time_scorer.py

"""
``time_scorer -h``
::

    Tests a scorer model.  This utility expects to get a file of
    tab-separated feature values and labels from which to test a model.

    Usage:
        time_scorer -h | --help
        time_scorer <wiki> [--revs=<path>] [--model=<model>] [--batch]

    Options:
        -h --help               Prints this documentation
        <wiki>                  Wiki DB
        --revs=<path>           Path to a file containing feature values and
                                labels [default: <stdin>]
        --model=<model>         Model [default: reverted]
        --batch                 Batch
"""
import logging
import sys
import time
import urllib.request
import docopt

from itertools import zip_longest

def grouper(n, iterable, padvalue=None):
    return zip_longest(*[iter(iterable)]*n, fillvalue=padvalue)

def main(argv=None):
    args = docopt.docopt(__doc__, argv=argv)
    wiki = args['<wiki>']
    if args['--revs'] == "<stdin>":
        revs = sys.stdin
    else:
        revs = open(args['--revs'], 'r')
    model = args['--model']
    batch = args['--batch']
    run(wiki, revs, model, batch)


def run(wiki, revs, model, batch):
    base_url = "http://ores.wmflabs.org/scores/{wiki}/?models={model}&revids=".format(wiki=wiki, model=model)
    batch_size = 50 if batch else 1
    print('Batch size: {0}'.format(batch_size))
    for rev_ids in grouper(batch_size, revs):
        res_id = []
        for i in rev_ids:
            if i is None:
                 continue
            try:
                 int(i)
            except:
                 continue
            res_id.append(i.strip())
        if not res_id:
            continue
        url = base_url + '|'.join(res_id)
        start_time = time.time()
        notes = ''
        try:
            res = urllib.request.urlopen(url).read()
        except Exception as e:
            notes += 'error:' + str(e)
        process_time = time.time() - start_time
        for rev_id in res_id:
            print(rev_id.strip(), process_time, notes)


main(sys.argv[1:])