def generate_reference_text_file_for_conll(conll_input_filepath, conll_output_filepath, text_folder): ''' generates reference text files and adds the corresponding filename and token offsets to conll file. conll_input_filepath: path to a conll-formatted file without filename and token offsets text_folder: folder to write the reference text file to ''' dataset_type = utils.get_basename_without_extension(conll_input_filepath) conll_file = codecs.open(conll_input_filepath, 'r', 'UTF-8') utils.create_folder_if_not_exists(text_folder) text = '' new_conll_string = '' character_index = 0 document_count = 0 text_base_filename = '{0}_text_{1}'.format(dataset_type, str(document_count).zfill(5)) for line in conll_file: split_line = line.strip().split(' ') # New document if '-DOCSTART-' in split_line[0]: new_conll_string += line if len(text) != 0: with codecs.open( os.path.join(text_folder, '{0}.txt'.format(text_base_filename)), 'w', 'UTF-8') as f: f.write(text) text = '' character_index = 0 document_count += 1 text_base_filename = '{0}_text_{1}'.format( dataset_type, str(document_count).zfill(5)) continue # New sentence elif len(split_line) == 0 or len(split_line[0]) == 0: new_conll_string += '\n' if text != '': text += '\n' character_index += 1 continue token = split_line[0] start = character_index end = start + len(token) text += token + ' ' character_index += len(token) + 1 new_conll_string += ' '.join( [token, text_base_filename, str(start), str(end)] + split_line[1:]) + '\n' if len(text) != 0: with codecs.open( os.path.join(text_folder, '{0}.txt'.format(text_base_filename)), 'w', 'UTF-8') as f: f.write(text) conll_file.close() with codecs.open(conll_output_filepath, 'w', 'UTF-8') as f: f.write(new_conll_string)
def xml_to_brat(input_folder, output_folder, overwrite=True): print('input_folder: {0}'.format(input_folder)) start_time = time.time() if overwrite: shutil.rmtree(output_folder, ignore_errors=True) utils.create_folder_if_not_exists(output_folder) for input_filepath in sorted(glob.glob(os.path.join(input_folder, '*.xml'))): filename = utils.get_basename_without_extension(input_filepath) output_text_filepath = os.path.join(output_folder, '{0}.txt'.format(filename)) xmldoc = xml.etree.ElementTree.parse(input_filepath).getroot() # Get text text = xmldoc.findtext('TEXT') with codecs.open(output_text_filepath, 'w', 'UTF-8') as f: f.write(text) # Get PHI tags tags = xmldoc.findall('TAGS')[0] # [0] because there is only one <TAGS>...</TAGS> entities = [] for tag in tags: entity = {} entity['label'] = tag.get('TYPE') entity['text'] = tag.get('text') entity['start'] = int(tag.get('start')) entity['end'] = int(tag.get('end')) entities.append(entity) output_entities(output_folder, filename, entities, output_text_filepath, text, overwrite=overwrite) time_spent = time.time() - start_time print("Time spent formatting: {0:.2f} seconds".format(time_spent))
def prepare_pretrained_model_for_restoring(output_folder_name, epoch_number, model_name, delete_token_mappings=False): ''' Copy the dataset.pickle, parameters.ini, and model checkpoint files after removing the data used for training. The dataset and labels are deleted from dataset.pickle by default. The only information about the dataset that remain in the pretrained model is the list of tokens that appears in the dataset and the corresponding token embeddings learned from the dataset. If delete_token_mappings is set to True, index_to_token and token_to_index mappings are deleted from dataset.pickle additionally, and the corresponding token embeddings are deleted from the model checkpoint files. In this case, the pretrained model would not contain any information about the dataset used for training the model. If you wish to share a pretrained model with delete_token_mappings = True, it is highly recommended to use some external pre-trained token embeddings and freeze them while training the model to obtain high performance. This can be done by specifying the token_pretrained_embedding_filepath and setting freeze_token_embeddings = True in parameters.ini for training. ''' input_model_folder = os.path.join('..', 'output', output_folder_name, 'model') output_model_folder = os.path.join('..', 'trained_models', model_name) utils.create_folder_if_not_exists(output_model_folder) # trim and copy dataset.pickle input_dataset_filepath = os.path.join(input_model_folder, 'dataset.pickle') output_dataset_filepath = os.path.join(output_model_folder, 'dataset.pickle') trim_dataset_pickle(input_dataset_filepath, output_dataset_filepath, delete_token_mappings=delete_token_mappings) # copy parameters.ini parameters_filepath = os.path.join(input_model_folder, 'parameters.ini') shutil.copy(parameters_filepath, output_model_folder) # (trim and) copy checkpoint files epoch_number_string = str(epoch_number).zfill(5) if delete_token_mappings: input_checkpoint_filepath = os.path.join( input_model_folder, 'model_{0}.ckpt'.format(epoch_number_string)) output_checkpoint_filepath = os.path.join(output_model_folder, 'model.ckpt') trim_model_checkpoint(parameters_filepath, output_dataset_filepath, input_checkpoint_filepath, output_checkpoint_filepath) else: for filepath in glob.glob( os.path.join(input_model_folder, 'model_{0}.ckpt*'.format(epoch_number_string))): shutil.copyfile( filepath, os.path.join( output_model_folder, os.path.basename(filepath).replace( '_' + epoch_number_string, '')))
def _create_stats_graph_folder(self, parameters): # Initialize stats_graph_folder experiment_timestamp = utils.get_current_time_in_miliseconds() dataset_name = utils.get_basename_without_extension( parameters['dataset_text_folder']) model_name = '{0}_{1}'.format(dataset_name, experiment_timestamp) utils.create_folder_if_not_exists(parameters['output_folder']) stats_graph_folder = os.path.join( parameters['output_folder'], model_name) # Folder where to save graphs utils.create_folder_if_not_exists(stats_graph_folder) return stats_graph_folder, experiment_timestamp
def predict(self, text): """ Predict Args: text (str): Description. """ self.prediction_count += 1 if self.prediction_count == 1: self.parameters['dataset_text_folder'] = os.path.join('.', 'data', 'temp') self.stats_graph_folder, _ = self._create_stats_graph_folder(self.parameters) # Update the deploy folder, file, and modeldata dataset_type = 'deploy' # Delete all deployment data for filepath in glob.glob(os.path.join(self.parameters['dataset_text_folder'], '{0}*'.format(dataset_type))): if os.path.isdir(filepath): shutil.rmtree(filepath) else: os.remove(filepath) # # Create brat folder and file dataset_brat_deploy_folder = os.path.join(self.parameters['dataset_text_folder'], dataset_type) utils.create_folder_if_not_exists(dataset_brat_deploy_folder) dataset_brat_deploy_filepath = os.path.join(dataset_brat_deploy_folder, 'temp_{0}.txt'.format(str(self.prediction_count).zfill(5))) #self._get_dataset_brat_deploy_filepath(dataset_brat_deploy_folder) with codecs.open(dataset_brat_deploy_filepath, 'w', 'UTF-8') as f: f.write(text) # Update deploy filepaths dataset_filepaths, dataset_brat_folders = self._get_valid_dataset_filepaths(self.parameters, dataset_types=[dataset_type]) self.dataset_filepaths.update(dataset_filepaths) self.dataset_brat_folders.update(dataset_brat_folders) # Update the dataset for the new deploy set self.modeldata.update_dataset(self.dataset_filepaths, [dataset_type]) # Predict labels and output brat output_filepaths = {} prediction_output = train.prediction_step(self.sess, self.modeldata, dataset_type, self.model, self.transition_params_trained, self.prediction_count, self.parameters) return prediction_output
def output_brat(output_filepaths, dataset_brat_folders, stats_graph_folder, overwrite=False): # Output brat files for dataset_type in ['train', 'valid', 'test', 'deploy']: if dataset_type not in output_filepaths.keys(): continue brat_output_folder = os.path.join(stats_graph_folder, 'brat', dataset_type) utils.create_folder_if_not_exists(brat_output_folder) conll_to_brat(output_filepaths[dataset_type], output_filepaths[dataset_type], dataset_brat_folders[dataset_type], brat_output_folder, overwrite=overwrite)
def predict(self, text): """ Predict Args: text (str): Description. """ self.prediction_count += 1 if self.prediction_count == 1: self.parameters['dataset_text_folder'] = os.path.join( '.', 'data', 'temp') self.stats_graph_folder, _ = self._create_stats_graph_folder( self.parameters) # Update the deploy folder, file, and modeldata dataset_type = 'deploy' # Delete all deployment data for filepath in glob.glob( os.path.join(self.parameters['dataset_text_folder'], '{0}*'.format(dataset_type))): if os.path.isdir(filepath): shutil.rmtree(filepath) else: os.remove(filepath) # Create brat folder and file dataset_brat_deploy_folder = os.path.join( self.parameters['dataset_text_folder'], dataset_type) utils.create_folder_if_not_exists(dataset_brat_deploy_folder) dataset_brat_deploy_filepath = os.path.join( dataset_brat_deploy_folder, 'temp_{0}.txt'.format(str(self.prediction_count).zfill(5))) #self._get_dataset_brat_deploy_filepath(dataset_brat_deploy_folder) with codecs.open(dataset_brat_deploy_filepath, 'w', 'UTF-8') as f: f.write(text) # Update deploy filepaths dataset_filepaths, dataset_brat_folders = self._get_valid_dataset_filepaths( self.parameters, dataset_types=[dataset_type]) self.dataset_filepaths.update(dataset_filepaths) self.dataset_brat_folders.update(dataset_brat_folders) # Update the dataset for the new deploy set self.modeldata.update_dataset(self.dataset_filepaths, [dataset_type]) # Predict labels and output brat output_filepaths = {} prediction_output = train.prediction_step( self.sess, self.modeldata, dataset_type, self.model, self.transition_params_trained, self.stats_graph_folder, self.prediction_count, self.parameters, self.dataset_filepaths) _, _, output_filepaths[dataset_type] = prediction_output conll_to_brat.output_brat(output_filepaths, self.dataset_brat_folders, self.stats_graph_folder, overwrite=True) # Print and output result text_filepath = os.path.join( self.stats_graph_folder, 'brat', 'deploy', os.path.basename(dataset_brat_deploy_filepath)) annotation_filepath = os.path.join( self.stats_graph_folder, 'brat', 'deploy', '{0}.ann'.format( utils.get_basename_without_extension( dataset_brat_deploy_filepath))) text2, entities = brat_to_conll.get_entities_from_brat( text_filepath, annotation_filepath, verbose=True) assert (text == text2) return entities
def fit(self): """ Fit the model. """ parameters = self.parameters conf_parameters = self.conf_parameters dataset_filepaths = self.dataset_filepaths modeldata = self.modeldata dataset_brat_folders = self.dataset_brat_folders sess = self.sess model = self.model transition_params_trained = self.transition_params_trained stats_graph_folder, experiment_timestamp = self._create_stats_graph_folder( parameters) # Initialize and save execution details start_time = time.time() results = {} results['epoch'] = {} results['execution_details'] = {} results['execution_details']['train_start'] = start_time results['execution_details']['time_stamp'] = experiment_timestamp results['execution_details']['early_stop'] = False results['execution_details']['keyboard_interrupt'] = False results['execution_details']['num_epochs'] = 0 results['model_options'] = copy.copy(parameters) model_folder = os.path.join(stats_graph_folder, 'model') utils.create_folder_if_not_exists(model_folder) with open(os.path.join(model_folder, 'parameters.ini'), 'w') as parameters_file: conf_parameters.write(parameters_file) pickle.dump(modeldata, open(os.path.join(model_folder, 'dataset.pickle'), 'wb')) tensorboard_log_folder = os.path.join(stats_graph_folder, 'tensorboard_logs') utils.create_folder_if_not_exists(tensorboard_log_folder) tensorboard_log_folders = {} for dataset_type in dataset_filepaths.keys(): tensorboard_log_folders[dataset_type] = os.path.join( stats_graph_folder, 'tensorboard_logs', dataset_type) utils.create_folder_if_not_exists( tensorboard_log_folders[dataset_type]) # Instantiate the writers for TensorBoard writers = {} for dataset_type in dataset_filepaths.keys(): writers[dataset_type] = tf.summary.FileWriter( tensorboard_log_folders[dataset_type], graph=sess.graph) # embedding_writer has to write in model_folder, otherwise TensorBoard won't be able to view embeddings embedding_writer = tf.summary.FileWriter(model_folder) embeddings_projector_config = projector.ProjectorConfig() tensorboard_token_embeddings = embeddings_projector_config.embeddings.add( ) tensorboard_token_embeddings.tensor_name = model.token_embedding_weights.name token_list_file_path = os.path.join(model_folder, 'tensorboard_metadata_tokens.tsv') tensorboard_token_embeddings.metadata_path = os.path.relpath( token_list_file_path, '.') tensorboard_character_embeddings = embeddings_projector_config.embeddings.add( ) tensorboard_character_embeddings.tensor_name = model.character_embedding_weights.name character_list_file_path = os.path.join( model_folder, 'tensorboard_metadata_characters.tsv') tensorboard_character_embeddings.metadata_path = os.path.relpath( character_list_file_path, '.') projector.visualize_embeddings(embedding_writer, embeddings_projector_config) # Write metadata for TensorBoard embeddings token_list_file = codecs.open(token_list_file_path, 'w', 'UTF-8') for token_index in range(modeldata.vocabulary_size): token_list_file.write('{0}\n'.format( modeldata.index_to_token[token_index])) token_list_file.close() character_list_file = codecs.open(character_list_file_path, 'w', 'UTF-8') for character_index in range(modeldata.alphabet_size): if character_index == modeldata.PADDING_CHARACTER_INDEX: character_list_file.write('PADDING\n') else: character_list_file.write('{0}\n'.format( modeldata.index_to_character[character_index])) character_list_file.close() # Start training + evaluation loop. Each iteration corresponds to 1 epoch. # number of epochs with no improvement on the validation test in terms of F1-score bad_counter = 0 previous_best_valid_f1_score = 0 epoch_number = -1 try: while True: step = 0 epoch_number += 1 print('\nStarting epoch {0}'.format(epoch_number)) epoch_start_time = time.time() if epoch_number != 0: # Train model: loop over all sequences of training set with shuffling sequence_numbers = list( range(len(modeldata.token_indices['train']))) random.shuffle(sequence_numbers) for sequence_number in sequence_numbers: transition_params_trained = train.train_step( sess, modeldata, sequence_number, model, parameters) step += 1 if step % 10 == 0: print('Training {0:.2f}% done'.format( step / len(sequence_numbers) * 100), end='\r', flush=True) epoch_elapsed_training_time = time.time() - epoch_start_time print('Training completed in {0:.2f} seconds'.format( epoch_elapsed_training_time), flush=True) y_pred, y_true, output_filepaths = train.predict_labels( sess, model, transition_params_trained, parameters, modeldata, epoch_number, stats_graph_folder, dataset_filepaths) # Evaluate model: save and plot results evaluate.evaluate_model(results, modeldata, y_pred, y_true, stats_graph_folder, epoch_number, epoch_start_time, output_filepaths, parameters) if parameters['use_pretrained_model'] and not parameters[ 'train_model']: conll_to_brat.output_brat(output_filepaths, dataset_brat_folders, stats_graph_folder) break # Save model model.saver.save( sess, os.path.join(model_folder, 'model_{0:05d}.ckpt'.format(epoch_number))) # Save TensorBoard logs summary = sess.run(model.summary_op, feed_dict=None) writers['train'].add_summary(summary, epoch_number) writers['train'].flush() utils.copytree(writers['train'].get_logdir(), model_folder) # Early stop valid_f1_score = results['epoch'][epoch_number][0]['valid'][ 'f1_score']['micro'] if valid_f1_score > previous_best_valid_f1_score: bad_counter = 0 previous_best_valid_f1_score = valid_f1_score conll_to_brat.output_brat(output_filepaths, dataset_brat_folders, stats_graph_folder, overwrite=True) self.transition_params_trained = transition_params_trained else: bad_counter += 1 print( "The last {0} epochs have not shown improvements on the validation set." .format(bad_counter)) if bad_counter >= parameters['patience']: print('Early Stop!') results['execution_details']['early_stop'] = True break if epoch_number >= parameters['maximum_number_of_epochs']: break except KeyboardInterrupt: results['execution_details']['keyboard_interrupt'] = True print('Training interrupted') print('Finishing the experiment') end_time = time.time() results['execution_details']['train_duration'] = end_time - start_time results['execution_details']['train_end'] = end_time evaluate.save_results(results, stats_graph_folder) for dataset_type in dataset_filepaths.keys(): writers[dataset_type].close()
def conll_to_brat(conll_input_filepath, conll_output_filepath, brat_original_folder, brat_output_folder, overwrite=False): ''' convert conll file in conll-filepath to brat annotations and output to brat_output_folder, with reference to the existing text files in brat_original_folder if brat_original_folder does not exist or contain any text file, then the text files are generated from conll files, and conll file is updated with filenames and token offsets accordingly. conll_input_filepath: path to conll file to convert to brat annotations conll_output_filepath: path to output conll file with filename and offsets that are compatible with brat annotations brat_original_folder: folder that contains the original .txt (and .ann) files that are formatted according to brat. .txt files are used to check if the token offsets match and generate the annotation from conll. brat_output_folder: folder to output the text and brat annotations .txt files are copied from brat_original_folder to brat_output_folder ''' verbose = False dataset_type = utils.get_basename_without_extension(conll_input_filepath) print("Formatting {0} set from CONLL to BRAT... ".format(dataset_type), end='') # if brat_original_folder does not exist or have any text file if not os.path.exists(brat_original_folder) or len( glob.glob(os.path.join(brat_original_folder, '*.txt'))) == 0: assert (conll_input_filepath != conll_output_filepath) generate_reference_text_file_for_conll(conll_input_filepath, conll_output_filepath, brat_original_folder) utils.create_folder_if_not_exists(brat_output_folder) conll_file = codecs.open(conll_output_filepath, 'r', 'UTF-8') previous_token_label = 'O' previous_filename = '' text_filepath = '' text = '' entity_id = 1 entities = [] entity = {} for line in conll_file: line = line.strip().split(' ') # New sentence if len(line) == 0 or len(line[0]) == 0 or '-DOCSTART-' in line[0]: # Add the last entity if entity != {}: if verbose: print("entity: {0}".format(entity)) entities.append(entity) entity_id += 1 entity = {} previous_token_label = 'O' continue filename = str(line[1]) # New file if filename != previous_filename: output_entities(brat_output_folder, previous_filename, entities, text_filepath, text, overwrite=overwrite) text_filepath = os.path.join(brat_original_folder, '{0}.txt'.format(filename)) with codecs.open(text_filepath, 'r', 'UTF-8') as f: text = f.read() previous_token_label = 'O' previous_filename = filename entity_id = 1 entities = [] entity = {} label = str(line[-1]).replace('_', '-') # For LOCATION-OTHER if label == 'O': # Previous entity ended if previous_token_label != 'O': if verbose: print("entity: {0}".format(entity)) entities.append(entity) entity_id += 1 entity = {} previous_token_label = 'O' continue token = {} token['text'] = str(line[0]) token['start'] = int(line[2]) token['end'] = int(line[3]) # check that the token text matches the original if token['text'] != text[token['start']:token['end']].replace( ' ', '-'): print("Warning: conll and brat text do not match.") print("\tCONLL: {0}".format(token['text'])) print("\tBRAT : {0}".format(text[token['start']:token['end']])) token['label'] = label[2:] if label[:2] == 'B-': if previous_token_label != 'O': # End the previous entity if verbose: print("entity: {0}".format(entity)) entities.append(entity) entity_id += 1 # Start a new entity entity = token elif label[:2] == 'I-': # Entity continued if previous_token_label == token['label']: # if there is no newline between the entity and the token if '\n' not in text[entity['end']:token['start']]: # Update entity entity['text'] = entity['text'] + ' ' + token['text'] entity['end'] = token['end'] else: # newline between the entity and the token # End the previous entity if verbose: print("entity: {0}".format(entity)) entities.append(entity) entity_id += 1 # Start a new entity entity = token elif previous_token_label != 'O': # TODO: count BI or II incompatibility # End the previous entity if verbose: print("entity: {0}".format(entity)) entities.append(entity) entity_id += 1 # Start new entity entity = token else: # previous_token_label == 'O' # TODO: count OI incompatibility # Start new entity entity = token previous_token_label = token['label'] output_entities(brat_output_folder, previous_filename, entities, text_filepath, text, overwrite=overwrite) conll_file.close() print('Done.')