PKG Add Xgboost

docs/project/changelog.md

@@ -173,7 +173,7 @@ substitutions:
 - New packages: opencv-python v4.5.5.64 {pr}`2305`, ffmpeg {pr}`2305`, libwebp {pr}`2305`,
   h5py, pkgconfig and libhdf5 {pr}`2411`, bitarray {pr}`2459`, gsw {pr}`2511`, cftime {pr}`2504`,
   svgwrite, jsonschema, tskit {pr}`2506`, xarray {pr}`2538`, demes, libgsl, newick,
-  ruamel, msprime {pr}`2548`, gmpy2 {pr}`2665`.
+  ruamel, msprime {pr}`2548`, gmpy2 {pr}`2665`, xgboost {pr}`2537`.
 
 ## Version 0.20.0
 

packages/xgboost/cmake/TestBigEndian.cmake

@@ -0,0 +1,30 @@
+#.rst:
+# TestBigEndian
+# -------------
+#
+# The TestBigEndian.cmake module that ships with CMake, which
+# checks if the system is big endian or little endian, assumes
+# that a binary is produced that will have bytes that correspond to the
+# endianness on the target system. Since emscripten produces Javascript, we
+# override the default behavior and always return little endian.
+#
+# ::
+#
+#   TEST_BIG_ENDIAN(VARIABLE)
+#   VARIABLE - variable to store the result to
+#=============================================================================
+# Copyright 2002-2009 Kitware, Inc.
+#
+# Distributed under the OSI-approved BSD License (the "License");
+# see accompanying file Copyright.txt for details.
+#
+# This software is distributed WITHOUT ANY WARRANTY; without even the
+# implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+# See the License for more information.
+#=============================================================================
+# (To distribute this file outside of CMake, substitute the full
+#  License text for the above reference.)
+
+function(TEST_BIG_ENDIAN VARIABLE)
+  set(${VARIABLE} 0 CACHE INTERNAL "Result of TEST_BIG_ENDIAN" FORCE)
+endfunction()

packages/xgboost/cmake/Toolchain.cmake

@@ -0,0 +1,26 @@
+set_property(GLOBAL PROPERTY TARGET_SUPPORTS_SHARED_LIBS TRUE)
+set(CMAKE_SKIP_COMPATIBILITY_TESTS 1)
+set(CMAKE_SIZEOF_CHAR 1)
+set(CMAKE_SIZEOF_UNSIGNED_SHORT 2)
+set(CMAKE_SIZEOF_SHORT 2)
+set(CMAKE_SIZEOF_INT 4)
+set(CMAKE_SIZEOF_UNSIGNED_LONG 4)
+set(CMAKE_SIZEOF_UNSIGNED_INT 4)
+set(CMAKE_SIZEOF_LONG 4)
+set(CMAKE_SIZEOF_VOID_P 4)
+set(CMAKE_SIZEOF_FLOAT 4)
+set(CMAKE_SIZEOF_DOUBLE 8)
+set(CMAKE_C_SIZEOF_DATA_PTR 4)
+set(CMAKE_CXX_SIZEOF_DATA_PTR 4)
+set(CMAKE_HAVE_LIMITS_H 1)
+set(CMAKE_HAVE_UNISTD_H 1)
+set(CMAKE_HAVE_PTHREAD_H 1)
+set(CMAKE_HAVE_SYS_PRCTL_H 1)
+set(CMAKE_WORDS_BIGENDIAN 0)
+set(CMAKE_DL_LIBS)
+set(CMAKE_RANLIB echo)
+set(CMAKE_CROSSCOMPILING TRUE)
+set(CMAKE_SYSTEM_PROCESSOR x86)
+set(UNIX 1)
+
+list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_LIST_DIR}")

packages/xgboost/meta.yaml

@@ -0,0 +1,31 @@
+package:
+  name: xgboost
+  version: 1.6.0
+source:
+  url: https://files.pythonhosted.org/packages/77/89/92b399140a7688443fc182b54240822c903e906121d63446eb2f84350e99/xgboost-1.6.0.tar.gz
+  sha256: 9c944c2495cb426b8a365021565755c39ee0b53156cf5e53a4346bdad2e3b734
+  patches:
+    - patches/0001-Add-missing-template-type.patch
+    - patches/0002-Add-library-loading-path.patch
+build:
+  cflags: |
+    -DDMLC_USE_FOPEN64=0
+    -DDMLC_ENABLE_STD_THREAD=0
+    -DDMLC_CXX11_THREAD_LOCAL=0
+    -DUSE_OPENMP=0
+  script: |
+    # export VERBOSE=1
+    export CMAKE_TOOLCHAIN_FILE=$PYODIDE_ROOT/packages/xgboost/cmake/Toolchain.cmake
+requirements:
+  run:
+    - numpy
+    - scipy
+    - setuptools
+test:
+  imports:
+    - xgboost
+about:
+  home: https://github.com/dmlc/xgboost
+  PyPI: https://pypi.org/project/xgboost
+  summary: XGBoost Python Package
+  license: Apache-2.0

packages/xgboost/patches/0001-Add-missing-template-type.patch

@@ -0,0 +1,37 @@
+From 4ac9a00d9e16b0879b4e734a4b604c7ce672894e Mon Sep 17 00:00:00 2001
+From: Gyeongjae Choi <def6488@gmail.com>
+Date: Mon, 9 May 2022 06:42:07 +0000
+Subject: [PATCH 1/2] Add missing template type
+
+TODO: Remove this patch when XGBoost version is updated.
+(Upstream PR: https://github.com/dmlc/xgboost/pull/7954)
+
+---
+ src/common/host_device_vector.cc | 5 ++++-
+ 1 file changed, 4 insertions(+), 1 deletion(-)
+
+diff --git a/xgboost/src/common/host_device_vector.cc b/xgboost/src/common/host_device_vector.cc
+index 3a4a59db..fc33317b 100644
+--- a/xgboost/src/common/host_device_vector.cc
++++ b/xgboost/src/common/host_device_vector.cc
+@@ -180,13 +180,16 @@ template class HostDeviceVector<uint64_t>;  // bst_row_t
+ template class HostDeviceVector<uint32_t>;  // bst_feature_t
+ template class HostDeviceVector<RegTree::Segment>;
+
+-#if defined(__APPLE__)
++#if defined(__APPLE__) || defined(__EMSCRIPTEN__)
+ /*
+  * On OSX:
+  *
+  * typedef unsigned int         uint32_t;
+  * typedef unsigned long long   uint64_t;
+  * typedef unsigned long       __darwin_size_t;
++ *
++ * On Emscripten:
++ * typedef unsigned long        size_t;
+  */
+ template class HostDeviceVector<std::size_t>;
+ #endif  // defined(__APPLE__)
+-- 
+2.35.1
+

packages/xgboost/patches/0002-Add-library-loading-path.patch

@@ -0,0 +1,29 @@
+From 54c2a9faeb0b0169172c5ab53367e6092f132c5a Mon Sep 17 00:00:00 2001
+From: Gyeongjae Choi <def6488@gmail.com>
+Date: Mon, 9 May 2022 12:07:44 +0000
+Subject: [PATCH 2/2] Add library loading path
+
+TODO: Remove this patch when XGBoost version is updated.
+(Upstream PR: https://github.com/dmlc/xgboost/pull/7954)
+
+---
+ python-package/xgboost/libpath.py | 3 +--
+ 1 file changed, 1 insertion(+), 2 deletions(-)
+
+diff --git a/xgboost/libpath.py b/xgboost/libpath.py
+index f7a7d9cd..1ab41cbe 100644
+--- a/xgboost/libpath.py
++++ b/xgboost/libpath.py
+@@ -43,8 +43,7 @@ def find_lib_path() -> List[str]:
+             # directory here
+             dll_path.append(os.path.join(curr_path, './windows/Release/'))
+         dll_path = [os.path.join(p, 'xgboost.dll') for p in dll_path]
+-    elif sys.platform.startswith('linux') or sys.platform.startswith(
+-            'freebsd'):
++    elif sys.platform.startswith(('linux', 'freebsd', 'emscripten')):
+         dll_path = [os.path.join(p, 'libxgboost.so') for p in dll_path]
+     elif sys.platform == 'darwin':
+         dll_path = [os.path.join(p, 'libxgboost.dylib') for p in dll_path]
+-- 
+2.35.1
+