Release 1.7.1 (#8413)

* Release 1.7.1

* Review comment

CMakeLists.txt

@@ -1,5 +1,5 @@
 cmake_minimum_required(VERSION 3.14 FATAL_ERROR)
-project(xgboost LANGUAGES CXX C VERSION 1.7.0)
+project(xgboost LANGUAGES CXX C VERSION 1.7.1)
 include(cmake/Utils.cmake)
 list(APPEND CMAKE_MODULE_PATH "${xgboost_SOURCE_DIR}/cmake/modules")
 cmake_policy(SET CMP0022 NEW)

R-package/DESCRIPTION

@@ -1,8 +1,8 @@
 Package: xgboost
 Type: Package
 Title: Extreme Gradient Boosting
-Version: 1.7.0.1
-Date: 2022-10-18
+Version: 1.7.1.1
+Date: 2022-11-03
 Authors@R: c(
   person("Tianqi", "Chen", role = c("aut"),
          email = "tianqi.tchen@gmail.com"),

R-package/configure

@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.69 for xgboost 1.7.0.
+# Generated by GNU Autoconf 2.69 for xgboost 1.7.1.
 #
 #
 # Copyright (C) 1992-1996, 1998-2012 Free Software Foundation, Inc.
@@ -576,8 +576,8 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='xgboost'
 PACKAGE_TARNAME='xgboost'
-PACKAGE_VERSION='1.7.0'
-PACKAGE_STRING='xgboost 1.7.0'
+PACKAGE_VERSION='1.7.1'
+PACKAGE_STRING='xgboost 1.7.1'
 PACKAGE_BUGREPORT=''
 PACKAGE_URL=''
 
@@ -1195,7 +1195,7 @@ 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 1.7.0 to adapt to many kinds of systems.
+\`configure' configures xgboost 1.7.1 to adapt to many kinds of systems.
 
 Usage: $0 [OPTION]... [VAR=VALUE]...
 
@@ -1257,7 +1257,7 @@ fi
 
 if test -n "$ac_init_help"; then
   case $ac_init_help in
-     short | recursive ) echo "Configuration of xgboost 1.7.0:";;
+     short | recursive ) echo "Configuration of xgboost 1.7.1:";;
    esac
   cat <<\_ACEOF
 
@@ -1336,7 +1336,7 @@ fi
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
   cat <<\_ACEOF
-xgboost configure 1.7.0
+xgboost configure 1.7.1
 generated by GNU Autoconf 2.69
 
 Copyright (C) 2012 Free Software Foundation, Inc.
@@ -1479,7 +1479,7 @@ 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 1.7.0, which was
+It was created by xgboost $as_me 1.7.1, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   $ $0 $@
@@ -3294,7 +3294,7 @@ cat >>$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 1.7.0, which was
+This file was extended by xgboost $as_me 1.7.1, which was
 generated by GNU Autoconf 2.69.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -3347,7 +3347,7 @@ _ACEOF
 cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
 ac_cs_config="`$as_echo "$ac_configure_args" | sed 's/^ //; s/[\\""\`\$]/\\\\&/g'`"
 ac_cs_version="\\
-xgboost config.status 1.7.0
+xgboost config.status 1.7.1
 configured by $0, generated by GNU Autoconf 2.69,
   with options \\"\$ac_cs_config\\"
 

R-package/configure.ac

@@ -2,7 +2,7 @@
 
 AC_PREREQ(2.69)
 
-AC_INIT([xgboost],[1.7.0],[],[xgboost],[])
+AC_INIT([xgboost],[1.7.1],[],[xgboost],[])
 
 # Use this line to set CC variable to a C compiler
 AC_PROG_CC

jvm-packages/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>ml.dmlc</groupId>
     <artifactId>xgboost-jvm_2.12</artifactId>
-    <version>1.7.0</version>
+    <version>1.7.1</version>
     <packaging>pom</packaging>
     <name>XGBoost JVM Package</name>
     <description>JVM Package for XGBoost</description>

jvm-packages/xgboost4j-example/pom.xml

@@ -6,10 +6,10 @@
     <parent>
         <groupId>ml.dmlc</groupId>
         <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>1.7.0</version>
+        <version>1.7.1</version>
     </parent>
     <artifactId>xgboost4j-example_2.12</artifactId>
-    <version>1.7.0</version>
+    <version>1.7.1</version>
     <packaging>jar</packaging>
     <build>
         <plugins>
@@ -26,7 +26,7 @@
         <dependency>
             <groupId>ml.dmlc</groupId>
             <artifactId>xgboost4j-spark_${scala.binary.version}</artifactId>
-            <version>1.7.0</version>
+            <version>1.7.1</version>
         </dependency>
         <dependency>
             <groupId>org.apache.spark</groupId>
@@ -37,7 +37,7 @@
         <dependency>
             <groupId>ml.dmlc</groupId>
             <artifactId>xgboost4j-flink_${scala.binary.version}</artifactId>
-            <version>1.7.0</version>
+            <version>1.7.1</version>
         </dependency>
         <dependency>
             <groupId>org.apache.commons</groupId>

jvm-packages/xgboost4j-flink/pom.xml

@@ -6,10 +6,10 @@
     <parent>
         <groupId>ml.dmlc</groupId>
         <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>1.7.0</version>
+        <version>1.7.1</version>
     </parent>
     <artifactId>xgboost4j-flink_2.12</artifactId>
-    <version>1.7.0</version>
+    <version>1.7.1</version>
     <build>
         <plugins>
             <plugin>
@@ -26,7 +26,7 @@
         <dependency>
             <groupId>ml.dmlc</groupId>
             <artifactId>xgboost4j_${scala.binary.version}</artifactId>
-            <version>1.7.0</version>
+            <version>1.7.1</version>
         </dependency>
         <dependency>
             <groupId>org.apache.commons</groupId>

jvm-packages/xgboost4j-gpu/pom.xml

@@ -6,10 +6,10 @@
     <parent>
         <groupId>ml.dmlc</groupId>
         <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>1.7.0</version>
+        <version>1.7.1</version>
     </parent>
     <artifactId>xgboost4j-gpu_2.12</artifactId>
-    <version>1.7.0</version>
+    <version>1.7.1</version>
     <packaging>jar</packaging>
 
     <dependencies>

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

@@ -6,7 +6,7 @@
     <parent>
         <groupId>ml.dmlc</groupId>
         <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>1.7.0</version>
+        <version>1.7.1</version>
     </parent>
     <artifactId>xgboost4j-spark-gpu_2.12</artifactId>
     <build>
@@ -24,7 +24,7 @@
         <dependency>
             <groupId>ml.dmlc</groupId>
             <artifactId>xgboost4j-gpu_${scala.binary.version}</artifactId>
-            <version>1.7.0</version>
+            <version>1.7.1</version>
         </dependency>
         <dependency>
             <groupId>org.apache.spark</groupId>

jvm-packages/xgboost4j-spark/pom.xml

@@ -6,7 +6,7 @@
     <parent>
         <groupId>ml.dmlc</groupId>
         <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>1.7.0</version>
+        <version>1.7.1</version>
     </parent>
     <artifactId>xgboost4j-spark_2.12</artifactId>
     <build>
@@ -24,7 +24,7 @@
         <dependency>
             <groupId>ml.dmlc</groupId>
             <artifactId>xgboost4j_${scala.binary.version}</artifactId>
-            <version>1.7.0</version>
+            <version>1.7.1</version>
         </dependency>
         <dependency>
             <groupId>org.apache.spark</groupId>

jvm-packages/xgboost4j/pom.xml

@@ -6,10 +6,10 @@
     <parent>
         <groupId>ml.dmlc</groupId>
         <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>1.7.0</version>
+        <version>1.7.1</version>
     </parent>
     <artifactId>xgboost4j_2.12</artifactId>
-    <version>1.7.0</version>
+    <version>1.7.1</version>
     <packaging>jar</packaging>
 
     <dependencies>

python-package/xgboost/VERSION

@@ -1 +1 @@
-1.7.0
+1.7.1

python-package/xgboost/__init__.py

@@ -4,7 +4,7 @@ Contributors: https://github.com/dmlc/xgboost/blob/master/CONTRIBUTORS.md
 """
 
 from . import tracker  # noqa
-from . import collective, dask
+from . import collective, dask, rabit
 from .core import (
     Booster,
     DataIter,

python-package/xgboost/rabit.py

@@ -0,0 +1,168 @@
+"""Compatibility shim for xgboost.rabit; to be removed in 2.0"""
+import logging
+import warnings
+from enum import IntEnum, unique
+from typing import Any, TypeVar, Callable, Optional, List
+
+import numpy as np
+
+from . import collective
+
+LOGGER = logging.getLogger("[xgboost.rabit]")
+
+
+def _deprecation_warning() -> str:
+    return (
+        "The xgboost.rabit submodule is marked as deprecated in 1.7 and will be removed "
+        "in 2.0. Please use xgboost.collective instead."
+    )
+
+
+def init(args: Optional[List[bytes]] = None) -> None:
+    """Initialize the rabit library with arguments"""
+    warnings.warn(_deprecation_warning(), FutureWarning)
+    parsed = {}
+    if args:
+        for arg in args:
+            kv = arg.decode().split('=')
+            if len(kv) == 2:
+                parsed[kv[0]] = kv[1]
+    collective.init(**parsed)
+
+
+def finalize() -> None:
+    """Finalize the process, notify tracker everything is done."""
+    collective.finalize()
+
+
+def get_rank() -> int:
+    """Get rank of current process.
+    Returns
+    -------
+    rank : int
+        Rank of current process.
+    """
+    return collective.get_rank()
+
+
+def get_world_size() -> int:
+    """Get total number workers.
+    Returns
+    -------
+    n : int
+        Total number of process.
+    """
+    return collective.get_world_size()
+
+
+def is_distributed() -> int:
+    """If rabit is distributed."""
+    return collective.is_distributed()
+
+
+def tracker_print(msg: Any) -> None:
+    """Print message to the tracker.
+    This function can be used to communicate the information of
+    the progress to the tracker
+    Parameters
+    ----------
+    msg : str
+        The message to be printed to tracker.
+    """
+    collective.communicator_print(msg)
+
+
+def get_processor_name() -> bytes:
+    """Get the processor name.
+    Returns
+    -------
+    name : str
+        the name of processor(host)
+    """
+    return collective.get_processor_name().encode()
+
+
+T = TypeVar("T")  # pylint:disable=invalid-name
+
+
+def broadcast(data: T, root: int) -> T:
+    """Broadcast object from one node to all other nodes.
+    Parameters
+    ----------
+    data : any type that can be pickled
+        Input data, if current rank does not equal root, this can be None
+    root : int
+        Rank of the node to broadcast data from.
+    Returns
+    -------
+    object : int
+        the result of broadcast.
+    """
+    return collective.broadcast(data, root)
+
+
+@unique
+class Op(IntEnum):
+    """Supported operations for rabit."""
+    MAX = 0
+    MIN = 1
+    SUM = 2
+    OR = 3
+
+
+def allreduce(  # pylint:disable=invalid-name
+        data: np.ndarray, op: Op, prepare_fun: Optional[Callable[[np.ndarray], None]] = None
+) -> np.ndarray:
+    """Perform allreduce, return the result.
+    Parameters
+    ----------
+    data :
+        Input data.
+    op :
+        Reduction operators, can be MIN, MAX, SUM, BITOR
+    prepare_fun :
+        Lazy preprocessing function, if it is not None, prepare_fun(data)
+        will be called by the function before performing allreduce, to initialize the data
+        If the result of Allreduce can be recovered directly,
+        then prepare_fun will NOT be called
+    Returns
+    -------
+    result :
+        The result of allreduce, have same shape as data
+    Notes
+    -----
+    This function is not thread-safe.
+    """
+    if prepare_fun is None:
+        return collective.allreduce(data, collective.Op(op))
+    raise Exception("preprocessing function is no longer supported")
+
+
+def version_number() -> int:
+    """Returns version number of current stored model.
+    This means how many calls to CheckPoint we made so far.
+    Returns
+    -------
+    version : int
+        Version number of currently stored model
+    """
+    return 0
+
+
+class RabitContext:
+    """A context controlling rabit initialization and finalization."""
+
+    def __init__(self, args: List[bytes] = None) -> None:
+        if args is None:
+            args = []
+        self.args = args
+
+    def __enter__(self) -> None:
+        init(self.args)
+        assert is_distributed()
+        LOGGER.warning(_deprecation_warning())
+        LOGGER.debug("-------------- rabit say hello ------------------")
+
+    def __exit__(self, *args: List) -> None:
+        finalize()
+        LOGGER.debug("--------------- rabit say bye ------------------")

tests/python/test_collective.py

@@ -39,6 +39,37 @@ def test_rabit_communicator():
         assert worker.exitcode == 0
 
 
+# TODO(rongou): remove this once we remove the rabit api.
+def run_rabit_api_worker(rabit_env, world_size):
+    with xgb.rabit.RabitContext(rabit_env):
+        assert xgb.rabit.get_world_size() == world_size
+        assert xgb.rabit.is_distributed()
+        assert xgb.rabit.get_processor_name().decode() == socket.gethostname()
+        ret = xgb.rabit.broadcast('test1234', 0)
+        assert str(ret) == 'test1234'
+        ret = xgb.rabit.allreduce(np.asarray([1, 2, 3]), xgb.rabit.Op.SUM)
+        assert np.array_equal(ret, np.asarray([2, 4, 6]))
+
+
+# TODO(rongou): remove this once we remove the rabit api.
+def test_rabit_api():
+    world_size = 2
+    tracker = RabitTracker(host_ip='127.0.0.1', n_workers=world_size)
+    tracker.start(world_size)
+    rabit_env = []
+    for k, v in tracker.worker_envs().items():
+        rabit_env.append(f"{k}={v}".encode())
+    workers = []
+    for _ in range(world_size):
+        worker = multiprocessing.Process(target=run_rabit_api_worker,
+                                         args=(rabit_env, world_size))
+        workers.append(worker)
+        worker.start()
+    for worker in workers:
+        worker.join()
+        assert worker.exitcode == 0
+
+
 def run_federated_worker(port, world_size, rank):
     with xgb.collective.CommunicatorContext(xgboost_communicator='federated',
                                             federated_server_address=f'localhost:{port}',