FROM ubuntu:latest

ADD get-data.sh /get-data.sh
ADD prepare_dataset.py /prepare_dataset.py
ADD prepare-stats.sh /prepare-stats.sh

ENV CUTOFF=1000
ENV KAGGLE_USERNAME=wleczny
ENV KAGGLE_KEY=2e89e20ceb0a48d9df01a01bad744776

RUN apt-get update
RUN apt-get install -y python3 python3-pip unzip
RUN pip install pandas
RUN pip install scikit-learn
RUN pip install kaggle

RUN ./get-data.sh
RUN python3 prepare_dataset.py
RUN ./prepare-stats.sh