xgboost: 0.90 -> 1.4.1

pkgs/development/libraries/xgboost/default.nix

@@ -1,6 +1,14 @@
-{ config, stdenv, lib, fetchgit, cmake
-, cudaSupport ? config.cudaSupport or false, cudatoolkit
-, ncclSupport ? false, nccl
+{ config
+, stdenv
+, lib
+, fetchFromGitHub
+, cmake
+, gtest
+, doCheck ? true
+, cudaSupport ? config.cudaSupport or false
+, cudatoolkit
+, ncclSupport ? false
+, nccl
 , llvmPackages
 }:
 
@@ -8,37 +16,43 @@ assert ncclSupport -> cudaSupport;
 
 stdenv.mkDerivation rec {
   pname = "xgboost";
-  version = "0.90";
+  version = "1.4.1";
 
-  # needs submodules
-  src = fetchgit {
-    url = "https://github.com/dmlc/xgboost";
-    rev = "refs/tags/v${version}";
-    sha256 = "1zs15k9crkiq7bnr4gqq53mkn3w8z9dq4nwlavmfcr5xr5gw2pw4";
+  src = fetchFromGitHub {
+    owner = "dmlc";
+    repo = pname;
+    rev = "v${version}";
+    fetchSubmodules = true;
+    sha256 = "12b1417dg8jqyxd72kg5a3xhg5h11vz0k7bkv72mzrv83jvgn5ci";
   };
 
   nativeBuildInputs = [ cmake ] ++ lib.optional stdenv.isDarwin llvmPackages.openmp;
 
-  buildInputs = lib.optional cudaSupport cudatoolkit
+  buildInputs = [ gtest ] ++ lib.optional cudaSupport cudatoolkit
                 ++ lib.optional ncclSupport nccl;
 
-  cmakeFlags = lib.optionals cudaSupport [ "-DUSE_CUDA=ON" "-DCUDA_HOST_COMPILER=${cudatoolkit.cc}/bin/cc" ]
-               ++ lib.optional ncclSupport "-DUSE_NCCL=ON";
+  cmakeFlags = lib.optionals doCheck [ "-DGOOGLE_TEST=ON" ]
+    ++ lib.optionals cudaSupport [ "-DUSE_CUDA=ON" "-DCUDA_HOST_COMPILER=${cudatoolkit.cc}/bin/cc" ]
+    ++ lib.optionals ncclSupport [ "-DUSE_NCCL=ON" ];
+
+  inherit doCheck;
 
   installPhase = let
     libname = "libxgboost${stdenv.hostPlatform.extensions.sharedLibrary}";
   in ''
+    runHook preInstall
     mkdir -p $out
     cp -r ../include $out
     install -Dm755 ../lib/${libname} $out/lib/${libname}
     install -Dm755 ../xgboost $out/bin/xgboost
+    runHook postInstall
   '';
 
   meta = with lib; {
     description = "Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library";
     homepage = "https://github.com/dmlc/xgboost";
     license = licenses.asl20;
-    platforms = [ "x86_64-linux" "i686-linux" "x86_64-darwin" ];
+    platforms = platforms.unix;
     maintainers = with maintainers; [ abbradar ];
   };
 }

pkgs/development/python-modules/xgboost/default.nix

@@ -1,6 +1,6 @@
 { buildPythonPackage
-, pytest
-, nose
+, pytestCheckHook
+, cmake
 , scipy
 , scikitlearn
 , stdenv
@@ -10,28 +10,52 @@
 , matplotlib
 , graphviz
 , datatable
+, hypothesis
 }:
 
 buildPythonPackage {
   pname = "xgboost";
   inherit (xgboost) version src meta;
 
-  patches = [
-    (substituteAll {
-      src = ./lib-path-for-python.patch;
-      libpath = "${xgboost}/lib";
-      extention = stdenv.hostPlatform.extensions.sharedLibrary;
-    })
+  nativeBuildInputs = [ cmake ];
+  buildInputs = [ xgboost ];
+  propagatedBuildInputs = [ scipy ];
+  checkInputs = [
+    pytestCheckHook
+    scikitlearn
+    pandas
+    matplotlib
+    graphviz
+    datatable
+    hypothesis
   ];
 
-  postPatch = "cd python-package";
-
-  propagatedBuildInputs = [ scipy ];
-  buildInputs = [ xgboost ];
-  checkInputs = [ nose pytest scikitlearn pandas matplotlib graphviz datatable ];
-
-  checkPhase = ''
-    ln -sf ../demo .
-    nosetests ../tests/python
+  # Override existing logic for locating libxgboost.so which is not appropriate for Nix
+  prePatch = let
+    libPath = "${xgboost}/lib/libxgboost${stdenv.hostPlatform.extensions.sharedLibrary}";
+  in ''
+    echo 'find_lib_path = lambda: ["${libPath}"]' > python-package/xgboost/libpath.py
   '';
+
+  dontUseCmakeConfigure = true;
+
+  postPatch = ''
+    cd python-package
+  '';
+
+  preCheck = ''
+    ln -sf ../demo .
+    ln -s ${xgboost}/bin/xgboost ../xgboost
+  '';
+
+  pytestFlagsArray = ["../tests/python"];
+  disabledTestPaths = [
+    # Requires internet access: https://github.com/dmlc/xgboost/blob/03cd087da180b7dff21bd8ef34997bf747016025/tests/python/test_ranking.py#L81
+    "../tests/python/test_ranking.py"
+  ];
+  disabledTests = [
+    "test_cli_binary_classification"
+    "test_model_compatibility"
+  ];
+
 }

pkgs/development/python-modules/xgboost/lib-path-for-python.patch

@@ -1,38 +0,0 @@
-diff --git a/python-package/xgboost/libpath.py b/python-package/xgboost/libpath.py
-index d87922c0..859a30fb 100644
---- a/python-package/xgboost/libpath.py
-+++ b/python-package/xgboost/libpath.py
-@@ -19,32 +19,4 @@ def find_lib_path():
-     lib_path: list(string)
-        List of all found library path to xgboost
-     """
--    curr_path = os.path.dirname(os.path.abspath(os.path.expanduser(__file__)))
--    # make pythonpack hack: copy this directory one level upper for setup.py
--    dll_path = [curr_path, os.path.join(curr_path, '../../lib/'),
--                os.path.join(curr_path, './lib/'),
--                os.path.join(sys.prefix, 'xgboost')]
--    if sys.platform == 'win32':
--        if platform.architecture()[0] == '64bit':
--            dll_path.append(os.path.join(curr_path, '../../windows/x64/Release/'))
--            # hack for pip installation when copy all parent source directory here
--            dll_path.append(os.path.join(curr_path, './windows/x64/Release/'))
--        else:
--            dll_path.append(os.path.join(curr_path, '../../windows/Release/'))
--            # hack for pip installation when copy all parent source 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'):
--        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]
--
--    lib_path = [p for p in dll_path if os.path.exists(p) and os.path.isfile(p)]
--
--    # From github issues, most of installation errors come from machines w/o compilers
--    if not lib_path and not os.environ.get('XGBOOST_BUILD_DOC', False):
--        raise XGBoostLibraryNotFound(
--            'Cannot find XGBoost Library in the candidate path, ' +
--            'did you install compilers and run build.sh in root path?\n'
--            'List of candidates:\n' + ('\n'.join(dll_path)))
--    return lib_path
-+    return ["@libpath@/libxgboost@extention@"]