def _download_pretrained_model():
"""Downloads the pre-trained BIST model if non-existent."""
if not path.isfile(path.join(SpacyBISTParser.dir, 'bist.model')):
print('Downloading pre-trained BIST model...')
zip_path = path.join(SpacyBISTParser.dir, 'bist-pretrained.zip')
makedirs(SpacyBISTParser.dir, exist_ok=True)
download_unlicensed_file('https://s3-us-west-1.amazonaws.com/nervana-modelzoo/parse/',
'bist-pretrained.zip', zip_path)
print('Unzipping...')
uncompress_file(zip_path, outpath=SpacyBISTParser.dir)
remove(zip_path)
print('Done.')
def _download_pretrained_model():
"""Downloads the pre-trained BIST model if non-existent."""
if not path.isfile(SpacyBISTParser.dir / 'bist.model'):
print('Downloading pre-trained BIST model...')
zip_path = SpacyBISTParser.dir / 'bist-pretrained.zip'
makedirs(SpacyBISTParser.dir, exist_ok=True)
download_unlicensed_file(
'https://s3-us-west-2.amazonaws.com/nlp-architect-data/models/dep_parse/',
'bist-pretrained.zip', zip_path)
print('Unzipping...')
uncompress_file(zip_path, outpath=str(SpacyBISTParser.dir))
remove(zip_path)
print('Done.')
def get_file_path(self):
"""
Return local file path of downloaded model files
"""
for filename in self.files:
cached_file_path, need_downloading = cached_path(
self.base_path + filename, self.download_path)
if filename.endswith("zip"):
if need_downloading:
print("Unzipping...")
uncompress_file(cached_file_path,
outpath=self.download_path)
print("Done.")
return self.download_path
def _download_pretrained_model():
"""Downloads the pre-trained BIST model if non-existent."""
if not path.isfile(SpacyBISTParser.dir / "bist.model"):
print("Downloading pre-trained BIST model...")
zip_path = SpacyBISTParser.dir / "bist-pretrained.zip"
makedirs(SpacyBISTParser.dir, exist_ok=True)
download_unlicensed_file(
"https://d2zs9tzlek599f.cloudfront.net/models/dep_parse/",
"bist-pretrained.zip",
zip_path,
)
print("Unzipping...")
uncompress_file(zip_path, outpath=str(SpacyBISTParser.dir))
remove(zip_path)
print("Done.")
def get_model_files(self):
"""
Return individual file names of downloaded models
"""
for fileName in self.files:
cached_file_path, need_downloading = cached_path(
self.base_path + fileName, self.download_path)
if fileName.endswith("zip"):
if need_downloading:
print("Unzipping...")
uncompress_file(cached_file_path,
outpath=self.download_path)
print("Done.")
self.model_files.extend(zipfile_list(cached_file_path))
else:
self.model_files.extend([fileName])
return self.model_files
parser.add_argument('--op_thresh', type=int, default=2)
parser.add_argument('--max_iter', type=int, default=3)
parser.add_argument('--large', type=str, default="no")
args = parser.parse_args()
# Download ABSA dependencies including spacy parser and glove embeddings
from spacy.cli.download import download as spacy_download
from nlp_architect.utils.io import uncompress_file
from nlp_architect.models.absa import TRAIN_OUT, LEXICONS_OUT
spacy_download('en')
GLOVE_ZIP = os.path.join(args.data_folder, 'clothing_data/glove.840B.300d.zip')
EMBEDDING_PATH = TRAIN_OUT / 'word_emb_unzipped' / 'glove.840B.300d.txt'
uncompress_file(GLOVE_ZIP, Path(EMBEDDING_PATH).parent)
clothing_train = os.path.join(args.data_folder,
'clothing_data/clothing_absa_train_small.csv')
if args.large == 'yes':
print(f'Using large dataset: clothing_data/clothing_absa_train.csv')
clothing_train = os.path.join(args.data_folder,
'clothing_data/clothing_absa_train.csv')
else:
print(f'Using small dataset: clothing_data/clothing_absa_train_small.csv')
clothing_train = os.path.join(
args.data_folder, 'clothing_data/clothing_absa_train_small.csv')
os.makedirs('outputs', exist_ok=True)