def create_dataset_header():
"""
Creates the dataset header.
:return: the header
:rtype: Instances
"""
att_msg = Attribute.create_string("Message")
att_cls = Attribute.create_nominal("Class", ["miss", "hit"])
result = Instances.create_instances("MessageClassificationProblem", [att_msg, att_cls], 0)
return result
def create_dataset(tweets):
text_att = Attribute.create_string('TEXT')
nom_att = Attribute.create_nominal('CLASS', class_values)
dataset = Instances.create_instances("tweets", [text_att, nom_att],
len(tweets))
for tweet in tweets:
values = []
values.append(dataset.attribute(0).add_string_value(tweet))
values.append(Instance.missing_value())
inst = Instance.create_instance(values)
dataset.add_instance(inst)
dataset.class_is_last()
return dataset
train_data = loader.load_file(os.path.dirname(os.path.realpath(__file__)) + "/datasets/train.arff")
train_data.class_is_last()
string_to_word_vector_filter = Filter(classname="weka.filters.unsupervised.attribute.StringToWordVector")
cls = Classifier(classname="weka.classifiers.bayes.NaiveBayesMultinomial")
fc = FilteredClassifier()
fc.filter = string_to_word_vector_filter
fc.classifier = cls
fc.build_classifier(train_data)
# Create test data
class_att = Attribute.create_nominal("class", ["good", "neutral", "bad"])
str_att = Attribute.create_string("title")
test_dataset = Instances.create_instances(
name="test_news_set",
atts=[str_att, class_att],
capacity=1
)
inst = Instance.create_instance([Instance.missing_value(), Instance.missing_value()])
test_dataset.add_instance(inst)
test_dataset.get_instance(0).set_string_value(0, article['processed']['title'])
test_dataset.class_is_last()
# Run classifier
article_instance = test_dataset.get_instance(0)