Skip to content

HTTPS clone URL

Subversion checkout URL

You can clone with
or
.
Download ZIP
Train NLTK objects with zero code
Python Shell
branch: master
Failed to load latest commit information.
docs cleanup
nltk_trainer tagset argument for train_chunker, remove babelfish references
tests tagset argument for train_chunker, remove babelfish references
.gitignore ignore compiled python files
.hgignore initial docs
LICENSE apache license, initial setup.py, shebang in scripts
README.rst links to text-processing.com & NLTK 3 cookbook
analyze_chunked_corpus.py analyze chunked corpus works for v3
analyze_chunker_coverage.py analyze chunker coverage working for v3
analyze_classifier_coverage.py py3 classification updates
analyze_tagged_corpus.py analyze tagger coverage v3
analyze_tagger_coverage.py analyze tagger coverage v3
categorized_corpus2csv.py Correctly pull in the environment python
classify_corpus.py tagset argument for train_chunker, remove babelfish references
combine_classifiers.py Correctly pull in the environment python
requirements.txt fix numpy requirement
setup.py include all nltk_trainer packages
tag_phrases.py Correctly pull in the environment python
train_chunker.py tagset argument for train_chunker, remove babelfish references
train_classifier.py Cleaner method using os.path.split
train_tagger.py train tagger tagset option, v3 specific test script

README.rst

NLTK Trainer

NLTK Trainer exists to make training and evaluating NLTK objects as easy as possible.

Requirements

You must have Python >=2.6 (but not 3.x) with argparse and NLTK 2.0 installed. NumPy, SciPy, and megam are recommended for training Maxent classifiers. To use the sklearn classifiers, you must also install scikit-learn.

If you want to use any of the corpora that come with NLTK, you should install the NLTK data.

Documentation

Documentation can be found at nltk-trainer.readthedocs.org (you can also find these documents in the docs directory. Many of the scripts are covered in Python 3 Text Processing with NLTK 3 Cookbook, and every script provides a --help option that describes all available parameters.

Something went wrong with that request. Please try again.