In [ ]:

    

# Run this cell before the lab !
import numpy as np
import os
import os.path as op

import zipfile
try:
    from urllib.request import urlretrieve
except ImportError:  # Python 2 compat
    from urllib import urlretrieve


# BBC dataset
BBC_DATASET_URL = "http://mlg.ucd.ie/files/datasets/bbc-fulltext.zip"
zip_filename = BBC_DATASET_URL.rsplit('/', 1)[1]
BBC_DATASET_FOLDER = 'bbc'
if not op.exists(zip_filename):
    print("Downloading %s to %s..." % (BBC_DATASET_URL, zip_filename))
    urlretrieve(BBC_DATASET_URL, zip_filename)

if not op.exists(BBC_DATASET_FOLDER):
    with zipfile.ZipFile(zip_filename, 'r') as f:
        print("Extracting contents of %s..." % zip_filename)
        f.extractall('.')

# Get pretrained Glove Word2Vec
URL_REPRESENTATIONS = "https://github.com/m2dsupsdlclass/lectures-labs/releases/download/0.3/glove100k.100d.zip"
ZIP_REPRESENTATIONS = "glove100k.100d.zip"
FILE_REPRESENTATIONS = "glove100K.100d.txt"

if not op.exists(ZIP_REPRESENTATIONS):
    print('Downloading from %s to %s...' % (URL_REPRESENTATIONS, ZIP_REPRESENTATIONS))
    urlretrieve(URL_REPRESENTATIONS, './' + ZIP_REPRESENTATIONS)
    
if not op.exists(FILE_REPRESENTATIONS):
    print("extracting %s..." % ZIP_REPRESENTATIONS)
    myzip = zipfile.ZipFile(ZIP_REPRESENTATIONS)
    myzip.extractall()
    
# Get the Nietzche dataset
from tensorflow.keras.utils import get_file

URL = "https://s3.amazonaws.com/text-datasets/nietzsche.txt"

corpus_path = get_file('nietzsche.txt', origin=URL)


    

In [ ]: