classifier.py

# coding=utf-8
# Copyright @akikaaa.

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from bert.run_classifier import *
import tensorflow as tf
import numpy as np

from tqdm import tqdm
import time

class MyProcessor(DataProcessor):

    def __init__(self):
      self.labels = ['anger', 'disgusting', 'happy', 'neutral', 'sad']


    def get_test_examples(self, data_dir):
        return self.create_examples(
            self._read_tsv(os.path.join(data_dir, "test.tsv")), "test")

    def get_train_examples(self, data_dir):
        """See base class."""
        return self.create_examples(
            self._read_tsv(os.path.join(data_dir, "train.tsv")), "train")

    def get_dev_examples(self, data_dir):
        """See base class."""
        return self.create_examples(self._read_tsv(os.path.join(data_dir, "dev.tsv")), "dev")
    # def get_dev_examples(self, data_dir):
    #     """See base class."""
    #     return self.create_examples(self._read_tsv(os.path.join(data_dir, "eval.tsv")), "dev")

    def get_pred_examples(self, data_dir):
        return self.create_examples(
            self._read_tsv(os.path.join(data_dir, "pred.tsv")), "pred")

    def get_labels(self):
        """See base class."""
        # return ["-1", "0", "1"]
        return self.labels

    def create_examples(self, lines, set_type, file_base=True):
        """Creates examples for the training and dev sets. each line is label+\t+text_a+\t+text_b """
        examples = []
        for (i, line) in tqdm(enumerate(lines)):

            # if file_base:
            #     if i == 0:
            #         continue

            guid = "%s-%s" % (set_type, i)
            text = tokenization.convert_to_unicode(line[1])
            label = tokenization.convert_to_unicode(line[0])
            # if set_type == "test" or set_type == "pred":
            #     label = "0"
            # else:
            #     label = tokenization.convert_to_unicode(line[0])
            examples.append(
                InputExample(guid=guid, text_a=text, label=label))
        return examples


def main(_):
  tf.logging.set_verbosity(tf.logging.INFO)

  processors = {
      "scene_cls": MyProcessor
  }

  if not FLAGS.do_train and not FLAGS.do_eval and not FLAGS.do_predict and not FLAGS.do_test:
    raise ValueError(
        "At least one of `do_train`, `do_eval` or `do_predict' or `do_test` must be True.")

  bert_config = modeling.BertConfig.from_json_file(FLAGS.bert_config_file)

  if FLAGS.max_seq_length > bert_config.max_position_embeddings:
    raise ValueError(
        "Cannot use sequence length %d because the BERT model "
        "was only trained up to sequence length %d" %
        (FLAGS.max_seq_length, bert_config.max_position_embeddings))

  tf.gfile.MakeDirs(FLAGS.output_dir)

  task_name = FLAGS.task_name.lower()

  if task_name not in processors:
    raise ValueError("Task not found: %s" % (task_name))

  processor = processors[task_name]()

  label_list = processor.get_labels()

  tokenizer = tokenization.FullTokenizer(
      vocab_file=FLAGS.vocab_file, do_lower_case=FLAGS.do_lower_case)

  tpu_cluster_resolver = None
  if FLAGS.use_tpu and FLAGS.tpu_name:
    tpu_cluster_resolver = tf.contrib.cluster_resolver.TPUClusterResolver(
        FLAGS.tpu_name, zone=FLAGS.tpu_zone, project=FLAGS.gcp_project)

  is_per_host = tf.contrib.tpu.InputPipelineConfig.PER_HOST_V2
  run_config = tf.contrib.tpu.RunConfig(
      cluster=tpu_cluster_resolver,
      master=FLAGS.master,
      model_dir=FLAGS.output_dir,
      save_checkpoints_steps=FLAGS.save_checkpoints_steps,
      tpu_config=tf.contrib.tpu.TPUConfig(
          iterations_per_loop=FLAGS.iterations_per_loop,
          num_shards=FLAGS.num_tpu_cores,
          per_host_input_for_training=is_per_host))

  train_examples = None
  num_train_steps = None
  num_warmup_steps = None
  if FLAGS.do_train:
    train_examples = processor.get_train_examples(FLAGS.data_dir)
    num_train_steps = int(
        len(train_examples) / FLAGS.train_batch_size * FLAGS.num_train_epochs)
    num_warmup_steps = int(num_train_steps * FLAGS.warmup_proportion)

  model_fn = model_fn_builder(
      bert_config=bert_config,
      num_labels=len(label_list),
      init_checkpoint=FLAGS.init_checkpoint,
      learning_rate=FLAGS.learning_rate,
      num_train_steps=num_train_steps,
      num_warmup_steps=num_warmup_steps,
      use_tpu=FLAGS.use_tpu,
      use_one_hot_embeddings=FLAGS.use_tpu)

  # If TPU is not available, this will fall back to normal Estimator on CPU
  # or GPU.
  estimator = tf.contrib.tpu.TPUEstimator(
      use_tpu=FLAGS.use_tpu,
      model_fn=model_fn,
      config=run_config,
      train_batch_size=FLAGS.train_batch_size,
      eval_batch_size=FLAGS.eval_batch_size,
      predict_batch_size=FLAGS.predict_batch_size)

  if FLAGS.do_train:
    train_file = os.path.join(FLAGS.output_dir, "train.tf_record")
    file_based_convert_examples_to_features(
        train_examples, label_list, FLAGS.max_seq_length, tokenizer, train_file)
    tf.logging.info("***** Running training *****")
    tf.logging.info("  Num examples = %d", len(train_examples))
    tf.logging.info("  Batch size = %d", FLAGS.train_batch_size)
    tf.logging.info("  Num steps = %d", num_train_steps)
    train_input_fn = file_based_input_fn_builder(
        input_file=train_file,
        seq_length=FLAGS.max_seq_length,
        is_training=True,
        drop_remainder=True)
    tensors_to_log = {'train loss': 'loss/Mean:0'}
    logging_hook = tf.train.LoggingTensorHook(tensors=tensors_to_log, every_n_iter=100)
    estimator.train(input_fn=train_input_fn, hooks=[logging_hook], max_steps=num_train_steps)

  if FLAGS.do_eval:
    eval_examples = processor.get_dev_examples(FLAGS.data_dir)
    num_actual_eval_examples = len(eval_examples)

    eval_file = os.path.join(FLAGS.output_dir, "eval.tf_record")
    file_based_convert_examples_to_features(
        eval_examples, label_list, FLAGS.max_seq_length, tokenizer, eval_file)

    tf.logging.info("***** Running evaluation *****")
    tf.logging.info("  Num examples = %d (%d actual, %d padding)",
                    len(eval_examples), num_actual_eval_examples,
                    len(eval_examples) - num_actual_eval_examples)
    tf.logging.info("  Batch size = %d", FLAGS.eval_batch_size)

    # This tells the estimator to run through the entire set.
    eval_steps = None
    # However, if running eval on the TPU, you will need to specify the
    # number of steps.
    if FLAGS.use_tpu:
      assert len(eval_examples) % FLAGS.eval_batch_size == 0
      eval_steps = int(len(eval_examples) // FLAGS.eval_batch_size)

    eval_drop_remainder = True if FLAGS.use_tpu else False
    eval_input_fn = file_based_input_fn_builder(
        input_file=eval_file,
        seq_length=FLAGS.max_seq_length,
        is_training=False,
        drop_remainder=eval_drop_remainder)

    result = estimator.evaluate(input_fn=eval_input_fn, steps=eval_steps)

    output_eval_file = os.path.join(FLAGS.output_dir, "eval_results.txt")
    with tf.gfile.GFile(output_eval_file, "w") as writer:
      tf.logging.info("***** Eval results *****")
      for key in sorted(result.keys()):
        tf.logging.info("  %s = %s", key, str(result[key]))
        writer.write("%s = %s\n" % (key, str(result[key])))


  if FLAGS.do_test:
    test_examples = processor.get_test_examples(FLAGS.data_dir)
    num_actual_test_examples = len(test_examples)

    test_file = os.path.join(FLAGS.output_dir, "test.tf_record")
    file_based_convert_examples_to_features(
        test_examples, label_list, FLAGS.max_seq_length, tokenizer, test_file)

    tf.logging.info("***** Running testing *****")
    tf.logging.info("  Num examples = %d (%d actual, %d padding)",
                    len(test_examples), num_actual_test_examples,
                    len(test_examples) - num_actual_test_examples)
    tf.logging.info("  Batch size = %d", FLAGS.test_batch_size)

    # This tells the estimator to run through the entire set.
    test_steps = None
    # However, if running eval on the TPU, you will need to specify the
    # number of steps.
    if FLAGS.use_tpu:
      assert len(test_examples) % FLAGS.test_batch_size == 0
      test_steps = int(len(test_examples) // FLAGS.test_batch_size)

    test_drop_remainder = True if FLAGS.use_tpu else False
    test_input_fn = file_based_input_fn_builder(
        input_file=test_file,
        seq_length=FLAGS.max_seq_length,
        is_training=False,
        drop_remainder=test_drop_remainder)

    result = estimator.evaluate(input_fn=test_input_fn, steps=test_steps)

    output_test_file = os.path.join(FLAGS.output_dir, "test_results.txt")
    with tf.gfile.GFile(output_test_file, "w") as writer:
      tf.logging.info("***** Test results *****")
      for key in sorted(result.keys()):
        tf.logging.info("  %s = %s", key, str(result[key]))
        writer.write("%s = %s\n" % (key, str(result[key])))

  if FLAGS.do_predict:
    predict_examples = processor.get_pred_examples(FLAGS.data_dir)
    num_actual_predict_examples = len(predict_examples)

    predict_file = os.path.join(FLAGS.output_dir, "predict.tf_record")
    print(predict_file)
    file_based_convert_examples_to_features(predict_examples, label_list,
                                            FLAGS.max_seq_length, tokenizer,
                                            predict_file)

    tf.logging.info("***** Running prediction*****")
    tf.logging.info("  Num examples = %d (%d actual, %d padding)",
                    len(predict_examples), num_actual_predict_examples,
                    len(predict_examples) - num_actual_predict_examples)
    tf.logging.info("  Batch size = %d", FLAGS.predict_batch_size)

    predict_drop_remainder = True if FLAGS.use_tpu else False
    predict_input_fn = file_based_input_fn_builder(
        input_file=predict_file,
        seq_length=FLAGS.max_seq_length,
        is_training=False,
        drop_remainder=predict_drop_remainder)

    start = time.time()
    result = estimator.predict(input_fn=predict_input_fn)
    cost = time.time() - start
    tf.logging.info('prediction time cost: %8f s' % cost)


    output_predict_file = os.path.join(FLAGS.output_dir, "pred_results.tsv")
    with tf.gfile.GFile(output_predict_file, "w") as writer:
        tf.logging.info("***** Predict results *****")
        for prediction in result:
            label_index = np.argmax(prediction, -1)
            label = label_list[label_index]
            output_line = "\t".join(str(class_probability) for class_probability in prediction) + "\t" + label + "\n"
            writer.write(output_line)


if __name__ == "__main__":
  flags.mark_flag_as_required("data_dir")
  flags.mark_flag_as_required("task_name")
  flags.mark_flag_as_required("vocab_file")
  flags.mark_flag_as_required("bert_config_file")
  flags.mark_flag_as_required("output_dir")
  tf.app.run()

  '''
INFO:tensorflow:***** Eval results *****
INFO:tensorflow:  eval_accuracy = 0.8647313
INFO:tensorflow:  eval_loss = 0.7771957
INFO:tensorflow:  global_step = 6072
INFO:tensorflow:  loss = 0.77480406
  '''