FROM ubuntu

ARG KAGGLE_USERNAME
ARG KAGGLE_KEY
ARG CUTOFF
ENV CUTOFF=${CUTOFF:-260000}
ENV IS_DOCKER=True

WORKDIR /app
COPY ./download_data.sh calc_stats.sh ./
COPY ./clean_and_split_data.py calc_stats.py ./
COPY ./train_model.py ./train_model_mlflow.py ./
COPY ./evaluate.py ./

RUN apt-get update && apt-get install -y python3-pip unzip sshpass openssh-client && rm -rf /var/lib/apt/lists/*

RUN export PATH="$PATH:/root/.local/bin"

RUN pip3 install kaggle pandas scikit-learn tensorflow keras matplotlib numpy sacred mlflow dvc 'dvc[ssh]' paramiko 

RUN mkdir /.kaggle && chmod o+w /.kaggle

RUN useradd -r -u 111 jenkins