halfak

import mwapi
from deltas.tokenizers import wikitext_split

rev_id = 57246316

session = mwapi.Session("https://ja.wikipedia.org")
doc = session.get(action="query", prop="revisions", revids=[rev_id], rvslots="main", rvprop="content", formatversion=2)
text = doc['query']['pages'][0]['revisions'][0]['slots']['main']['content']

location = 0

halfak

NORMALIZED_LABELS = {
  "ВС": ["ВС", "вс", "Вибрана стаття", "вибрана стаття"],
  "ДС":	["ДС", "дс", "Добра стаття", "добра стаття"],
  "I":	["I", "1"],
  "II":	["II", "2"],
  "III": ["III", "3"],
  "IV":	["IV", "4", "Stub", "stub"]
}
LABEL_MAP = {observed_label: normalized_label
             for normalized_label, observed_labels in NORMALIZED_LABELS.items()

halfak

$ git diff
diff --git a/revscoring/languages/features/matches/regex_matches.py b/revscoring/languages/features/matches/regex_matches.py
index 767ee20..5070dd0 100644
--- a/revscoring/languages/features/matches/regex_matches.py
+++ b/revscoring/languages/features/matches/regex_matches.py
@@ -1,3 +1,10 @@
+"""
+Implements a feature set based off of list of regular expressions to match.
+
+.. autoclass:: revscoring.languages.features.RegexMatches^M

halfak

$ python
Python 3.7.7 (default, May 19 2020, 15:54:35) 
[GCC 5.4.0 20160609] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> from revscoring.languages.features import RegexMatches, SubstringMatches
>>> from revscoring.datasources import revision_oriented as ro
>>> from revscoring.dependencies import solve
>>> rm = RegexMatches("Foo", ["bad", "badword"])
>>> solve(rm.revision.diff.matches_added, cache={ro.revision.text: "I have some bad words don't you know?", ro.revision.parent.text: "I have some badword words just so you bad."})
1.0

halfak

"""
``$ articlequality weighted_sum -h``
::
    Extracts probabilities assigned to each class from the output of 
    revscoring score utility and outputs the weighted sum of the article
    quality predicted where each class is represented as a weight sorted
    in a yaml config file.
    
    Usage:
        weighted_sum <weights> [--scores=<path>] [--output=<path>]

halfak

>>> import yamlconf
>>> yamlconf.load(open("ptwiki.yaml"))
{1: 1, 2: 2, 3: 3, 4: 4, 5: 5, 6: 6}

halfak

$ python
Python 3.5.1+ (default, Mar 30 2016, 22:46:26) 
[GCC 5.3.1 20160330] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import requests
>>> import mwapi
>>> session = mwapi.Session("https://deployment.wikimedia.beta.wmflabs.org/")
Sending requests with default User-Agent.  Set 'user_agent' on mwapi.Session to quiet this message.
>>> session.get(action='query', meta="tokens", format="json")
{'query': {'tokens': {'csrftoken': '+\\'}}, 'batchcomplete': ''}

halfak

$ bzcat datasets/ptwiki.draft_quality.balanced_3k.with_text.json.bz2 | \
  shuf -n 100 | python demo_ptwiki_w2w.py | sort -k1,1

halfak

$ python
Python 3.5.3 (default, Sep 27 2018, 17:25:39) 
[GCC 6.3.0 20170516] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> from revscoring import Model
>>> model = Model.load(open("models/ptwiki.wp10.gradient_boosting.model"))
>>> importance_features = list(sorted(zip(model.estimator.feature_importances_, model.features), reverse=True))
>>> for importance, feature in importance_features:
...   print(round(importance, 3), feature)
... 

halfak

import time

import mwapi
import re
from deltas.tokenizers import wikitext_split

'''text = """
This is a sentence [[derp|link]].

Here is another paragraph with the number 10.