def extract_mind(train_zip, valid_zip, train_folder="train", valid_folder="valid"):
"""Extract MIND dataset
Args:
train_zip (str): Path to train zip file
valid_zip (str): Path to valid zip file
train_folder (str): Destination forder for train set
valid_folder (str): Destination forder for validation set
Returns:
str, str: Train and validation folders
"""
root_folder = os.path.basename(train_zip)
train_path = os.path.join(root_folder, train_folder)
valid_path = os.path.join(root_folder, valid_folder)
unzip_file(train_zip, train_path)
unzip_file(valid_zip, valid_path)
return train_path, valid_path
def extract_mind(train_zip,
valid_zip,
test_zip=None,
train_folder="train",
valid_folder="valid",
test_folder='test',
root_folder=""):
"""Extract MIND dataset
Args:
train_zip (str): Path to train zip file
valid_zip (str): Path to valid zip file
train_folder (str): Destination forder for train set
valid_folder (str): Destination forder for validation set
Returns:
str, str: Train and validation folders
"""
train_path = os.path.join(root_folder, train_folder)
valid_path = os.path.join(root_folder, valid_folder)
unzip_file(train_zip, train_path)
unzip_file(valid_zip, valid_path)
if test_zip is not None:
test_path = os.path.join(root_folder, test_folder)
unzip_file(test_zip, test_path)
return train_path, valid_path, test_path
return train_path, valid_path
def _download_and_extract_globe(dest_path):
url = "http://nlp.stanford.edu/data/glove.6B.zip"
filepath = maybe_download(url=url, work_directory=dest_path)
glove_path = os.path.join(dest_path, "glove")
unzip_file(filepath, glove_path, clean_zip_file=False)
return glove_path