sklearn-crfsuite

sklearn-crfsuite is thin a CRFsuite (python-crfsuite) wrapper which provides scikit-learn-compatible sklearn_crfsuite.CRF estimator: you can use e.g. scikit-learn model selection utilities (cross-validation, hyperparameter optimization) with it, or save/load CRF models using joblib.

License is MIT.

Contents

• Install Instructions
• Tutorial
  • Let’s use CoNLL 2002 data to build a NER system
  • Features
  • Training
  • Evaluation
  • Hyperparameter Optimization
  • Check best estimator on our test data
  • Let’s check what classifier learned
• API Reference
  • CRF
  • sklearn_crfsuite.metrics
• Contributing
  • Authors
  • License
• Changes
  • 0.3.6 (2017-06-22)
  • 0.3.5 (2017-03-21)
  • 0.3.4 (2016-11-17)
  • 0.3.3 (2016-03-15)
  • 0.3.2 (2015-12-18)
  • 0.3.1 (2015-12-17)
  • 0.3 (2015-12-17)
  • 0.2 (2015-12-11)
  • 0.1 (2015-11-27)