Exemple #1
0
 def build_word_list(self):
     text, _ = load_data.load_questions(self.file_path)
     text = text[0::2]
     text = [nlp.tokens(t) for t in text]
     text = [word for sentence in text for word in sentence]
     text = list(set(text))
     text.sort()
     return text
Exemple #2
0
 def fit(self):
     texts, targets = load_data.load_questions(self.file_path)
     data = []
     for t in texts:
         vector = self.text_vector(t, False)
         data.append(vector)
     model = svm.SVC()
     # model = GaussianNB()
     model.fit(data, targets)
     return model
 def predict(self, query, model=None, word_vector_hash=None):
     pred = self.hardcode(query)
     if pred != None:
         return pred
     if model == None or word_vector_hash == None:
         questions, types = load_data.load_questions(self.file_path)
         questions = questions[1::2]
         types = types[1::2]
         model, word_vector_hash = self.fit(questions, types)
     q = query.split(" ")
     q_vect = self.question_vectors(word_vector_hash, [q])[0]
     pred = model.predict(q_vect)[0]
     return pred
 def __init__(self, file_path, model, test_size=0.3):
     self.file_path = file_path
     self.model = model
     self.data, self.target = load_data.load_questions(self.file_path)
     self.test_size = test_size
     self.train, self.test, self.t_train, self.t_test = None, None, None, None