# Copyright 2018 Amazon.com, Inc. or its affiliates. All Rights Reserved.
#
# Permission is hereby granted, free of charge, to any person obtaining a copy of this
# software and associated documentation files (the "Software"), to deal in the Software
# without restriction, including without limitation the rights to use, copy, modify,
# merge, publish, distribute, sublicense, and/or sell copies of the Software, and to
# permit persons to whom the Software is furnished to do so.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
# INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A
# PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
# HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
# OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
# SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

# 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.
# This example uses TFFM.

FROM ubuntu:16.04

MAINTAINER Randy DeFauw <rddefauw@amazon.com>


RUN apt-get -y update && apt-get install -y --no-install-recommends \
         wget \
         python \
         python-dev \
         nginx \
         gcc \
         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 && python get-pip.py && \
    pip install numpy scipy scikit-learn pandas flask gevent gunicorn tffm tensorflow sagemaker boto3 --upgrade && \
        (cd /usr/local/lib/python2.7/dist-packages/scipy/.libs; rm *; ln ../../numpy/.libs/* .) && \
        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 tffm /opt/program
WORKDIR /opt/program