def get_users(self, date_start, date_end, project='enwiki'):
"""
Returns a Generator for MediaWiki user IDs.
"""
# @TODO MOVE DB REFS INTO QUERY MODULE
params = {
'date_start': format_mediawiki_timestamp(date_start),
'date_end': format_mediawiki_timestamp(date_end),
}
conn = Connector(instance=settings.PROJECT_DB_MAP[project])
query = sub_tokens(self.QUERY_TYPES[self._query_type],
db=escape_var(project))
conn._cur_.execute(query, params)
for row in conn._cur_:
yield row[0]
def generate_test_cohort(project,
max_size=10,
write=False,
user_interval_size=1,
rev_interval_size=7,
rev_lower_limit=0):
"""
Build a test cohort (list of UIDs) for the given project.
Parameters
~~~~~~~~~~
project : str
Wikipedia project e.g. 'enwiki'.
size : uint
Number of users to include in the cohort.
write: boolean
Flag indicating whether to write the cohort to
settings.__cohort_meta_db__ and settings.__cohort_db__.
user_interval_size: uint
Number of days within which to take registered users
rev_lower_limit: int
Minimum number of revisions a user must have between registration
and the
Returns the list of UIDs from the corresponding project that defines
the test cohort.
"""
# Determine the time bounds that define the cohort acceptance criteria
ts_start_o = datetime.now() + timedelta(days=-60)
ts_end_user_o = ts_start_o + timedelta(days=int(user_interval_size))
ts_end_revs_o = ts_start_o + timedelta(days=int(rev_interval_size))
ts_start = format_mediawiki_timestamp(ts_start_o)
ts_end_user = format_mediawiki_timestamp(ts_end_user_o)
ts_end_revs = format_mediawiki_timestamp(ts_end_revs_o)
# Synthesize query and execute
logging.info(__name__ + ' :: Getting users from {0}.\n\n'
'\tUser interval: {1} - {2}\n'
'\tRevision interval: {1} - {3}\n'
'\tMax users = {4}\n'
'\tMin revs = {5}\n'.
format(project,
ts_start,
ts_end_user,
ts_end_revs,
max_size,
rev_lower_limit
)
)
query = sub_tokens(SELECT_PROJECT_IDS, db=escape_var(str(project)))
# @TODO MOVE DB REFS INTO QUERY MODULE
try:
params = {
'ts_start': str(ts_start),
'ts_end_user': str(ts_end_user),
'ts_end_revs': str(ts_end_revs),
'max_size': int(max_size),
'rev_lower_limit': int(rev_lower_limit),
}
except ValueError as e:
raise Exception(__name__ + ' :: Bad params ' + str(e))
conn = Connector(instance=settings.PROJECT_DB_MAP[project])
conn._cur_.execute(query, params)
users = [row for row in conn._cur_]
del conn
# get latest cohort id & cohort name
utm_name = generate_test_cohort_name(project)
# add new ids to usertags & usertags_meta
if write:
logging.info(__name__ + ' :: Inserting records...\n\n'
'\tCohort name - {0}\n'
'\t{2} - {3} record(s)\n'.
format(utm_name,
settings.__cohort_db__,
len(users)))
query_mod.add_cohort_data(utm_name, users, project)
return users