- Python 3.6+ installed
- Pip (
curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py && python get-pip.py
) - Jupyter notebook
- Anaconda: https://www.anaconda.com/download/#windows
- cmder: https://github.com/cmderdev/cmder/releases/download/v1.3.6/cmder.zip
- Clone this repository
- Download the training data from: https://drive.google.com/file/d/1CD-wyXoZ5UKJWN20kZDWvdVqcQvRCzP5/view
- Download the test data from: https://drive.google.com/file/d/1d3doBKzy3TNgtAnqkiB0BouwdOuf9pPF/view
- Copy it to
data/
- Make sure all the requirements are installed
pip3 install -r requirements.txt
ORconda install --yes --file requirements.txt
if you're with Anaconda - Launch Jupyter by running
cd notebooks; jupyter notebook
in your terminal
data.zip
- The raw contracts, classified by their filenametest_data.zip
- Unlabeled contracts
is available at http://goren.ml/uattcontract
A minimum accuracy of 90% is required