cthoyt

"""This file contains code that implements the original ID* algorithm.

The algorithm is described in the paper "Complete Identification Methods for the Causal Hierarchy"
but the algorithm itself is not complete, as there are identifiable queries that cannot be
identified with this algorithm.
"""

import logging
from typing import Collection, Set, Tuple, cast

cthoyt

import time

import pystow
import requests
from bioregistry.external import get_obofoundry
from tqdm.auto import tqdm

TOKEN = pystow.get_config("github", "token")

TEXT_FORMAT = """\

cthoyt

cthoyt

cthoyt

The purpose of this script is to assist in connecting all contributors to OBO Foundry ontologies to Wikidata pages via their GitHub usernames. Here's a screencast of me explaining this and showing some demo curations: https://www.youtube.com/watch?v=ERJyrh7UIbg

Progress can be observed via the [Wikidata Query Service](https://query.wikidata.org/#SELECT%20DISTINCT%20%3Fgithub%20%3Fname%20%3Fperson%20%3FpersonLabel%20%3FgenderLabel%0AWHERE%0A%7B%0A%20%20%20%20VALUES%20%28%3Fgithub%20%3Fname%29%20%7B%20%0A%20%20%20%20%20%20%20%20%28%22ANiknejad%22%20%22Anne%20Niknejad%22%29%20%28%22AlanRace%22%20%22Alan%20Race%22%29%20%28%22AmosBairoch%22%20UNDEF%29%20%28%22AnaReisCosta%22%20UNDEF%29%20%28%22Anoosha-Sehar%22%20%22Anoosha%20Sehar%22%29%20%28%22AntonPetrov%22%20%22Anton%20Petrov%22%29%20%28%22Antonarctica%22%20UNDEF%29%20%28%22Antonialock%22%20%22Antonia%22%29%20%28%22Apujar%22%20%22Anu%22%29%20%28%22Aqua1ung%22%20%22Cristian%20Cocos%22%29%20%28%22Arlene-1998%22%20%22Arlene%22%29%20%28%22Astghik-S%22%20UNDEF%29%2

cthoyt

import bioregistry


def main():
    """Identify resources with uncurated bananas."""
    for resource in bioregistry.resources():
        pattern = resource.get_pattern()
        if not pattern:
            continue
        for peel in ":_-":

cthoyt

"""Get Journal of Cheminformatics DOIs."""

import requests
import pystow

MODULE = pystow.module("jcheminf", "volumes")
USER = "egonw"  # alternative use first-party jcheminform if it ever gets updated
REPO = "jcheminform-kb"
BRANCH = "main"
PREFIX = "https://doi.org/10.1186/"

cthoyt

"""Update the dependencies."""

import json
from pathlib import Path
from typing import Iterable, Optional

import bioontologies
import bioregistry
import click
from bioontologies.obograph import Graph

cthoyt

"""Generate author list text from a Google Sheet."""

from operator import itemgetter

import click
import pandas as pd

ROLE = {"Lead": 0, "Senior": 2}

SUPERSCRIPTS = {

cthoyt