Extracting 77 features
stat | value |
---|---|
extractions | 148 |
total_time | 81.527 |
min_time | 0.114 |
max_time | 3.539 |
mean_time | 0.551 |
median_time | 0.337 |
class FeatureTestCase: | |
"""docstring for FeatureTestCase""" | |
def __init__(self, name): | |
super(FeatureTestCase, self).__init__() | |
self.name = name | |
def test_pickle(test_case): | |
return eq_(pickle.loads(pickle.dumps(test_case)), test_case) |
import json | |
import pywikibase | |
with open('alan_touring.json', 'r') as f: | |
res = json.loads(f.read()) | |
item = pywikibase.ItemPage() | |
item.get(res) | |
qua = 0 | |
for p_number in item.claims: | |
claim = item.claims[p_number] |
import urllib.request | |
import json | |
with open('/home/ladsgroup/res_aaron.txt', 'r') as f: | |
res = f.read().split('\n')[1:] | |
def chunks(l, n): | |
"""Yield successive n-sized chunks from l.""" | |
for i in range(0, len(l), n): | |
yield l[i:i+n] |
from revscoring.features.modifiers import not_, log | |
from revscoring.features.revision_oriented import revision | |
from revscoring.datasources.revision_oriented import revision as revision_datasource | |
from revscoring.features.wikibase.datasources.revision_oriented import Revision | |
from revscoring.features.wikibase.features.revision_oriented import Revision as it_is_driving_me_crazy | |
revision_wikibase_datasource = Revision('wikibase.revision', revision_datasource) | |
wikibase_revision = it_is_driving_me_crazy('wikibase.revision', revision_wikibase_datasource) |
from ipaddress import ip_address | |
try: | |
ip_address(user.name) | |
except ValueError: | |
return False | |
else: | |
return True |
{ | |
"continue": { | |
"rvcontinue": "20151226095623|696846306", | |
"continue": "||" | |
}, | |
"query": { | |
"pages": { | |
"15580374": { | |
"pageid": 15580374, | |
"ns": 0, |
AUC of the classifier: 0.91944 | |
f0.125-score (thrashhold, precision, recall, edits to review, total edits): 0.974, 0.875, 0.075269, 16, 4960 (0.32258%) | |
f0.25-score (thrashhold, precision, recall, edits to review, total edits): 0.931, 0.78049, 0.17204, 41, 4960 (0.82661%) | |
f0.5-score (thrashhold, precision, recall, edits to review, total edits): 0.892, 0.67606, 0.25806, 71, 4960 (1.4315%) | |
f1-score (thrashhold, precision, recall, edits to review, total edits): 0.847, 0.53571, 0.40323, 140, 4960 (2.8226%) | |
f2-score (thrashhold, precision, recall, edits to review, total edits): 0.749, 0.25, 0.73118, 544, 4960 (10.968%) | |
f3-score (thrashhold, precision, recall, edits to review, total edits): 0.749, 0.25, 0.73118, 544, 4960 (10.968%) | |
f4-score (thrashhold, precision, recall, edits to review, total edits): 0.578, 0.14734, 0.9086, 1147, 4960 (23.125%) |
""" | |
``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] |
from collections import OrderedDict | |
import json | |
import os | |
path = '.' | |
i18n_dir = os.path.join(path, 'i18n') | |
js_file = os.path.join(path, 'wsgi/static/js/wikiLabels/wikiLabels.js') | |
i18n = {} | |
for lang_file in os.listdir(i18n_dir): |
Extracting 77 features
stat | value |
---|---|
extractions | 148 |
total_time | 81.527 |
min_time | 0.114 |
max_time | 3.539 |
mean_time | 0.551 |
median_time | 0.337 |