FROM ubuntu:latest
RUN apt-get update \
    && apt-get install -y git python3 python3-pip curl \
    && curl -O https://bootstrap.pypa.io/get-pip.py \
    && python3 get-pip.py --user \
    && rm get-pip.py \
    && pip3 install --user kaggle \
    && pip3 install --user pandas \
    && pip3 install --user seaborn \
    && pip3 install --user scikit-learn
ENV PATH="/root/.local/bin:$PATH"
WORKDIR /app
COPY . /app
CMD ["python", "create_dataset.py"]