Python ToLower Examples

Example #1

File: functions.py Project: pan-webis-de/schaetti18c

def text_transformer(n_gram, window_size):
    """
    Get tweet transformer
    :param lang:
    :param n_gram:
    :return:
    """
    if n_gram == 'c1':
        return transforms.Compose([
            ltransforms.ToLower(),
            ltransforms.Character(),
            ltransforms.ToIndex(start_ix=0),
            ltransforms.ToNGram(n=window_size, overlapse=True),
            ltransforms.Reshape((-1, window_size)),
            ltransforms.MaxIndex(max_id=settings.voc_sizes[n_gram] - 1)
        ])
    else:
        return transforms.Compose([
            ltransforms.ToLower(),
            ltransforms.Character2Gram(),
            ltransforms.ToIndex(start_ix=0),
            ltransforms.ToNGram(n=window_size, overlapse=True),
            ltransforms.Reshape((-1, window_size)),
            ltransforms.MaxIndex(max_id=settings.voc_sizes[n_gram] - 1)
        ])

Example #2

File: functions.py Project: nschaetti/PAN18-Author-Profiling

def tweet_transformer(lang, n_gram, voc=None):
    """
    Get tweet transformer
    :param lang:
    :param n_gram:
    :return:
    """
    if voc is None:
        token_to_ix = dict()
    else:
        token_to_ix = voc
    # end if
    if n_gram == 'c1':
        return transforms.Compose([
            ltransforms.RemoveRegex(
                regex=r'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+'),
            ltransforms.ToLower(),
            ltransforms.Character(),
            ltransforms.ToIndex(start_ix=1, token_to_ix=token_to_ix),
            ltransforms.ToLength(length=settings.min_length),
            ltransforms.MaxIndex(max_id=settings.voc_sizes[n_gram][lang] - 1)
        ])
    else:
        return transforms.Compose([
            ltransforms.RemoveRegex(
                regex=r'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+'),
            ltransforms.ToLower(),
            ltransforms.Character2Gram(),
            ltransforms.ToIndex(start_ix=1, token_to_ix=token_to_ix),
            ltransforms.ToLength(length=settings.min_length),
            ltransforms.MaxIndex(max_id=settings.voc_sizes[n_gram][lang] - 1)
        ])

Example #3

File: functions.py Project: pan-webis-de/schaetti18c

def text_transformer_cnn(window_size, n_gram, token_to_ix):
    """
    Get text transformer for CNNSCD
    :param window_size:
    :param n_gram:
    :return:
    """
    if n_gram == 'c1':
        return ltransforms.Compose([
            ltransforms.ToLower(),
            ltransforms.Character(),
            ltransforms.ToIndex(start_ix=1, token_to_ix=token_to_ix),
            ltransforms.ToLength(length=window_size),
            ltransforms.Reshape((-1)),
            ltransforms.MaxIndex(max_id=settings.voc_sizes[n_gram])
        ])
    else:
        return ltransforms.Compose([
            ltransforms.ToLower(),
            ltransforms.Character2Gram(),
            ltransforms.ToIndex(start_ix=1, token_to_ix=token_to_ix),
            ltransforms.ToLength(length=window_size),
            ltransforms.Reshape((-1)),
            ltransforms.MaxIndex(max_id=settings.voc_sizes[n_gram])
        ])

Example #4

File: model_cnndist_sents_class.py Project: nschaetti/PAN18-Style-Change-Detection

    model.cuda()
# end if

# Load model and voc
model.load_state_dict(torch.load(open(args.model, 'rb')))
if args.cuda:
    model.cuda()
# end if
voc = torch.load(open(args.voc, 'rb'))

# Eval
model.eval()

if args.n_gram == 'c1':
    transforms = ltransforms.Compose([
        ltransforms.ToLower(),
        ltransforms.Character(),
        ltransforms.ToIndex(start_ix=1, token_to_ix=voc),
        ltransforms.ToLength(length=window_size),
        ltransforms.MaxIndex(max_id=settings.voc_sizes[args.n_gram])
    ])
else:
    transforms = ltransforms.Compose([
        ltransforms.ToLower(),
        ltransforms.Character2Gram(),
        ltransforms.ToIndex(start_ix=1, token_to_ix=voc),
        ltransforms.ToLength(length=window_size),
        ltransforms.MaxIndex(max_id=settings.voc_sizes[args.n_gram])
    ])
# end if