FROM ubuntu

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

WORKDIR /app
COPY ./download_data.sh calc_stats.sh ./
COPY ./clean_and_split_data.py calc_stats.py ./

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

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

RUN pip3 install kaggle pandas scikit-learn