def PULearning_test(samples_positive, samples_unlabeled):
threshold_pd_word = 0.4
threshold_speciality = 0.8
threshold_popularity = 0.01
tsm_positive = samples_positive.tsm
tsm_unlabeled = samples_unlabeled.tsm
terms_positive_degree = select_features_by_positive_degree(tsm_positive, tsm_unlabeled, (threshold_pd_word, threshold_speciality, threshold_popularity))
vocabulary = samples_positive.corpus.vocabulary
pd.save_terms_positive_degree(terms_positive_degree, vocabulary, "./result/keywords.txt")
#samples_positive_degree_P = pd.calculate_samples_positive_degree(tsm_positive, terms_positive_degree, max_terms = 20)
#pd.save_samples_positive_degree(samples_positive, samples_positive_degree_P)
samples_positive_degree_U = pd.calculate_samples_positive_degree(tsm_unlabeled, terms_positive_degree, max_terms = 20)
pd.save_samples_positive_degree(samples_unlabeled, samples_positive_degree_U)
def show_category_keywords(self, result_dir):
if not os.path.isdir(result_dir):
try:
os.mkdir(result_dir)
except OSError:
logging.error(Logger.error("mkdir %s failed." % (result_dir)))
return
tsm = self.tsm
categories = self.get_categories()
for category_name in categories.categories_2:
category_id = categories.categories_2[category_name]
positive_samples_list, unlabeled_samples_list = tsm.get_samples_list_by_category_2(category_id)
print "%s(%d) Positive Samples: %d Unlabeled Samples: %d" % (category_name, category_id, len(positive_samples_list), len(unlabeled_samples_list))
terms_positive_degree = get_terms_positive_degree_by_category(tsm, positive_samples_list, unlabeled_samples_list)
pd.save_terms_positive_degree(terms_positive_degree, self.corpus.vocabulary, "%s/keywords_%d_%s.txt" % (result_dir, category_id, category_name))
samples_positive = None
samples_unlabeled = None