[jvm-packages] [CI] Publish XGBoost4J JARs with Scala 2.11 and 2.12

* Avoid importing datatable.
* Fix #5363.

CMakeLists.txt

@@ -1,5 +1,5 @@
 cmake_minimum_required(VERSION 3.12)
-project(xgboost LANGUAGES CXX C VERSION 1.0.1)
+project(xgboost LANGUAGES CXX C VERSION 1.0.2)
 include(cmake/Utils.cmake)
 list(APPEND CMAKE_MODULE_PATH "${xgboost_SOURCE_DIR}/cmake/modules")
 cmake_policy(SET CMP0022 NEW)

Jenkinsfile

@@ -95,6 +95,17 @@ pipeline {
         milestone ordinal: 4
       }
     }
+    stage('Jenkins Linux: Deploy') {
+      agent none
+      steps {
+        script {
+          parallel ([
+            'deploy-jvm-packages': { DeployJVMPackages(spark_version: '2.4.3') }
+          ])
+        }
+        milestone ordinal: 5
+      }
+    }
   }
 }
 
@@ -380,3 +391,18 @@ def TestR(args) {
     deleteDir()
   }
 }
+
+def DeployJVMPackages(args) {
+  node('linux && cpu') {
+    unstash name: 'srcs'
+    if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
+      echo 'Deploying to xgboost-maven-repo S3 repo...'
+      def container_type = "jvm"
+      def docker_binary = "docker"
+      sh """
+      ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/deploy_jvm_packages.sh ${args.spark_version}
+      """
+    }
+    deleteDir()
+  }
+}

R-package/tests/testthat/test_helpers.R

@@ -7,8 +7,8 @@ require(vcd, quietly = TRUE)
 
 float_tolerance = 5e-6
 
-# disable some tests for Win32
-win32_flag = .Platform$OS.type == "windows" && .Machine$sizeof.pointer != 8
+# disable some tests for 32-bit environment
+flag_32bit = .Machine$sizeof.pointer != 8
 
 set.seed(1982)
 data(Arthritis)
@@ -44,7 +44,7 @@ mbst.GLM <- xgboost(data = as.matrix(iris[, -5]), label = mlabel, verbose = 0,
 
 
 test_that("xgb.dump works", {
-  if (!win32_flag)
+  if (!flag_32bit)
     expect_length(xgb.dump(bst.Tree), 200)
   dump_file = file.path(tempdir(), 'xgb.model.dump')
   expect_true(xgb.dump(bst.Tree, dump_file, with_stats = T))
@@ -54,7 +54,7 @@ test_that("xgb.dump works", {
   # JSON format
   dmp <- xgb.dump(bst.Tree, dump_format = "json")
   expect_length(dmp, 1)
-  if (!win32_flag)
+  if (!flag_32bit)
     expect_length(grep('nodeid', strsplit(dmp, '\n')[[1]]), 188)
 })
 
@@ -256,7 +256,7 @@ 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))
-  if (!win32_flag)
+  if (!flag_32bit)
     expect_equal(dim(dt.tree), c(188, 10))
   expect_output(str(dt.tree), 'Feature.*\\"Age\\"')
 
@@ -283,7 +283,7 @@ 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)
-  if (!win32_flag)
+  if (!flag_32bit)
     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\\"')

doc/jvm/index.rst

@@ -8,15 +8,143 @@ XGBoost JVM Package
   <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">
+  <img alt="GitHub license" src="https://dmlc.github.io/img/apache2.svg">
   </a>
 
 You have found the XGBoost JVM Package!
 
+.. _install_jvm_packages:
+
 ************
 Installation
 ************
 
+.. contents::
+  :local:
+  :backlinks: none
+
+Installation from Maven repository
+==================================
+
+Access release version
+----------------------
+You can use XGBoost4J in your Java/Scala application by adding XGBoost4J as a dependency:
+
+.. code-block:: xml
+  :caption: Maven
+
+  <properties>
+    ...
+    <!-- Specify Scala version in package name -->
+    <scala.binary.version>2.12</scala.binary.version>
+  </properties>
+
+  <dependencies>
+    ...
+    <dependency>
+        <groupId>ml.dmlc</groupId>
+        <artifactId>xgboost4j_${scala.binary.version}</artifactId>
+        <version>latest_version_num</version>
+    </dependency>
+    <dependency>
+        <groupId>ml.dmlc</groupId>
+        <artifactId>xgboost4j-spark_${scala.binary.version}</artifactId>
+        <version>latest_version_num</version>
+    </dependency>
+  </dependencies>
+
+.. code-block:: scala
+  :caption: sbt
+
+  libraryDependencies ++= Seq(
+    "ml.dmlc" %% "xgboost4j" % "latest_version_num",
+    "ml.dmlc" %% "xgboost4j-spark" % "latest_version_num"
+  )
+
+This will check out the latest stable version from the Maven Central.
+
+For the latest release version number, please check `here <https://github.com/dmlc/xgboost/releases>`_.
+
+.. note:: Using Maven repository hosted by the XGBoost project
+
+  There may be some delay until a new release becomes available to Maven Central. If you would like to access the latest release immediately, add the Maven repository hosted by the XGBoost project:
+
+  .. code-block:: xml
+    :caption: Maven
+
+    <repository>
+      <id>XGBoost4J Release Repo</id>
+      <name>XGBoost4J Release Repo</name>
+      <url>https://s3-us-west-2.amazonaws.com/xgboost-maven-repo/release/</url>
+    </repository>
+
+  .. code-block:: scala
+    :caption: sbt
+
+    resolvers += "XGBoost4J Release Repo" at "https://s3-us-west-2.amazonaws.com/xgboost-maven-repo/release/"
+
+Access SNAPSHOT version
+-----------------------
+
+First add the following Maven repository hosted by the XGBoost project:
+
+.. code-block:: xml
+  :caption: Maven
+
+  <repository>
+    <id>XGBoost4J Snapshot Repo</id>
+    <name>XGBoost4J Snapshot Repo</name>
+    <url>https://s3-us-west-2.amazonaws.com/xgboost-maven-repo/snapshot/</url>
+  </repository>
+
+.. code-block:: scala
+  :caption: sbt
+
+  resolvers += "XGBoost4J Snapshot Repo" at "https://s3-us-west-2.amazonaws.com/xgboost-maven-repo/snapshot/"
+
+Then add XGBoost4J as a dependency:
+
+.. code-block:: xml
+  :caption: maven
+
+  <properties>
+    ...
+    <!-- Specify Scala version in package name -->
+    <scala.binary.version>2.12</scala.binary.version>
+  </properties>
+
+  <dependencies>
+    ...
+    <dependency>
+        <groupId>ml.dmlc</groupId>
+        <artifactId>xgboost4j_${scala.binary.version}</artifactId>
+        <version>latest_version_num-SNAPSHOT</version>
+    </dependency>
+    <dependency>
+        <groupId>ml.dmlc</groupId>
+        <artifactId>xgboost4j-spark_${scala.binary.version}</artifactId>
+        <version>latest_version_num-SNAPSHOT</version>
+    </dependency>
+  </dependencies>
+
+.. code-block:: scala
+  :caption: sbt
+
+  libraryDependencies ++= Seq(
+    "ml.dmlc" %% "xgboost4j" % "latest_version_num-SNAPSHOT",
+    "ml.dmlc" %% "xgboost4j-spark" % "latest_version_num-SNAPSHOT"
+  )
+
+Look up the ``version`` field in `pom.xml <https://github.com/dmlc/xgboost/blob/master/jvm-packages/pom.xml>`_ to get the correct version number.
+
+The SNAPSHOT JARs are hosted by the XGBoost project. Every commit in the ``master`` branch will automatically trigger generation of a new SNAPSHOT JAR. You can control how often Maven should upgrade your SNAPSHOT installation by specifying ``updatePolicy``. See `here <http://maven.apache.org/pom.html#Repositories>`_ for details.
+
+You can browse the file listing of the Maven repository at https://s3-us-west-2.amazonaws.com/xgboost-maven-repo/list.html.
+
+.. 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>`_.
+
 Installation from source
 ========================
 
@@ -64,73 +192,6 @@ If you want to use XGBoost4J-Spark, replace ``xgboost4j`` with ``xgboost4j-spark
 
   Also, make sure to install Spark directly from `Apache website <https://spark.apache.org/>`_. **Upstream XGBoost is not guaranteed to work with third-party distributions of Spark, such as Cloudera Spark.** Consult appropriate third parties to obtain their distribution of XGBoost.
 
-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

doc/jvm/xgboost4j_spark_tutorial.rst

@@ -27,39 +27,7 @@ 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-spark</artifactId>
-      <version>next_version_num-SNAPSHOT</version>
-  </dependency>
+Before we go into the tour of how to use XGBoost4J-Spark, you should first consult :ref:`Installation from Maven repository <install_jvm_packages>` in order to add XGBoost4J-Spark as a dependency for your project. We provide both stable releases and snapshots.
 
 .. note:: XGBoost4J-Spark requires Apache Spark 2.4+
 

jvm-packages/pom.xml

@@ -205,6 +205,29 @@
                 </plugins>
             </build>
         </profile>
+        <profile>
+            <id>release-to-s3</id>
+            <distributionManagement>
+                <snapshotRepository>
+                    <id>maven-s3-snapshot-repo</id>
+                    <url>s3://xgboost-maven-repo/snapshot</url>
+                </snapshotRepository>
+                <repository>
+                    <id>maven-s3-release-repo</id>
+                    <url>s3://xgboost-maven-repo/release</url>
+                </repository>
+            </distributionManagement>
+            <repositories>
+                <repository>
+                    <id>maven-s3-snapshot-repo</id>
+                    <url>https://s3.amazonaws.com/xgboost-maven-repo/snapshot</url>
+                </repository>
+                <repository>
+                    <id>maven-s3-release-repo</id>
+                    <url>https://s3.amazonaws.com/xgboost-maven-repo/release</url>
+                </repository>
+            </repositories>
+        </profile>
     </profiles>
     <distributionManagement>
         <snapshotRepository>
@@ -324,6 +347,13 @@
                 </executions>
             </plugin>
         </plugins>
+        <extensions>
+            <extension>
+                <groupId>org.kuali.maven.wagons</groupId>
+                <artifactId>maven-s3-wagon</artifactId>
+                <version>1.2.1</version>
+            </extension>
+        </extensions>
     </build>
     <reporting>
         <plugins>

python-package/xgboost/VERSION

@@ -1 +1 @@
-1.0.1
+1.0.2

python-package/xgboost/compat.py

@@ -79,6 +79,14 @@ else:
 # END NUMPY PATHLIB ATTRIBUTION
 ###############################################################################
 
+
+def lazy_isinstance(instance, module, name):
+    '''Use string representation to identify a type.'''
+    module = type(instance).__module__ == module
+    name = type(instance).__name__ == name
+    return module and name
+
+
 # pandas
 try:
     from pandas import DataFrame, Series
@@ -95,27 +103,6 @@ except ImportError:
     pandas_concat = None
     PANDAS_INSTALLED = False
 
-# dt
-try:
-    # Workaround for #4473, compatibility with dask
-    if sys.__stdin__ is not None and sys.__stdin__.closed:
-        sys.__stdin__ = None
-    import datatable
-
-    if hasattr(datatable, "Frame"):
-        DataTable = datatable.Frame
-    else:
-        DataTable = datatable.DataTable
-    DT_INSTALLED = True
-except ImportError:
-
-    # pylint: disable=too-few-public-methods
-    class DataTable(object):
-        """ dummy for datatable.DataTable """
-
-    DT_INSTALLED = False
-
-
 # cudf
 try:
     from cudf import DataFrame as CUDF_DataFrame

python-package/xgboost/core.py

@@ -19,9 +19,9 @@ import scipy.sparse
 
 from .compat import (
     STRING_TYPES, DataFrame, MultiIndex, Int64Index, py_str,
-    PANDAS_INSTALLED, DataTable,
-    CUDF_INSTALLED, CUDF_DataFrame, CUDF_Series, CUDF_MultiIndex,
-    os_fspath, os_PathLike)
+    PANDAS_INSTALLED, CUDF_INSTALLED,
+    CUDF_DataFrame, CUDF_Series, CUDF_MultiIndex,
+    os_fspath, os_PathLike, lazy_isinstance)
 from .libpath import find_lib_path
 
 # c_bst_ulong corresponds to bst_ulong defined in xgboost/c_api.h
@@ -319,7 +319,8 @@ DT_TYPE_MAPPER2 = {'bool': 'i', 'int': 'int', 'real': 'float'}
 def _maybe_dt_data(data, feature_names, feature_types,
                    meta=None, meta_type=None):
     """Validate feature names and types if data table"""
-    if not isinstance(data, DataTable):
+    if (not lazy_isinstance(data, 'datatable', 'Frame') and
+            not lazy_isinstance(data, 'datatable', 'DataTable')):
         return data, feature_names, feature_types
 
     if meta and data.shape[1] > 1:
@@ -470,7 +471,7 @@ class DMatrix(object):
             self._init_from_csc(data)
         elif isinstance(data, np.ndarray):
             self._init_from_npy2d(data, missing, nthread)
-        elif isinstance(data, DataTable):
+        elif lazy_isinstance(data, 'datatable', 'Frame'):
             self._init_from_dt(data, nthread)
         elif hasattr(data, "__cuda_array_interface__"):
             self._init_from_array_interface(data, missing, nthread)
@@ -1052,7 +1053,7 @@ class Booster(object):
             _check_call(
                 _LIB.XGBoosterUnserializeFromBuffer(self.handle, ptr, length))
             self.__dict__.update(state)
-        elif isinstance(model_file, (STRING_TYPES, os_PathLike)):
+        elif isinstance(model_file, (STRING_TYPES, os_PathLike, bytearray)):
             self.load_model(model_file)
         elif model_file is None:
             pass
@@ -1512,7 +1513,8 @@ class Booster(object):
         return ctypes2buffer(cptr, length.value)
 
     def load_model(self, fname):
-        """Load the model from a file, local or as URI.
+        """Load the model from a file or bytearray. Path to file can be local
+        or as an URI.
 
         The model is loaded from an XGBoost format which is universal among the
         various XGBoost interfaces. Auxiliary attributes of the Python Booster
@@ -1530,6 +1532,12 @@ class Booster(object):
             # from URL.
             _check_call(_LIB.XGBoosterLoadModel(
                 self.handle, c_str(os_fspath(fname))))
+        elif isinstance(fname, bytearray):
+            buf = fname
+            length = c_bst_ulong(len(buf))
+            ptr = (ctypes.c_char * len(buf)).from_buffer(buf)
+            _check_call(_LIB.XGBoosterLoadModelFromBuffer(self.handle, ptr,
+                                                          length))
         else:
             raise TypeError('Unknown file type: ', fname)
 

python-package/xgboost/training.py

@@ -38,7 +38,7 @@ def _train_internal(params, dtrain,
 
     _params = dict(params) if isinstance(params, list) else params
 
-    if 'num_parallel_tree' in _params and params[
+    if 'num_parallel_tree' in _params and _params[
             'num_parallel_tree'] is not None:
         num_parallel_tree = _params['num_parallel_tree']
         nboost //= num_parallel_tree

src/common/hist_util.cc

@@ -663,7 +663,11 @@ void GHistIndexBlockMatrix::Init(const GHistIndexMatrix& gmat,
  * \brief fill a histogram by zeroes
  */
 void InitilizeHistByZeroes(GHistRow hist, size_t begin, size_t end) {
+#if defined(XGBOOST_STRICT_R_MODE) && XGBOOST_STRICT_R_MODE == 1
+  std::fill(hist.begin() + begin, hist.begin() + end, tree::GradStats());
+#else  // defined(XGBOOST_STRICT_R_MODE) && XGBOOST_STRICT_R_MODE == 1
   memset(hist.data() + begin, '\0', (end-begin)*sizeof(tree::GradStats));
+#endif  // defined(XGBOOST_STRICT_R_MODE) && XGBOOST_STRICT_R_MODE == 1
 }
 
 /*!

src/common/io.cc

@@ -117,14 +117,16 @@ std::string LoadSequentialFile(std::string fname) {
   size_t f_size_bytes = fs.st_size;
   buffer.resize(f_size_bytes + 1);
   int32_t fd = open(fname.c_str(), O_RDONLY);
+#if defined(__linux__)
   posix_fadvise(fd, 0, 0, POSIX_FADV_SEQUENTIAL);
+#endif  // defined(__linux__)
   ssize_t bytes_read = read(fd, &buffer[0], f_size_bytes);
   if (bytes_read < 0) {
     close(fd);
     ReadErr();
   }
   close(fd);
-#else
+#else  // defined(__unix__)
   FILE *f = fopen(fname.c_str(), "r");
   if (f == NULL) {
     std::string msg;

src/common/observer.h

@@ -15,15 +15,15 @@
 #include "xgboost/base.h"
 #include "xgboost/tree_model.h"
 
-#if defined(XGBOOST_STRICT_R_MODE)
+#if defined(XGBOOST_STRICT_R_MODE) && XGBOOST_STRICT_R_MODE == 1
 #define OBSERVER_PRINT LOG(INFO)
 #define OBSERVER_ENDL ""
 #define OBSERVER_NEWLINE ""
-#else
+#else  // defined(XGBOOST_STRICT_R_MODE) && XGBOOST_STRICT_R_MODE == 1
 #define OBSERVER_PRINT std::cout
 #define OBSERVER_ENDL std::endl
 #define OBSERVER_NEWLINE "\n"
-#endif  // defined(XGBOOST_STRICT_R_MODE)
+#endif  // defined(XGBOOST_STRICT_R_MODE) && XGBOOST_STRICT_R_MODE == 1
 
 namespace xgboost {
 /*\brief  An observer for logging internal data structures.

tests/ci_build/deploy_jvm_packages.sh

@@ -0,0 +1,35 @@
+#!/bin/bash
+
+set -e
+set -x
+
+if [ $# -ne 1 ]; then
+  echo "Usage: $0 [spark version]"
+  exit 1
+fi
+
+spark_version=$1
+
+# Initialize local Maven repository
+./tests/ci_build/initialize_maven.sh
+
+rm -rf build/
+cd jvm-packages
+
+# Re-build package without Mock Rabit
+# Deploy to S3 bucket xgboost-maven-repo
+mvn --no-transfer-progress package deploy -P release-to-s3 -Dspark.version=${spark_version} -DskipTests
+
+# Compile XGBoost4J with Scala 2.11 too
+mvn clean
+# Rename artifactId of all XGBoost4J packages with suffix _2.11
+sed -i -e 's/<artifactId>xgboost\(.*\)_[0-9\.]\+/<artifactId>xgboost\1_2.11/' $(find . -name pom.xml)
+# Modify scala.version and scala.binary.version fields
+sed -i -e 's/<scala\.version>[0-9\.]\+/<scala.version>2.11.12/' $(find . -name pom.xml)
+sed -i -e 's/<scala\.binary\.version>[0-9\.]\+/<scala.binary.version>2.11/' $(find . -name pom.xml)
+
+# Re-build and deploy
+mvn --no-transfer-progress package deploy -P release-to-s3 -Dspark.version=${spark_version} -DskipTests
+
+set +x
+set +e

tests/python/test_basic.py

@@ -35,6 +35,11 @@ def captured_output():
 
 
 class TestBasic(unittest.TestCase):
+    def test_compat(self):
+        from xgboost.compat import lazy_isinstance
+        a = np.array([1, 2, 3])
+        assert lazy_isinstance(a, 'numpy', 'ndarray')
+        assert not lazy_isinstance(a, 'numpy', 'dataframe')
 
     def test_basic(self):
         dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')

tests/python/test_basic_models.py

@@ -300,6 +300,13 @@ class TestModels(unittest.TestCase):
         assert float(config['learner']['objective'][
             'reg_loss_param']['scale_pos_weight']) == 0.5
 
+        buf = bst.save_raw()
+        from_raw = xgb.Booster()
+        from_raw.load_model(buf)
+
+        buf_from_raw = from_raw.save_raw()
+        assert buf == buf_from_raw
+
     def test_model_json_io(self):
         loc = locale.getpreferredencoding(False)
         model_path = 'test_model_json_io.json'

tests/python/test_with_sklearn.py

@@ -34,7 +34,8 @@ def test_binary_classification():
     kf = KFold(n_splits=2, shuffle=True, random_state=rng)
     for cls in (xgb.XGBClassifier, xgb.XGBRFClassifier):
         for train_index, test_index in kf.split(X, y):
-            xgb_model = cls(random_state=42).fit(X[train_index], y[train_index])
+            clf = cls(random_state=42)
+            xgb_model = clf.fit(X[train_index], y[train_index], eval_metric=['auc', 'logloss'])
             preds = xgb_model.predict(X[test_index])
             labels = y[test_index]
             err = sum(1 for i in range(len(preds))

tests/python/testing.py

@@ -1,5 +1,5 @@
 # coding: utf-8
-from xgboost.compat import SKLEARN_INSTALLED, PANDAS_INSTALLED, DT_INSTALLED
+from xgboost.compat import SKLEARN_INSTALLED, PANDAS_INSTALLED
 from xgboost.compat import CUDF_INSTALLED, DASK_INSTALLED
 
 
@@ -19,7 +19,9 @@ def no_pandas():
 
 
 def no_dt():
-    return {'condition': not DT_INSTALLED,
+    import importlib.util
+    spec = importlib.util.find_spec('datatable')
+    return {'condition': spec is None,
             'reason': 'Datatable is not installed.'}