Dockerfile

# Build an image that can do training and inference in SageMaker
# This is a Python 3 image that uses the nginx, gunicorn, flask stack
# for serving inferences in a stable way.

FROM ubuntu:20.04

MAINTAINER Amazon AI <sage-learner@amazon.com>

RUN apt-get update
RUN apt-get install -y software-properties-common
RUN add-apt-repository ppa:deadsnakes/ppa
RUN apt-get update

RUN apt-get install -y build-essential python3.9 python3.9-dev python3-pip python3.9-venv
RUN python3.9 -m pip install pip --upgrade

RUN apt-get -y update && apt-get install -y --no-install-recommends \
         wget \
         nginx \
         libgcc-7-dev \ 
         ca-certificates \
    && rm -rf /var/lib/apt/lists/*

# Here we get all python packages.
# There's substantial overlap between scipy and numpy that we eliminate by
# linking them together. Likewise, pip leaves the install caches populated which uses
# a significant amount of space. These optimizations save a fair amount of space in the
# image, which reduces start up time.
RUN wget https://bootstrap.pypa.io/get-pip.py && python3.9 get-pip.py && \
    pip install --upgrade pip && \
    pip install smdebug numpy scipy scikit-learn xgboost pandas flask gevent gunicorn

# Set some environment variables. PYTHONUNBUFFERED keeps Python from buffering our standard
# output stream, which means that logs can be delivered to the user quickly. PYTHONDONTWRITEBYTECODE
# keeps Python from writing the .pyc files which are unnecessary in this case. We also update
# PATH so that the train and serve programs are found when the container is invoked.

ENV PYTHONUNBUFFERED=TRUE
ENV PYTHONDONTWRITEBYTECODE=TRUE

ENV PATH="/opt/ml/code:${PATH}"

# /opt/ml and all subdirectories are utilized by SageMaker, we use the /code subdirectory to store our user code.

COPY xgboost /opt/ml/code
WORKDIR /opt/ml/code
RUN chmod +x /opt/ml/code/train
RUN chmod +x /opt/ml/code/serve