bennokr

TLJH setup

the patch is to customize /opt/tljh/hub/share/jupyterhub/templates/login.html

bennokr

from flask import Flask, request, abort, render_template

app = Flask(__name__, template_folder='.')

import gspread
import textwrap


gc = gspread.oauth(
    credentials_filename='credentials.json',

bennokr

{"installed":{"client_id":"258409864674-jcqkeivqrd8dcb2gv5egl76g384vflld.apps.googleusercontent.com","project_id":"scopus-review","auth_uri":"https://accounts.google.com/o/oauth2/auth","token_uri":"https://oauth2.googleapis.com/token","auth_provider_x509_cert_url":"https://www.googleapis.com/oauth2/v1/certs","client_secret":"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","redirect_uris":["http://localhost"]}}

bennokr

"""
Convert an Apple Binary Property List (bplist) to json
"""

import ccl_bplist # https://github.com/cclgroupltd/ccl-bplist

from datetime import datetime

def clean_archive(d):
    if type(d) in [dict, ccl_bplist.NsKeyedArchiverDictionary]:

bennokr

Extract citations from Wikipedia dumps

This script makes a best-effort at resolving inline references and citations. Wikipedia citations are complicated, so this is a quick and dirty hack. It's intented for research in resolving citations and natural language processing.

Similar tools:

• https://github.com/mediawiki-utilities/python-mwcites

bennokr

from flask import Flask, g, request, render_template_string, redirect, url_for
from werkzeug.middleware.proxy_fix import ProxyFix
import sqlite3
import pathlib

app = Flask(__name__)
app.url_map.strict_slashes = False
app.wsgi_app = ProxyFix(
    app.wsgi_app, x_for=1, x_proto=1, x_host=1, x_prefix=1
)

bennokr

Jupyter Binder with git collaboration

This gist can be changed via binder!

bennokr

[
  {
    "id": 10259,
    "cuisine": "greek",
    "ingredients": [
      "romaine lettuce",
      "black olives",
      "grape tomatoes",
      "garlic",
      "pepper",

bennokr

BEGIN TRANSACTION;
CREATE TABLE categorylinks (
  cl_from integer  NOT NULL DEFAULT '0'
,  cl_to blob NOT NULL DEFAULT ''
,  cl_sortkey blob NOT NULL DEFAULT ''
,  cl_timestamp timestamp NOT NULL DEFAULT current_timestamp
,  cl_sortkey_prefix blob NOT NULL DEFAULT ''
,  cl_collation blob NOT NULL DEFAULT ''
,  cl_type text  NOT NULL DEFAULT 'page'
,  PRIMARY KEY (cl_from,cl_to)

bennokr

from mip import *
import string, collections
a = string.ascii_uppercase
item_clusters, cluster_size = {}, collections.Counter()
for ci,c in enumerate([a[:6],a[:3],a[3:6],a[6:10],a[10:12]]):
    for i in c:
        name = 'c'+str(ci)
        cluster_size[name] += 1
        item_clusters.setdefault(i, set()).add( name )
print(item_clusters, cluster_size)