Release patch release 1.3.1 (#6543)

Co-authored-by: Philip Hyunsu Cho <chohyu01@cs.washington.edu>

CMakeLists.txt

@@ -1,5 +1,5 @@
 cmake_minimum_required(VERSION 3.13)
-project(xgboost LANGUAGES CXX C VERSION 1.3.0)
+project(xgboost LANGUAGES CXX C VERSION 1.3.1)
 include(cmake/Utils.cmake)
 list(APPEND CMAKE_MODULE_PATH "${xgboost_SOURCE_DIR}/cmake/modules")
 cmake_policy(SET CMP0022 NEW)

Jenkinsfile

@@ -198,10 +198,10 @@ def BuildCUDA(args) {
     """
     if (args.cuda_version == ref_cuda_ver) {
       sh """
-      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} auditwheel repair --plat ${wheel_tag} python-package/dist/*.whl
+      ${dockerRun} auditwheel_x86_64 ${docker_binary} auditwheel repair --plat ${wheel_tag} python-package/dist/*.whl
       mv -v wheelhouse/*.whl python-package/dist/
       # Make sure that libgomp.so is vendored in the wheel
-      ${dockerRun} ${container_type} ${docker_binary} ${docker_args} bash -c "unzip -l python-package/dist/*.whl | grep libgomp  || exit -1"
+      ${dockerRun} auditwheel_x86_64 ${docker_binary} bash -c "unzip -l python-package/dist/*.whl | grep libgomp  || exit -1"
       """
     }
     echo 'Stashing Python wheel...'

R-package/DESCRIPTION

@@ -1,7 +1,7 @@
 Package: xgboost
 Type: Package
 Title: Extreme Gradient Boosting
-Version: 1.3.0.1
+Version: 1.3.1.1
 Date: 2020-08-28
 Authors@R: c(
   person("Tianqi", "Chen", role = c("aut"),

R-package/tests/helper_scripts/generate_models.R

@@ -2,7 +2,6 @@
 # of saved model files from XGBoost version 0.90 and 1.0.x.
 library(xgboost)
 library(Matrix)
-source('./generate_models_params.R')
 
 set.seed(0)
 metadata <- list(
@@ -53,11 +52,16 @@ generate_logistic_model <- function () {
   y <- sample(0:1, size = metadata$kRows, replace = TRUE)
   stopifnot(max(y) == 1, min(y) == 0)
 
+  objective <- c('binary:logistic', 'binary:logitraw')
+  name <- c('logit', 'logitraw')
+
+  for (i in seq_len(length(objective))) {
     data <- xgb.DMatrix(X, label = y, weight = w)
     params <- list(tree_method = 'hist', num_parallel_tree = metadata$kForests,
-                 max_depth = metadata$kMaxDepth, objective = 'binary:logistic')
+                   max_depth = metadata$kMaxDepth, objective = objective[i])
     booster <- xgb.train(params, data, nrounds = metadata$kRounds)
-  save_booster(booster, 'logit')
+    save_booster(booster, name[i])
+  }
 }
 
 generate_classification_model <- function () {

R-package/tests/testthat/test_model_compatibility.R

@@ -39,6 +39,10 @@ run_booster_check <- function (booster, name) {
     testthat::expect_equal(config$learner$learner_train_param$objective, 'multi:softmax')
     testthat::expect_equal(as.numeric(config$learner$learner_model_param$num_class),
                            metadata$kClasses)
+  } else if (name == 'logitraw') {
+    testthat::expect_equal(get_num_tree(booster), metadata$kForests * metadata$kRounds)
+    testthat::expect_equal(as.numeric(config$learner$learner_model_param$num_class), 0)
+    testthat::expect_equal(config$learner$learner_train_param$objective, 'binary:logitraw')
   } else if (name == 'logit') {
     testthat::expect_equal(get_num_tree(booster), metadata$kForests * metadata$kRounds)
     testthat::expect_equal(as.numeric(config$learner$learner_model_param$num_class), 0)

include/xgboost/version_config.h

@@ -6,6 +6,6 @@
 
 #define XGBOOST_VER_MAJOR 1
 #define XGBOOST_VER_MINOR 3
-#define XGBOOST_VER_PATCH 0
+#define XGBOOST_VER_PATCH 1
 
 #endif  // XGBOOST_VERSION_CONFIG_H_

jvm-packages/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>ml.dmlc</groupId>
     <artifactId>xgboost-jvm_2.12</artifactId>
-    <version>1.3.0</version>
+    <version>1.3.1</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>1.3.0</version>
+        <version>1.3.1</version>
     </parent>
     <artifactId>xgboost4j-example_2.12</artifactId>
-    <version>1.3.0</version>
+    <version>1.3.1</version>
     <packaging>jar</packaging>
     <build>
         <plugins>
@@ -26,7 +26,7 @@
         <dependency>
             <groupId>ml.dmlc</groupId>
             <artifactId>xgboost4j-spark_${scala.binary.version}</artifactId>
-            <version>1.3.0</version>
+            <version>1.3.1</version>
         </dependency>
         <dependency>
             <groupId>org.apache.spark</groupId>
@@ -37,7 +37,7 @@
         <dependency>
             <groupId>ml.dmlc</groupId>
             <artifactId>xgboost4j-flink_${scala.binary.version}</artifactId>
-            <version>1.3.0</version>
+            <version>1.3.1</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>1.3.0</version>
+        <version>1.3.1</version>
     </parent>
     <artifactId>xgboost4j-flink_2.12</artifactId>
-    <version>1.3.0</version>
+    <version>1.3.1</version>
     <build>
         <plugins>
             <plugin>
@@ -26,7 +26,7 @@
         <dependency>
             <groupId>ml.dmlc</groupId>
             <artifactId>xgboost4j_${scala.binary.version}</artifactId>
-            <version>1.3.0</version>
+            <version>1.3.1</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>1.3.0</version>
+        <version>1.3.1</version>
     </parent>
     <artifactId>xgboost4j-gpu_2.12</artifactId>
-    <version>1.3.0</version>
+    <version>1.3.1</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>1.3.0</version>
+        <version>1.3.1</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>1.3.0</version>
+            <version>1.3.1</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>1.3.0</version>
+        <version>1.3.1</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>1.3.0</version>
+            <version>1.3.1</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>1.3.0</version>
+        <version>1.3.1</version>
     </parent>
     <artifactId>xgboost4j_2.12</artifactId>
-    <version>1.3.0</version>
+    <version>1.3.1</version>
     <packaging>jar</packaging>
 
     <dependencies>

python-package/xgboost/VERSION

@@ -1 +1 @@
-1.3.0
+1.3.1

python-package/xgboost/callback.py

@@ -456,6 +456,7 @@ class LearningRateScheduler(TrainingCallback):
 
     def after_iteration(self, model, epoch, evals_log):
         model.set_param('learning_rate', self.learning_rates(epoch))
+        return False
 
 
 # pylint: disable=too-many-instance-attributes
@@ -565,7 +566,7 @@ class EarlyStopping(TrainingCallback):
     def after_training(self, model: Booster):
         try:
             if self.save_best:
-                model = model[: int(model.attr('best_iteration'))]
+                model = model[: int(model.attr('best_iteration')) + 1]
         except XGBoostError as e:
             raise XGBoostError('`save_best` is not applicable to current booster') from e
         return model
@@ -621,7 +622,7 @@ class EvaluationMonitor(TrainingCallback):
                     msg += self._fmt_metric(data, metric_name, score, stdv)
             msg += '\n'
 
-            if (epoch % self.period) != 0 or self.period == 1:
+            if (epoch % self.period) == 0 or self.period == 1:
                 rabit.tracker_print(msg)
                 self._latest = None
             else:
@@ -677,6 +678,7 @@ class TrainingCheckPoint(TrainingCallback):
                 else:
                     model.save_model(path)
         self._epoch += 1
+        return False
 
 
 class LegacyCallbacks:

python-package/xgboost/core.py

@@ -1,11 +1,12 @@
 # coding: utf-8
 # pylint: disable=too-many-arguments, too-many-branches, invalid-name
-# pylint: disable=too-many-lines, too-many-locals
+# pylint: disable=too-many-lines, too-many-locals, no-self-use
 """Core XGBoost Library."""
 import collections
 # pylint: disable=no-name-in-module,import-error
 from collections.abc import Mapping
 # pylint: enable=no-name-in-module,import-error
+from typing import Dict, Union, List
 import ctypes
 import os
 import re
@@ -1012,6 +1013,7 @@ class Booster(object):
         _check_call(_LIB.XGBoosterCreate(dmats, c_bst_ulong(len(cache)),
                                          ctypes.byref(self.handle)))
         params = params or {}
+        params = self._configure_metrics(params.copy())
         if isinstance(params, list):
             params.append(('validate_parameters', True))
         else:
@@ -1041,6 +1043,17 @@ class Booster(object):
         else:
             raise TypeError('Unknown type:', model_file)
 
+    def _configure_metrics(self, params: Union[Dict, List]) -> Union[Dict, List]:
+        if isinstance(params, dict) and 'eval_metric' in params \
+           and isinstance(params['eval_metric'], list):
+            params = dict((k, v) for k, v in params.items())
+            eval_metrics = params['eval_metric']
+            params.pop("eval_metric", None)
+            params = list(params.items())
+            for eval_metric in eval_metrics:
+                params += [('eval_metric', eval_metric)]
+        return params
+
     def __del__(self):
         if hasattr(self, 'handle') and self.handle is not None:
             _check_call(_LIB.XGBoosterFree(self.handle))

python-package/xgboost/sklearn.py

@@ -841,14 +841,18 @@ class XGBClassifier(XGBModel, XGBClassifierBase):
             self.classes_ = cp.unique(y.values)
             self.n_classes_ = len(self.classes_)
             can_use_label_encoder = False
-            if not cp.array_equal(self.classes_, cp.arange(self.n_classes_)):
+            expected_classes = cp.arange(self.n_classes_)
+            if (self.classes_.shape != expected_classes.shape or
+                    not (self.classes_ == expected_classes).all()):
                 raise ValueError(label_encoding_check_error)
         elif _is_cupy_array(y):
             import cupy as cp  # pylint: disable=E0401
             self.classes_ = cp.unique(y)
             self.n_classes_ = len(self.classes_)
             can_use_label_encoder = False
-            if not cp.array_equal(self.classes_, cp.arange(self.n_classes_)):
+            expected_classes = cp.arange(self.n_classes_)
+            if (self.classes_.shape != expected_classes.shape or
+                    not (self.classes_ == expected_classes).all()):
                 raise ValueError(label_encoding_check_error)
         else:
             self.classes_ = np.unique(y)

python-package/xgboost/training.py

@@ -40,18 +40,6 @@ def _is_new_callback(callbacks):
                for c in callbacks) or not callbacks
 
 
-def _configure_metrics(params):
-    if isinstance(params, dict) and 'eval_metric' in params \
-       and isinstance(params['eval_metric'], list):
-        params = dict((k, v) for k, v in params.items())
-        eval_metrics = params['eval_metric']
-        params.pop("eval_metric", None)
-        params = list(params.items())
-        for eval_metric in eval_metrics:
-            params += [('eval_metric', eval_metric)]
-    return params
-
-
 def _train_internal(params, dtrain,
                     num_boost_round=10, evals=(),
                     obj=None, feval=None,
@@ -61,7 +49,6 @@ def _train_internal(params, dtrain,
     """internal training function"""
     callbacks = [] if callbacks is None else copy.copy(callbacks)
     evals = list(evals)
-    params = _configure_metrics(params.copy())
 
     bst = Booster(params, [dtrain] + [d[0] for d in evals])
     nboost = 0

src/objective/regression_loss.h

@@ -162,6 +162,9 @@ struct LogisticRaw : public LogisticRegression {
     predt = common::Sigmoid(predt);
     return std::max(predt * (T(1.0f) - predt), eps);
   }
+  static bst_float ProbToMargin(bst_float base_score) {
+    return base_score;
+  }
   static const char* DefaultEvalMetric() { return "auc"; }
 
   static const char* Name() { return "binary:logitraw"; }

tests/ci_build/Dockerfile.auditwheel_x86_64

@@ -0,0 +1,15 @@
+FROM quay.io/pypa/manylinux2010_x86_64
+
+# Install lightweight sudo (not bound to TTY)
+ENV GOSU_VERSION 1.10
+RUN set -ex; \
+    curl -o /usr/local/bin/gosu -L "https://github.com/tianon/gosu/releases/download/$GOSU_VERSION/gosu-amd64" && \
+    chmod +x /usr/local/bin/gosu && \
+    gosu nobody true
+
+# Default entry-point to use if running locally
+# It will preserve attributes of created files
+COPY entrypoint.sh /scripts/
+
+WORKDIR /workspace
+ENTRYPOINT ["/scripts/entrypoint.sh"]

tests/python/generate_models.py

@@ -64,22 +64,24 @@ def generate_logistic_model():
     y = np.random.randint(0, 2, size=kRows)
     assert y.max() == 1 and y.min() == 0
 
+    for objective, name in [('binary:logistic', 'logit'), ('binary:logitraw', 'logitraw')]:
         data = xgboost.DMatrix(X, label=y, weight=w)
         booster = xgboost.train({'tree_method': 'hist',
                                  'num_parallel_tree': kForests,
                                  'max_depth': kMaxDepth,
-                             'objective': 'binary:logistic'},
+                                 'objective': objective},
                                 num_boost_round=kRounds, dtrain=data)
-    booster.save_model(booster_bin('logit'))
+        booster.save_model(booster_bin(name))
-    booster.save_model(booster_json('logit'))
+        booster.save_model(booster_json(name))
 
         reg = xgboost.XGBClassifier(tree_method='hist',
                                     num_parallel_tree=kForests,
                                     max_depth=kMaxDepth,
-                                n_estimators=kRounds)
+                                    n_estimators=kRounds,
+                                    objective=objective)
         reg.fit(X, y, w)
-    reg.save_model(skl_bin('logit'))
+        reg.save_model(skl_bin(name))
-    reg.save_model(skl_json('logit'))
+        reg.save_model(skl_json(name))
 
 
 def generate_classification_model():

tests/python/test_basic.py

@@ -57,6 +57,25 @@ class TestBasic:
             # assert they are the same
             assert np.sum(np.abs(preds2 - preds)) == 0
 
+    def test_metric_config(self):
+        # Make sure that the metric configuration happens in booster so the
+        # string `['error', 'auc']` doesn't get passed down to core.
+        dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')
+        dtest = xgb.DMatrix(dpath + 'agaricus.txt.test')
+        param = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
+                 'objective': 'binary:logistic', 'eval_metric': ['error', 'auc']}
+        watchlist = [(dtest, 'eval'), (dtrain, 'train')]
+        num_round = 2
+        booster = xgb.train(param, dtrain, num_round, watchlist)
+        predt_0 = booster.predict(dtrain)
+        with tempfile.TemporaryDirectory() as tmpdir:
+            path = os.path.join(tmpdir, 'model.json')
+            booster.save_model(path)
+
+            booster = xgb.Booster(params=param, model_file=path)
+            predt_1 = booster.predict(dtrain)
+            np.testing.assert_allclose(predt_0, predt_1)
+
     def test_record_results(self):
         dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')
         dtest = xgb.DMatrix(dpath + 'agaricus.txt.test')
@@ -124,8 +143,8 @@ class TestBasic:
 
         dump2 = bst.get_dump(with_stats=True)
         assert dump2[0].count('\n') == 3, 'Expected 1 root and 2 leaves - 3 lines in dump.'
-        assert (dump2[0].find('\n') > dump1[0].find('\n'),
+        msg = 'Expected more info when with_stats=True is given.'
-                'Expected more info when with_stats=True is given.')
+        assert dump2[0].find('\n') > dump1[0].find('\n'), msg
 
         dump3 = bst.get_dump(dump_format="json")
         dump3j = json.loads(dump3[0])
@@ -248,13 +267,11 @@ class TestBasicPathLike:
         assert binary_path.exists()
         Path.unlink(binary_path)
 
-
     def test_Booster_init_invalid_path(self):
         """An invalid model_file path should raise XGBoostError."""
         with pytest.raises(xgb.core.XGBoostError):
             xgb.Booster(model_file=Path("invalidpath"))
 
-
     def test_Booster_save_and_load(self):
         """Saving and loading model files from paths."""
         save_path = Path("saveload.model")

tests/python/test_callback.py

@@ -33,15 +33,18 @@ class TestCallbacks:
                       verbose_eval=verbose_eval)
             output: str = out.getvalue().strip()
 
-        pos = 0
+        if int(verbose_eval) == 1:
-        msg = 'Train-error'
+            # Should print each iteration info
-        for i in range(rounds // int(verbose_eval)):
+            assert len(output.split('\n')) == rounds
-            pos = output.find('Train-error', pos)
+        elif int(verbose_eval) > rounds:
-            assert pos != -1
+            # Should print first and latest iteration info
-            pos += len(msg)
+            assert len(output.split('\n')) == 2
-
+        else:
-        assert output.find('Train-error', pos) == -1
+            # Should print info by each period additionaly to first and latest iteration
-
+            num_periods = rounds // int(verbose_eval)
+            # Extra information is required for latest iteration
+            is_extra_info_required = num_periods * int(verbose_eval) < (rounds - 1) 
+            assert len(output.split('\n')) == 1 + num_periods + int(is_extra_info_required)
 
     def test_evaluation_monitor(self):
         D_train = xgb.DMatrix(self.X_train, self.y_train)
@@ -57,8 +60,10 @@ class TestCallbacks:
         assert len(evals_result['Train']['error']) == rounds
         assert len(evals_result['Valid']['error']) == rounds
 
-        self.run_evaluation_monitor(D_train, D_valid, rounds, 2)
         self.run_evaluation_monitor(D_train, D_valid, rounds, True)
+        self.run_evaluation_monitor(D_train, D_valid, rounds, 2)
+        self.run_evaluation_monitor(D_train, D_valid, rounds, 4)
+        self.run_evaluation_monitor(D_train, D_valid, rounds, rounds + 1)        
 
     def test_early_stopping(self):
         D_train = xgb.DMatrix(self.X_train, self.y_train)
@@ -148,7 +153,7 @@ class TestCallbacks:
                 eval_metric=tm.eval_error_metric, callbacks=[early_stop])
         booster = cls.get_booster()
         dump = booster.get_dump(dump_format='json')
-        assert len(dump) == booster.best_iteration
+        assert len(dump) == booster.best_iteration + 1
 
         early_stop = xgb.callback.EarlyStopping(rounds=early_stopping_rounds,
                                                 save_best=True)

tests/python/test_model_compatibility.py

@@ -24,6 +24,10 @@ def run_booster_check(booster, name):
             config['learner']['learner_model_param']['base_score']) == 0.5
         assert config['learner']['learner_train_param'][
             'objective'] == 'multi:softmax'
+    elif name.find('logitraw') != -1:
+        assert len(booster.get_dump()) == gm.kForests * gm.kRounds
+        assert config['learner']['learner_model_param']['num_class'] == str(0)
+        assert config['learner']['learner_train_param']['objective'] == 'binary:logitraw'
     elif name.find('logit') != -1:
         assert len(booster.get_dump()) == gm.kForests * gm.kRounds
         assert config['learner']['learner_model_param']['num_class'] == str(0)
@@ -77,6 +81,13 @@ def run_scikit_model_check(name, path):
         assert config['learner']['learner_train_param'][
             'objective'] == 'rank:ndcg'
         run_model_param_check(config)
+    elif name.find('logitraw') != -1:
+        logit = xgboost.XGBClassifier()
+        logit.load_model(path)
+        assert (len(logit.get_booster().get_dump()) ==
+                gm.kRounds * gm.kForests)
+        config = json.loads(logit.get_booster().save_config())
+        assert config['learner']['learner_train_param']['objective'] == 'binary:logitraw'
     elif name.find('logit') != -1:
         logit = xgboost.XGBClassifier()
         logit.load_model(path)