def test_tfidf(self): clean_tmp() t = TfIdf(self.data, root_dir) self.assertTrue(t.idf_cache['I'] < t.idf_cache['hello']) self.assertTrue(t.idf_cache['I'] < t.idf_cache['You']) self.assertTrue(t.idf_cache['I'] < t.idf_cache['not exist feature'], "test default idf_default_val") result1 = t.tfidf_in_a_doc(self.data[1]) self.assertTrue(result1['I'] < result1['You']) self.assertTrue(result1['You'] < result1['hello']) self.assertTrue(result1['hello'] == result1['world']) clean_tmp()