def test_tagger(tagger_name, tagger_input, test_data, **kwargs):
# initialise results
tagger_eval = dict()
# train
tic()
tagger_tagger = tagger_name(tagger_input, **kwargs)
tagger_eval['train_time'] = toc()
# test
tic()
tagger_eval['test_accuracy'] = tagger_tagger.evaluate(test_data)
tagger_eval['test_time'] = toc()
# show results
display_training_metrics(tagger_eval)
""" 0. set up the corpora for training and testing of tagging methods """
# load the corpus as tagged sentences
train_sents, val_sents, test_sents = read_corpus('INTERA',
role='train',
proportion=PROPORTION,
tag_length=TAG_LENGTH)
"""
# =============================================================================
# investigate NLTK classification tagging options
# =============================================================================
"""
""" 1. TNT tagger """
tnt_eval = dict()
# train
tic()
tnt_tagger = tnt.TnT()
tnt_tagger.train(train_sents)
tnt_eval['train_time'] = toc()
# test
tic()
tnt_eval['test_accuracy'] = tnt_tagger.evaluate(val_sents)
tnt_eval['test_time'] = toc()
# display results
display_training_metrics(tnt_eval)
""" 2. Naive Bayes classifier tagger """
nb_eval = dict()
# train
tic()
nb_tagger = ClassifierBasedPOSTagger(train=train_sents)
nb_eval['train_time'] = toc()