Helder he7d3r

## fix.py
#!/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):

## wp-words-by-frequency.pl
#!/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;

## wmgrep.js
// 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]]
 */

## informal-words.txt
# 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

## print_dependency_graph.py
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,

## commands.sh
# Create some folders
mkdir models datasets

# Generate a file with a new model
./new_model revscores.scorers.LinearSVCModel \
    revscores.features.added_badwords_ratio \
    revscores.features.added_misspellings_ratio \
    revscores.features.day_of_week_in_utc \
    revscores.features.hour_of_day_in_utc \
    revscores.features.is_custom_comment \

## demonstrate_GridSearchCV.py
"""
Test GridSearchCV using a dataset obtained from a tsv file
"""
import csv
from sklearn import svm
from sklearn import metrics
from sklearn.cross_validation import train_test_split
from sklearn.grid_search import GridSearchCV
#from revscores.scorers import LinearSVC
from revscores.features import (added_badwords_ratio, added_misspellings_ratio,

## classification_report.txt
== Classification Report ==
             precision    recall  f1-score   support

          0       0.85      0.95      0.90      1617
          1       0.56      0.30      0.39       379

avg / total       0.80      0.82      0.80      1996

## Output for direction="newer"
$ python demonstrate_rc.py
39753618 (0 chars): 9a233f038c5f692efb3f0fbff7f4ced8a8c22cb0
40663045 (0 chars): 1f0c550dceb5c542dfb304e5d6337c063aaa3c48
34693351 (0 chars): 479dc3b4d6397134ce9d53e84c2fea0f451c1ae9
34764900 (0 chars): f23ac498773c3a74037ba7f91e68653fa8fa5809
40663042 (0 chars): 4416ce970a3a1bc1b2e1f1638cb716f9bf91c9fa
0 (0 chars):
36949986 (0 chars): 0f3919a4a56b1071087a09dce780a75374e216c6
0 (0 chars):
40659670 (0 chars): 9c1a70783ec78719d16533106816c76887fd139f

## stemToMostFrequentWord.py
#!/usr/bin/env python
# -*- coding: UTF-8 -*-
# Copyright © 2014 He7d3r
# License: http://he7d3r.mit-license.org/
"""
For each stem, prints out the most frequent word which is matched by some regex rule and has that stem

Example:
python stemToMostFrequentWord.py SALEBOT.TXT SALEBOT-STEMS-WORDS-STATS.TXT BADWORDSLIST.TXT
"""