Store categories from pandas.

CMakeLists.txt

@@ -4,7 +4,7 @@ if(PLUGIN_SYCL)
   string(REPLACE " -isystem ${CONDA_PREFIX}/include" "" CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS}")
 endif()
 
-project(xgboost LANGUAGES CXX C VERSION 3.0.0)
+project(xgboost LANGUAGES CXX C VERSION 3.1.0)
 include(cmake/Utils.cmake)
 list(APPEND CMAKE_MODULE_PATH "${xgboost_SOURCE_DIR}/cmake/modules")
 

R-package/DESCRIPTION

@@ -1,8 +1,8 @@
 Package: xgboost
 Type: Package
 Title: Extreme Gradient Boosting
-Version: 3.0.0.0
-Date: 2024-11-26
+Version: 3.1.0.0
+Date: 2025-03-03
 Authors@R: c(
   person("Tianqi", "Chen", role = c("aut"),
          email = "[email protected]"),

R-package/configure

@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.71 for xgboost 3.0.0.
+# Generated by GNU Autoconf 2.71 for xgboost 3.1.0.
 #
 #
 # Copyright (C) 1992-1996, 1998-2017, 2020-2021 Free Software Foundation,
@@ -607,8 +607,8 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='xgboost'
 PACKAGE_TARNAME='xgboost'
-PACKAGE_VERSION='3.0.0'
-PACKAGE_STRING='xgboost 3.0.0'
+PACKAGE_VERSION='3.1.0'
+PACKAGE_STRING='xgboost 3.1.0'
 PACKAGE_BUGREPORT=''
 PACKAGE_URL=''
 
@@ -1262,7 +1262,7 @@ if test "$ac_init_help" = "long"; then
   # Omit some internal or obsolete options to make the list less imposing.
   # This message is too long to be a string in the A/UX 3.1 sh.
   cat <<_ACEOF
-\`configure' configures xgboost 3.0.0 to adapt to many kinds of systems.
+\`configure' configures xgboost 3.1.0 to adapt to many kinds of systems.
 
 Usage: $0 [OPTION]... [VAR=VALUE]...
 
@@ -1324,7 +1324,7 @@ fi
 
 if test -n "$ac_init_help"; then
   case $ac_init_help in
-     short | recursive ) echo "Configuration of xgboost 3.0.0:";;
+     short | recursive ) echo "Configuration of xgboost 3.1.0:";;
    esac
   cat <<\_ACEOF
 
@@ -1407,7 +1407,7 @@ fi
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
   cat <<\_ACEOF
-xgboost configure 3.0.0
+xgboost configure 3.1.0
 generated by GNU Autoconf 2.71
 
 Copyright (C) 2021 Free Software Foundation, Inc.
@@ -1668,7 +1668,7 @@ cat >config.log <<_ACEOF
 This file contains any messages produced by compilers while
 running configure, to aid debugging if configure makes a mistake.
 
-It was created by xgboost $as_me 3.0.0, which was
+It was created by xgboost $as_me 3.1.0, which was
 generated by GNU Autoconf 2.71.  Invocation command line was
 
   $ $0$ac_configure_args_raw
@@ -2796,11 +2796,11 @@ if test x$ac_prog_cxx_stdcxx = xno
 then :
   { printf "%s\n" "$as_me:${as_lineno-$LINENO}: checking for $CXX option to enable C++11 features" >&5
 printf %s "checking for $CXX option to enable C++11 features... " >&6; }
-if test ${ac_cv_prog_cxx_cxx11+y}
+if test ${ac_cv_prog_cxx_11+y}
 then :
   printf %s "(cached) " >&6
 else $as_nop
-  ac_cv_prog_cxx_cxx11=no
+  ac_cv_prog_cxx_11=no
 ac_save_CXX=$CXX
 cat confdefs.h - <<_ACEOF >conftest.$ac_ext
 /* end confdefs.h.  */
@@ -2842,11 +2842,11 @@ if test x$ac_prog_cxx_stdcxx = xno
 then :
   { printf "%s\n" "$as_me:${as_lineno-$LINENO}: checking for $CXX option to enable C++98 features" >&5
 printf %s "checking for $CXX option to enable C++98 features... " >&6; }
-if test ${ac_cv_prog_cxx_cxx98+y}
+if test ${ac_cv_prog_cxx_98+y}
 then :
   printf %s "(cached) " >&6
 else $as_nop
-  ac_cv_prog_cxx_cxx98=no
+  ac_cv_prog_cxx_98=no
 ac_save_CXX=$CXX
 cat confdefs.h - <<_ACEOF >conftest.$ac_ext
 /* end confdefs.h.  */
@@ -3855,7 +3855,7 @@ cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1
 # report actual input values of CONFIG_FILES etc. instead of their
 # values after options handling.
 ac_log="
-This file was extended by xgboost $as_me 3.0.0, which was
+This file was extended by xgboost $as_me 3.1.0, which was
 generated by GNU Autoconf 2.71.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -3919,7 +3919,7 @@ ac_cs_config_escaped=`printf "%s\n" "$ac_cs_config" | sed "s/^ //; s/'/'\\\\\\\\
 cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
 ac_cs_config='$ac_cs_config_escaped'
 ac_cs_version="\\
-xgboost config.status 3.0.0
+xgboost config.status 3.1.0
 configured by $0, generated by GNU Autoconf 2.71,
   with options \\"\$ac_cs_config\\"
 

R-package/configure.ac

@@ -2,7 +2,7 @@
 
 AC_PREREQ(2.69)
 
-AC_INIT([xgboost],[3.0.0],[],[xgboost],[])
+AC_INIT([xgboost],[3.1.0],[],[xgboost],[])
 
 : ${R_HOME=`R RHOME`}
 if test -z "${R_HOME}"; then

R-package/src/Makevars.in

@@ -66,6 +66,7 @@ OBJECTS= \
     $(PKGROOT)/src/gbm/gblinear_model.o \
     $(PKGROOT)/src/data/adapter.o \
     $(PKGROOT)/src/data/array_interface.o \
+    $(PKGROOT)/src/data/cat_container.o \
     $(PKGROOT)/src/data/simple_dmatrix.o \
     $(PKGROOT)/src/data/data.o \
     $(PKGROOT)/src/data/sparse_page_raw_format.o \

R-package/src/Makevars.win.in

@@ -65,6 +65,7 @@ OBJECTS= \
     $(PKGROOT)/src/gbm/gblinear_model.o \
     $(PKGROOT)/src/data/adapter.o \
     $(PKGROOT)/src/data/array_interface.o \
+    $(PKGROOT)/src/data/cat_container.o \
     $(PKGROOT)/src/data/simple_dmatrix.o \
     $(PKGROOT)/src/data/data.o \
     $(PKGROOT)/src/data/sparse_page_raw_format.o \

include/xgboost/data.h

@@ -1,5 +1,5 @@
 /**
- * Copyright 2015-2024, XGBoost Contributors
+ * Copyright 2015-2025, XGBoost Contributors
  * \file data.h
  * \brief The input data structure of xgboost.
  * \author Tianqi Chen
@@ -8,8 +8,8 @@
 #define XGBOOST_DATA_H_
 
 #include <dmlc/base.h>
-#include <dmlc/data.h>
-#include <dmlc/serializer.h>
+#include <dmlc/io.h>          // for Stream
+#include <dmlc/serializer.h>  // for Handler
 #include <xgboost/base.h>
 #include <xgboost/host_device_vector.h>
 #include <xgboost/linalg.h>
@@ -42,13 +42,16 @@ enum class FeatureType : uint8_t { kNumerical = 0, kCategorical = 1 };
 
 enum class DataSplitMode : int { kRow = 0, kCol = 1 };
 
-/*!
- * \brief Meta information about dataset, always sit in memory.
+// Forward declaration of the container used by the meta info.
+struct CatContainer;
+
+/**
+ * @brief Meta information about dataset, always sit in memory.
  */
 class MetaInfo {
  public:
   /*! \brief number of data fields in MetaInfo */
-  static constexpr uint64_t kNumField = 12;
+  static constexpr uint64_t kNumField = 13;
 
   /*! \brief number of rows in the data */
   bst_idx_t num_row_{0};  // NOLINT
@@ -100,9 +103,9 @@ class MetaInfo {
    */
   HostDeviceVector<float> feature_weights;
 
-  /*! \brief default constructor */
-  MetaInfo()  = default;
+  MetaInfo();
   MetaInfo(MetaInfo&& that) = default;
+  MetaInfo(MetaInfo const& that) = delete;
   MetaInfo& operator=(MetaInfo&& that) = default;
   MetaInfo& operator=(MetaInfo const& that) = delete;
 
@@ -205,6 +208,16 @@ class MetaInfo {
    * @brief Flag for whether the DMatrix has categorical features.
    */
   bool HasCategorical() const { return has_categorical_; }
+  /**
+   * @brief Getters for categories.
+   */
+  [[nodiscard]] CatContainer const* Cats() const;
+  [[nodiscard]] CatContainer* Cats();
+  [[nodiscard]] std::shared_ptr<CatContainer const>  CatsShared() const;
+  /**
+   * @brief Setter for categories.
+   */
+  void Cats(std::shared_ptr<CatContainer> cats);
 
  private:
   void SetInfoFromHost(Context const* ctx, StringView key, Json arr);
@@ -213,6 +226,8 @@ class MetaInfo {
   /*! \brief argsort of labels */
   mutable std::vector<size_t> label_order_cache_;
   bool has_categorical_{false};
+
+  std::shared_ptr<CatContainer> cats_;
 };
 
 /*! \brief Element from a sparse vector */
@@ -691,7 +706,15 @@ class DMatrix {
    * @param slice_id Index of the current slice
    * @return DMatrix containing the slice of columns
    */
-  virtual DMatrix *SliceCol(int num_slices, int slice_id) = 0;
+  virtual DMatrix* SliceCol(int num_slices, int slice_id) = 0;
+  /**
+   * @brief Accessor for the string representation of the categories.
+   */
+  CatContainer const* Cats() const { return this->CatsShared().get(); }
+  [[nodiscard]] virtual std::shared_ptr<CatContainer const> CatsShared() const {
+    LOG(FATAL) << "Not implemented for the current DMatrix type.";
+    return nullptr;
+  }
 
  protected:
   virtual BatchSet<SparsePage> GetRowBatches() = 0;

include/xgboost/predictor.h

@@ -5,7 +5,8 @@
  *  performs predictions for a gradient booster.
  */
 #pragma once
-#include <xgboost/base.h>
+#include <dmlc/registry.h>    // for FunctionRegEntryBase
+#include <xgboost/base.h>     // for bst_tree_t
 #include <xgboost/cache.h>    // for DMatrixCache
 #include <xgboost/context.h>  // for Context
 #include <xgboost/context.h>

include/xgboost/version_config.h

@@ -5,7 +5,7 @@
 #define XGBOOST_VERSION_CONFIG_H_
 
 #define XGBOOST_VER_MAJOR 3  /* NOLINT */
-#define XGBOOST_VER_MINOR 0  /* NOLINT */
+#define XGBOOST_VER_MINOR 1  /* NOLINT */
 #define XGBOOST_VER_PATCH 0  /* NOLINT */
 
 #endif  // XGBOOST_VERSION_CONFIG_H_

jvm-packages/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>ml.dmlc</groupId>
     <artifactId>xgboost-jvm_2.12</artifactId>
-    <version>3.0.0-SNAPSHOT</version>
+    <version>3.1.0-SNAPSHOT</version>
     <packaging>pom</packaging>
     <name>XGBoost JVM Package</name>
     <description>JVM Package for XGBoost</description>

jvm-packages/xgboost4j-example/pom.xml

@@ -6,11 +6,11 @@
     <parent>
         <groupId>ml.dmlc</groupId>
         <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>3.0.0-SNAPSHOT</version>
+        <version>3.1.0-SNAPSHOT</version>
     </parent>
     <name>xgboost4j-example</name>
     <artifactId>xgboost4j-example_2.12</artifactId>
-    <version>3.0.0-SNAPSHOT</version>
+    <version>3.1.0-SNAPSHOT</version>
     <packaging>jar</packaging>
     <build>
         <plugins>

jvm-packages/xgboost4j-flink/pom.xml

@@ -6,12 +6,12 @@
     <parent>
         <groupId>ml.dmlc</groupId>
         <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>3.0.0-SNAPSHOT</version>
+        <version>3.1.0-SNAPSHOT</version>
     </parent>
 
     <name>xgboost4j-flink</name>
     <artifactId>xgboost4j-flink_2.12</artifactId>
-    <version>3.0.0-SNAPSHOT</version>
+    <version>3.1.0-SNAPSHOT</version>
     <properties>
       <flink-ml.version>2.2.0</flink-ml.version>
     </properties>

jvm-packages/xgboost4j-spark-gpu/pom.xml

@@ -6,7 +6,7 @@
     <parent>
         <groupId>ml.dmlc</groupId>
         <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>3.0.0-SNAPSHOT</version>
+        <version>3.1.0-SNAPSHOT</version>
     </parent>
     <name>xgboost4j-spark-gpu</name>
     <artifactId>xgboost4j-spark-gpu_2.12</artifactId>

jvm-packages/xgboost4j-spark/pom.xml

@@ -6,7 +6,7 @@
     <parent>
         <groupId>ml.dmlc</groupId>
         <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>3.0.0-SNAPSHOT</version>
+        <version>3.1.0-SNAPSHOT</version>
     </parent>
     <name>xgboost4j-spark</name>
     <artifactId>xgboost4j-spark_2.12</artifactId>

jvm-packages/xgboost4j/pom.xml

@@ -6,11 +6,11 @@
     <parent>
         <groupId>ml.dmlc</groupId>
         <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>3.0.0-SNAPSHOT</version>
+        <version>3.1.0-SNAPSHOT</version>
     </parent>
     <name>xgboost4j</name>
     <artifactId>xgboost4j_2.12</artifactId>
-    <version>3.0.0-SNAPSHOT</version>
+    <version>3.1.0-SNAPSHOT</version>
     <packaging>jar</packaging>
 
     <dependencies>

ops/script/lint_python.py

@@ -27,6 +27,7 @@ class LintersPaths:
         "tests/python/test_early_stopping.py",
         "tests/python/test_multi_target.py",
         "tests/python/test_objectives.py",
+        "tests/python/test_ordinal.py",
         "tests/python/test_predict.py",
         "tests/python/test_quantile_dmatrix.py",
         "tests/python/test_tracker.py",
@@ -101,6 +102,7 @@ class LintersPaths:
         "tests/python-gpu/load_pickle.py",
         "tests/python-gpu/test_gpu_training_continuation.py",
         "tests/python/test_model_io.py",
+        "tests/python/test_ordinal.py",
         "tests/test_distributed/test_federated/",
         "tests/test_distributed/test_gpu_federated/",
         "tests/test_distributed/test_with_dask/test_ranking.py",

python-package/pyproject.toml

@@ -15,7 +15,7 @@ authors = [
     { name = "Hyunsu Cho", email = "[email protected]" },
     { name = "Jiaming Yuan", email = "[email protected]" }
 ]
-version = "3.0.0-dev"
+version = "3.1.0-dev"
 requires-python = ">=3.10"
 license = { text = "Apache-2.0" }
 classifiers = [

python-package/pyproject.toml.in

@@ -14,7 +14,7 @@ authors = [
     { name = "Hyunsu Cho", email = "[email protected]" },
     { name = "Jiaming Yuan", email = "[email protected]" }
 ]
-version = "3.0.0-dev"
+version = "3.1.0-dev"
 requires-python = ">=3.10"
 license = { text = "Apache-2.0" }
 classifiers = [

python-package/xgboost/VERSION

@@ -1 +1 @@
-3.0.0-dev
+3.1.0-dev