def retrieve_bugs(self):
bugzilla.set_token(secrets[secrets.BUGZILLA_TOKEN])
six_months_ago = datetime.utcnow() - relativedelta(months=6)
two_years_and_six_months_ago = six_months_ago - relativedelta(years=2)
logger.info('Downloading bugs from {} to {}'.format(
two_years_and_six_months_ago, six_months_ago))
bugzilla.download_bugs_between(two_years_and_six_months_ago,
six_months_ago)
logger.info('Downloading labelled bugs')
bug_ids = labels.get_all_bug_ids()
bugzilla.download_bugs(bug_ids)
# Try to re-download inconsistent bugs, up to three times.
for i in range(3):
bug_ids = bug_snapshot.get_inconsistencies()
if len(bug_ids) == 0:
break
logger.info(
f'Re-downloading {len(bug_ids)} bugs, as they were inconsistent'
)
bugzilla.delete_bugs(bug_ids)
bugzilla.download_bugs(bug_ids)
self.compress_file('data/bugs.json')
def retrieve_bugs(self):
bugzilla.set_token(get_secret("BUGZILLA_TOKEN"))
six_months_ago = datetime.utcnow() - relativedelta(months=6)
two_years_and_six_months_ago = six_months_ago - relativedelta(years=2)
logger.info(
"Downloading bugs from {} to {}".format(
two_years_and_six_months_ago, six_months_ago
)
)
bugzilla.download_bugs_between(two_years_and_six_months_ago, six_months_ago)
logger.info("Downloading labelled bugs")
bug_ids = labels.get_all_bug_ids()
bugzilla.download_bugs(bug_ids)
# Try to re-download inconsistent bugs, up to three times.
for i in range(3):
bug_ids = bug_snapshot.get_inconsistencies()
if len(bug_ids) == 0:
break
logger.info(
f"Re-downloading {len(bug_ids)} bugs, as they were inconsistent"
)
bugzilla.delete_bugs(bug_ids)
bugzilla.download_bugs(bug_ids)
self.compress_file("data/bugs.json")
def retrieve_bugs(self):
bugzilla.set_token(secrets[secrets.BUGZILLA_TOKEN])
six_months_ago = datetime.utcnow() - timedelta(182)
two_years_and_six_months_ago = six_months_ago - timedelta(365)
bugzilla.download_bugs_between(two_years_and_six_months_ago,
six_months_ago)
bug_ids = labels.get_all_bug_ids()
bugzilla.download_bugs(bug_ids)
self.compress_file('data/bugs.json')
def go(self):
# Download models that were trained by bugbug_train.
with ThreadPoolExecutorResult(max_workers=3) as executor:
f1 = executor.submit(lambda: urlretrieve(
'https://index.taskcluster.net/v1/task/project.releng.services.project.testing.bugbug_train.latest/artifacts/public/bug.model.xz',
'bug.model.xz')) # noqa
f1.add_done_callback(lambda f: self.decompress_file('bug.model'))
f2 = executor.submit(lambda: urlretrieve(
'https://index.taskcluster.net/v1/task/project.releng.services.project.testing.bugbug_train.latest/artifacts/public/regression.model.xz',
'regression.model.xz')) # noqa
f2.add_done_callback(
lambda f: self.decompress_file('regression.model'))
f3 = executor.submit(lambda: urlretrieve(
'https://index.taskcluster.net/v1/task/project.releng.services.project.testing.bugbug_train.latest/artifacts/public/tracking.model.xz',
'tracking.model.xz')) # noqa
f3.add_done_callback(
lambda f: self.decompress_file('tracking.model'))
# Download bugs from the last week that we want to analyze.
bugzilla.set_token(secrets[secrets.BUGZILLA_TOKEN])
today = datetime.utcnow()
one_week_ago = today - timedelta(7)
bugzilla.download_bugs_between(one_week_ago, today)
# Eval classifier for bug-vs-nonbug.
self.eval_bug()
# Eval classifier for regression-vs-nonregression.
self.eval_regression()
# Eval classifier for tracking bugs.
self.eval_tracking()
# Index the task in the TaskCluster index.
self.index_service.insertTask(
'project.releng.services.project.{}.bugbug_eval.latest'.format(
secrets[secrets.APP_CHANNEL]), {
'taskId':
os.environ['TASK_ID'],
'rank':
0,
'data': {},
'expires':
(datetime.utcnow() +
timedelta(31)).strftime('%Y-%m-%dT%H:%M:%S.%fZ'),
})
def retrieve_bugs(self):
bugzilla.set_token(secrets[secrets.BUGZILLA_TOKEN])
six_months_ago = datetime.utcnow() - timedelta(182)
two_years_and_six_months_ago = six_months_ago - timedelta(365)
logger.info('Downloading bugs from {} to {}'.format(
two_years_and_six_months_ago, six_months_ago))
bugzilla.download_bugs_between(two_years_and_six_months_ago,
six_months_ago)
logger.info('Downloading labelled bugs')
bug_ids = labels.get_all_bug_ids()
bugzilla.download_bugs(bug_ids)
self.compress_file('data/bugs.json')
def fetch_untriaged(args):
from bugbug import bugzilla
today = date.today()
three_months_ago = today - timedelta(days=args.days_back)
# Set bugzilla token and download bugs
bugzilla.set_token(args.token)
bug_ids = bugzilla.download_bugs_between(three_months_ago, today)
# Get untriaged bugs
bugs = bugzilla.get_bugs()
untriaged_bugs = []
for bug in bugs:
if bug['id'] not in bug_ids:
continue
for history in bug['history']:
for change in history['changes']:
if change['field_name'] == 'component' and change['removed'] == 'Untriaged':
untriaged_bugs.append(bug)
with open('bugs-{}.json'.format(datetime.now().strftime('%s')), 'w') as f:
json.dump(untriaged_bugs, f)
return untriaged_bugs
def fetch_untriaged(args):
from bugbug import bugzilla
today = date.today()
three_months_ago = today - timedelta(days=args.days_back)
# Set bugzilla token and download bugs
bugzilla.set_token(args.token)
bug_ids = bugzilla.download_bugs_between(three_months_ago, today)
# Get untriaged bugs
bugs = bugzilla.get_bugs()
untriaged_bugs = []
for bug in bugs:
if bug["id"] not in bug_ids:
continue
for history in bug["history"]:
for change in history["changes"]:
if (change["field_name"] == "component"
and change["removed"] == "Untriaged"):
untriaged_bugs.append(bug)
with open("bugs-{}.json".format(datetime.now().strftime("%s")), "w") as f:
json.dump(untriaged_bugs, f)
return untriaged_bugs
def go(self):
# Download models that were trained by bugbug_train.
with ThreadPoolExecutorResult(max_workers=3) as executor:
f1 = executor.submit(lambda: urlretrieve('https://index.taskcluster.net/v1/task/project.releng.services.project.testing.bugbug_train.latest/artifacts/public/bugmodel.xz', 'bugmodel.xz')) # noqa
f1.add_done_callback(lambda f: self.decompress_file('bugmodel'))
f2 = executor.submit(lambda: urlretrieve('https://index.taskcluster.net/v1/task/project.releng.services.project.testing.bugbug_train.latest/artifacts/public/regressionmodel.xz', 'regressionmodel.xz')) # noqa
f2.add_done_callback(lambda f: self.decompress_file('regressionmodel'))
f3 = executor.submit(lambda: urlretrieve('https://index.taskcluster.net/v1/task/project.releng.services.project.testing.bugbug_train.latest/artifacts/public/trackingmodel.xz', 'trackingmodel.xz')) # noqa
f3.add_done_callback(lambda f: self.decompress_file('trackingmodel'))
# Download bugs from the last week that we want to analyze.
bugzilla.set_token(secrets[secrets.BUGZILLA_TOKEN])
today = datetime.utcnow()
one_week_ago = today - timedelta(7)
bugzilla.download_bugs_between(one_week_ago, today)
# Eval classifier for bug-vs-nonbug.
self.eval_bug()
# Eval classifier for regression-vs-nonregression.
self.eval_regression()
# Eval classifier for tracking bugs.
self.eval_tracking()
# Index the task in the TaskCluster index.
self.index_service.insertTask(
'project.releng.services.project.{}.bugbug_eval.latest'.format(secrets[secrets.APP_CHANNEL]),
{
'taskId': os.environ['TASK_ID'],
'rank': 0,
'data': {},
'expires': (datetime.utcnow() + timedelta(31)).strftime('%Y-%m-%dT%H:%M:%S.%fZ'),
}
)
feature_names = model.get_feature_names()
for i, (importance, index, is_positive) in enumerate(importances):
print(
f'{i + 1}. \'{feature_names[int(index)]}\' ({"+" if (is_positive) else "-"}{importance})'
)
if np.argmax(probas) == 1:
print(f'Positive! {probas}')
else:
print(f'Negative! {probas}')
input()
if args.generate_sheet:
today = datetime.utcnow()
a_week_ago = today - timedelta(7)
bug_ids = bugzilla.download_bugs_between(a_week_ago, today)
print(f'Classifying {len(bug_ids)} bugs...')
rows = [['Bug', f'{args.goal}(model)', args.goal, 'Title']]
for bug in bugzilla.get_bugs():
if bug['id'] not in bug_ids:
continue
p = model.classify(bug, probabilities=True)
rows.append([
f'https://bugzilla.mozilla.org/show_bug.cgi?id={bug["id"]}',
'y' if p[0][1] >= 0.7 else 'n', '', bug['summary']
])
def main(args):
model_file_name = "{}{}model".format(
args.goal, "" if args.classifier == "default" else args.classifier)
if args.goal == "component":
if args.classifier == "default":
model_class_name = "component"
else:
model_class_name = "component_nn"
else:
model_class_name = args.goal
model_class = get_model_class(model_class_name)
if args.train:
db.download(bugzilla.BUGS_DB)
db.download(repository.COMMITS_DB)
historical_supported_tasks = [
"defect",
"bugtype",
"defectenhancementtask",
"regression",
]
if args.goal in historical_supported_tasks:
model = model_class(args.lemmatization, args.historical)
elif args.goal == "duplicate":
model = model_class(args.training_set_size, args.lemmatization)
else:
model = model_class(args.lemmatization)
model.train()
else:
model = model_class.load(model_file_name)
if args.classify:
for bug in bugzilla.get_bugs():
print(
f'https://bugzilla.mozilla.org/show_bug.cgi?id={ bug["id"] } - { bug["summary"]} '
)
if model.calculate_importance:
probas, importance = model.classify(bug,
probabilities=True,
importances=True)
feature_names = model.get_feature_names()
for i, (importance, index,
is_positive) in enumerate(importance["importances"]):
print(
f'{i + 1}. \'{feature_names[int(index)]}\' ({"+" if (is_positive) else "-"}{importance})'
)
else:
probas = model.classify(bug,
probabilities=True,
importances=False)
if np.argmax(probas) == 1:
print(f"Positive! {probas}")
else:
print(f"Negative! {probas}")
input()
if args.generate_sheet:
assert (args.token is not None
), "A Bugzilla token should be set in order to download bugs"
today = datetime.utcnow()
a_week_ago = today - timedelta(7)
bugzilla.set_token(args.token)
bugs = bugzilla.download_bugs_between(a_week_ago, today)
print(f"Classifying {len(bugs)} bugs...")
rows = [["Bug", f"{args.goal}(model)", args.goal, "Title"]]
for bug in bugs:
p = model.classify(bug, probabilities=True)
rows.append([
f'https://bugzilla.mozilla.org/show_bug.cgi?id={bug["id"]}',
"y" if p[0][1] >= 0.7 else "n",
"",
bug["summary"],
])
os.makedirs("sheets", exist_ok=True)
with open(
os.path.join(
"sheets",
f'{args.goal}-{datetime.utcnow().strftime("%Y-%m-%d")}-labels.csv',
),
"w",
) as f:
writer = csv.writer(f)
writer.writerows(rows)
from bugbug import bugzilla
from bugbug.models.duplicate import DuplicateModel
m = DuplicateModel.load("duplicatemodel")
REPORTERS_TO_IGNORE = {
"*****@*****.**", "*****@*****.**"
}
try:
with open("duplicate_test_bugs.json", "r") as f:
test_bugs = json.load(f)
except FileNotFoundError:
test_bugs = bugzilla.download_bugs_between(datetime.now() -
timedelta(days=21),
datetime.now(),
store=False)
test_bugs = [
bug for bug in test_bugs if not bug["creator"] in REPORTERS_TO_IGNORE
]
with open("duplicate_test_bugs.json", "w") as f:
json.dump(test_bugs, f)
bug_tuples = list(itertools.combinations(test_bugs, 2))
# Warning: Classifying all the test bugs takes a while
probs = m.classify(bug_tuples, probabilities=True)
with open("duplicate_predictions.csv", "w") as csvfile:
spamwriter = csv.writer(csvfile)
probas = model.classify(bug, probabilities=True, importances=False)
if np.argmax(probas) == 1:
print(f"Positive! {probas}")
else:
print(f"Negative! {probas}")
input()
if args.generate_sheet:
assert (
args.token is not None
), "A Bugzilla token should be set in order to download bugs"
today = datetime.utcnow()
a_week_ago = today - timedelta(7)
bugzilla.set_token(args.token)
bugs = bugzilla.download_bugs_between(a_week_ago, today)
print(f"Classifying {len(bugs)} bugs...")
rows = [["Bug", f"{args.goal}(model)", args.goal, "Title"]]
for bug in bugs:
p = model.classify(bug, probabilities=True)
rows.append(
[
f'https://bugzilla.mozilla.org/show_bug.cgi?id={bug["id"]}',
"y" if p[0][1] >= 0.7 else "n",
"",
bug["summary"],
]
)
