linux安装lightGBM（GPU版本）

参考https://blog.csdn.net/u012969412/article/details/71433960

删除干净原来的GBM
1、安装lightgbm
git clone --recursive https://github.com/Microsoft/LightGBM
cd LightGBM
mkdir build ; cd build
cmake ..   （cmake -DUSE_GPU=1 ..     ）
make -j4

cmake -DUSE_GPU=1 -DOpenCL_LIBRARY=/usr/local/cuda/lib64/libOpenCL.so -DOpenCL_INCLUDE_DIR=/usr/local/cuda/include/ ..(?)

sudo apt-get install --no-install-recommends git cmake build-essential libboost-dev libboost-system-dev libboost-filesystem-dev

2安装GPU支持
$ sudo apt-get install ocl-icd-libopencl1
$ sudo apt-get install ocl-icd-opencl-dev
$ sudo apt-get install libboost-dev
$ sudo apt-get install libboost-system-dev
$ sudo apt-get install libboost-filesystem-dev

第步配置GPU选项:    cmake -DUSE_GPU=1 ..
cd到LightGBM/python-package目录下:    python setup.py install

安装 Python 接口 (可选)

cd python-package/

sudo python setup.py install --precompile

cd ..

不行的话安装如下

sudo apt-get -y install python-pip

sudo -H pip install setuptools numpy scipy scikit-learn -U

第四步：用例
examples/python-guide目录下 python simple_example.py

device:'GPU'  或者用等于

/?GPU version cannot support categorical features with high cardinality.
You can fix it by split one categorical feature into multi categorical features.

 

运行后