1. Python 3.6 installed
2. Pip (curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py && python get-pip.py)
3. Jupyter notebook

1. Anaconda: https://www.anaconda.com/download/#windows
2. cmder: https://github.com/cmderdev/cmder/releases/download/v1.3.6/cmder.zip

1. Clone this repository
2. Download the training data from: http://goren.ml/pdnlp
3. Extract it to data/
4. Make sure all the requirements are installed pip3 install -r requirements.txt OR conda install --yes --file requirements.txt if you're with Anaconda
5. Launch Jupyter by running cd notebooks; jupyter notebook in your terminal

1. data.zip - The raw contracts, classified by their filename
2. stemmed.zip - The contracts after preprocessing and stemming (here to save you time)
3. w2v.pickle - Word2Vec model trained on the data (gensim model)
4. test_data.zip - Unlabeled contracts, for those who would like to participate in the competition ( http://goren4u.com/nlp_classification/ )

For more details, contact me at goren.ml .