for doc in traning_docs:
vocabulary += doc.words
vocabulary = set(vocabulary)
vocabulary_length = len(vocabulary)
topics = ["earn", "acq", "money-fx", "grain", "crude"]
knowledge = {}
# Train topic with all lexicons
for topic in topics:
t = Topic(name=topic,
documents=[doc for doc in traning_docs if doc.topic == topic],
total_n_docs=number_of_docs,
vocabulary_length=vocabulary_length)
t.train_all_features()
knowledge[topic] = t
# Select features
feature_vocabulary = []
for topic in knowledge.values():
topic.select_features(knowledge.values(), 50)
feature_vocabulary += topic.features
# Find feature vocabulary length
feature_vocabulary = set(feature_vocabulary)
feature_vocabulary_length = len(feature_vocabulary)
for topic in knowledge.values():
topic.train_mutual(feature_vocabulary)
