Bump release version to 1.3.3. (#6624)

The old (before fix) best_ntree_limit ignores the num_class parameters, which is incorrect. In before we workarounded it in c++ layer to avoid possible breaking changes on other language bindings. But the Python interpretation stayed incorrect. The PR fixed that in Python to consider num_class, but didn't remove the old workaround, so tree calculation in predictor is incorrect, see PredictBatch in CPUPredictor.

CMakeLists.txt

@@ -1,5 +1,5 @@
 cmake_minimum_required(VERSION 3.13)
-project(xgboost LANGUAGES CXX C VERSION 1.3.2)
+project(xgboost LANGUAGES CXX C VERSION 1.3.3)
 include(cmake/Utils.cmake)
 list(APPEND CMAKE_MODULE_PATH "${xgboost_SOURCE_DIR}/cmake/modules")
 cmake_policy(SET CMP0022 NEW)

R-package/DESCRIPTION

@@ -1,7 +1,7 @@
 Package: xgboost
 Type: Package
 Title: Extreme Gradient Boosting
-Version: 1.3.2.1
+Version: 1.3.3.1
 Date: 2020-08-28
 Authors@R: c(
   person("Tianqi", "Chen", role = c("aut"),

include/xgboost/version_config.h

@@ -6,6 +6,6 @@
 
 #define XGBOOST_VER_MAJOR 1
 #define XGBOOST_VER_MINOR 3
-#define XGBOOST_VER_PATCH 2
+#define XGBOOST_VER_PATCH 3
 
 #endif  // XGBOOST_VERSION_CONFIG_H_

jvm-packages/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>ml.dmlc</groupId>
     <artifactId>xgboost-jvm_2.12</artifactId>
-    <version>1.3.2</version>
+    <version>1.3.3</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>1.3.2</version>
+        <version>1.3.3</version>
     </parent>
     <artifactId>xgboost4j-example_2.12</artifactId>
-    <version>1.3.2</version>
+    <version>1.3.3</version>
     <packaging>jar</packaging>
     <build>
         <plugins>
@@ -26,7 +26,7 @@
         <dependency>
             <groupId>ml.dmlc</groupId>
             <artifactId>xgboost4j-spark_${scala.binary.version}</artifactId>
-            <version>1.3.2</version>
+            <version>1.3.3</version>
         </dependency>
         <dependency>
             <groupId>org.apache.spark</groupId>
@@ -37,7 +37,7 @@
         <dependency>
             <groupId>ml.dmlc</groupId>
             <artifactId>xgboost4j-flink_${scala.binary.version}</artifactId>
-            <version>1.3.2</version>
+            <version>1.3.3</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>1.3.2</version>
+        <version>1.3.3</version>
     </parent>
     <artifactId>xgboost4j-flink_2.12</artifactId>
-    <version>1.3.2</version>
+    <version>1.3.3</version>
     <build>
         <plugins>
             <plugin>
@@ -26,7 +26,7 @@
         <dependency>
             <groupId>ml.dmlc</groupId>
             <artifactId>xgboost4j_${scala.binary.version}</artifactId>
-            <version>1.3.2</version>
+            <version>1.3.3</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>1.3.2</version>
+        <version>1.3.3</version>
     </parent>
     <artifactId>xgboost4j-gpu_2.12</artifactId>
-    <version>1.3.2</version>
+    <version>1.3.3</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>1.3.2</version>
+        <version>1.3.3</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>1.3.2</version>
+            <version>1.3.3</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>1.3.2</version>
+        <version>1.3.3</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>1.3.2</version>
+            <version>1.3.3</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>1.3.2</version>
+        <version>1.3.3</version>
     </parent>
     <artifactId>xgboost4j_2.12</artifactId>
-    <version>1.3.2</version>
+    <version>1.3.3</version>
     <packaging>jar</packaging>
 
     <dependencies>

python-package/xgboost/VERSION

@@ -1 +1 @@
-1.3.2
+1.3.3

python-package/xgboost/training.py

@@ -142,9 +142,7 @@ def _train_internal(params, dtrain,
         )
     else:
         raise ValueError(f'Unknown booster: {booster}')
-    num_groups = int(config['learner']['learner_model_param']['num_class'])
+    bst.best_ntree_limit = (bst.best_iteration + 1) * num_parallel_tree
-    num_groups = 1 if num_groups == 0 else num_groups
-    bst.best_ntree_limit = (bst.best_iteration + 1) * num_parallel_tree * num_groups
 
     # Copy to serialise and unserialise booster to reset state and free
     # training memory
@@ -184,9 +182,10 @@ def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
         If there's more than one metric in the **eval_metric** parameter given in
         **params**, the last metric will be used for early stopping.
         If early stopping occurs, the model will have three additional fields:
-        ``bst.best_score``, ``bst.best_iteration`` and ``bst.best_ntree_limit``.
+        ``bst.best_score``, ``bst.best_iteration`` and ``bst.best_ntree_limit``.  Use
-        (Use ``bst.best_ntree_limit`` to get the correct value if
+        ``bst.best_ntree_limit`` to get the correct value if ``num_parallel_tree`` and/or
-        ``num_parallel_tree`` and/or ``num_class`` appears in the parameters)
+        ``num_class`` appears in the parameters.  ``best_ntree_limit`` is the result of
+        ``num_parallel_tree * best_iteration``.
     evals_result: dict
         This dictionary stores the evaluation results of all the items in watchlist.
 

src/gbm/gblinear_model.cc

@@ -10,10 +10,6 @@ namespace xgboost {
 namespace gbm {
 
 void GBLinearModel::SaveModel(Json* p_out) const {
-  using WeightType = std::remove_reference<decltype(std::declval<decltype(weight)>().back())>::type;
-  using JsonFloat = Number::Float;
-  static_assert(std::is_same<WeightType, JsonFloat>::value,
-                "Weight type should be of the same type with JSON float");
   auto& out = *p_out;
 
   size_t const n_weights = weight.size();

tests/python/test_predict.py

@@ -33,9 +33,15 @@ def run_predict_leaf(predictor):
     y = rng.randint(low=0, high=classes, size=rows)
     m = xgb.DMatrix(X, y)
     booster = xgb.train(
-        {'num_parallel_tree': num_parallel_tree, 'num_class': classes,
+        {
-         'predictor': predictor, 'tree_method': 'hist'}, m,
+            "num_parallel_tree": num_parallel_tree,
-        num_boost_round=num_boost_round)
+            "num_class": classes,
+            "predictor": predictor,
+            "tree_method": "hist",
+        },
+        m,
+        num_boost_round=num_boost_round,
+    )
 
     empty = xgb.DMatrix(np.ones(shape=(0, cols)))
     empty_leaf = booster.predict(empty, pred_leaf=True)
@@ -52,12 +58,19 @@ def run_predict_leaf(predictor):
             end = classes * num_parallel_tree * (j + 1)
             layer = row[start: end]
             for c in range(classes):
-                tree_group = layer[c * num_parallel_tree:
+                tree_group = layer[c * num_parallel_tree: (c + 1) * num_parallel_tree]
-                                   (c+1) * num_parallel_tree]
                 assert tree_group.shape[0] == num_parallel_tree
                 # no subsampling so tree in same forest should output same
                 # leaf.
                 assert np.all(tree_group == tree_group[0])
+
+    ntree_limit = 2
+    sliced = booster.predict(
+        m, pred_leaf=True, ntree_limit=num_parallel_tree * ntree_limit
+    )
+    first = sliced[0, ...]
+
+    assert first.shape[0] == classes * num_parallel_tree * ntree_limit
     return leaf
 
 

tests/python/test_training_continuation.py

@@ -123,13 +123,13 @@ class TestTrainingContinuation:
         gbdt_05 = xgb.train(xgb_params_03, dtrain_5class,
                             num_boost_round=7)
         assert gbdt_05.best_ntree_limit == (
-            gbdt_05.best_iteration + 1) * self.num_parallel_tree * 5
+            gbdt_05.best_iteration + 1) * self.num_parallel_tree
         gbdt_05 = xgb.train(xgb_params_03,
                             dtrain_5class,
                             num_boost_round=3,
                             xgb_model=gbdt_05)
         assert gbdt_05.best_ntree_limit == (
-            gbdt_05.best_iteration + 1) * self.num_parallel_tree * 5
+            gbdt_05.best_iteration + 1) * self.num_parallel_tree
 
         res1 = gbdt_05.predict(dtrain_5class)
         res2 = gbdt_05.predict(dtrain_5class,

tests/python/test_with_sklearn.py

@@ -92,7 +92,7 @@ def test_best_ntree_limit():
         )
 
         if forest:
-            assert cls.best_ntree_limit == rounds * forest * cls.n_classes_
+            assert cls.best_ntree_limit == rounds * forest
         else:
             assert cls.best_ntree_limit == 0