model_es = word_vectors.load_model('resources/big/vectors_es_100.bin')
model_pt = word_vectors.load_model('resources/big/vectors_pt_100.bin')
logging.info("computing equal words...")
equal_words = model_es.vocab.keys() & model_pt.vocab.keys()
print("Equal words number in the Wikipedia's:", len(equal_words))
SAMPLE_SIZE = 20
print("Sample", SAMPLE_SIZE, "equal words found:",
random.sample(equal_words, SAMPLE_SIZE))
T = linear_trans.load_linear_transformation(
'resources/big/trans_es_100_pt_100.npz')
clf = classifier.build_classifier()
X_train, y_train = classifier.features_and_labels(training_friend_pairs,
model_es, model_pt, T)
logging.info("training...")
clf.fit(X_train, y_train)
equal_friend_pairs = (classifier.FriendPair(word, word, None)
for word in equal_words)
logging.info("computing features...")
X_equal, _ = classifier.features_and_labels(equal_friend_pairs, model_es,
model_pt, T)
logging.info("predicting equal words...")
def command_classify(args_):
training_friend_pairs = util.read_words(
args_.training_friends_file_name)
testing_friend_pairs = util.read_words(args_.testing_friends_file_name)
model_es, model_pt = util.read_models(args_)
T = linear_trans.load_linear_transformation(
args_.translation_matrix_file_name)
clf = classifier.build_classifier(CLF_OPTIONS[args_.classifier])
if args_.cross_validation:
friend_pairs = training_friend_pairs + testing_friend_pairs
X, y, = classifier.features_and_labels(
friend_pairs,
model_es,
model_pt,
T,
backwards=args_.backwards,
topx=args_.top,
use_taxonomy=args_.use_taxonomy)
measures = classifier.classify_with_cross_validation(X, y, clf=clf)
print('')
print("Cross-validation measures with 95% of confidence:")
for measure_name, (mean, delta) in measures.items():
print(
"{measure_name}: {mean:0.4f} ± {delta:0.4f} --- [{inf:0.4f}, {sup:0.4f}]"
.format(measure_name=measure_name,
mean=mean,
delta=delta,
inf=mean - delta,
sup=mean + delta))
print('')
mean_measures = {
measure_name: mean
for measure_name, (mean, delta) in measures.items()
}
_print_metrics_matrix(mean_measures)
_print_confusion_matrix(mean_measures)
else:
X_train, y_train = classifier.features_and_labels(
training_friend_pairs,
model_es,
model_pt,
T,
backwards=args_.backwards,
topx=args_.top,
use_taxonomy=args_.use_taxonomy)
X_test, y_test = classifier.features_and_labels(
testing_friend_pairs,
model_es,
model_pt,
T,
backwards=args_.backwards,
topx=args_.top,
use_taxonomy=args_.use_taxonomy)
measures = classifier.classify(X_train, X_test, y_train, y_test,
clf)
print('')
_print_metrics_matrix(measures)
_print_confusion_matrix(measures)