def get_features(model_file, output_file):
"""\
"""
m = Model.load_from_file(model_file)
labels = m.data_headers.get_attrib(m.class_attr).labels
feats = m.vectorizer.get_feature_names()
fh = codecs.open(output_file, 'w', 'UTF-8')
for i, label in enumerate(labels):
log_info('Enumerating features for label %d (\'%s\')' % (i, label))
coefs = m.classifier.coef_[i]
nonzero = [(f, c) for (f, c) in zip(feats, coefs) if c != 0]
print >> fh, 'LABEL == %s' % label
for f, c in sorted(nonzero, key=itemgetter(1), reverse=True):
print >> fh, '%s - %f' % (f, c)
print >> fh, "\n\n"
fh.close()
def get_features(model_file, output_file):
"""\
"""
m = Model.load_from_file(model_file)
labels = m.data_headers.get_attrib(m.class_attr).labels
feats = m.vectorizer.get_feature_names()
fh = codecs.open(output_file, 'w', 'UTF-8')
for i, label in enumerate(labels):
log_info('Enumerating features for label %d (\'%s\')' % (i, label))
coefs = m.classifier.coef_[i]
nonzero = [(f, c) for (f, c) in zip(feats, coefs) if c != 0]
print >> fh, 'LABEL == %s' % label
for f, c in sorted(nonzero, key=itemgetter(1), reverse=True):
print >> fh, '%s - %f' % (f, c)
print >> fh, "\n\n"
fh.close()
def run_training(work_dir, config_file, train_file, model_file,
test_file=None, classif_file=None, memory=MEMORY,
name='train'):
"""\
Run the model training.
"""
# initialization from the configuration file
_, ext = os.path.splitext(config_file)
# load configuration from a pickle (we're already in the working directory)
if ext == '.pickle':
fh = open(config_file, mode='rb')
cfg = pickle.load(fh)
fh.close()
demarshal_lambda(cfg, 'filter_attr')
demarshal_lambda(cfg, 'postprocess')
# load by running Python code (make paths relative to working directory)
else:
config_file = os.path.join(work_dir, config_file)
cfg = Config(config_file)
# training
if cfg.get('unfold_pattern'):
pattern = cfg['unfold_pattern']
del cfg['unfold_pattern']
unfold_key = cfg.get('unfold_key', 'unfold_key')
cfgs = cfg.unfold_lists(pattern, unfold_key)
for cfg in cfgs:
key = re.sub(r'[^A-Za-z0-9_]', '', cfg[unfold_key])
create_job(cfg, name + '-' + key, work_dir, train_file, model_file,
test_file, classif_file, memory)
return
if cfg.get('divide_func'):
model = SplitModel(cfg)
model.train(train_file, work_dir, memory)
else:
model = Model(cfg)
model.train(train_file)
# evaluation
if test_file is not None and classif_file is not None:
if ext != '.pickle': # this means we're not in the working directory
classif_file = os.path.join(work_dir, classif_file)
log_info('Evaluation on file: ' + test_file)
score = model.evaluate(test_file, classif_file=classif_file)
log_info('Score: ' + str(score))
# save the model
if ext != '.pickle': # we need to make the path relative to work_dir
model_file = os.path.join(work_dir, model_file)
model.save_to_file(model_file)
def test_models(file_in, file_out, model_files, source_attr, target_attr,
oov_test_file, oov_part, pos_attr, test_indiv):
"""\
Test all the given models on the selected file and save the target.
If oov_test_file is set, performs also OOV evaluation.
If test_pos is True, prints detailed results for various POSs.
"""
# load testing data
log_info('Loading data: ' + file_in)
data = DataSet()
data.load_from_arff(file_in)
forms = data[source_attr]
# apply all models
for model_num, model_file in enumerate(model_files, start=1):
model = Model.load_from_file(model_file)
log_info('Applying model: ' + model_file)
rules = model.classify(data)
output_attr = 'OUTPUT_M' + str(model_num)
data.add_attrib(Attribute(output_attr, 'string'), rules)
if test_indiv:
good = count_correct(data, model.class_attr, output_attr)
print_score(good, len(data), 'Model accuracy')
forms = [inflect(form, rule) for form, rule in zip(forms, rules)]
forms_attr = 'FORMS_M' + str(model_num)
data.add_attrib(Attribute(forms_attr, 'string'), forms)
# test the final performance
log_info('Evaluating...')
good = count_correct(data, target_attr, forms_attr)
print_score(good, len(data), 'ALL')
# evaluate without punctuation
evaluate_nopunct(data, source_attr, target_attr, forms_attr)
# evaluate forms different from lemma
evaluate_nolemma(data, source_attr, target_attr, forms_attr)
# load training data for OOV tests, evaluate on OOV
if oov_test_file:
evaluate_oov(data, source_attr, target_attr, forms_attr,
oov_test_file, oov_part)
# test on different POSes
if pos_attr:
evaluate_poses(data, target_attr, forms_attr, pos_attr)
# save the classification results
log_info('Saving data: ' + file_out)
data.save_to_arff(file_out)
def test_models(file_in, file_out, model_files, source_attr, target_attr,
oov_test_file, oov_part, pos_attr, test_indiv):
"""\
Test all the given models on the selected file and save the target.
If oov_test_file is set, performs also OOV evaluation.
If test_pos is True, prints detailed results for various POSs.
"""
# load testing data
log_info('Loading data: ' + file_in)
data = DataSet()
data.load_from_arff(file_in)
forms = data[source_attr]
# apply all models
for model_num, model_file in enumerate(model_files, start=1):
model = Model.load_from_file(model_file)
log_info('Applying model: ' + model_file)
rules = model.classify(data)
output_attr = 'OUTPUT_M' + str(model_num)
data.add_attrib(Attribute(output_attr, 'string'), rules)
if test_indiv:
good = count_correct(data, model.class_attr, output_attr)
print_score(good, len(data), 'Model accuracy')
forms = [inflect(form, rule) for form, rule in zip(forms, rules)]
forms_attr = 'FORMS_M' + str(model_num)
data.add_attrib(Attribute(forms_attr, 'string'), forms)
# test the final performance
log_info('Evaluating...')
good = count_correct(data, target_attr, forms_attr)
print_score(good, len(data), 'ALL')
# evaluate without punctuation
evaluate_nopunct(data, source_attr, target_attr, forms_attr)
# evaluate forms different from lemma
evaluate_nolemma(data, source_attr, target_attr, forms_attr)
# load training data for OOV tests, evaluate on OOV
if oov_test_file:
evaluate_oov(data, source_attr, target_attr, forms_attr, oov_test_file,
oov_part)
# test on different POSes
if pos_attr:
evaluate_poses(data, target_attr, forms_attr, pos_attr)
# save the classification results
log_info('Saving data: ' + file_out)
data.save_to_arff(file_out)
