
-bst = xgb.train(param, dtrain, num_round)
-# make prediction
-preds = bst.predict(dtest)
-```
-
-## R
-
-```r
-# load data
-data(agaricus.train, package='xgboost')
-data(agaricus.test, package='xgboost')
-train <- agaricus.train
-test <- agaricus.test
-# fit model
-bst <- xgboost(data = train$data, label = train$label, max.depth = 2, eta = 1, nround = 2,
-               nthread = 2, objective = "binary:logistic")
-# predict
-pred <- predict(bst, test$data)
-```
-
-## Julia
-```julia
-using XGBoost
-# read data
-train_X, train_Y = readlibsvm("demo/data/agaricus.txt.train", (6513, 126))
-test_X, test_Y = readlibsvm("demo/data/agaricus.txt.test", (1611, 126))
-# fit model
-num_round = 2
-bst = xgboost(train_X, num_round, label=train_Y, eta=1, max_depth=2)
-# predict
-pred = predict(bst, test_X)
-```
-
-## Scala
-```scala
-import ml.dmlc.xgboost4j.scala.DMatrix
-import ml.dmlc.xgboost4j.scala.XGBoost
-
-object XGBoostScalaExample {
-  def main(args: Array[String]) {
-    // read trainining data, available at xgboost/demo/data
-    val trainData =
-      new DMatrix("/path/to/agaricus.txt.train")
-    // define parameters
-    val paramMap = List(
-      "eta" -> 0.1,
-      "max_depth" -> 2,
-      "objective" -> "binary:logistic").toMap
-    // number of iterations
-    val round = 2
-    // train the model
-    val model = XGBoost.train(trainData, paramMap, round)
-    // run prediction
-    val predTrain = model.predict(trainData)
-    // save model to the file.
-    model.saveModel("/local/path/to/model")
-  }
-}
-```

doc/gpu/index.md

@@ -1,105 +0,0 @@
-XGBoost GPU Support
-===================
-
-This page contains information about GPU algorithms supported in XGBoost.
-To install GPU support, checkout the [build and installation instructions](../build.md).
-
-# CUDA Accelerated Tree Construction Algorithms
-This plugin adds GPU accelerated tree construction and prediction algorithms to XGBoost.
-## Usage
-Specify the 'tree_method' parameter as one of the following algorithms. 
-
-### Algorithms
-
-```eval_rst
-+--------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------+
-| tree_method  | Description                                                                                                                                                           |
-+==============+=======================================================================================================================================================================+
-| gpu_exact    | The standard XGBoost tree construction algorithm. Performs exact search for splits. Slower and uses considerably more memory than 'gpu_hist'                          |
-+--------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------+
-| gpu_hist     | Equivalent to the XGBoost fast histogram algorithm. Much faster and uses considerably less memory. NOTE: Will run very slowly on GPUs older than Pascal architecture. |
-+--------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------+
-```
-
-### Supported parameters 
-
-```eval_rst
-.. |tick| unicode:: U+2714 
-.. |cross| unicode:: U+2718 
-
-+----------------------+------------+-----------+
-| parameter            | gpu_exact  | gpu_hist  |
-+======================+============+===========+
-| subsample            | |cross|    | |tick|    |
-+----------------------+------------+-----------+
-| colsample_bytree     | |cross|    | |tick|    |
-+----------------------+------------+-----------+
-| colsample_bylevel    | |cross|    | |tick|    |
-+----------------------+------------+-----------+
-| max_bin              | |cross|    | |tick|    |
-+----------------------+------------+-----------+
-| gpu_id               | |tick|     | |tick|    |
-+----------------------+------------+-----------+
-| n_gpus               | |cross|    | |tick|    |
-+----------------------+------------+-----------+
-| predictor            | |tick|     | |tick|    |
-+----------------------+------------+-----------+
-| grow_policy          | |cross|    | |tick|    |
-+----------------------+------------+-----------+
-| monotone_constraints |  |cross|   | |tick|    |
-+----------------------+------------+-----------+
-```
-
-GPU accelerated prediction is enabled by default for the above mentioned 'tree_method' parameters but can be switched to CPU prediction by setting 'predictor':'cpu_predictor'. This could be useful if you want to conserve GPU memory. Likewise when using CPU algorithms, GPU accelerated prediction can be enabled by setting 'predictor':'gpu_predictor'.
-
-The device ordinal can be selected using the 'gpu_id' parameter, which defaults to 0.
-
-Multiple GPUs can be used with the grow_gpu_hist parameter using the n_gpus parameter. which defaults to 1. If this is set to -1 all available GPUs will be used.  If gpu_id is specified as non-zero, the gpu device order is mod(gpu_id + i) % n_visible_devices for i=0 to n_gpus-1.  As with GPU vs. CPU, multi-GPU will not always be faster than a single GPU due to PCI bus bandwidth that can limit performance.
-
-This plugin currently works with the CLI, python and R - see installation guide for details.
-
-Python example:
-```python
-param['gpu_id'] = 0
-param['max_bin'] = 16
-param['tree_method'] = 'gpu_hist'
-```
-## Benchmarks
-To run benchmarks on synthetic data for binary classification:
-```bash
-$ python tests/benchmark/benchmark.py
-```
-
-Training time time on 1,000,000 rows x 50 columns with 500 boosting iterations and 0.25/0.75 test/train split on i7-6700K CPU @ 4.00GHz and Pascal Titan X.
-
-```eval_rst
-+--------------+----------+
-| tree_method  | Time (s) |
-+==============+==========+
-| gpu_hist     | 13.87    |
-+--------------+----------+
-| hist         | 63.55    |
-+--------------+----------+
-| gpu_exact    | 161.08   |
-+--------------+----------+
-| exact        | 1082.20  |
-+--------------+----------+
-
-```
-
-[See here](http://dmlc.ml/2016/12/14/GPU-accelerated-xgboost.html) for additional performance benchmarks of the 'gpu_exact' tree_method.
-
-## References
-[Mitchell R, Frank E. (2017) Accelerating the XGBoost algorithm using GPU computing. PeerJ Computer Science 3:e127 https://doi.org/10.7717/peerj-cs.127](https://peerj.com/articles/cs-127/)
-
-[Nvidia Parallel Forall: Gradient Boosting, Decision Trees and XGBoost with CUDA](https://devblogs.nvidia.com/parallelforall/gradient-boosting-decision-trees-xgboost-cuda/)
-
-## Author
-Rory Mitchell
-Jonathan C. McKinney
-Shankara Rao Thejaswi Nanditale
-Vinay Deshpande
-... and the rest of the H2O.ai and NVIDIA team.
-
-Please report bugs to the xgboost/issues page.
-

doc/gpu/index.rst

@@ -0,0 +1,121 @@
+###################
+XGBoost GPU Support
+###################
+
+This page contains information about GPU algorithms supported in XGBoost.
+To install GPU support, checkout the :doc:`/build`.
+
+.. note:: CUDA 8.0, Compute Capability 3.5 required
+
+  The GPU algorithms in XGBoost require a graphics card with compute capability 3.5 or higher, with
+  CUDA toolkits 8.0 or later.
+  (See `this list <https://en.wikipedia.org/wiki/CUDA#GPUs_supported>`_ to look up compute capability of your GPU card.)
+
+*********************************************
+CUDA Accelerated Tree Construction Algorithms
+*********************************************
+Tree construction (training) and prediction can be accelerated with CUDA-capable GPUs.
+
+Usage
+=====
+Specify the ``tree_method`` parameter as one of the following algorithms. 
+
+Algorithms
+----------
+
++--------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------+
+| tree_method  | Description                                                                                                                                                           |
++==============+=======================================================================================================================================================================+
+| gpu_exact    | The standard XGBoost tree construction algorithm. Performs exact search for splits. Slower and uses considerably more memory than ``gpu_hist``.                       |
++--------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------+
+| gpu_hist     | Equivalent to the XGBoost fast histogram algorithm. Much faster and uses considerably less memory. NOTE: Will run very slowly on GPUs older than Pascal architecture. |
++--------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------+
+
+Supported parameters 
+--------------------
+
+.. |tick| unicode:: U+2714 
+.. |cross| unicode:: U+2718 
+
++--------------------------+---------------+--------------+
+| parameter                | ``gpu_exact`` | ``gpu_hist`` |
++==========================+===============+==============+
+| ``subsample``            | |cross|       | |tick|       |
++--------------------------+---------------+--------------+
+| ``colsample_bytree``     | |cross|       | |tick|       |
++--------------------------+---------------+--------------+
+| ``colsample_bylevel``    | |cross|       | |tick|       |
++--------------------------+---------------+--------------+
+| ``max_bin``              | |cross|       | |tick|       |
++--------------------------+---------------+--------------+
+| ``gpu_id``               | |tick|        | |tick|       |
++--------------------------+---------------+--------------+
+| ``n_gpus``               | |cross|       | |tick|       |
++--------------------------+---------------+--------------+
+| ``predictor``            | |tick|        | |tick|       |
++--------------------------+---------------+--------------+
+| ``grow_policy``          | |cross|       | |tick|       |
++--------------------------+---------------+--------------+
+| ``monotone_constraints`` | |cross|       | |tick|       |
++--------------------------+---------------+--------------+
+
+GPU accelerated prediction is enabled by default for the above mentioned ``tree_method`` parameters but can be switched to CPU prediction by setting ``predictor`` to ``cpu_predictor``. This could be useful if you want to conserve GPU memory. Likewise when using CPU algorithms, GPU accelerated prediction can be enabled by setting ``predictor`` to ``gpu_predictor``.
+
+The device ordinal can be selected using the ``gpu_id`` parameter, which defaults to 0.
+
+Multiple GPUs can be used with the ``gpu_hist`` tree method using the ``n_gpus`` parameter. which defaults to 1. If this is set to -1 all available GPUs will be used.  If ``gpu_id`` is specified as non-zero, the gpu device order is ``mod(gpu_id + i) % n_visible_devices`` for ``i=0`` to ``n_gpus-1``.  As with GPU vs. CPU, multi-GPU will not always be faster than a single GPU due to PCI bus bandwidth that can limit performance.
+
+.. note:: Enabling multi-GPU training
+
+  Default installation may not enable multi-GPU training. To use multiple GPUs, make sure to read :ref:`build_gpu_support`.
+
+The GPU algorithms currently work with CLI, Python and R packages. See :doc:`/build` for details.
+
+.. code-block:: python
+  :caption: Python example
+
+  param['gpu_id'] = 0
+  param['max_bin'] = 16
+  param['tree_method'] = 'gpu_hist'
+
+Benchmarks
+==========
+You can run benchmarks on synthetic data for binary classification:
+
+.. code-block:: bash
+
+  python tests/benchmark/benchmark.py
+
+Training time time on 1,000,000 rows x 50 columns with 500 boosting iterations and 0.25/0.75 test/train split on i7-6700K CPU @ 4.00GHz and Pascal Titan X yields the following results:
+
++--------------+----------+
+| tree_method  | Time (s) |
++==============+==========+
+| gpu_hist     | 13.87    |
++--------------+----------+
+| hist         | 63.55    |
++--------------+----------+
+| gpu_exact    | 161.08   |
++--------------+----------+
+| exact        | 1082.20  |
++--------------+----------+
+
+See `GPU Accelerated XGBoost <https://xgboost.ai/2016/12/14/GPU-accelerated-xgboost.html>`_ and `Updates to the XGBoost GPU algorithms <https://xgboost.ai/2018/07/04/gpu-xgboost-update.html>`_ for additional performance benchmarks of the ``gpu_exact`` and ``gpu_hist`` tree methods.
+
+**********
+References
+**********
+`Mitchell R, Frank E. (2017) Accelerating the XGBoost algorithm using GPU computing. PeerJ Computer Science 3:e127 https://doi.org/10.7717/peerj-cs.127 <https://peerj.com/articles/cs-127/>`_
+
+`Nvidia Parallel Forall: Gradient Boosting, Decision Trees and XGBoost with CUDA <https://devblogs.nvidia.com/parallelforall/gradient-boosting-decision-trees-xgboost-cuda/>`_
+
+Authors
+=======
+* Rory Mitchell
+* Jonathan C. McKinney
+* Shankara Rao Thejaswi Nanditale
+* Vinay Deshpande
+* ... and the rest of the H2O.ai and NVIDIA team.
+
+Please report bugs to the user forum https://discuss.xgboost.ai/.
+

doc/how_to/contribute.md

@@ -1,164 +0,0 @@
-Contribute to XGBoost
-=====================
-XGBoost has been developed and used by a group of active community members.
-Everyone is more than welcome to contribute. It is a way to make the project better and more accessible to more users.
-
-- Please add your name to [CONTRIBUTORS.md](../../CONTRIBUTORS.md) after your patch has been merged.
-- Please also update [NEWS.md](../../NEWS.md) to add note on your changes to the API or added a new document.
-
-Guidelines
-----------
-* [Submit Pull Request](#submit-pull-request)
-* [Git Workflow Howtos](#git-workflow-howtos)
-  - [How to resolve conflict with master](#how-to-resolve-conflict-with-master)
-  - [How to combine multiple commits into one](#how-to-combine-multiple-commits-into-one)
-  - [What is the consequence of force push](#what-is-the-consequence-of-force-push)
-* [Document](#document)
-* [Testcases](#testcases)
-* [Examples](#examples)
-* [Core Library](#core-library)
-* [Python Package](#python-package)
-* [R Package](#r-package)
-
-Submit Pull Request
--------------------
-* Before submit, please rebase your code on the most recent version of master, you can do it by
-```bash
-git remote add upstream https://github.com/dmlc/xgboost
-git fetch upstream
-git rebase upstream/master
-```
-* If you have multiple small commits,
-  it might be good to merge them together(use git rebase then squash) into more meaningful groups.
-* Send the pull request!
-  - Fix the problems reported by automatic checks
-  - If you are contributing a new module, consider add a testcase in [tests](../tests)
-
-Git Workflow Howtos
--------------------
-### How to resolve conflict with master
-- First rebase to most recent master
-```bash
-# The first two steps can be skipped after you do it once.
-git remote add upstream https://github.com/dmlc/xgboost
-git fetch upstream
-git rebase upstream/master
-```
-- The git may show some conflicts it cannot merge, say ```conflicted.py```.
-  - Manually modify the file to resolve the conflict.
-  - After you resolved the conflict, mark it as resolved by
-```bash
-git add conflicted.py
-```
-- Then you can continue rebase by
-```bash
-git rebase --continue
-```
-- Finally push to your fork, you may need to force push here.
-```bash
-git push --force
-```
-
-### How to combine multiple commits into one
-Sometimes we want to combine multiple commits, especially when later commits are only fixes to previous ones,
-to create a PR with set of meaningful commits. You can do it by following steps.
-- Before doing so, configure the default editor of git if you haven't done so before.
-```bash
-git config core.editor the-editor-you-like
-```
-- Assume we want to merge last 3 commits, type the following commands
-```bash
-git rebase -i HEAD~3
-```
-- It will pop up an text editor. Set the first commit as ```pick```, and change later ones to ```squash```.
-- After you saved the file, it will pop up another text editor to ask you modify the combined commit message.
-- Push the changes to your fork, you need to force push.
-```bash
-git push --force
-```
-
-### What is the consequence of force push
-The previous two tips requires force push, this is because we altered the path of the commits.
-It is fine to force push to your own fork, as long as the commits changed are only yours.
-
-Documents
----------
-* The document is created using sphinx and [recommonmark](http://recommonmark.readthedocs.org/en/latest/)
-* You can build document locally to see the effect.
-
-Testcases
----------
-* All the testcases are in [tests](../tests)
-* We use python nose for python test cases.
-
-Examples
---------
-* Usecases and examples will be in [demo](../demo)
-* We are super excited to hear about your story, if you have blogposts,
-  tutorials code solutions using xgboost, please tell us and we will add
-  a link in the example pages.
-
-Core Library
-------------
-- Follow Google C style for C++.
-- We use doxygen to document all the interface code.
-- You can reproduce the linter checks by typing ```make lint```
-
-Python Package
---------------
-- Always add docstring to the new functions in numpydoc format.
-- You can reproduce the linter checks by typing ```make lint```
-
-R Package
----------
-### Code Style
-- We follow Google's C++ Style guide on C++ code.
-  - This is mainly to be consistent with the rest of the project.
-  - Another reason is we will be able to check style automatically with a linter.
-- You can check the style of the code by typing the following command at root folder.
-```bash
-make rcpplint
-```
-- When needed, you can disable the linter warning of certain line with ```// NOLINT(*)``` comments.
-- We use [roxygen](https://cran.r-project.org/web/packages/roxygen2/vignettes/roxygen2.html) for documenting the R package.
-
-### Rmarkdown Vignettes
-Rmarkdown vignettes are placed in [R-package/vignettes](../R-package/vignettes)
-These Rmarkdown files are not compiled. We host the compiled version on [doc/R-package](R-package)
-
-The following steps are followed to add a new Rmarkdown vignettes:
-- Add the original rmarkdown to ```R-package/vignettes```
-- Modify ```doc/R-package/Makefile``` to add the markdown files to be build
-- Clone the [dmlc/web-data](https://github.com/dmlc/web-data) repo to folder ```doc```
-- Now type the following command on ```doc/R-package```
-```bash
-make the-markdown-to-make.md
-```
-- This will generate the markdown, as well as the figures into ```doc/web-data/xgboost/knitr```
-- Modify the ```doc/R-package/index.md``` to point to the generated markdown.
-- Add the generated figure to the ```dmlc/web-data``` repo.
-  - If you already cloned the repo to doc, this means a ```git add```
-- Create PR for both the markdown  and ```dmlc/web-data```
-- You can also build the document locally by typing the following command at ```doc```
-```bash
-make html
-```
-The reason we do this is to avoid exploded repo size due to generated images sizes.
-
-### R package versioning
-Since version 0.6.4.3, we have adopted a versioning system that uses an ```x.y.z``` (or ```core_major.core_minor.cran_release```)
-format for CRAN releases and an ```x.y.z.p``` (or ```core_major.core_minor.cran_release.patch```) format for development patch versions.
-This approach is similar to the one described in Yihui Xie's
-[blog post on R Package Versioning](https://yihui.name/en/2013/06/r-package-versioning/),
-except we need an additional field to accomodate the ```x.y``` core library version.
-
-Each new CRAN release bumps up the 3rd field, while developments in-between CRAN releases
-would be marked by an additional 4th field on the top of an existing CRAN release version.
-Some additional consideration is needed when the core library version changes.
-E.g., after the core changes from 0.6 to 0.7, the R package development version would become 0.7.0.1, working towards
-a 0.7.1 CRAN release. The 0.7.0 would not be released to CRAN, unless it would require almost no additional development.
-
-### Registering native routines in R
-According to [R extension manual](https://cran.r-project.org/doc/manuals/r-release/R-exts.html#Registering-native-routines),
-it is good practice to register native routines and to disable symbol search. When any changes or additions are made to the
-C++ interface of the R package, please make corresponding changes in ```src/init.c``` as well.

doc/how_to/external_memory.md

@@ -1,42 +0,0 @@
-Using XGBoost External Memory Version(beta)
-===========================================
-There is no big difference between using external memory version and in-memory version.
-The only difference is the filename format.
-
-The external memory version takes in the following filename format
-```
-filename#cacheprefix
-```
-
-The ```filename``` is the normal path to libsvm file you want to load in, ```cacheprefix``` is a
-path to a cache file that xgboost will use for external memory cache.
-
-The following code was extracted from [../../demo/guide-python/external_memory.py](../../demo/guide-python/external_memory.py)
-```python
-dtrain = xgb.DMatrix('../data/agaricus.txt.train#dtrain.cache')
-```
-You can find that there is additional ```#dtrain.cache``` following the libsvm file, this is the name of cache file.
-For CLI version, simply use ```"../data/agaricus.txt.train#dtrain.cache"``` in filename.
-
-Performance Note
-----------------
-* the parameter ```nthread``` should be set to number of ***real*** cores
-  - Most modern CPU offer hyperthreading, which means you can have a 4 core cpu with 8 threads
-  - Set nthread to be 4 for maximum performance in such case
-
-Distributed Version
--------------------
-The external memory mode naturally works on distributed version, you can simply set path like
-```
-data = "hdfs://path-to-data/#dtrain.cache"
-```
-xgboost will cache the data to the local position. When you run on YARN, the current folder is temporal
-so that you can directly use ```dtrain.cache``` to cache to current folder.
-
-
-Usage Note
-----------
-* This is a experimental version
-  - If you like to try and test it, report results to https://github.com/dmlc/xgboost/issues/244
-* Currently only importing from libsvm format is supported
-  - Contribution of ingestion from other common external memory data source is welcomed

doc/how_to/index.md

@@ -1,17 +0,0 @@
-# XGBoost How To
-
-This page contains guidelines to use and develop XGBoost.
-
-## Installation
-- [How to Install XGBoost](../build.md)
-
-## Use XGBoost in Specific Ways
-- [Parameter tuning guide](param_tuning.md)
-- [Use out of core computation for large dataset](external_memory.md)
-- [Use XGBoost GPU algorithms](../gpu/index.md)
-
-## Develop and Hack XGBoost
-- [Contribute to XGBoost](contribute.md)
-
-## Frequently Ask Questions
-- [FAQ](../faq.md)

doc/index.md

@@ -1,16 +0,0 @@
-XGBoost Documentation
-=====================
-This document is hosted at http://xgboost.readthedocs.org/. You can also browse most of the documents in github directly.
-
-
-These are used to generate the index used in search.
-
-* [Python Package Document](python/index.md)
-* [R Package Document](R-package/index.md)
-* [Java/Scala Package Document](jvm/index.md)
-* [Julia Package Document](julia/index.md)
-* [CLI Package Document](cli/index.md)
-* [GPU Support Document](gpu/index.md)
-- [Howto Documents](how_to/index.md)
-- [Get Started Documents](get_started/index.md)
-- [Tutorials](tutorials/index.md)

doc/index.rst

@@ -0,0 +1,30 @@
+#####################
+XGBoost Documentation
+#####################
+
+**XGBoost** is an optimized distributed gradient boosting library designed to be highly **efficient**, **flexible** and **portable**.
+It implements machine learning algorithms under the `Gradient Boosting <https://en.wikipedia.org/wiki/Gradient_boosting>`_ framework.
+XGBoost provides a parallel tree boosting (also known as GBDT, GBM) that solve many data science problems in a fast and accurate way.
+The same code runs on major distributed environment (Hadoop, SGE, MPI) and can solve problems beyond billions of examples.
+
+********
+Contents
+********
+
+.. toctree::
+  :maxdepth: 2
+  :titlesonly:
+
+  build
+  get_started
+  tutorials/index
+  faq
+  XGBoost User Forum <https://discuss.xgboost.ai>
+  GPU support <gpu/index>
+  parameter
+  Python package <python/index>
+  R package <R-package/index>
+  JVM package <jvm/index>
+  Julia package <julia>
+  CLI interface <cli>
+  contribute

doc/input_format.md

@@ -1,56 +0,0 @@
-Text Input Format of DMatrix
-============================
-
-## Basic Input Format
-As we have mentioned, XGBoost takes LibSVM format. For training or predicting, XGBoost takes an instance file with the format as below:
-
-train.txt
-```
-1 101:1.2 102:0.03
-0 1:2.1 10001:300 10002:400
-0 0:1.3 1:0.3
-1 0:0.01 1:0.3
-0 0:0.2 1:0.3
-```
-Each line represent a single instance, and in the first line '1' is the instance label,'101' and '102' are feature indices, '1.2' and '0.03' are feature values. In the binary classification case, '1' is used to indicate positive samples, and '0' is used to indicate negative samples. We also support probability values in [0,1] as label, to indicate the probability of the instance being positive.
-
-Additional Information
-----------------------
-Note: these additional information are only applicable to single machine version of the package.
-
-### Group Input Format
-As XGBoost supports accomplishing [ranking task](../demo/rank), we support the group input format. In ranking task, instances are categorized into different groups in real world scenarios, for example, in the learning to rank web pages scenario, the web page instances are grouped by their queries. Except the instance file mentioned in the group input format, XGBoost need an file indicating the group information. For example, if the instance file is the "train.txt" shown above,
-and the group file is as below:
-
-train.txt.group
-```
-2
-3
-```
-This means that, the data set contains 5 instances, and the first two instances are in a group and the other three are in another group. The numbers in the group file are actually indicating the number of instances in each group in the instance file in order.
-While configuration, you do not have to indicate the path of the group file. If the instance file name is "xxx", XGBoost will check whether there is a file named "xxx.group" in the same directory and decides whether to read the data as group input format.
-
-### Instance Weight File
-XGBoost supports providing each instance an weight to differentiate the importance of instances. For example, if we provide an instance weight file for the "train.txt" file in the example as below:
-
-train.txt.weight
-```
-1
-0.5
-0.5
-1
-0.5
-```
-It means that XGBoost will emphasize more on the first and fourth instance， that is to say positive instances while training.
-The configuration is similar to configuring the group information. If the instance file name is "xxx", XGBoost will check whether there is a file named "xxx.weight" in the same directory and if there is, will use the weights while training models. Weights will be included into an "xxx.buffer" file that is created by XGBoost automatically. If you want to update the weights, you need to delete the "xxx.buffer" file prior to launching XGBoost.
-
-### Initial Margin file
-XGBoost supports providing each instance an initial margin prediction. For example, if we have a initial prediction using logistic regression for "train.txt" file, we can create the following file:
-
-train.txt.base_margin
-```
--0.4
-1.0
-3.4
-```
-XGBoost will take these values as initial margin prediction and boost from that. An important note about base_margin is that it should be margin prediction before transformation, so if you are doing logistic loss, you will need to put in value before logistic transformation. If you are using XGBoost predictor, use pred_margin=1 to output margin values.

doc/julia.rst

@@ -0,0 +1,5 @@
+##########
+XGBoost.jl
+##########
+
+See `XGBoost.jl Project page <https://github.com/dmlc/XGBoost.jl>`_.

doc/julia/index.md

@@ -1,3 +0,0 @@
-# XGBoost.jl
-
-See [XGBoost.jl Project page](https://github.com/dmlc/XGBoost.jl)

doc/jvm/index.md

@@ -1,49 +0,0 @@
-XGBoost JVM Package
-===================
-[![Build Status](https://travis-ci.org/dmlc/xgboost.svg?branch=master)](https://travis-ci.org/dmlc/xgboost)
-[![GitHub license](http://dmlc.github.io/img/apache2.svg)](../LICENSE)
-
-You have found the XGBoost JVM Package!
-
-Installation
-------------
-Currently, XGBoost4J only support installation from source. Building XGBoost4J using Maven requires Maven 3 or newer, Java 7+ and CMake 3.2+ for compiling the JNI bindings.
-
-Before you install XGBoost4J, you need to define environment variable `JAVA_HOME` as your JDK directory to ensure that your compiler can find `jni.h` correctly, since XGBoost4J relies on JNI to implement the interaction between the JVM and native libraries.
-
-After your `JAVA_HOME` is defined correctly, it is as simple as run `mvn package` under jvm-packages directory to install XGBoost4J. You can also skip the tests by running `mvn -DskipTests=true package`, if you are sure about the correctness of your local setup.
-
-To publish the artifacts to your local maven repository, run
-
-    mvn install
-
-Or, if you would like to skip tests, run
-
-    mvn -DskipTests install
-
-This command will publish the xgboost binaries, the compiled java classes as well as the java sources to your local repository. Then you can use XGBoost4J in your Java projects by including the following dependency in `pom.xml`:
-
-    <dependency>
-      <groupId>ml.dmlc</groupId>
-      <artifactId>xgboost4j</artifactId>
-      <version>0.7</version>
-    </dependency>
-
-
-
-
-After integrating with Dataframe/Dataset APIs of Spark 2.0, XGBoost4J-Spark only supports compile with Spark 2.x. You can build XGBoost4J-Spark as a component of XGBoost4J by running `mvn package`, and you can specify the version of spark with `mvn -Dspark.version=2.0.0 package`.   (To continue working with Spark 1.x, the users are supposed to update pom.xml by modifying the properties like `spark.version`, `scala.version`, and `scala.binary.version`. Users also need to change the implementation by replacing SparkSession with SQLContext and the type of API parameters from Dataset[_] to Dataframe)
-
-Contents
---------
-* [Java Overview Tutorial](java_intro.md)
-
-Resources
----------
-* [Code Examples](https://github.com/dmlc/xgboost/tree/master/jvm-packages/xgboost4j-example)
-* [Java API Docs](http://dmlc.ml/docs/javadocs/index.html)
-
-## Scala API Docs
-  * [XGBoost4J](http://dmlc.ml/docs/scaladocs/xgboost4j/index.html)
-  * [XGBoost4J-Spark](http://dmlc.ml/docs/scaladocs/xgboost4j-spark/index.html)
-  * [XGBoost4J-Flink](http://dmlc.ml/docs/scaladocs/xgboost4j-flink/index.html)

doc/jvm/index.rst

@@ -0,0 +1,155 @@
+###################
+XGBoost JVM Package
+###################
+
+.. raw:: html
+
+  <a href="https://travis-ci.org/dmlc/xgboost">
+  <img alt="Build Status" src="https://travis-ci.org/dmlc/xgboost.svg?branch=master">
+  </a>
+  <a href="https://github.com/dmlc/xgboost/blob/master/LICENSE">
+  <img alt="GitHub license" src="http://dmlc.github.io/img/apache2.svg">
+  </a>
+
+You have found the XGBoost JVM Package!
+
+************
+Installation
+************
+
+Installation from source
+========================
+
+Building XGBoost4J using Maven requires Maven 3 or newer, Java 7+ and CMake 3.2+ for compiling the JNI bindings.
+
+Before you install XGBoost4J, you need to define environment variable ``JAVA_HOME`` as your JDK directory to ensure that your compiler can find ``jni.h`` correctly, since XGBoost4J relies on JNI to implement the interaction between the JVM and native libraries.
+
+After your ``JAVA_HOME`` is defined correctly, it is as simple as run ``mvn package`` under jvm-packages directory to install XGBoost4J. You can also skip the tests by running ``mvn -DskipTests=true package``, if you are sure about the correctness of your local setup.
+
+To publish the artifacts to your local maven repository, run
+
+.. code-block:: bash
+
+  mvn install
+
+Or, if you would like to skip tests, run
+
+.. code-block:: bash
+
+  mvn -DskipTests install
+
+This command will publish the xgboost binaries, the compiled java classes as well as the java sources to your local repository. Then you can use XGBoost4J in your Java projects by including the following dependency in ``pom.xml``:
+
+.. code-block:: xml
+
+  <dependency>
+    <groupId>ml.dmlc</groupId>
+    <artifactId>xgboost4j</artifactId>
+    <version>latest_source_version_num</version>
+  </dependency>
+
+For sbt, please add the repository and dependency in build.sbt as following:
+
+.. code-block:: scala
+
+  resolvers += "Local Maven Repository" at "file://"+Path.userHome.absolutePath+"/.m2/repository"
+
+  "ml.dmlc" % "xgboost4j" % "latest_source_version_num"
+
+If you want to use XGBoost4J-Spark, replace ``xgboost4j`` with ``xgboost4j-spark``.
+
+.. note:: XGBoost4J-Spark requires Spark 2.3+
+
+  XGBoost4J-Spark now requires Spark 2.3+. Latest versions of XGBoost4J-Spark uses facilities of `org.apache.spark.ml.param.shared` extensively to provide for a tight integration with Spark MLLIB framework, and these facilities are not fully available on earlier versions of Spark.
+
+Installation from maven repo
+============================
+
+Access release version
+----------------------
+
+.. code-block:: xml
+  :caption: maven
+
+  <dependency>
+      <groupId>ml.dmlc</groupId>
+      <artifactId>xgboost4j</artifactId>
+      <version>latest_version_num</version>
+  </dependency>
+
+.. code-block:: scala
+  :caption: sbt
+
+  "ml.dmlc" % "xgboost4j" % "latest_version_num"
+
+This will checkout the latest stable version from the Maven Central.
+
+For the latest release version number, please check `here <https://github.com/dmlc/xgboost/releases>`_.
+
+if you want to use XGBoost4J-Spark, replace ``xgboost4j`` with ``xgboost4j-spark``.
+
+Access SNAPSHOT version
+-----------------------
+
+You need to add GitHub as repo:
+
+.. code-block:: xml
+  :caption: maven
+
+  <repository>
+    <id>GitHub Repo</id>
+    <name>GitHub Repo</name>
+    <url>https://raw.githubusercontent.com/CodingCat/xgboost/maven-repo/</url>
+  </repository>
+
+.. code-block:: scala
+  :caption: sbt
+
+  resolvers += "GitHub Repo" at "https://raw.githubusercontent.com/CodingCat/xgboost/maven-repo/"
+
+Then add dependency as following:
+
+.. code-block:: xml
+  :caption: maven
+
+  <dependency>
+      <groupId>ml.dmlc</groupId>
+      <artifactId>xgboost4j</artifactId>
+      <version>latest_version_num</version>
+  </dependency>
+
+.. code-block:: scala
+  :caption: sbt
+
+  "ml.dmlc" % "xgboost4j" % "latest_version_num"
+
+For the latest release version number, please check `here <https://github.com/CodingCat/xgboost/tree/maven-repo/ml/dmlc/xgboost4j>`_.
+
+.. note:: Windows not supported by published JARs
+
+  The published JARs from the Maven Central and GitHub currently only supports Linux and MacOS. Windows users should consider building XGBoost4J / XGBoost4J-Spark from the source. Alternatively, checkout pre-built JARs from `criteo-forks/xgboost-jars <https://github.com/criteo-forks/xgboost-jars>`_.
+
+Enabling OpenMP for Mac OS
+--------------------------
+If you are on Mac OS and using a compiler that supports OpenMP, you need to go to the file ``xgboost/jvm-packages/create_jni.py`` and comment out the line
+
+.. code-block:: python
+
+  CONFIG["USE_OPENMP"] = "OFF"
+
+in order to get the benefit of multi-threading.
+
+********
+Contents
+********
+
+.. toctree::
+  :maxdepth: 2
+
+  java_intro
+  XGBoost4J-Spark Tutorial <xgboost4j_spark_tutorial>
+  Code Examples <https://github.com/dmlc/xgboost/tree/master/jvm-packages/xgboost4j-example>
+  XGBoost4J Java API <javadocs/index>
+  XGBoost4J Scala API <scaladocs/xgboost4j/index>
+  XGBoost4J-Spark Scala API <scaladocs/xgboost4j-spark/index>
+  XGBoost4J-Flink Scala API <scaladocs/xgboost4j-flink/index>

doc/jvm/java_intro.md

@@ -1,143 +0,0 @@
-XGBoost4J Java API
-==================
-This tutorial introduces
-
-## Data Interface
-Like the xgboost python module, xgboost4j uses ```DMatrix``` to handle data,
-libsvm txt format file, sparse matrix in CSR/CSC format, and dense matrix is
-supported.
-
-* To import ```DMatrix``` :
-```java
-import org.dmlc.xgboost4j.DMatrix;
-```
-
-* To load libsvm text format file, the usage is like :
-```java
-DMatrix dmat = new DMatrix("train.svm.txt");
-```
-
-* To load sparse matrix in CSR/CSC format is a little complicated, the usage is like :
-suppose a sparse matrix :
-1 0 2 0
-4 0 0 3
-3 1 2 0
-
-  for CSR format
-```java
-long[] rowHeaders = new long[] {0,2,4,7};
-float[] data = new float[] {1f,2f,4f,3f,3f,1f,2f};
-int[] colIndex = new int[] {0,2,0,3,0,1,2};
-DMatrix dmat = new DMatrix(rowHeaders, colIndex, data, DMatrix.SparseType.CSR);
-```
-
-  for CSC format
-```java
-long[] colHeaders = new long[] {0,3,4,6,7};
-float[] data = new float[] {1f,4f,3f,1f,2f,2f,3f};
-int[] rowIndex = new int[] {0,1,2,2,0,2,1};
-DMatrix dmat = new DMatrix(colHeaders, rowIndex, data, DMatrix.SparseType.CSC);
-```
-
-* To load 3*2 dense matrix, the usage is like :
-suppose a matrix :
-1    2
-3    4
-5    6
-
-```java
-float[] data = new float[] {1f,2f,3f,4f,5f,6f};
-int nrow = 3;
-int ncol = 2;
-float missing = 0.0f;
-DMatrix dmat = new Matrix(data, nrow, ncol, missing);
-```
-
-* To set weight :
-```java
-float[] weights = new float[] {1f,2f,1f};
-dmat.setWeight(weights);
-```
-
-## Setting Parameters
-* in xgboost4j any ```Iterable<Entry<String, Object>>``` object could be used as parameters.
-
-* to set parameters, for non-multiple value params, you can simply use entrySet of an Map:
-```java
-Map<String, Object> paramMap = new HashMap<>() {
-  {
-    put("eta", 1.0);
-    put("max_depth", 2);
-    put("silent", 1);
-    put("objective", "binary:logistic");
-    put("eval_metric", "logloss");
-  }
-};
-Iterable<Entry<String, Object>> params = paramMap.entrySet();
-```
-* for the situation that multiple values with same param key, List<Entry<String, Object>> would be a good choice, e.g. :
-```java
-List<Entry<String, Object>> params = new ArrayList<Entry<String, Object>>() {
-    {
-        add(new SimpleEntry<String, Object>("eta", 1.0));
-        add(new SimpleEntry<String, Object>("max_depth", 2.0));
-        add(new SimpleEntry<String, Object>("silent", 1));
-        add(new SimpleEntry<String, Object>("objective", "binary:logistic"));
-    }
-};
-```
-
-## Training Model
-With parameters and data, you are able to train a booster model.
-* Import ```Trainer``` and ```Booster``` :
-```java
-import org.dmlc.xgboost4j.Booster;
-import org.dmlc.xgboost4j.util.Trainer;
-```
-
-* Training
-```java
-DMatrix trainMat = new DMatrix("train.svm.txt");
-DMatrix validMat = new DMatrix("valid.svm.txt");
-//specify a watchList to see the performance
-//any Iterable<Entry<String, DMatrix>> object could be used as watchList
-List<Entry<String, DMatrix>> watchs =  new ArrayList<>();
-watchs.add(new SimpleEntry<>("train", trainMat));
-watchs.add(new SimpleEntry<>("test", testMat));
-int round = 2;
-Booster booster = Trainer.train(params, trainMat, round, watchs, null, null);
-```
-
-* Saving model
-After training, you can save model and dump it out.
-```java
-booster.saveModel("model.bin");
-```
-
-* Dump Model and Feature Map
-```java
-booster.dumpModel("modelInfo.txt", false)
-//dump with featureMap
-booster.dumpModel("modelInfo.txt", "featureMap.txt", false)
-```
-
-* Load a model
-```java
-Params param = new Params() {
-  {
-    put("silent", 1);
-    put("nthread", 6);
-  }
-};
-Booster booster = new Booster(param, "model.bin");
-```
-
-## Prediction
-after training and loading a model, you use it to predict other data, the predict results will be a two-dimension float array (nsample, nclass), for predict leaf, it would be (nsample, nclass*ntrees)
-```java
-DMatrix dtest = new DMatrix("test.svm.txt");
-//predict
-float[][] predicts = booster.predict(dtest);
-//predict leaf
-float[][] leafPredicts = booster.predict(dtest, 0, true);
-```

doc/jvm/java_intro.rst

@@ -0,0 +1,160 @@
+##############################
+Getting Started with XGBoost4J
+##############################
+This tutorial introduces Java API for XGBoost.
+
+**************
+Data Interface
+**************
+Like the XGBoost python module, XGBoost4J uses DMatrix to handle data.
+LIBSVM txt format file, sparse matrix in CSR/CSC format, and dense matrix are
+supported.
+
+* The first step is to import DMatrix:
+
+  .. code-block:: java
+
+    import ml.dmlc.xgboost4j.java.DMatrix;
+
+* Use DMatrix constructor to load data from a libsvm text format file:
+
+  .. code-block:: java
+
+    DMatrix dmat = new DMatrix("train.svm.txt");
+
+* Pass arrays to DMatrix constructor to load from sparse matrix.
+
+  Suppose we have a sparse matrix
+  
+  .. code-block:: none
+  
+    1 0 2 0
+    4 0 0 3
+    3 1 2 0
+  
+  We can express the sparse matrix in `Compressed Sparse Row (CSR) <https://en.wikipedia.org/wiki/Sparse_matrix#Compressed_sparse_row_(CSR,_CRS_or_Yale_format)>`_ format:
+  
+  .. code-block:: java
+  
+    long[] rowHeaders = new long[] {0,2,4,7};
+    float[] data = new float[] {1f,2f,4f,3f,3f,1f,2f};
+    int[] colIndex = new int[] {0,2,0,3,0,1,2};
+    int numColumn = 4;
+    DMatrix dmat = new DMatrix(rowHeaders, colIndex, data, DMatrix.SparseType.CSR, numColumn);
+  
+  ... or in `Compressed Sparse Column (CSC) <https://en.wikipedia.org/wiki/Sparse_matrix#Compressed_sparse_column_(CSC_or_CCS)>`_ format:
+  
+  .. code-block:: java
+  
+    long[] colHeaders = new long[] {0,3,4,6,7};
+    float[] data = new float[] {1f,4f,3f,1f,2f,2f,3f};
+    int[] rowIndex = new int[] {0,1,2,2,0,2,1};
+    int numRow = 3;
+    DMatrix dmat = new DMatrix(colHeaders, rowIndex, data, DMatrix.SparseType.CSC, numRow);
+
+* You may also load your data from a dense matrix. Let's assume we have a matrix of form
+
+  .. code-block:: none
+
+    1    2
+    3    4
+    5    6
+
+  Using `row-major layout <https://en.wikipedia.org/wiki/Row-_and_column-major_order>`_, we specify the dense matrix as follows:
+
+  .. code-block:: java
+
+    float[] data = new float[] {1f,2f,3f,4f,5f,6f};
+    int nrow = 3;
+    int ncol = 2;
+    float missing = 0.0f;
+    DMatrix dmat = new DMatrix(data, nrow, ncol, missing);
+
+* To set weight:
+
+  .. code-block:: java
+
+    float[] weights = new float[] {1f,2f,1f};
+    dmat.setWeight(weights);
+
+******************
+Setting Parameters
+******************
+To set parameters, parameters are specified as a Map:
+
+.. code-block:: java
+
+  Map<String, Object> params = new HashMap<String, Object>() {
+    {
+      put("eta", 1.0);
+      put("max_depth", 2);
+      put("silent", 1);
+      put("objective", "binary:logistic");
+      put("eval_metric", "logloss");
+    }
+  };
+
+**************
+Training Model
+**************
+With parameters and data, you are able to train a booster model.
+
+* Import Booster and XGBoost:
+
+  .. code-block:: java
+
+    import ml.dmlc.xgboost4j.java.Booster;
+    import ml.dmlc.xgboost4j.java.XGBoost;
+
+* Training
+
+  .. code-block:: java
+
+    DMatrix trainMat = new DMatrix("train.svm.txt");
+    DMatrix validMat = new DMatrix("valid.svm.txt");
+    // Specify a watch list to see model accuracy on data sets
+    Map<String, DMatrix> watches = new HashMap<String, DMatrix>() {
+      {
+        put("train", trainMat);
+        put("test", testMat);
+      }
+    };
+    int nround = 2;
+    Booster booster = XGBoost.train(trainMat, params, nround, watches, null, null);
+
+* Saving model
+
+  After training, you can save model and dump it out.
+
+  .. code-block:: java
+
+    booster.saveModel("model.bin");
+
+* Generaing model dump with feature map
+
+  .. code-block:: java
+
+    // dump without feature map
+    String[] model_dump = booster.getModelDump(null, false);
+    // dump with feature map
+    String[] model_dump_with_feature_map = booster.getModelDump("featureMap.txt", false);
+
+* Load a model
+
+  .. code-block:: java
+
+    Booster booster = XGBoost.loadModel("model.bin");
+
+**********
+Prediction
+**********
+After training and loading a model, you can use it to make prediction for other data. The result will be a two-dimension float array ``(nsample, nclass)``; for ``predictLeaf()``, the result would be of shape ``(nsample, nclass*ntrees)``.
+
+.. code-block:: java
+
+  DMatrix dtest = new DMatrix("test.svm.txt");
+  // predict
+  float[][] predicts = booster.predict(dtest);
+  // predict leaf
+  float[][] leafPredicts = booster.predictLeaf(dtest, 0);
+

doc/jvm/javadocs/index.rst

@@ -0,0 +1,3 @@
+==================
+XGBoost4J Java API
+==================

doc/jvm/scaladocs/xgboost4j-flink/index.rst

@@ -0,0 +1,3 @@
+=========================
+XGBoost4J-Flink Scala API
+=========================

doc/jvm/scaladocs/xgboost4j-spark/index.rst

@@ -0,0 +1,3 @@
+=========================
+XGBoost4J-Spark Scala API
+=========================

doc/jvm/scaladocs/xgboost4j/index.rst

@@ -0,0 +1,3 @@
+===================
+XGBoost4J Scala API
+===================

doc/jvm/xgboost4j-intro.md

@@ -1,187 +0,0 @@
----
-layout: post
-title:  XGBoost4J: Portable Distributed Tree Boosting in DataFlow
-date:   2016-03-15 12:00:00
-author: Nan Zhu, Tianqi Chen
-comments: true
----
-
-## Introduction
-[XGBoost](https://github.com/dmlc/xgboost) is a library designed and optimized for tree boosting. Gradient boosting trees model is originally proposed by Friedman et al. By embracing multi-threads and introducing regularization, XGBoost delivers higher computational power and more accurate prediction.  **More than half of the winning solutions in machine learning challenges** hosted at Kaggle adopt XGBoost ([Incomplete list](https://github.com/dmlc/xgboost/tree/master/demo#machine-learning-challenge-winning-solutions)).
-XGBoost has provided native interfaces for  C++, R, python, Julia and Java users.
-It is used by both [data exploration and production scenarios](https://github.com/dmlc/xgboost/tree/master/demo#usecases) to solve real world machine learning problems.
-
-The distributed XGBoost is described in the [recently published paper](http://arxiv.org/abs/1603.02754).
-In short, the XGBoost system runs magnitudes faster than existing alternatives of distributed ML,
-and uses far fewer resources. The reader is more than welcomed to refer to the paper for more details.
-
-Despite the current great success, one of our ultimate goals is to make XGBoost even more available for all production scenario.
-Programming languages and data processing/storage systems based on Java Virtual Machine (JVM) play the significant roles in the BigData ecosystem. [Hadoop](http://hadoop.apache.org/), [Spark](http://spark.apache.org/) and more recently introduced [Flink](http://flink.apache.org/) are very useful solutions to general large-scale data processing.
-
-On the other side, the emerging demands of machine learning and deep learning
-inspires many excellent machine learning libraries.
-Many of these machine learning libraries(e.g. [XGBoost](https://github.com/dmlc/xgboost)/[MxNet](https://github.com/dmlc/mxnet))
-requires new computation abstraction and native support (e.g. C++ for GPU computing).
-They are also often [much more efficient](http://arxiv.org/abs/1603.02754).
-
-The gap between the implementation fundamentals of the general data processing frameworks and the more specific machine learning libraries/systems prohibits the smooth connection between these two types of systems, thus brings unnecessary inconvenience to the end user. The common workflow to the user is to utilize the systems like Spark/Flink to preprocess/clean data, pass the results to machine learning systems like [XGBoost](https://github.com/dmlc/xgboost)/[MxNet](https://github.com/dmlc/mxnet))  via the file systems and then conduct the following machine learning phase. This process jumping across two types of systems creates certain inconvenience for the users and brings additional overhead to the operators of the infrastructure.
-
-We want best of both worlds, so we can use the data processing frameworks like Spark and Flink together with
-the best distributed machine learning solutions.
-To resolve the situation, we introduce the new-brewed [XGBoost4J](https://github.com/dmlc/xgboost/tree/master/jvm-packages),
-<b>XGBoost</b> for <b>J</b>VM Platform. We aim to provide the clean Java/Scala APIs and the integration with the most popular data processing systems developed in JVM-based languages.
-
-## Unix Philosophy in Machine Learning
-
-XGBoost and XGBoost4J adopts Unix Philosophy.
-XGBoost **does its best in one thing -- tree boosting** and is **being designed to work with other systems**.
-We strongly believe that machine learning solution should not be restricted to certain language or certain platform.
-
-Specifically, users will be able to use distributed XGBoost in both Spark and Flink, and possibly more frameworks in Future.
-We have made the API in a portable way so it **can be easily ported to other Dataflow frameworks provided by the Cloud**.
-XGBoost4J shares its core with other XGBoost libraries, which means data scientists can use R/python
-read and visualize the model trained distributedly.
-It also means that user can start with single machine version for exploration,
-which already can handle hundreds of million examples.
-
-## System Overview
-
-In the following Figure, we describe the overall architecture of XGBoost4J. XGBoost4J provides the Java/Scala API calling the core functionality of XGBoost library. Most importantly, it not only supports the single-machine model training, but also provides an abstraction layer which masks the difference of the underlying data processing engines and scales training to the distributed servers.
-
-![XGBoost4J Architecture](https://raw.githubusercontent.com/dmlc/web-data/master/xgboost/xgboost4j.png)
-
-
-By calling the XGBoost4J API, users can scale the model training to the cluster. XGBoost4J calls the running instance of XGBoost worker in Spark/Flink task and run them across the cluster. The communication among the distributed model training tasks and the XGBoost4J runtime environment go through [Rabit] (https://github.com/dmlc/rabit).
-
-With the abstraction of XGBoost4J, users can build an unified data analytic application ranging from Extract-Transform-Loading, data exploration, machine learning model training and the final data product service. The following figure illustrate an example application built on top of Apache Spark. The application seamlessly embeds XGBoost into the processing pipeline and exchange data with other Spark-based processing phase through Spark's distributed memory layer.
-
-![XGBoost4J Architecture](https://raw.githubusercontent.com/dmlc/web-data/master/xgboost/unified_pipeline.png)
-
-
-## Single-machine Training Walk-through
-
-In this section, we will work through the APIs of XGBoost4J by examples.
-We will be using scala for demonstration, but we also have a complete API for java users.
-
-To start the model training and evaluation, we need to prepare the training and test set:
-
-```scala
-val trainMax = new DMatrix("../../demo/data/agaricus.txt.train")
-val testMax = new DMatrix("../../demo/data/agaricus.txt.test")
-```
-
-After preparing the data, we can train our model:
-
-```scala
-val params = new mutable.HashMap[String, Any]()
-params += "eta" -> 1.0
-params += "max_depth" -> 2
-params += "silent" -> 1
-params += "objective" -> "binary:logistic"
-
-val watches = new mutable.HashMap[String, DMatrix]
-watches += "train" -> trainMax
-watches += "test" -> testMax
-
-val round = 2
-// train a model
-val booster = XGBoost.train(trainMax, params.toMap, round, watches.toMap)
-```
-
-We then evaluate our model:
-
-```scala
-val predicts = booster.predict(testMax)
-```
-
-`predict` can output the predict results and you can define a customized evaluation method to derive your own metrics (see the example in ([Customized Evaluation Metric in Java](https://github.com/dmlc/xgboost/blob/master/jvm-packages/xgboost4j-example/src/main/java/ml/dmlc/xgboost4j/java/example/CustomObjective.java), [Customized Evaluation Metric in Scala] (https://github.com/dmlc/xgboost/blob/master/jvm-packages/xgboost4j-example/src/main/scala/ml/dmlc/xgboost4j/scala/example/CustomObjective.scala)).
-
-
-## Distributed Model Training with Distributed Dataflow Frameworks
-
-The most exciting part in this XGBoost4J release is the integration with the Distributed Dataflow Framework. The most popular data processing frameworks fall into this category, e.g. [Apache Spark](http://spark.apache.org/), [Apache Flink] (http://flink.apache.org/), etc. In this part, we will walk through the steps to build the unified data analytic applications containing data preprocessing and distributed model training with Spark and Flink. (currently, we only provide Scala API for the integration with Spark and Flink)
-
-Similar to the single-machine training, we need to prepare the training and test dataset.
-
-### Spark Example
-
-In Spark, the dataset is represented as the [Resilient Distributed Dataset (RDD)](http://spark.apache.org/docs/latest/programming-guide.html#resilient-distributed-datasets-rdds), we can utilize the Spark-distributed tools to parse libSVM file and wrap it as the RDD:
-
-```scala
-val trainRDD = MLUtils.loadLibSVMFile(sc, inputTrainPath).repartition(args(1).toInt)
-```
-
-We move forward to train the models:
-
-```scala
-val xgboostModel = XGBoost.train(trainRDD, paramMap, numRound, numWorkers)
-
-```
-
-The next step is to evaluate the model, you can either predict in local side or in a distributed fashion
-
-
-```scala
-// testSet is an RDD containing testset data represented as
-// org.apache.spark.mllib.regression.LabeledPoint
-val testSet = MLUtils.loadLibSVMFile(sc, inputTestPath)
-
-// local prediction
-// import methods in DataUtils to convert Iterator[org.apache.spark.mllib.regression.LabeledPoint]
-// to Iterator[ml.dmlc.xgboost4j.LabeledPoint] in automatic
-import DataUtils._
-xgboostModel.predict(new DMatrix(testSet.collect().iterator)
-
-// distributed prediction
-xgboostModel.predict(testSet)
-
-```
-### Flink example
-
-In Flink, we represent training data as Flink's [DataSet](https://ci.apache.org/projects/flink/flink-docs-master/apis/batch/index.html)
-
-```scala
-val trainData = MLUtils.readLibSVM(env, "/path/to/data/agaricus.txt.train")
-```
-
-Model Training can be done as follows
-
-```scala
-val xgboostModel = XGBoost.train(trainData, paramMap, round)
-
-```
-
-Training and prediction.
-
-```scala
-// testData is a Dataset containing testset data represented as
-// org.apache.flink.ml.math.Vector.LabeledVector
-val testData = MLUtils.readLibSVM(env, "/path/to/data/agaricus.txt.test")
-
-// local prediction
-xgboostModel.predict(testData.collect().iterator)
-
-// distributed prediction
-xgboostModel.predict(testData.map{x => x.vector})
-```
-
-## Road Map
-
-It is the first release of XGBoost4J package, we are actively move forward for more charming features in the next release. You can watch our progress in [XGBoost4J Road Map](https://github.com/dmlc/xgboost/issues/935).
-
-While we are trying our best to keep the minimum changes to the APIs, it is still subject to the incompatible changes.
-
-## Further Readings
-
-If you are interested in knowing more about XGBoost, you can find rich resources in
-
-- [The github repository of XGBoost](https://github.com/dmlc/xgboost)
-- [The comprehensive documentation site for XGBoostl](http://xgboost.readthedocs.org/en/latest/index.html)
-- [An introduction to the gradient boosting model](http://xgboost.readthedocs.org/en/latest/model.html)
-- [Tutorials for the R package](xgboost.readthedocs.org/en/latest/R-package/index.html)
-- [Introduction of the Parameters](http://xgboost.readthedocs.org/en/latest/parameter.html)
-- [Awesome XGBoost, a curated list of examples, tutorials, blogs about XGBoost usecases](https://github.com/dmlc/xgboost/tree/master/demo)
-
-## Acknowledgements
-
-We would like to send many thanks to [Zixuan Huang](https://github.com/yanqingmen), the early developer of XGBoost for Java (XGBoost for Java).

doc/jvm/xgboost4j_full_integration.md

@@ -1,139 +0,0 @@
-## Introduction
-
-On March 2016, we released the first version of [XGBoost4J](http://dmlc.ml/2016/03/14/xgboost4j-portable-distributed-xgboost-in-spark-flink-and-dataflow.html), which is a set of packages providing Java/Scala interfaces of XGBoost and the integration with prevalent JVM-based distributed data processing platforms, like Spark/Flink.
-
-The integrations with Spark/Flink, a.k.a. <b>XGBoost4J-Spark</b> and <b>XGBoost-Flink</b>, receive the tremendous positive feedbacks from the community. It enables users to build a unified pipeline, embedding  XGBoost into the data processing system based on the widely-deployed frameworks like Spark. The following figure shows the general architecture of such a pipeline with the first version of <b>XGBoost4J-Spark</b>, where the data processing is based on the low-level [Resilient Distributed Dataset (RDD)](http://spark.apache.org/docs/latest/programming-guide.html#resilient-distributed-datasets-rdds) abstraction.
-
-![XGBoost4J Architecture](https://raw.githubusercontent.com/dmlc/web-data/master/xgboost/unified_pipeline.png)
-
-In the last months, we have a lot of communication with the users and gain the deeper understanding of the users' latest usage scenario and requirements:
-
-* XGBoost keeps gaining more and more deployments in the production environment and the adoption in machine learning competitions [Link](http://datascience.la/xgboost-workshop-and-meetup-talk-with-tianqi-chen/).
-
-* While Spark is still the mainstream data processing tool in most of scenarios, more and more users are porting their RDD-based Spark programs to [DataFrame/Dataset APIs](http://spark.apache.org/docs/latest/sql-programming-guide.html) for the well-designed interfaces to manipulate structured data and the [significant performance improvement](https://databricks.com/blog/2016/07/26/introducing-apache-spark-2-0.html).
-
-* Spark itself has presented a clear roadmap that DataFrame/Dataset would be the base of the latest and future features, e.g. latest version of [ML pipeline](http://spark.apache.org/docs/latest/ml-guide.html) and [Structured Streaming](http://spark.apache.org/docs/latest/structured-streaming-programming-guide.html).
-
-Based on these feedbacks from the users, we observe a gap between the original RDD-based XGBoost4J-Spark and the users' latest usage scenario as well as the future direction of Spark ecosystem. To fill this gap, we start working on the <b><i>integration of XGBoost and Spark's DataFrame/Dataset abstraction</i></b> in September. In this blog, we will introduce <b>the latest version of XGBoost4J-Spark</b> which allows the user to work with DataFrame/Dataset directly and embed XGBoost to Spark's ML pipeline seamlessly.
-
-
-## A Full Integration of XGBoost and DataFrame/Dataset
-
-The following figure illustrates the new pipeline architecture with the latest XGBoost4J-Spark.
-
-![XGBoost4J New Architecture](https://raw.githubusercontent.com/dmlc/web-data/master/xgboost/unified_pipeline_new.png)
-
-Being different with the previous version, users are able to use both low- and high-level memory abstraction in Spark, i.e. RDD and DataFrame/Dataset. The DataFrame/Dataset abstraction grants the user to manipulate structured datasets and utilize the built-in routines in Spark or User Defined Functions (UDF) to explore the value distribution in columns before they feed data into the machine learning phase in the pipeline. In the following example, the structured sales records can be saved in a JSON file, parsed as DataFrame through Spark's API and feed to train XGBoost model in two lines of Scala code.
-
-```scala
-// load sales records saved in json files
-val salesDF = spark.read.json("sales.json")
-// call XGBoost API to train with the DataFrame-represented training set
-val xgboostModel = XGBoost.trainWithDataFrame(
-      salesDF, paramMap, numRound, nWorkers, useExternalMemory)
-```
-
-By integrating with DataFrame/Dataset, XGBoost4J-Spark not only enables users to call DataFrame/Dataset APIs directly but also make  DataFrame/Dataset-based Spark features available to XGBoost users, e.g. ML Package.
-
-### Integration with ML Package
-
-ML package of Spark provides a set of convenient tools for feature extraction/transformation/selection. Additionally, with the model selection tool in ML package, users can select the best model through an automatic parameter searching process which is defined with through ML package APIs. After integrating with DataFrame/Dataset abstraction, these charming features in ML package are also available to XGBoost users.
-
-#### Feature Extraction/Transformation/Selection
-
-The following example shows a feature transformer which converts the string-typed storeType feature to the numeric storeTypeIndex. The transformed DataFrame is then fed to train XGBoost model.
-
-```scala
-import org.apache.spark.ml.feature.StringIndexer
-
-// load sales records saved in json files
-val salesDF = spark.read.json("sales.json")
-
-// transform the string-represented storeType feature to numeric storeTypeIndex
-val indexer = new StringIndexer()
-  .setInputCol("storeType")
-  .setOutputCol("storeTypeIndex")
-// drop the extra column
-val indexed = indexer.fit(salesDF).transform(df).drop("storeType")
-
-// use the transformed dataframe as training dataset
-val xgboostModel = XGBoost.trainWithDataFrame(
-      indexed, paramMap, numRound, nWorkers, useExternalMemory)
-```
-
-#### Pipelining
-
-Spark ML package allows the user to build a complete pipeline from feature extraction/transformation/selection to model training. We integrate XGBoost with ML package and make it feasible to embed XGBoost into such a pipeline seamlessly. The following example shows how to build such a pipeline consisting of feature transformers and the XGBoost estimator.
-
-```scala
-import org.apache.spark.ml.feature.StringIndexer
-
-// load sales records saved in json files
-val salesDF = spark.read.json("sales.json")
-
-// transform the string-represented storeType feature to numeric storeTypeIndex
-val indexer = new StringIndexer()
-  .setInputCol("storeType")
-  .setOutputCol("storeTypeIndex")
-
-// assemble the columns in dataframe into a vector
-val vectorAssembler = new VectorAssembler()
-      .setInputCols(Array("storeId", "storeTypeIndex", ...))
-      .setOutputCol("features")
-
-// construct the pipeline       
-val pipeline = new Pipeline().setStages(
-      Array(storeTypeIndexer, ..., vectorAssembler, new XGBoostEstimator(Map[String, Any]("num_rounds" -> 100)))
-
-// use the transformed dataframe as training dataset
-val xgboostModel = pipeline.fit(salesDF)
-
-// predict with the trained model
-val salesTestDF = spark.read.json("sales_test.json")
-val salesRecordsWithPred = xgboostModel.transform(salesTestDF)
-
-```
-
-#### Model Selection
-
-The most critical operation to maximize the power of XGBoost is to select the optimal parameters for the model. Tuning parameters manually is a tedious and labor-consuming process. With the latest version of XGBoost4J-Spark, we can utilize the Spark model selecting tool to automate this process. The following example shows the code snippet utilizing [TrainValidationSplit](http://spark.apache.org/docs/latest/api/scala/index.html#org.apache.spark.ml.tuning.TrainValidationSplit) and [RegressionEvaluator](http://spark.apache.org/docs/latest/api/scala/index.html#org.apache.spark.ml.evaluation.RegressionEvaluator) to search the optimal combination of two XGBoost parameters, [max_depth and eta] (https://github.com/dmlc/xgboost/blob/master/doc/parameter.md). The model producing the minimum cost function value defined by RegressionEvaluator is selected and used to generate the prediction for the test set.
-
-```scala
-// create XGBoostEstimator
-val xgbEstimator = new XGBoostEstimator(xgboostParam).setFeaturesCol("features").
-      setLabelCol("sales")
-val paramGrid = new ParamGridBuilder()
-      .addGrid(xgbEstimator.maxDepth, Array(5, 6))
-      .addGrid(xgbEstimator.eta, Array(0.1, 0.4))
-      .build()
-val tv = new TrainValidationSplit()
-      .setEstimator(xgbEstimator)
-      .setEvaluator(new RegressionEvaluator().setLabelCol("sales"))
-      .setEstimatorParamMaps(paramGrid)
-      .setTrainRatio(0.8)  
-val salesTestDF = spark.read.json("sales_test.json")
-val salesRecordsWithPred = xgboostModel.transform(salesTestDF)
-```
-
-## Summary
-
-Through the latest XGBoost4J-Spark, XGBoost users can build a more efficient data processing pipeline which works with DataFrame/Dataset APIs to handle the structured data with the excellent performance, and simultaneously embrace the powerful XGBoost to explore the insights from the dataset and transform this insight into action. Additionally, XGBoost4J-Spark seamlessly connect XGBoost with Spark ML package which makes the job of feature extraction/transformation/selection and parameter model much easier than before.
-
-The latest version of XGBoost4J-Spark has been available in the [GitHub Repository] (https://github.com/dmlc/xgboost), and the latest API docs are in [here](http://xgboost.readthedocs.io/en/latest/jvm/index.html).
-
-
-## Portable Machine Learning Systems
-
-XGBoost is one of the projects incubated by [Distributed Machine Learning Community (DMLC)](http://dmlc.ml/), which also creates several other popular projects on machine learning systems ([Link](https://github.com/dmlc/)), e.g. one of the most popular deep learning frameworks, [MXNet](http://mxnet.io/). We strongly believe that machine learning solution should not be restricted to certain language or certain platform. We realize this design philosophy in several projects, like XGBoost and MXNet. We are willing to see more contributions from the community in this direction.
-
-
-## Further Readings
-
-If you are interested in knowing more about XGBoost, you can find rich resources in
-
-- [The github repository of XGBoost](https://github.com/dmlc/xgboost)
-- [The comprehensive documentation site for XGBoostl](http://xgboost.readthedocs.org/en/latest/index.html)
-- [An introduction to the gradient boosting model](http://xgboost.readthedocs.org/en/latest/model.html)
-- [Tutorials for the R package](xgboost.readthedocs.org/en/latest/R-package/index.html)
-- [Introduction of the Parameters](http://xgboost.readthedocs.org/en/latest/parameter.html)
-- [Awesome XGBoost, a curated list of examples, tutorials, blogs about XGBoost usecases](https://github.com/dmlc/xgboost/tree/master/demo)

doc/jvm/xgboost4j_spark_tutorial.rst

@@ -0,0 +1,513 @@
+#######################################
+XGBoost4J-Spark Tutorial (version 0.8+)
+#######################################
+
+**XGBoost4J-Spark** is a project aiming to seamlessly integrate XGBoost and Apache Spark by fitting XGBoost to Apache Spark's MLLIB framework. With the integration, user can not only uses the high-performant algorithm implementation of XGBoost, but also leverages the powerful  data processing engine of Spark for:
+
+* Feature Engineering: feature extraction, transformation, dimensionality reduction, and selection, etc.
+* Pipelines: constructing, evaluating, and tuning ML Pipelines
+* Persistence: persist and load machine learning models and even whole Pipelines
+
+This tutorial is to cover the end-to-end process to build a machine learning pipeline with XGBoost4J-Spark. We will discuss
+
+* Using Spark to preprocess data to fit to XGBoost/XGBoost4J-Spark's data interface
+* Training a XGBoost model with XGBoost4J-Spark
+* Serving XGBoost model (prediction) with Spark
+* Building a Machine Learning Pipeline with XGBoost4J-Spark
+* Running XGBoost4J-Spark in Production
+
+.. contents::
+  :backlinks: none
+  :local:
+
+********************************************
+Build an ML Application with XGBoost4J-Spark
+********************************************
+
+Refer to XGBoost4J-Spark Dependency
+===================================
+
+Before we go into the tour of how to use XGBoost4J-Spark, we would bring a brief introduction about how to build a machine learning application with XGBoost4J-Spark. The first thing you need to do is to refer to the dependency in Maven Central.
+
+You can add the following dependency in your ``pom.xml``.
+
+.. code-block:: xml
+
+  <dependency>
+    <groupId>ml.dmlc</groupId>
+    <artifactId>xgboost4j-spark</artifactId>
+    <version>latest_version_num</version>
+  </dependency>
+
+For the latest release version number, please check `here <https://github.com/dmlc/xgboost/releases>`_.
+
+We also publish some functionalities which would be included in the coming release in the form of snapshot version. To access these functionalities, you can add dependency to the snapshot artifacts. We publish snapshot version in github-based repo, so you can add the following repo in ``pom.xml``:
+
+.. code-block:: xml
+
+  <repository>
+    <id>XGBoost4J-Spark Snapshot Repo</id>
+    <name>XGBoost4J-Spark Snapshot Repo</name>
+    <url>https://raw.githubusercontent.com/CodingCat/xgboost/maven-repo/</url>
+  </repository>
+
+and then refer to the snapshot dependency by adding:
+
+.. code-block:: xml
+
+  <dependency>
+      <groupId>ml.dmlc</groupId>
+      <artifactId>xgboost4j</artifactId>
+      <version>next_version_num-SNAPSHOT</version>
+  </dependency>
+
+.. note:: XGBoost4J-Spark requires Spark 2.3+
+
+  XGBoost4J-Spark now requires Spark 2.3+. Latest versions of XGBoost4J-Spark uses facilities of `org.apache.spark.ml.param.shared` extensively to provide for a tight integration with Spark MLLIB framework, and these facilities are not fully available on earlier versions of Spark.
+
+Data Preparation
+================
+
+As aforementioned, XGBoost4J-Spark seamlessly integrates Spark and XGBoost. The integration enables
+users to apply various types of transformation over the training/test datasets with the convenient
+and powerful data processing framework, Spark.
+
+In this section, we use `Iris <https://archive.ics.uci.edu/ml/datasets/iris>`_ dataset as an example to
+showcase how we use Spark to transform raw dataset and make it fit to the data interface of XGBoost.
+
+Iris dataset is shipped in CSV format. Each instance contains 4 features, "sepal length", "sepal width",
+"petal length" and "petal width". In addition, it contains the "class" columnm, which is essentially the label with three possible values: "Iris Setosa", "Iris Versicolour" and "Iris Virginica".
+
+Read Dataset with Spark's Built-In Reader
+-----------------------------------------
+
+The first thing in data transformation is to load the dataset as Spark's structured data abstraction, DataFrame.
+
+.. code-block:: scala
+
+  import org.apache.spark.sql.SparkSession
+  import org.apache.spark.sql.types.{DoubleType, StringType, StructField, StructType}
+
+  val spark = SparkSession.builder().getOrCreate()
+  val schema = new StructType(Array(
+    StructField("sepal length", DoubleType, true),
+    StructField("sepal width", DoubleType, true),
+    StructField("petal length", DoubleType, true),
+    StructField("petal width", DoubleType, true),
+    StructField("class", StringType, true)))
+  val rawInput = spark.read.schema(schema).csv("input_path")
+
+At the first line, we create a instance of `SparkSession <http://spark.apache.org/docs/latest/sql-programming-guide.html#starting-point-sparksession>`_ which is the entry of any Spark program working with DataFrame. The ``schema`` variable defines the schema of DataFrame wrapping Iris data. With this explicitly set schema, we can define the columns' name as well as their types; otherwise the column name would be the default ones derived by Spark, such as ``_col0``, etc. Finally, we can use Spark's built-in csv reader to load Iris csv file as a DataFrame named ``rawInput``.
+
+Spark also contains many built-in readers for other format. The latest version of Spark supports CSV, JSON, Parquet, and LIBSVM.
+
+Transform Raw Iris Dataset
+--------------------------
+
+To make Iris dataset be recognizable to XGBoost, we need to
+
+1. Transform String-typed label, i.e. "class", to Double-typed label.
+2. Assemble the feature columns as a vector to fit to the data interface of Spark ML framework.
+
+To convert String-typed label to Double, we can use Spark's built-in feature transformer `StringIndexer <https://spark.apache.org/docs/2.3.1/api/scala/index.html#org.apache.spark.ml.feature.StringIndexer>`_.
+
+.. code-block:: scala
+
+  import org.apache.spark.ml.feature.StringIndexer
+  val stringIndexer = new StringIndexer().
+    setInputCol("class").
+    setOutputCol("classIndex").
+    fit(rawInput)
+  val labelTransformed = stringIndexer.transform(rawInput).drop("class")
+
+With a newly created StringIndexer instance:
+
+1. we set input column, i.e. the column containing String-typed label
+2. we set output column, i.e. the column to contain the Double-typed label.
+3. Then we ``fit`` StringIndex with our input DataFrame ``rawInput``, so that Spark internals can get information like total number of distinct values, etc.
+
+Now we have a StringIndexer which is ready to be applied to our input DataFrame. To execute the transformation logic of StringIndexer, we ``transform`` the input DataFrame ``rawInput`` and to keep a concise DataFrame,
+we drop the column "class" and only keeps the feature columns and the transformed Double-typed label column (in the last line of the above code snippet).
+
+The ``fit`` and ``transform`` are two key operations in MLLIB. Basically, ``fit`` produces a "transformer", e.g. StringIndexer, and each transformer applies ``transform`` method on DataFrame to add new column(s) containing transformed features/labels or prediction results, etc. To understand more about ``fit`` and ``transform``, You can find more details in `here <http://spark.apache.org/docs/latest/ml-pipeline.html#pipeline-components>`_.
+
+Similarly, we can use another transformer, `VectorAssembler <https://spark.apache.org/docs/2.3.1/api/scala/index.html#org.apache.spark.ml.feature.VectorAssembler>`_, to assemble feature columns "sepal length", "sepal width", "petal length" and "petal width" as a vector.
+
+.. code-block:: scala
+
+  import org.apache.spark.ml.feature.VectorAssembler
+  val vectorAssembler = new VectorAssembler().
+    setInputCols(Array("sepal length", "sepal width", "petal length", "petal width")).
+    setOutputCol("features")
+  val xgbInput = vectorAssembler.transform(labelTransformed).select("features", "classIndex")
+
+Now, we have a DataFrame containing only two columns, "features" which contains vector-represented
+"sepal length", "sepal width", "petal length" and "petal width" and "classIndex" which has Double-typed
+labels. A DataFrame like this (containing vector-represented features and numeric labels) can be fed to XGBoost4J-Spark's training engine directly.
+
+Training
+========
+
+XGBoost supports both regression and classification. While we use Iris dataset in this tutorial to show how we use XGBoost/XGBoost4J-Spark to resolve a multi-classes classification problem, the usage in Regression is very similar to classification.
+
+To train a XGBoost model for classification, we need to claim a XGBoostClassifier first:
+
+.. code-block:: scala
+
+  import ml.dmlc.xgboost4j.scala.spark.XGBoostClassifier
+  val xgbParam = Map("eta" -> 0.1f,
+        "max_depth" -> 2,
+        "objective" -> "multi:softprob",
+        "num_class" -> 3,
+        "num_round" -> 100,
+        "num_workers" -> 2)
+  val xgbClassifier = new XGBoostClassifier(xgbParam).
+        setFeaturesCol("features").
+        setLabelCol("classIndex")
+
+The available parameters for training a XGBoost model can be found in :doc:`here </parameter>`. In XGBoost4J-Spark, we support not only the default set of parameters but also the camel-case variant of these parameters to keep consistent with Spark's MLLIB parameters.
+
+Specifically, each parameter in :doc:`this page </parameter>` has its
+equivalent form in XGBoost4J-Spark with camel case. For example, to set ``max_depth`` for each tree, you can pass parameter just like what we did in the above code snippet (as ``max_depth`` wrapped in a Map), or you can do it through setters in XGBoostClassifer:
+
+.. code-block:: scala
+
+  val xgbClassifier = new XGBoostClassifier().
+    setFeaturesCol("features").
+    setLabelCol("classIndex")
+  xgbClassifier.setMaxDepth(2)
+
+After we set XGBoostClassifier parameters and feature/label column, we can build a transformer, XGBoostClassificationModel by fitting XGBoostClassifier with the input DataFrame. This ``fit`` operation is essentially the training process and the generated model can then be used in prediction.
+
+.. code-block:: scala
+
+  val xgbClassificationModel = xgbClassifier.fit(xgbInput)
+
+Prediction
+==========
+
+XGBoost4j-Spark supports two ways for model serving: batch prediction and single instance prediction.
+
+Batch Prediction
+----------------
+
+When we get a model, either XGBoostClassificationModel or XGBoostRegressionModel, it takes a DataFrame, read the column containing feature vectors, predict for each feature vector, and output a new DataFrame with the following columns by default:
+
+* XGBoostClassificationModel will output margins (``rawPredictionCol``), probabilities(``probabilityCol``) and the eventual prediction labels (``predictionCol``) for each possible label.
+* XGBoostRegressionModel will output prediction label(``predictionCol``).
+
+Batch prediction expects the user to pass the testset in the form of a DataFrame. XGBoost4J-Spark starts a XGBoost worker for each partition of DataFrame for parallel prediction and generates prediction results for the whole DataFrame in a batch.
+
+.. code-block:: scala
+
+  val xgbClassificationModel = xgbClassifier.fit(xgbInput)
+  val results = xgbClassificationModel.transform(testSet)
+
+With the above code snippet, we get a result DataFrame, result containing margin, probability for each class and the prediction for each instance
+
+.. code-block:: none
+
+  +-----------------+----------+--------------------+--------------------+----------+
+  |         features|classIndex|       rawPrediction|         probability|prediction|
+  +-----------------+----------+--------------------+--------------------+----------+
+  |[5.1,3.5,1.4,0.2]|       0.0|[3.45569849014282...|[0.99579632282257...|       0.0|
+  |[4.9,3.0,1.4,0.2]|       0.0|[3.45569849014282...|[0.99618089199066...|       0.0|
+  |[4.7,3.2,1.3,0.2]|       0.0|[3.45569849014282...|[0.99643349647521...|       0.0|
+  |[4.6,3.1,1.5,0.2]|       0.0|[3.45569849014282...|[0.99636095762252...|       0.0|
+  |[5.0,3.6,1.4,0.2]|       0.0|[3.45569849014282...|[0.99579632282257...|       0.0|
+  |[5.4,3.9,1.7,0.4]|       0.0|[3.45569849014282...|[0.99428516626358...|       0.0|
+  |[4.6,3.4,1.4,0.3]|       0.0|[3.45569849014282...|[0.99643349647521...|       0.0|
+  |[5.0,3.4,1.5,0.2]|       0.0|[3.45569849014282...|[0.99579632282257...|       0.0|
+  |[4.4,2.9,1.4,0.2]|       0.0|[3.45569849014282...|[0.99618089199066...|       0.0|
+  |[4.9,3.1,1.5,0.1]|       0.0|[3.45569849014282...|[0.99636095762252...|       0.0|
+  |[5.4,3.7,1.5,0.2]|       0.0|[3.45569849014282...|[0.99428516626358...|       0.0|
+  |[4.8,3.4,1.6,0.2]|       0.0|[3.45569849014282...|[0.99643349647521...|       0.0|
+  |[4.8,3.0,1.4,0.1]|       0.0|[3.45569849014282...|[0.99618089199066...|       0.0|
+  |[4.3,3.0,1.1,0.1]|       0.0|[3.45569849014282...|[0.99618089199066...|       0.0|
+  |[5.8,4.0,1.2,0.2]|       0.0|[3.45569849014282...|[0.97809928655624...|       0.0|
+  |[5.7,4.4,1.5,0.4]|       0.0|[3.45569849014282...|[0.97809928655624...|       0.0|
+  |[5.4,3.9,1.3,0.4]|       0.0|[3.45569849014282...|[0.99428516626358...|       0.0|
+  |[5.1,3.5,1.4,0.3]|       0.0|[3.45569849014282...|[0.99579632282257...|       0.0|
+  |[5.7,3.8,1.7,0.3]|       0.0|[3.45569849014282...|[0.97809928655624...|       0.0|
+  |[5.1,3.8,1.5,0.3]|       0.0|[3.45569849014282...|[0.99579632282257...|       0.0|
+  +-----------------+----------+--------------------+--------------------+----------+
+
+Single instance prediction
+--------------------------
+
+XGBoostClassificationModel or XGBoostRegressionModel support make prediction on single instance as well.
+It accepts a single Vector as feature, and output the prediction label.
+
+However, the overhead of single-instance prediction is high due to the internal overhead of XGBoost, use it carefully!
+
+.. code-block:: scala
+
+  val features = xgbInput.head().getAs[Vector]("features")
+  val result = xgbClassificationModel.predict(features)
+
+Model Persistence
+=================
+
+Model and pipeline persistence
+------------------------------
+
+A data scientist produces an ML model and hands it over to an engineering team for deployment in a production environment. Reversely, a trained model may be used by data scientists, for example as a baseline, across the process of data exploration. So it's important to support model persistence to make the models available across usage scenarios and programming languages.
+
+XGBoost4j-Spark supports saving and loading XGBoostClassifier/XGBoostClassificationModel and XGBoostRegressor/XGBoostRegressionModel. It also supports saving and loading a ML pipeline which includes these estimators and models.
+
+We can save the XGBoostClassificationModel to file system:
+
+.. code-block:: scala
+
+  val xgbClassificationModelPath = "/tmp/xgbClassificationModel"
+  xgbClassificationModel.write.overwrite().save(xgbClassificationModelPath)
+
+and then loading the model in another session:
+
+.. code-block:: scala
+
+  import ml.dmlc.xgboost4j.scala.spark.XGBoostClassificationModel
+
+  val xgbClassificationModel2 = XGBoostClassificationModel.load(xgbClassificationModelPath)
+  xgbClassificationModel2.transform(xgbInput)
+
+With regards to ML pipeline save and load, please refer the next section.
+
+Interact with Other Bindings of XGBoost
+---------------------------------------
+After we train a model with XGBoost4j-Spark on massive dataset, sometimes we want to do model serving in single machine or integrate it with other single node libraries for further processing. XGBoost4j-Spark supports export model to local by:
+
+.. code-block:: scala
+
+  val nativeModelPath = "/tmp/nativeModel"
+  xgbClassificationModel.nativeBooster.saveModel(nativeModelPath)
+
+Then we can load this model with single node Python XGBoost:
+
+.. code-block:: python
+
+  import xgboost as xgb
+  bst = xgb.Booster({'nthread': 4})
+  bst.load_model(nativeModelPath)
+
+.. note:: Using HDFS and S3 for exporting the models with nativeBooster.saveModel()
+
+  When interacting with other language bindings, XGBoost also supports saving-models-to and loading-models-from file systems other than the local one. You can use HDFS and S3 by prefixing the path with ``hdfs://`` and ``s3://`` respectively. However, for this capability, you must do **one** of the following:
+
+  1. Build XGBoost4J-Spark with the steps described in `here <https://xgboost.readthedocs.io/en/latest/jvm/index.html#installation-from-source>`_, but turning `USE_HDFS <https://github.com/dmlc/xgboost/blob/e939192978a0c152ad7b49b744630e99d54cffa8/jvm-packages/create_jni.py#L18>`_ (or USE_S3, etc. in the same place) switch on. With this approach, you can reuse the above code example by replacing "nativeModelPath" with a HDFS path.
+
+     - However, if you build with USE_HDFS, etc. you have to ensure that the involved shared object file, e.g. libhdfs.so, is put in the LIBRARY_PATH of your cluster. To avoid the complicated cluster environment configuration, choose the other option.
+
+  2. Use bindings of HDFS, S3, etc. to pass model files around. Here are the steps (taking HDFS as an example):
+
+     - Create a new file with
+
+       .. code-block:: scala
+
+         val outputStream = fs.create("hdfs_path")
+
+       where "fs" is an instance of `org.apache.hadoop.fs.FileSystem <https://hadoop.apache.org/docs/stable/api/org/apache/hadoop/fs/FileSystem.html>`_ class in Hadoop.
+
+     - Pass the returned OutputStream in the first step to nativeBooster.saveModel():
+
+       .. code-block:: scala
+
+         xgbClassificationModel.nativeBooster.saveModel(outputStream)
+
+     - Download file in other languages from HDFS and load with the pre-built (without the requirement of libhdfs.so) version of XGBoost. (The function "download_from_hdfs" is a helper function to be implemented by the user)
+
+       .. code-block:: python
+
+         import xgboost as xgb
+         bst = xgb.Booster({'nthread': 4})
+         local_path = download_from_hdfs("hdfs_path")
+         bst.load_model(local_path)
+
+.. note:: Consistency issue between XGBoost4J-Spark and other bindings
+
+  There is a consistency issue between XGBoost4J-Spark and other language bindings of XGBoost.
+
+  When users use Spark to load training/test data in LIBSVM format with the following code snippet:
+
+  .. code-block:: scala
+
+    spark.read.format("libsvm").load("trainingset_libsvm")
+
+  Spark assumes that the dataset is using 1-based indexing (feature indices staring with 1). However, when you do prediction with other bindings of XGBoost (e.g. Python API of XGBoost), XGBoost assumes that the dataset is using 0-based indexing (feature indices starting with 0) by default. It creates a pitfall for the users who train model with Spark but predict with the dataset in the same format in other bindings of XGBoost. The solution is to transform the dataset to 0-based indexing before you predict with, for example, Python API, or you append ``?indexing_mode=1`` to your file path when loading with DMatirx. For example in Python:
+
+  .. code-block:: python
+
+    xgb.DMatrix('test.libsvm?indexing_mode=1')
+
+*******************************************
+Building a ML Pipeline with XGBoost4J-Spark
+*******************************************
+
+Basic ML Pipeline
+=================
+
+Spark ML pipeline can combine multiple algorithms or functions into a single pipeline.
+It covers from feature extraction, transformation, selection to model training and prediction.
+XGBoost4j-Spark makes it feasible to embed XGBoost into such a pipeline seamlessly.
+The following example shows how to build such a pipeline consisting of Spark MLlib feature transformer
+and XGBoostClassifier estimator.
+
+We still use `Iris <https://archive.ics.uci.edu/ml/datasets/iris>`_ dataset and the ``rawInput`` DataFrame.
+First we need to split the dataset into training and test dataset.
+
+.. code-block:: scala
+
+  val Array(training, test) = rawInput.randomSplit(Array(0.8, 0.2), 123)
+
+The we build the ML pipeline which includes 4 stages:
+
+* Assemble all features into a single vector column.
+* From string label to indexed double label.
+* Use XGBoostClassifier to train classification model.
+* Convert indexed double label back to original string label.
+
+We have shown the first three steps in the earlier sections, and the last step is finished with a new transformer `IndexToString <https://spark.apache.org/docs/2.3.1/api/scala/index.html#org.apache.spark.ml.feature.IndexToString>`_:
+
+.. code-block:: scala
+
+	val labelConverter = new IndexToString()
+        .setInputCol("prediction")
+        .setOutputCol("realLabel")
+        .setLabels(stringIndexer.labels)
+
+We need to organize these steps as a Pipeline in Spark ML framework and evaluate the whole pipeline to get a PipelineModel:
+
+.. code-block:: scala
+
+  import org.apache.spark.ml.feature._
+  import org.apache.spark.ml.Pipeline
+
+  val pipeline = new Pipeline()
+      .setStages(Array(assembler, stringIndexer, booster, labelConverter))
+  val model = pipeline.fit(training)
+
+After we get the PipelineModel, we can make prediction on the test dataset and evaluate the model accuracy.
+
+.. code-block:: scala
+
+  import org.apache.spark.ml.evaluation.MulticlassClassificationEvaluator
+
+  val prediction = model.transform(test)
+  val evaluator = new MulticlassClassificationEvaluator()
+  val accuracy = evaluator.evaluate(prediction)
+
+Pipeline with Hyper-parameter Tunning
+=====================================
+The most critical operation to maximize the power of XGBoost is to select the optimal parameters for the model. Tuning parameters manually is a tedious and labor-consuming process. With the latest version of XGBoost4J-Spark, we can utilize the Spark model selecting tool to automate this process.
+
+The following example shows the code snippet utilizing CrossValidation and MulticlassClassificationEvaluator
+to search the optimal combination of two XGBoost parameters, ``max_depth`` and ``eta``. (See :doc:`/parameter`.)
+The model producing the maximum accuracy defined by MulticlassClassificationEvaluator is selected and used to generate the prediction for the test set.
+
+.. code-block:: scala
+
+  import org.apache.spark.ml.tuning._
+  import org.apache.spark.ml.PipelineModel
+  import ml.dmlc.xgboost4j.scala.spark.XGBoostClassificationModel
+
+  val paramGrid = new ParamGridBuilder()
+      .addGrid(booster.maxDepth, Array(3, 8))
+      .addGrid(booster.eta, Array(0.2, 0.6))
+      .build()
+  val cv = new CrossValidator()
+      .setEstimator(pipeline)
+      .setEvaluator(evaluator)
+      .setEstimatorParamMaps(paramGrid)
+      .setNumFolds(3)
+
+  val cvModel = cv.fit(training)
+
+  val bestModel = cvModel.bestModel.asInstanceOf[PipelineModel].stages(2)
+      .asInstanceOf[XGBoostClassificationModel]
+  bestModel.extractParamMap()
+
+*********************************
+Run XGBoost4J-Spark in Production
+*********************************
+
+XGBoost4J-Spark is one of the most important steps to bring XGBoost to production environment easier. In this section, we introduce three key features to run XGBoost4J-Spark in production.
+
+Parallel/Distributed Training
+=============================
+The massive size of training dataset is one of the most significant characteristics in production environment. To ensure that training in XGBoost scales with the data size, XGBoost4J-Spark bridges the distributed/parallel processing framework of Spark and the parallel/distributed training mechanism of XGBoost.
+
+In XGBoost4J-Spark, each XGBoost worker is wrapped by a Spark task and the training dataset in Spark's memory space is fed to XGBoost workers in a transparent approach to the user.
+
+In the code snippet where we build XGBoostClassifier, we set parameter ``num_workers`` (or ``numWorkers``).
+This parameter controls how many parallel workers we want to have when training a XGBoostClassificationModel.
+
+.. note:: Regarding OpenMP optimization
+
+  By default, we allocate a core per each XGBoost worker. Therefore, the OpenMP optimization within each XGBoost worker does not take effect and the parallelization of training is achieved
+  by running multiple workers (i.e. Spark tasks) at the same time.
+
+  If you do want OpenMP optimization, you have to
+
+  1. set ``nthread`` to a value larger than 1 when creating XGBoostClassifier/XGBoostRegressor
+  2. set ``spark.task.cpus`` in Spark to the same value as ``nthread``
+
+Gang Scheduling
+===============
+XGBoost uses `AllReduce <http://mpitutorial.com/tutorials/mpi-reduce-and-allreduce/>`_.
+algorithm to synchronize the stats, e.g. histogram values, of each worker during training. Therefore XGBoost4J-Spark requires that all of ``nthread * numWorkers`` cores should be available before the training runs.
+
+In the production environment where many users share the same cluster, it's hard to guarantee that your XGBoost4J-Spark application can get all requested resources for every run. By default, the communication layer in XGBoost will block the whole application when it requires more resources to be available. This process usually brings unnecessary resource waste as it keeps the ready resources and try to claim more. Additionally, this usually happens silently and does not bring the attention of users.
+
+XGBoost4J-Spark allows the user to setup a timeout threshold for claiming resources from the cluster. If the application cannot get enough resources within this time period, the application would fail instead of wasting resources for hanging long. To enable this feature, you can set with XGBoostClassifier/XGBoostRegressor:
+
+.. code-block:: scala
+
+  xgbClassifier.setTimeoutRequestWorkers(60000L)
+
+or pass in ``timeout_request_workers`` in ``xgbParamMap`` when building XGBoostClassifier:
+
+.. code-block:: scala
+
+  val xgbParam = Map("eta" -> 0.1f,
+     "max_depth" -> 2,
+     "objective" -> "multi:softprob",
+     "num_class" -> 3,
+     "num_round" -> 100,
+     "num_workers" -> 2,
+     "timeout_request_workers" -> 60000L)
+  val xgbClassifier = new XGBoostClassifier(xgbParam).
+      setFeaturesCol("features").
+      setLabelCol("classIndex")
+
+If XGBoost4J-Spark cannot get enough resources for running two XGBoost workers, the application would fail. Users can have external mechanism to monitor the status of application and get notified for such case.
+
+Checkpoint During Training
+==========================
+
+Transient failures are also commonly seen in production environment. To simplify the design of XGBoost,
+we stop training if any of the distributed workers fail. However, if the training fails after having been through a long time, it would be a great waste of resources.
+
+We support creating checkpoint during training to facilitate more efficient recovery from failture. To enable this feature, you can set how many iterations we build each checkpoint with ``setCheckpointInterval`` and the location of checkpoints with ``setCheckpointPath``:
+
+.. code-block:: scala
+
+  xgbClassifier.setCheckpointInterval(2)
+  xgbClassifier.setCheckpointPath("/checkpoint_path")
+
+An equivalent way is to pass in parameters in XGBoostClassifier's constructor:
+
+.. code-block:: scala
+
+  val xgbParam = Map("eta" -> 0.1f,
+     "max_depth" -> 2,
+     "objective" -> "multi:softprob",
+     "num_class" -> 3,
+     "num_round" -> 100,
+     "num_workers" -> 2,
+     "checkpoint_path" -> "/checkpoints_path",
+     "checkpoint_interval" -> 2)
+  val xgbClassifier = new XGBoostClassifier(xgbParam).
+      setFeaturesCol("features").
+      setLabelCol("classIndex")
+
+If the training failed during these 100 rounds, the next run of training would start by reading the latest checkpoint file in ``/checkpoints_path`` and start from the iteration when the checkpoint was built until to next failure or the specified 100 rounds.