# Build an image that can do training and inference in SageMaker
# This is a Python 2 image that uses the nginx, gunicorn, flask stack
# for serving inferences in a stable way.
FROM public.ecr.aws/lts/ubuntu:20.04

ENV DEBIAN_FRONTEND=noninteractive

RUN apt-get -y update && apt-get install -y --no-install-recommends \
         wget \
         python3-pip \
         python3-dev \
         nginx \
         ca-certificates \
    && rm -rf /var/lib/apt/lists/* \
    && cd /usr/local/bin \
    && ln -s /usr/bin/python3 python \
    && pip3 install --upgrade pip

# 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/pip/get-pip.py && python3 get-pip.py && \
    pip install numpy scipy scikit-learn pandas flask gevent gunicorn && \
        rm -rf /root/.cache

# 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/program:${PATH}"

# Set up the program in the image
COPY decision_trees /opt/program
WORKDIR /opt/program