NLP challenge - Emaill Prediction - ALTEGRAD course
- Pauline Nicolas
- Leo Treguer
- Rachid Riad
This code is for the Kaggle Challenge for NLP class, we got 0.39075 as final score. To reproduce the result, all the utilities function are in function.py and to get the csv file launch tfidf_centroid_model.py.
1] Vitor R Carvalho and William Cohen. Recommending recipients in the enron email corpus.Machine Learning,2007.
[2] David Graus, David Van Dijk, Manos Tsagkias, Wouter Weerkamp, and Maarten De Rijke. Recipient recom-mendation in enterprises using communication graphs and email content. InProceedings of the 37th internationalACM SIGIR conference on Research & development in information retrieval, pages 1079–1082. ACM, 2014.
A part of the code is taken from this Scikit Learn Examples.