# Base image
FROM ubuntu:latest

# Install python and pip
RUN apt-get update && apt-get install -y \
    python3 \
    python3-pip

# Install the required Python packages
RUN pip3 install numpy pandas kaggle scikit-learn

# Set the working directory
WORKDIR /app

# Copy scripts to the working directory
COPY download_dataset.py ./
COPY get_stats.py ./

# Default command
CMD bash