# Create a Dataset.
train_dataset = Dataset(train_loader, schema).shuffle()
test_dataset = Dataset(test_loader, schema)
# Create a Classifier Service.
cfg = Config(
method = 'PA',
converter = {
'string_rules': [{'key': 'first_name', 'type': 'unigram', 'sample_weight': 'bin', 'global_weight': 'bin'}]
}
)
classifier = Classifier.run(cfg)
# Train the classifier.
for _ in classifier.train(train_dataset): pass
# Classify using the classifier.
for (idx, label, result) in classifier.classify(test_dataset):
true_family_name = label
pred_family_name = result[0][0]
first_name = test_dataset.get(idx)['first_name']
print("{0} {1} ({2})".format(
pred_family_name,
first_name,
'correct!' if pred_family_name == true_family_name else 'incorrect'
))
# Stop the classifier.
classifier.stop()
train_dataset = Dataset(train_loader, schema).shuffle()
test_dataset = Dataset(test_loader, schema)
# Create a Classifier Service.
cfg = Config(method='PA',
converter={
'string_rules': [{
'key': 'first_name',
'type': 'unigram',
'sample_weight': 'bin',
'global_weight': 'bin'
}]
})
classifier = Classifier.run(cfg)
# Train the classifier.
for _ in classifier.train(train_dataset):
pass
# Classify using the classifier.
for (idx, label, result) in classifier.classify(test_dataset):
true_family_name = label
pred_family_name = result[0][0]
first_name = test_dataset.get(idx)['first_name']
print("{0} {1} ({2})".format(
pred_family_name, first_name,
'correct!' if pred_family_name == true_family_name else 'incorrect'))
# Stop the classifier.
classifier.stop()
classifier = Classifier.run(Config())
# Number of tweets used for training.
n_train = 1000
print('---- Train: {0} tweets -------------------------------------'.format(
n_train))
# Train the classifier using tweets from Twitter stream.
trained_labels = set()
dataset = Dataset(get_loader(), schema)
for (idx, label) in classifier.train(dataset):
if idx == n_train: break
trained_labels.add(label)
text_summary = dataset.get(idx)['.text'].replace('\n', '')
print('Train[{0}]: language {1} >> {2}'.format(idx, label, text_summary))
print('Languages Trained: {0}'.format(str(trained_labels)))
print('---- Prediction (Ctrl-C to stop) -------------------------------------')
try:
# Classify tweets using the classifier.
(y_true, y_pred) = ([], [])
dataset = Dataset(get_loader(), schema)
for (idx, label, result) in classifier.classify(dataset):
(true_lang, pred_lang) = (label, result[0][0])
text_summary = dataset.get(idx)['.text'].replace('\n', '')
message = None