bert1.py

BERT 모델을 활용한 영화 리뷰 감성 분석

핵심 개념

• TensorFlow Hub를 이용한 BERT 모델 로드
• 텍스트 전처리 (preprocessing)
• IMDB 영화 리뷰 데이터셋 활용
• Small BERT 모델 사용

import os
import shutil

import tensorflow as tf
import tensorflow_hub as hub
import tensorflow_text as text
from official.nlp import optimization  # to create AdamW optimizer

import matplotlib.pyplot as plt

tf.get_logger().setLevel('ERROR')

url = 'https://ai.stanford.edu/~amaas/data/sentiment/aclImdb_v1.tar.gz'

dataset = tf.keras.utils.get_file('aclImdb_v1.tar.gz', url,
                                  untar=True, cache_dir='.',
                                  cache_subdir='')

dataset_dir = os.path.join(os.path.dirname(dataset), 'aclImdb')

train_dir = os.path.join(dataset_dir, 'train')

# remove unused folders to make it easier to load the data
remove_dir = os.path.join(train_dir, 'unsup')
shutil.rmtree(remove_dir)

AUTOTUNE = tf.data.AUTOTUNE
batch_size = 32
seed = 42

raw_train_ds = tf.keras.preprocessing.text_dataset_from_directory(
    'aclImdb/train',
    batch_size=batch_size,
    validation_split=0.2,
    subset='training',
    seed=seed)

class_names = raw_train_ds.class_names
train_ds = raw_train_ds.cache().prefetch(buffer_size=AUTOTUNE)

val_ds = tf.keras.preprocessing.text_dataset_from_directory(
    'aclImdb/train',
    batch_size=batch_size,
    validation_split=0.2,
    subset='validation',
    seed=seed)

val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)

test_ds = tf.keras.preprocessing.text_dataset_from_directory(
    'aclImdb/test',
    batch_size=batch_size)

test_ds = test_ds.cache().prefetch(buffer_size=AUTOTUNE)

for text_batch, label_batch in train_ds.take(1):
  for i in range(3):
    print(f'Review: {text_batch.numpy()[i]}')
    label = label_batch.numpy()[i]
    print(f'Label : {label} ({class_names[label]})')

bert_model_name = 'small_bert/bert_en_uncased_L-4_H-512_A-8'

map_name_to_handle = {
    'bert_en_uncased_L-12_H-768_A-12':
        'https://tfhub.dev/tensorflow/bert_en_uncased_L-12_H-768_A-12/3',
    'small_bert/bert_en_uncased_L-4_H-512_A-8':
        'https://tfhub.dev/tensorflow/small_bert/bert_en_uncased_L-4_H-512_A-8/1',
    # ... 다양한 BERT 모델 옵션
}

map_model_to_preprocess = {
    'small_bert/bert_en_uncased_L-4_H-512_A-8':
        'https://tfhub.dev/tensorflow/bert_en_uncased_preprocess/3',
    # ... 전처리 모델 매핑
}

tfhub_handle_encoder = map_name_to_handle[bert_model_name]
tfhub_handle_preprocess = map_model_to_preprocess[bert_model_name]

print(f'BERT model selected           : {tfhub_handle_encoder}')
print(f'Preprocess model auto-selected: {tfhub_handle_preprocess}')

bert_preprocess_model = hub.KerasLayer(tfhub_handle_preprocess)
text_test = ['this is such an amazing movie!']
text_preprocessed = bert_preprocess_model(text_test)

print(f'Keys       : {list(text_preprocessed.keys())}')
print(f'Shape      : {text_preprocessed["input_word_ids"].shape}')
print(f'Word Ids   : {text_preprocessed["input_word_ids"][0, :12]}')
print(f'Input Mask : {text_preprocessed["input_mask"][0, :12]}')
print(f'Type Ids   : {text_preprocessed["input_type_ids"][0, :12]}')