From d545c1e2a096d1c3e60c872fd1e6dc3c35865699 Mon Sep 17 00:00:00 2001
From: John Quitto-Graham <johnq@nvidia.com>
Date: Wed, 21 Oct 2020 13:15:21 -0700
Subject: [PATCH 1/2] fixed csv reader issue for the bosch dataset

---
 datasets.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/datasets.py b/datasets.py
index f31ccec..4421f1b 100644
--- a/datasets.py
+++ b/datasets.py
@@ -137,8 +137,9 @@ def prepare_bosch(dataset_folder, nrows):
 
     os.system("kaggle competitions download -c bosch-production-line-performance -f " +
               filename + " -p " + dataset_folder)
-    X = pd.read_csv(local_url, index_col=0, compression='zip', dtype=np.float32,
-                    nrows=nrows)
+    X = pd.read_csv(local_url,compression='zip', dtype=np.float32)
+    X = X.set_index('Id')
+    X.index = X.index.astype('int64')
     y = X.iloc[:, -1].to_numpy(dtype=np.float32)
     X.drop(X.columns[-1], axis=1, inplace=True)
     X = X.to_numpy(dtype=np.float32)

From ef715a33f65f320e07c8cd1fd34735cdfd958ea5 Mon Sep 17 00:00:00 2001
From: John Quitto-Graham <72091066+nvidia-johnq@users.noreply.github.com>
Date: Fri, 18 Dec 2020 22:47:40 -0800
Subject: [PATCH 2/2] lightgbm docker build update

Install from pip instead of from source to avoid errors.
---
 Dockerfile | 63 ++++++------------------------------------------------
 1 file changed, 7 insertions(+), 56 deletions(-)

diff --git a/Dockerfile b/Dockerfile
index 3db40af..5c551fb 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -1,4 +1,5 @@
 ARG CUDA_VERSION
+ARG XGB_HASH=6d293020fbfa2c67b532d550fe5d55689662caac
 FROM nvidia/cuda:$CUDA_VERSION-devel-ubuntu16.04
 SHELL ["/bin/bash", "-c"]
 # Install conda (and use python 3.7)
@@ -26,6 +27,7 @@ RUN curl -o /opt/miniconda.sh \
     /opt/conda/bin/conda update -n base conda && \
     rm /opt/miniconda.sh
 ENV PATH /opt/conda/bin:$PATH
+
 RUN conda install -c conda-forge \
         bokeh \
         h5py \
@@ -64,69 +66,17 @@ RUN wget --no-check-certificate \
     rm -rf cmake-${CMAKE_LONG_VERSION}.tar.gz cmake-${CMAKE_LONG_VERSION}
 
 # lightgbm
-ENV LANG=C.UTF-8 LC_ALL=C.UTF-8
-RUN apt-get update && \
-    apt-get install -y --no-install-recommends \
-        build-essential \
-        bzip2 \
-        ca-certificates \
-        curl \
-        git \
-        libblas-dev \
-        libboost-dev \
-        libboost-filesystem-dev \
-        libboost-system-dev \
-        libbz2-dev \
-        libc6 \
-        libglib2.0-0 \
-        liblapack-dev \
-        libsm6 \
-        libxext6 \
-        libxrender1 \
-        make \
-        tar \
-        unzip \
-        wget && \
-    rm -rf /var/lib/apt/*
-RUN mkdir -p /etc/OpenCL/vendors && \
-    echo "libnvidia-opencl.so.1" > /etc/OpenCL/vendors/nvidia.icd
-ENV OPENCL_LIBRARIES /usr/local/cuda/lib64
-ENV OPENCL_INCLUDE_DIR /usr/local/cuda/include
-RUN git config --global http.sslVerify false && \
-    git clone --recursive https://github.com/Microsoft/LightGBM /opt/LightGBM && \
-    cd /opt/LightGBM && \
-    mkdir build && \
-    cd build && \
-    cmake .. \
-        -DUSE_GPU=1 \
-        -DOpenCL_LIBRARY=$OPENCL_LIBRARIES/libOpenCL.so \
-        -DOpenCL_INCLUDE_DIR=$OPENCL_INCLUDE_DIR && \
-    make OPENCL_HEADERS="/usr/local/cuda/targets/x86_64-linux/include" \
-        LIBOPENCL="/usr/local/cuda/targets/x86_64-linux/lib" -j4 && \
-    cd ../python-package && \
-    python setup.py install --precompile
+RUN pip install lightgbm
 
 # catboost
-RUN if ["$CUDA_VERSION" < "11.0"]; then git config --global http.sslVerify false && \
-    git clone --recursive "https://github.com/catboost/catboost" /opt/catboost && \
-    cd /opt/catboost && \
-    cd catboost/python-package/catboost && \
-    ../../../ya make \
-        -r \
-        -o ../../.. \
-        -DUSE_ARCADIA_PYTHON=no \
-        -DUSE_SYSTEM_PYTHON=3.7\
-        -DPYTHON_CONFIG=python3-config \
-        -DCUDA_ROOT=$(dirname $(dirname $(which nvcc))); \
-        fi
-ENV if ["$CUDA_VERSION" < "11.0"]; then PYTHONPATH=$PYTHONPATH:/opt/catboost/catboost/python-package; fi\
-
-
+RUN pip install catboost
 
 # xgboost
 RUN git config --global http.sslVerify false && \
     git clone --recursive https://github.com/dmlc/xgboost /opt/xgboost && \
     cd /opt/xgboost && \
+    git checkout $XGB_HASH && \
+    git submodule update --init --recursive && \
     mkdir build && \
     cd build && \
     RMM_ROOT=/opt/conda cmake .. \
@@ -134,6 +84,7 @@ RUN git config --global http.sslVerify false && \
         -DUSE_NCCL=ON \
         -DPLUGIN_RMM=ON && \
     make -j4 && \
+    git log > xgb_log.txt && \
     cd ../python-package && \
     pip uninstall -y xgboost && \
     python setup.py install