Add kaggle notebook Dockerfile

components/contrib/kaggle-notebook-image/Dockerfile

@@ -0,0 +1,75 @@
+# Copyright (c) Jupyter Development Team.
+# Distributed under the terms of the Modified BSD License.
+
+# use basic syntax for now
+FROM gcr.io/kaggle-images/python:latest
+
+USER root
+
+ENV DEBIAN_FRONTEND noninteractive
+
+ENV NB_USER jovyan
+ENV NB_UID 1000
+ENV HOME /home/$NB_USER
+# We prefer to have a global conda install
+# to minimize the amount of content in $HOME
+ENV CONDA_DIR=/opt/conda
+ENV PATH $CONDA_DIR/bin:$PATH
+
+# Use bash instead of sh
+SHELL ["/bin/bash", "-c"]
+
+# add https support 
+RUN apt-get update && apt-get install -yq --no-install-recommends apt-transport-https
+
+RUN echo "en_US.UTF-8 UTF-8" > /etc/locale.gen && \
+    locale-gen
+
+ENV LC_ALL en_US.UTF-8
+ENV LANG en_US.UTF-8
+ENV LANGUAGE en_US.UTF-8
+
+# Create jovyan user with UID=1000 and in the 'users' group
+# but allow for non-initial launches of the notebook to have
+# $HOME provided by the contents of a PV
+RUN useradd -M -s /bin/bash -N -u $NB_UID $NB_USER && \
+    chown -R ${NB_USER}:users /usr/local/bin && \
+    mkdir -p $HOME
+
+RUN export CLOUD_SDK_REPO="cloud-sdk-$(lsb_release -c -s)" && \
+    echo "deb https://packages.cloud.google.com/apt $CLOUD_SDK_REPO main" > /etc/apt/sources.list.d/google-cloud-sdk.list && \
+    curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | apt-key add - && \
+    apt-get update && \
+    apt-get install -y google-cloud-sdk kubectl 
+
+# Install Tini - used as entrypoint for container
+RUN cd /tmp && \
+    wget --quiet https://github.com/krallin/tini/releases/download/v0.10.0/tini && \
+    echo "1361527f39190a7338a0b434bd8c88ff7233ce7b9a4876f3315c22fce7eca1b0 *tini" | sha256sum -c - && \
+    mv tini /usr/local/bin/tini && \
+    chmod +x /usr/local/bin/tini
+
+RUN chown -R ${NB_USER}:users $HOME
+
+ENV GITHUB_REF https://raw.githubusercontent.com/kubeflow/kubeflow/master/components/tensorflow-notebook-image
+
+ADD --chown=jovyan:users $GITHUB_REF/jupyter_notebook_config.py /tmp
+
+# Wipe $HOME for PVC detection later
+WORKDIR $HOME
+RUN rm -fr $(ls -A $HOME)
+
+# Get init scripts from kubeflow 
+ADD --chown=jovyan:users \
+    $GITHUB_REF/start-singleuser.sh \
+    $GITHUB_REF/start-notebook.sh \
+    $GITHUB_REF/start.sh \
+    $GITHUB_REF/pvc-check.sh \
+    /usr/local/bin/
+
+RUN chmod a+rx /usr/local/bin/*
+
+# Configure container startup
+EXPOSE 8888
+ENTRYPOINT ["tini", "--"]
+CMD ["start-notebook.sh"]

components/contrib/kaggle-notebook-image/README.md

@@ -0,0 +1,16 @@
+# Kaggle notebook
+
+This Dockerfile builds an image that is derived from the latest [Kaggle python image](gcr.io/kaggle-images/pythoni:latest) but which is compatible for launching from the Kubeflow JupyterHub. [Kaggle](https://www.kaggle.com/) is the home of data science collaboration and competition.
+
+Important notes:
+* this notebook is not curated by the Kubeflow project and is not regularly tested
+* the versions of TensorFlow, PyTorch, and the other libraries included may change at any time
+* this is a very large notebook, over 21 Gb in size. Since our notebook uses the latest Kaggle image, docker pulls (and notebook launches) can take a lengthy period of time.
+* the base image size for docker is 10 Gb, which won't be large enough to run this image. Your docker daemon must be configured for at least 30 Gb (`-storage-opt dm.basesize=30G`) or use a storage driver like overlay2. 
+* the Kaggle image includes TensorFlow 1.9 or greater built with AVX2 support, so the image may not run on older CPU
+
+To build the image run:
+```
+docker build --pull -t kubeflow-kaggle-notebook:latest .
+```
+Of course specify whatever repo and image tag you need for your purposes.