def predict_dataset(self): if self.predict_queue is None: self.predict_queue = PathContextReader.PathContextReader(word_to_index=self.word_to_index, path_to_index=self.path_to_index, target_word_to_index=self.target_word_to_index, config=self.config, is_evaluating=True) self.predict_placeholder = self.predict_queue.get_input_placeholder() self.predict_top_words_op, self.predict_top_values_op, self.predict_original_names_op, \ self.attention_weights_op, self.predict_source_string, self.predict_path_string, self.predict_path_target_string = \ self.build_test_graph(self.predict_queue.get_filtered_batches(), normalize_scores=True) self.initialize_session_variables(self.sess) self.saver = tf.train.Saver() self.load_model(self.sess) self.predict_data_lines = common.load_file_lines(self.config.TEST_PATH) with open(self.config.OUTPUT_FILE, 'a+') as output_file: batch_num = 0 for batch in common.split_to_batches(self.predict_data_lines, self.config.TEST_BATCH_SIZE): batch_num += 1 top_words, top_scores, original_names, attention_weights, source_strings, path_strings, target_strings = self.sess.run( [self.predict_top_words_op, self.predict_top_values_op, self.predict_original_names_op, self.attention_weights_op, self.predict_source_string, self.predict_path_string, self.predict_path_target_string], feed_dict={self.predict_placeholder: batch}) top_words, original_names = common.binary_to_string_matrix(top_words), common.binary_to_string_matrix(original_names) original_names = [w for l in original_names for w in l] for res_index in range(len(original_names)): output_file.write("%s;" % (original_names[res_index],)) output_file.write(";".join(top_words[res_index])) output_file.write("\n") print("Finished batch %s with %s elements" % (batch_num, len(original_names)))
def _eval_in_file(self, data_file_path, output_file): top_k, precision, recall, f1 = self.model.evaluate(common.load_file_lines(data_file_path)) output_file.write("%s;%s;%s;%s" % (self.current_batch,precision, recall, f1)) for topk_val in top_k: output_file.write(";%s" % (topk_val,)) output_file.write("\n") output_file.flush()
def evaluate(self): eval_start_time = time.time() if self.eval_queue is None: self.eval_queue = PathContextReader.PathContextReader(word_to_index=self.word_to_index, path_to_index=self.path_to_index, target_word_to_index=self.target_word_to_index, config=self.config, is_evaluating=True) self.eval_placeholder = self.eval_queue.get_input_placeholder() self.eval_top_words_op, self.eval_top_values_op, self.eval_original_names_op, _, _, _, _, self.eval_code_vectors = \ self.build_test_graph(self.eval_queue.get_filtered_batches()) self.saver = tf.train.Saver() if self.config.LOAD_PATH and not self.config.TRAIN_PATH: self.initialize_session_variables(self.sess) self.load_model(self.sess) if self.config.RELEASE: release_name = self.config.LOAD_PATH + '.release' print('Releasing model, output model: %s' % release_name ) self.saver.save(self.sess, release_name ) return None if self.eval_data_lines is None: print('Loading test data from: ' + self.config.TEST_PATH) self.eval_data_lines = common.load_file_lines(self.config.TEST_PATH) print('Done loading test data') with open('log.txt', 'w') as output_file: if self.config.EXPORT_CODE_VECTORS: code_vectors_file = open(self.config.TEST_PATH + '.vectors', 'w') num_correct_predictions = np.zeros(self.topk) total_predictions = 0 total_prediction_batches = 0 true_positive, false_positive, false_negative = 0, 0, 0 start_time = time.time() for batch in common.split_to_batches(self.eval_data_lines, self.config.TEST_BATCH_SIZE): top_words, top_scores, original_names, code_vectors = self.sess.run( [self.eval_top_words_op, self.eval_top_values_op, self.eval_original_names_op, self.eval_code_vectors], feed_dict={self.eval_placeholder: batch}) top_words, original_names = common.binary_to_string_matrix(top_words), common.binary_to_string_matrix( original_names) # Flatten original names from [[]] to [] original_names = [w for l in original_names for w in l] num_correct_predictions = self.update_correct_predictions(num_correct_predictions, output_file, zip(original_names, top_words)) true_positive, false_positive, false_negative = self.update_per_subtoken_statistics( zip(original_names, top_words), true_positive, false_positive, false_negative) total_predictions += len(original_names) total_prediction_batches += 1 if self.config.EXPORT_CODE_VECTORS: self.write_code_vectors(code_vectors_file, code_vectors) if total_prediction_batches % self.num_batches_to_log == 0: elapsed = time.time() - start_time # start_time = time.time() self.trace_evaluation(output_file, num_correct_predictions, total_predictions, elapsed, len(self.eval_data_lines)) print('Done testing, epoch reached') output_file.write(str(num_correct_predictions / total_predictions) + '\n') if self.config.EXPORT_CODE_VECTORS: code_vectors_file.close() elapsed = int(time.time() - eval_start_time) precision, recall, f1 = self.calculate_results(true_positive, false_positive, false_negative) print("Evaluation time: %sH:%sM:%sS" % ((elapsed // 60 // 60), (elapsed // 60) % 60, elapsed % 60)) del self.eval_data_lines self.eval_data_lines = None return num_correct_predictions / total_predictions, precision, recall, f1