This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import os | |
import asyncio | |
import requests | |
from concurrent.futures import ThreadPoolExecutor | |
class DataLoader(): | |
def __init__(self, urls, fnames, data_dir, workers=200, verbose=True): |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
""" | |
Usage: python remove_output.py notebook.ipynb [ > without_output.ipynb ] | |
Modified from remove_output by Minrk | |
""" | |
import sys | |
import io | |
import os | |
from IPython.nbformat.current import read, write |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -*- coding: utf-8 -*- | |
import re, string | |
import unicodedata, html | |
PUNCTUATION = re.compile('[%s]' % re.escape(string.punctuation)) | |
class Fingerprinter(object): | |
''' | |
Python implementation of Google Refine fingerprinting algorithm described here: |