a7v8x

[1,2,3].length; // 3
[1,2,3].push(4); // [1,2,3,4] * 
[1,2,3].unshift(0); // [0,1,2,3] *
[1,2,3].pop(); // [1,2] *
[1,2,3].shift(); // [2,3] *
[1,2,3].at(2); // 3 
[1,2,3].indexOf(3); // 2
[1,2,3].includes(3); // true
[1,2,3].map((num) => Math.pow(num, 2)); // [1, 4, 9] 
[1,2,3].filter((num) => num % 2); // [1,3]

a7v8x

from transformers import TFBertForSequenceClassification
import tensorflow as tf

# recommended learning rate for Adam 5e-5, 3e-5, 2e-5
learning_rate = 2e-5
# we will do just 1 epoch for illustration, though multiple epochs might be better as long as we will not overfit the model
number_of_epochs = 1

# model initialization
model = TFBertForSequenceClassification.from_pretrained('bert-base-uncased')

a7v8x

# train dataset
ds_train_encoded = encode_examples(ds_train).shuffle(10000).batch(batch_size)
# test dataset
ds_test_encoded = encode_examples(ds_test).batch(batch_size)

a7v8x

# map to the expected input to TFBertForSequenceClassification, see here 
def map_example_to_dict(input_ids, attention_masks, token_type_ids, label):
  return {
      "input_ids": input_ids,
      "token_type_ids": token_type_ids,
      "attention_mask": attention_masks,
  }, label
def encode_examples(ds, limit=-1):
  # prepare list, so that we can build up final TensorFlow dataset from slices.
  input_ids_list = []

a7v8x

for review, label in tfds.as_numpy(ds_train.take(5)):
    print('review', review.decode()[0:50], label)
<<
review This was an absolutely terrible movie. Don't be lu 0
review I have been known to fall asleep during films, but 0
review Mann photographs the Alberta Rocky Mountains in a  0
review This is the kind of film for a snowy Sunday aftern 1
review As others have mentioned, all the women that go nu 1

a7v8x

tfds.core.DatasetInfo(
    name='imdb_reviews',
    version=1.0.0,
    description='Large Movie Review Dataset.
This is a dataset for binary sentiment classification containing substantially more data than previous benchmark datasets. We provide a set of 25,000 highly polar movie reviews for training, and 25,000 for testing. There is additional unlabeled data for use as well.',
    homepage='http://ai.stanford.edu/~amaas/data/sentiment/',
    features=FeaturesDict({
        'label': ClassLabel(shape=(), dtype=tf.int64, num_classes=2),
        'text': Text(shape=(), dtype=tf.string),
    }),

a7v8x

import tensorflow_datasets as tfds
(ds_train, ds_test), ds_info = tfds.load('imdb_reviews', 
          split = (tfds.Split.TRAIN, tfds.Split.TEST),
          as_supervised=True,
          with_info=True)
print('info', ds_info)

a7v8x

bert_input = tokenizer.encode_plus(
                        test_sentence,                      
                        add_special_tokens = True, # add [CLS], [SEP]
                        max_length = max_length_test, # max length of the text that can go to BERT
                        pad_to_max_length = True, # add [PAD] tokens
                        return_attention_mask = True, # add attention mask to not focus on pad tokens
              )
print('encoded', bert_input)

a7v8x

tokenized ['[CLS]', 'test', 'token', '##ization', 'sentence', '.', 'followed', 'by', 'another', 'sentence', '[SEP]']
{
  'token_ids': [101, 3231, 19204, 3989, 6251, 1012, 2628, 2011, 2178, 6251, 102, 0, 0, 0, 0, 0, 0, 0, 0, 0],
  'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 
  'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
}

a7v8x

from transformers import BertTokenizer

tokenizer = BertTokenizer.from_pretrained('bert-base-uncased', do_lower_case=True)


max_length_test = 20
test_sentence = 'Test tokenization sentence. Followed by another sentence'

# add special tokens
test_sentence_with_special_tokens = '[CLS]' + test_sentence + '[SEP]'