def info(self):
"""
Print the feature statistics for the given model. (Assumes MaxEnt)
"""
mallet = c['mallet']
env = set_env_lang_utf8()
info_bin = os.path.join(os.path.join(mallet, 'bin'), 'classifier2info')
info_p = sub.Popen([info_bin, '--classifier', self._model],
stdout=sub.PIPE, stdin=sub.PIPE, stderr=sub.PIPE, env=env)
cur_class = None
feats = TwoLevelCountDict()
# Go through and pick out what the features are for
for line in info_p.stdout:
content = line.decode(encoding='utf-8')
class_change = re.search('FEATURES FOR CLASS (.*)', content)
# Set the current class if the section changes
if class_change:
cur_class = class_change.group(1).strip()
continue
# Otherwise, let's catalog the features.
word, prob = content.split()
feats.add(cur_class, word, float(prob))
# Now, print some info
for cur_class in feats.keys():
print(cur_class, end='\t')
print('%s:%.4f' % ('<default>', feats[cur_class]['<default>']), end='\t')
top_10 = feats.top_n(cur_class, n=10, key2_re='^nom')
print('\t'.join(['%s:%.4f' % (w,p) for w,p in top_10]))
def __init__(self, model=None):
if model is None:
self._model = classifier
else:
self._model = model
mallet_bin = os.path.join(os.path.join(mallet, 'bin'), 'mallet')
env = set_env_lang_utf8()
self.c = sub.Popen([mallet_bin,
'classify-file',
'--classifier', self._model,
'--input', '-',
'--output', '-'],
stdout=sub.PIPE, stdin=sub.PIPE, env=env)
self._first = True