Merge branch 'master' into rocm3

src/treelearner/serial_tree_learner.h

@@ -2,8 +2,8 @@
  * Copyright (c) 2016 Microsoft Corporation. All rights reserved.
  * Licensed under the MIT License. See LICENSE file in the project root for license information.
  */
-#ifndef LIGHTGBM_TREELEARNER_SERIAL_TREE_LEARNER_H_
-#define LIGHTGBM_TREELEARNER_SERIAL_TREE_LEARNER_H_
+#ifndef LIGHTGBM_SRC_TREELEARNER_SERIAL_TREE_LEARNER_H_
+#define LIGHTGBM_SRC_TREELEARNER_SERIAL_TREE_LEARNER_H_
 
 #include <LightGBM/dataset.h>
 #include <LightGBM/tree.h>
@@ -247,4 +247,4 @@ inline data_size_t SerialTreeLearner::GetGlobalDataCountInLeaf(int leaf_idx) con
 }
 
 }  // namespace LightGBM
-#endif   // LightGBM_TREELEARNER_SERIAL_TREE_LEARNER_H_
+#endif   // LIGHTGBM_SRC_TREELEARNER_SERIAL_TREE_LEARNER_H_

src/treelearner/split_info.hpp

@@ -2,8 +2,8 @@
  * Copyright (c) 2016 Microsoft Corporation. All rights reserved.
  * Licensed under the MIT License. See LICENSE file in the project root for license information.
  */
-#ifndef LIGHTGBM_TREELEARNER_SPLIT_INFO_HPP_
-#define LIGHTGBM_TREELEARNER_SPLIT_INFO_HPP_
+#ifndef LIGHTGBM_SRC_TREELEARNER_SPLIT_INFO_HPP_
+#define LIGHTGBM_SRC_TREELEARNER_SPLIT_INFO_HPP_
 
 #include <LightGBM/meta.h>
 
@@ -291,4 +291,4 @@ struct LightSplitInfo {
 };
 
 }  // namespace LightGBM
-#endif   // LightGBM_TREELEARNER_SPLIT_INFO_HPP_
+#endif   // LIGHTGBM_SRC_TREELEARNER_SPLIT_INFO_HPP_

src/treelearner/tree_learner.cpp

@@ -4,6 +4,8 @@
  */
 #include <LightGBM/tree_learner.h>
 
+#include <string>
+
 #include "gpu_tree_learner.h"
 #include "linear_tree_learner.h"
 #include "parallel_tree_learner.h"

src/treelearner/voting_parallel_tree_learner.cpp

@@ -4,7 +4,9 @@
  */
 #include <LightGBM/utils/common.h>
 
+#include <algorithm>
 #include <cstring>
+#include <functional>
 #include <tuple>
 #include <vector>
 
@@ -13,8 +15,7 @@
 namespace LightGBM {
 
 template <typename TREELEARNER_T>
-VotingParallelTreeLearner<TREELEARNER_T>::VotingParallelTreeLearner(const Config* config)
-  :TREELEARNER_T(config) {
+VotingParallelTreeLearner<TREELEARNER_T>::VotingParallelTreeLearner(const Config* config):TREELEARNER_T(config) {
   top_k_ = this->config_->top_k;
 }
 

swig/StringArray.hpp

@@ -4,8 +4,8 @@
  *
  * Author: Alberto Ferreira
  */
-#ifndef LIGHTGBM_SWIG_STRING_ARRAY_H_
-#define LIGHTGBM_SWIG_STRING_ARRAY_H_
+#ifndef LIGHTGBM_SWIG_STRINGARRAY_HPP_
+#define LIGHTGBM_SWIG_STRINGARRAY_HPP_
 
 #include <algorithm>
 #include <new>
@@ -137,4 +137,4 @@ class StringArray {
     std::vector<char*> _array;
 };
 
-#endif  // LIGHTGBM_SWIG_STRING_ARRAY_H_
+#endif  // LIGHTGBM_SWIG_STRINGARRAY_HPP_

tests/cpp_tests/test_array_args.cpp

@@ -8,6 +8,7 @@
 #include <LightGBM/utils/array_args.h>
 
 #include <random>
+#include <vector>
 
 using LightGBM::data_size_t;
 using LightGBM::score_t;

tests/cpp_tests/test_arrow.cpp

@@ -10,6 +10,7 @@
 
 #include <cmath>
 #include <cstdlib>
+#include <vector>
 
 using LightGBM::ArrowChunkedArray;
 using LightGBM::ArrowTable;

tests/cpp_tests/test_byte_buffer.cpp

@@ -6,6 +6,7 @@
 #include <gtest/gtest.h>
 #include <LightGBM/utils/byte_buffer.h>
 
+#include <memory>
 #include <random>
 
 using LightGBM::ByteBuffer;

tests/cpp_tests/test_chunked_array.cpp

@@ -5,6 +5,9 @@
  * Author: Alberto Ferreira
  */
 #include <gtest/gtest.h>
+
+#include <vector>
+
 #include "../include/LightGBM/utils/chunked_array.hpp"
 
 using LightGBM::ChunkedArray;

tests/cpp_tests/test_serialize.cpp

@@ -11,6 +11,7 @@
 #include <LightGBM/dataset.h>
 
 #include <iostream>
+#include <string>
 
 using LightGBM::ByteBuffer;
 using LightGBM::Dataset;

tests/cpp_tests/test_single_row.cpp

@@ -7,8 +7,10 @@
 #include <testutils.h>
 #include <LightGBM/c_api.h>
 
-#include <iostream>
+#include <algorithm>
 #include <fstream>
+#include <iostream>
+#include <vector>
 
 using LightGBM::TestUtils;
 

tests/cpp_tests/test_stream.cpp

@@ -10,6 +10,8 @@
 #include <LightGBM/dataset.h>
 
 #include <iostream>
+#include <string>
+#include <vector>
 
 using LightGBM::Dataset;
 using LightGBM::Log;

tests/cpp_tests/testutils.cpp

@@ -3,24 +3,25 @@
  * Licensed under the MIT License. See LICENSE file in the project root for license information.
  */
 
+#include <gtest/gtest.h>
 #include <testutils.h>
 #include <LightGBM/c_api.h>
 #include <LightGBM/utils/random.h>
 
-#include <gtest/gtest.h>
 #include <string>
 #include <thread>
 #include <utility>
+#include <vector>
 
 using LightGBM::Log;
 using LightGBM::Random;
 
 namespace LightGBM {
 
-  /*!
-  * Creates a Dataset from the internal repository examples.
-  */
-  int TestUtils::LoadDatasetFromExamples(const char* filename, const char* config, DatasetHandle* out) {
+/*!
+* Creates a Dataset from the internal repository examples.
+*/
+int TestUtils::LoadDatasetFromExamples(const char* filename, const char* config, DatasetHandle* out) {
   std::string fullPath("examples/");
   fullPath += filename;
   Log::Info("Debug sample data path: %s", fullPath.c_str());
@@ -29,12 +30,12 @@ namespace LightGBM {
     config,
     nullptr,
     out);
-  }
+}
 
-  /*!
-  * Creates fake data in the passed vectors.
-  */
-  void TestUtils::CreateRandomDenseData(
+/*!
+* Creates fake data in the passed vectors.
+*/
+void TestUtils::CreateRandomDenseData(
   int32_t nrows,
   int32_t ncols,
   int32_t nclasses,
@@ -53,12 +54,12 @@ namespace LightGBM {
   }
 
   CreateRandomMetadata(nrows, nclasses, labels, weights, init_scores, groups);
-  }
+}
 
-  /*!
-  * Creates fake data in the passed vectors.
-  */
-  void TestUtils::CreateRandomSparseData(
+/*!
+* Creates fake data in the passed vectors.
+*/
+void TestUtils::CreateRandomSparseData(
   int32_t nrows,
   int32_t ncols,
   int32_t nclasses,
@@ -88,12 +89,12 @@ namespace LightGBM {
   }
 
   CreateRandomMetadata(nrows, nclasses, labels, weights, init_scores, groups);
-  }
+}
 
-  /*!
-  * Creates fake data in the passed vectors.
-  */
-  void TestUtils::CreateRandomMetadata(int32_t nrows,
+/*!
+* Creates fake data in the passed vectors.
+*/
+void TestUtils::CreateRandomMetadata(int32_t nrows,
   int32_t nclasses,
   std::vector<float>* labels,
   std::vector<float>* weights,
@@ -130,9 +131,9 @@ namespace LightGBM {
       groups->push_back(group);
     }
   }
-  }
+}
 
-  void TestUtils::StreamDenseDataset(DatasetHandle dataset_handle,
+void TestUtils::StreamDenseDataset(DatasetHandle dataset_handle,
   int32_t nrows,
   int32_t ncols,
   int32_t nclasses,
@@ -205,9 +206,9 @@ namespace LightGBM {
 
   auto cur_time = std::chrono::steady_clock::now();
   Log::Info(" Time: %d", cur_time - start_time);
-  }
+}
 
-  void TestUtils::StreamSparseDataset(DatasetHandle dataset_handle,
+void TestUtils::StreamSparseDataset(DatasetHandle dataset_handle,
                                     int32_t nrows,
                                     int32_t nclasses,
                                     int32_t batch_count,
@@ -272,14 +273,14 @@ namespace LightGBM {
 
   auto cur_time = std::chrono::steady_clock::now();
   Log::Info(" Time: %d", cur_time - start_time);
-  }
+}
 
-  /*!
+/*!
   * Pushes data from 1 thread into a Dataset based on thread_id and nrows.
   * e.g. with 100 rows, thread 0 will push rows 0-49, and thread 2 will push rows 50-99.
   * Note that rows are still pushed in microbatches within their range.
   */
-  void TestUtils::PushSparseBatch(DatasetHandle dataset_handle,
+void TestUtils::PushSparseBatch(DatasetHandle dataset_handle,
                                 int32_t nrows,
                                 int32_t nclasses,
                                 int32_t batch_count,
@@ -345,10 +346,10 @@ namespace LightGBM {
       groups_ptr += batch_count;
     }
   }
-  }
+}
 
 
-  void TestUtils::AssertMetadata(const Metadata* metadata,
+void TestUtils::AssertMetadata(const Metadata* metadata,
   const std::vector<float>* ref_labels,
   const std::vector<float>* ref_weights,
   const std::vector<double>* ref_init_scores,
@@ -418,9 +419,9 @@ namespace LightGBM {
   } else if (ref_groups) {
     FAIL() << "Expected non-null query_boundaries";
   }
-  }
+}
 
-  const double* TestUtils::CreateInitScoreBatch(std::vector<double>* init_score_batch,
+const double* TestUtils::CreateInitScoreBatch(std::vector<double>* init_score_batch,
   int32_t index,
   int32_t nrows,
   int32_t nclasses,
@@ -434,6 +435,6 @@ namespace LightGBM {
     }
   }
   return init_score_batch->data();
-  }
+}
 
 }  // namespace LightGBM

tests/cpp_tests/testutils.h

@@ -2,8 +2,8 @@
  * Copyright (c) 2022 Microsoft Corporation. All rights reserved.
  * Licensed under the MIT License. See LICENSE file in the project root for license information.
  */
-#ifndef LIGHTGBM_TESTUTILS_H_
-#define LIGHTGBM_TESTUTILS_H_
+#ifndef LIGHTGBM_TESTS_CPP_TESTS_TESTUTILS_H_
+#define LIGHTGBM_TESTS_CPP_TESTS_TESTUTILS_H_
 
 #include <LightGBM/c_api.h>
 #include <LightGBM/dataset.h>
@@ -121,4 +121,4 @@ class TestUtils {
     int32_t thread_id);
 };
 }  // namespace LightGBM
-#endif  // LIGHTGBM_TESTUTILS_H_
+#endif  // LIGHTGBM_TESTS_CPP_TESTS_TESTUTILS_H_

tests/python_package_test/test_engine.py

@@ -16,7 +16,14 @@ import psutil
 import pytest
 from scipy.sparse import csr_matrix, isspmatrix_csc, isspmatrix_csr
 from sklearn.datasets import load_svmlight_file, make_blobs, make_classification, make_multilabel_classification
-from sklearn.metrics import average_precision_score, log_loss, mean_absolute_error, mean_squared_error, roc_auc_score
+from sklearn.metrics import (
+    average_precision_score,
+    log_loss,
+    mean_absolute_error,
+    mean_squared_error,
+    r2_score,
+    roc_auc_score,
+)
 from sklearn.model_selection import GroupKFold, TimeSeriesSplit, train_test_split
 
 import lightgbm as lgb
@@ -4049,6 +4056,29 @@ def test_average_precision_metric():
     assert res["training"]["average_precision"][-1] == pytest.approx(1)
 
 
+def test_r2_metric():
+    # test against sklearn R2 metric
+    X, y = make_synthetic_regression()
+    params = {"objective": "regression", "metric": "r2", "verbose": -1}
+    res = {}
+    train_data = lgb.Dataset(X, label=y)
+    est = lgb.train(
+        params, train_data, num_boost_round=1, valid_sets=[train_data], callbacks=[lgb.record_evaluation(res)]
+    )
+    r2 = res["training"]["r2"][-1]
+    pred = est.predict(X)
+    sklearn_r2 = r2_score(y, pred)
+    assert r2 == pytest.approx(sklearn_r2)
+    assert r2 != 0
+    assert r2 != 1
+    # test that R2 is 1 when y has no variance and the model predicts perfectly
+    y = y.copy()
+    y[:] = 1
+    lgb_X = lgb.Dataset(X, label=y)
+    lgb.train(params, lgb_X, num_boost_round=1, valid_sets=[lgb_X], callbacks=[lgb.record_evaluation(res)])
+    assert res["training"]["r2"][-1] == pytest.approx(1)
+
+
 def test_reset_params_works_with_metric_num_class_and_boosting():
     X, y = load_breast_cancer(return_X_y=True)
     dataset_params = {"max_bin": 150}