def bot_gen(rev_pages, language, api_url):
session = api.Session(api_url)
extractor = APIExtractor(session, language=language)
for rev_id, page_id in rev_pages:
sys.stderr.write(".")
sys.stderr.flush()
try:
# Detect reverted status
revert = reverts.api.check(session, rev_id, page_id, radius=3)
reverted = revert is not None
added_words = list(extractor.extract(rev_id,
[diff.added_words]))[0]
yield Edit(rev_id, added_words, reverted)
except KeyboardInterrupt:
sys.stderr.write("\n^C Caught. Exiting...")
break
except:
sys.stderr.write(traceback.format_exc())
sys.stderr.write("\n")
sys.stderr.write("\n")
def bot_gen(rev_pages, language, api_url):
session = api.Session(api_url)
extractor = APIExtractor(session, language=language)
for rev_id, page_id in rev_pages:
sys.stderr.write(".")
sys.stderr.flush()
try:
# Detect reverted status
revert = reverts.api.check(session, rev_id, page_id, radius=3)
reverted = revert is not None
added_words = list(
extractor.extract(rev_id, [diff.added_words]))[0]
yield Edit(rev_id, added_words, reverted)
except KeyboardInterrupt:
sys.stderr.write("\n^C Caught. Exiting...")
break
except:
sys.stderr.write(traceback.format_exc())
sys.stderr.write("\n")
sys.stderr.write("\n")
import mwapi
from revscoring import ScorerModel
from revscoring.extractors import APIExtractor
with open("models/enwiki.damaging.linear_svc.model") as f:
scorer_model = ScorerModel.load(f)
extractor = APIExtractor(mwapi.Session(host="https://en.wikipedia.org",
user_agent="revscoring demo"))
feature_values = extractor.extract(123456789, scorer_model.features)
print(scorer_model.score(feature_values))
import mwapi
from revscoring import ScorerModel
from revscoring.extractors import APIExtractor
with open("models/enwiki.damaging.linear_svc.model") as f:
scorer_model = ScorerModel.load(f)
extractor = APIExtractor(
mwapi.Session(host="https://en.wikipedia.org",
user_agent="revscoring demo"))
feature_values = extractor.extract(123456789, scorer_model.features)
print(scorer_model.score(feature_values))
count += 1
else:
break
"""
Feature to examine. Let FEATURE be one of
diff.added_tokens
diff.removed_tokens
diff.added_segments
diff.removed_segments
revision.content
revision.content_tokens
"""
FEATURE = diff.added_segments
# extract data from selected revisions and write to selected file
extr = APIExtractor(mwapi.Session("https://en.wikipedia.org"))
for id in rev_ids:
data = extr.extract(id, FEATURE)
dump_target.write("\n\nBeginning %s of revision %d\n\n" % (FEATURE, id))
if type(data) is str:
dump_target.write(data)
elif type(data) is list:
dump_target.writelines(data)
else:
print("Unknown Type")
exit()
dump_target.write("\n\nEnd %s of revision %d" % (FEATURE, id))
import sys
from mw.api import Session
sys.path.insert(0, ".")
from revscoring.extractors import APIExtractor
from revscoring.features import (diff, page, parent_revision,
previous_user_revision, revision, user)
from revscoring.languages import portuguese
api_extractor = APIExtractor(
Session("https://pt.wikipedia.org/w/api.php"),
language=portuguese
)
features = [diff.added_badwords_ratio, diff.added_markup_chars_ratio,
diff.added_misspellings_ratio, diff.added_number_chars_ratio,
diff.added_symbolic_chars_ratio, diff.added_uppercase_chars_ratio,
diff.badwords_added, diff.badwords_removed, diff.chars_added,
diff.chars_removed, diff.longest_repeated_char_added,
diff.longest_token_added, diff.markup_chars_added,
diff.markup_chars_removed, diff.misspellings_added,
diff.misspellings_removed, diff.numeric_chars_added,
diff.numeric_chars_removed,
diff.proportion_of_badwords_added,
diff.proportion_of_badwords_removed,
diff.proportion_of_chars_added,
diff.proportion_of_chars_removed,
diff.proportion_of_markup_chars_added,
diff.proportion_of_misspellings_added,
diff.proportion_of_misspellings_removed,
from mw.api import Session
from revscoring.extractors import APIExtractor
from revscoring.features import diff, parent_revision, revision, user
api_extractor = APIExtractor(Session("https://en.wikipedia.org/w/api.php"))
features = [revision.day_of_week,
revision.hour_of_day,
revision.has_custom_comment,
diff.bytes_changed,
diff.chars_added,
user.age,
user.is_anon,
user.is_bot]
values = api_extractor.extract(
624577024,
features
)
for feature, value in zip(features, values):
print("{0}: {1}".format(feature, value))
from mw.api import Session
from revscoring.extractors import APIExtractor
from revscoring.scorers import MLScorerModel, Scorer
api_session = Session("https://en.wikipedia.org/w/api.php")
filename = "models/reverts.halfak_mix.trained.model"
model = MLScorerModel.load(open(filename, 'rb'))
extractor = APIExtractor(api_session, model.language)
scorer = Scorer({'reverted': model}, extractor)
for rev_id in [105, 642215410, 638307884]:
score_doc = scorer.score(rev_id)
print("{0}: {1}".format(rev_id, score_doc))
import sys
from mw.api import Session
sys.path.insert(0, ".")
from revscoring.extractors import APIExtractor
from revscoring.features import (diff, page, parent_revision,
previous_user_revision, revision, user)
from revscoring.languages import portuguese
api_extractor = APIExtractor(Session("https://pt.wikipedia.org/w/api.php"),
language=portuguese)
features = [
diff.added_badwords_ratio, diff.added_markup_chars_ratio,
diff.added_misspellings_ratio, diff.added_number_chars_ratio,
diff.added_symbolic_chars_ratio, diff.added_uppercase_chars_ratio,
diff.badwords_added, diff.badwords_removed, diff.chars_added,
diff.chars_removed, diff.longest_repeated_char_added,
diff.longest_token_added, diff.markup_chars_added,
diff.markup_chars_removed, diff.misspellings_added,
diff.misspellings_removed, diff.numeric_chars_added,
diff.numeric_chars_removed, diff.proportion_of_badwords_added,
diff.proportion_of_badwords_removed, diff.proportion_of_chars_added,
diff.proportion_of_chars_removed, diff.proportion_of_markup_chars_added,
diff.proportion_of_misspellings_added,
diff.proportion_of_misspellings_removed,
diff.proportion_of_numeric_chars_added,
diff.proportion_of_symbolic_chars_added,
diff.proportion_of_uppercase_chars_added, diff.removed_badwords_ratio,
diff.removed_misspellings_ratio, diff.segments_added,
