he7d3r

Copied from https://github.com/wikimedia/articlequality/blob/5a7b0054af8f018d5569acc35648fc0293d0ed40/model_info/ptwiki.wp10.md

Full period; Bots included

Model Information: - type: GradientBoosting - version: 0.8.0 - params: {'min_samples_split': 2, 'label_weights': None, 'max_depth': 7, 'min_impurity_split': None, 'learning_rate': 0.01, 'verbose': 0, 'max_features': 'log2', 'center': True, 'subsample': 1.0, 'n_estimators': 300, 'warm_start': False, 'multilabel': False, 'min_samples_leaf': 1, 'labels': ['1', '2', '3', '4', '5', '6'], 'scale': True, 'presort': 'auto', 'population_rates': None, 'loss': 'deviance', 'random_state': None, 'max_leaf_nodes': None, 'init': None, 'n_iter_no_change': None, 'criterion': 'friedman_mse', 'min_impurity_decrease': 0.0, 'validation_fraction': 0.1, 'tol': 0.0001, 'min_weight_fraction_leaf': 0.0} Environment: - revscoring_version: '2.6.9' - platform: 'Linux-4.9.0-11-amd64-x86_64-with-debian-9.12' - machine: 'x86_64'

he7d3r

he7d3r

he7d3r

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline

# Before and after https://github.com/wikimedia/articlequality/pull/127
file_names = ['ptwiki.labelings.20200301.json',
              'ptwiki.labelings.20200301.extractor-and-reverts.json']
sets = []
for file_name in file_names:

he7d3r

Usage

1. Open the Moodle course of interest and go to Administration> Course Administration > Reports > Logs.
2. Click on "Get these logs"
3. Download table data as comma separated values (e.g. input1.csv). The script will use this as one of its input files.
4. Create a file "videos.csv", with a column title (containing the titles that are present in the logs) and a column length, with the length (in minutes) of each video.
5. Run the script passing the names of the csv files used as input and output:

$ python process-moodle-logs.py --logs input1.csv --videos videos.csv --stats output.csv --aggregated output_agg.csv

6. Check out the resulting two files:

he7d3r

#!/usr/bin/python3
# Copyright © 2018 He7d3r <http://he7d3r.mit-license.org>
import argparse
import re
import fileinput
from pathlib import Path

re_rule = re.compile("<(?:Typo)?\s+(?:word=\"(.*?)\"\s+)?find=\"(.*?)\"\s+replace=\"(.*?)\"\s*\/?>")

def fix_typos(typos, filename):

he7d3r

#!/usr/bin/perl -w

# Code : Dake
use strict;
use Parse::MediaWikiDump;
use utf8;

my $dump = shift(@ARGV) or die "Please specify a dump file";
my $pages = Parse::MediaWikiDump::Pages->new($dump);
my $page;

he7d3r

// Based on https://meta.wikimedia.org/wiki/User:Krinkle/Tools/Global_SUL.js?oldid=10130488
/**
 * This script provides an extra Special-page action called "WMGrep" which
 * allows searching over all WMF wikis.
 * After enabling the script, the tool is accessible from [[Special:BlankPage/wmgrep]].
 *
 * @source meta.wikimedia.org/wiki/User:Krinkle/Tools/Global_SUL
 * @revision 4 (2014-10-08)
 * @stats [[File:Krinkle_Global_SUL.js]]
 */

he7d3r

# The raw original list is at
# https://gist.github.com/Ladsgroup/cc22515f55ae3d868f47/c7343517b47b6908ac89e3bd2df68f9cee6cd188#file-ptwiki
# Caveats: https://meta.wikimedia.org/w/index.php?title=Research_talk:Revision_scoring_as_a_service&oldid=12148651#Badwords

adoro
aki
amo
bla
blablabla
coco

he7d3r

from revscoring.features import *
from revscoring.datasources import *
features = [added_badwords_ratio, added_misspellings_ratio, badwords_added,
    bytes_changed, chars_added, day_of_week_in_utc, hour_of_day_in_utc,
    is_content_namespace, is_custom_comment, is_mainspace,
    is_previous_user_same, is_section_comment, longest_repeated_char_added,
    longest_token_added, markup_chars_added, misspellings_added,
    numeric_chars_added, page_age_in_seconds, prev_badwords,
    prev_misspellings, prev_words, proportion_of_badwords_added,
    proportion_of_markup_added, proportion_of_misspellings_added,