def test_project(self):
for i in xrange(25):
self.kronos_client.put({
self.stream: [{constants.TIMESTAMP_FIELD: random.randint(0, 999),
'i': i,
'i+1': i + 1}]
})
events = self.query(Project(KronosStream('http://localhost:9191',
self.stream,
0,
1000),
[Property('i', alias='I'),
Constant(10, alias='const'),
Add([Property('i'), Property('i+1'),
Constant(5)],
alias='func')],
merge=True).to_dict())
self.assertEqual(len(events), 25)
for event in events:
self.assertEqual(event['i'], event['I'])
self.assertEqual(event['const'], 10)
self.assertEqual(event['func'], event['i'] * 2 + 6)
self.assertEqual(event['i+1'], event['i'] + 1)
self.assertTrue(event[constants.TIMESTAMP_FIELD] >= 0)
self.assertTrue(event[constants.TIMESTAMP_FIELD] < 1000)
def _cohort_stream_transform(source, stream, start, end,
transform, grouping_key, unit):
start_stream = KronosSource(source, stream, start, end)
if transform:
transformed = transform(start_stream)
else:
transformed = start_stream
projected = Project(transformed,
[Property(TIMESTAMP_FIELD,
alias=TIMESTAMP_FIELD),
Property(grouping_key,
alias=grouping_key),
Floor([Property(TIMESTAMP_FIELD),
Constant(DateUnit.unit_to_kronos_time(unit)),
Constant(start)],
alias='date')])
# This leaves us with a single event per (user, unit time) pair.
aggregated = Aggregate(
projected,
GroupBy([Property(grouping_key,
alias=grouping_key),
Property('date',
alias='date')]),
# The first time the user performed the event in that bucket.
[Min([Property(TIMESTAMP_FIELD)], alias=TIMESTAMP_FIELD)])
return aggregated
def test_filter(self):
for i in xrange(2000):
event = {
constants.TIMESTAMP_FIELD: random.randint(0, 999),
'a': random.randint(0, 10),
'b': random.randint(50, 150),
'c': [random.randint(0, 20) for j in xrange(10)]
}
if random.randint(0, 100) > 50:
event['d'] = 'iamlolcat'
else:
event['d'] = 'helloworld'
self.kronos_client.put({self.stream: [event]})
events = self.query(
Filter(KronosSource('kronos', self.stream, 0, 1000), (
(Condition(Condition.Op.GT, Property(
constants.TIMESTAMP_FIELD), Constant(500))
| Condition(Condition.Op.LTE, Property('b'), Constant(100))) &
(Condition(Condition.Op.CONTAINS, Property('c'), Property('a'))
| Condition(Condition.Op.REGEX, Property('d'),
Constant('lolcat'))))).to_dict())
self.assertTrue(len(events) > 0)
self.assertTrue(len(events) < 2000)
for event in events:
self.assertTrue(event[constants.TIMESTAMP_FIELD] > 500
or event['b'] <= 100)
self.assertTrue(event['a'] in event['c'] or 'lolcat' in event['d'])
self.assertTrue(event[constants.TIMESTAMP_FIELD] >= 0)
self.assertTrue(event[constants.TIMESTAMP_FIELD] < 1000)
def test_get_properties_accessed_by_value(self):
self.assertEqual(get_properties_accessed_by_value(Property('lolcat')),
['lolcat'])
self.assertEqual(get_properties_accessed_by_value(Constant(0)), [])
self.assertEqual(
get_properties_accessed_by_value(
Add([
Property('lolcat'),
Constant(1),
Add([Property('hello'), Constant(2)])
])), ['lolcat', 'hello'])
def test_aggregate(self):
sums = defaultdict(int)
for i in xrange(200):
a = random.randint(0, 2)
self.kronos_client.put(
{self.stream: [{
constants.TIMESTAMP_FIELD: i,
'a': a
}]})
sums[50 * (i / 50)] += a
events = self.query(
Aggregate(
Project(KronosSource('kronos', self.stream, 0, 1000), [
Floor([Property(constants.TIMESTAMP_FIELD),
Constant(50)],
alias=constants.TIMESTAMP_FIELD)
],
merge=True),
GroupBy(
Property(constants.TIMESTAMP_FIELD,
alias=constants.TIMESTAMP_FIELD)), [
Count([], alias='count'),
Sum([Property('a')], alias='sum'),
Min([Property('a')], alias='min'),
Max([Property('a')], alias='max'),
Avg([Property('a')], alias='avg')
]).to_dict())
self.assertEqual(len(events), 200 / 50)
for event in events:
self.assertEqual(event[constants.TIMESTAMP_FIELD] % 50, 0)
self.assertEqual(event['count'], 50)
self.assertEqual(event['min'], 0)
self.assertEqual(event['max'], 2)
self.assertEqual(event['sum'],
sums[event[constants.TIMESTAMP_FIELD]])
self.assertTrue(event['avg'] * 50 > event['sum'] - 0.1)
self.assertTrue(event['avg'] * 50 < event['sum'] + 0.1)
events = self.query(
Aggregate(
KronosSource('kronos', self.stream, 0, 1000),
GroupBy(
Floor([Property(constants.TIMESTAMP_FIELD),
Constant(50)],
alias=constants.TIMESTAMP_FIELD)),
[Count([], alias='count')]).to_dict())
self.assertEqual(len(events), 200 / 50)
def cpf(args, alias=None):
if args['cpf_type'] == 'constant':
try:
constant = float(args['constant_value'])
except:
constant = args['constant_value']
return Constant(constant, alias=alias)
elif args['cpf_type'] == 'property':
return Property(args['property_name'], alias=alias)
elif args['cpf_type'] == 'function':
for i in range(len(args['function_args'])):
args['function_args'][i] = cpf(args['function_args'][i])
module = metis.core.query.value
func = args['function_name']
func_args = args['function_args']
return getattr(module, func)(func_args, alias=alias)
else:
raise ValueError("cpf_type must be constant, property, or function")
def cohort_queryplan(plan):
"""
Input:
{
'source': 'kronos', # Name of data source from settings
'cohort':
{'stream': CohortTest.EMAIL_STREAM, # Kronos stream to define cohort from.
'transform': lambda x: x, # Transformations on the kstream.
'start': date.now(), # The day of the first cohort.
'unit': DateUnit.XX, # Users are in the same cohort
# if they are in the same day/week.
'cohorts': 5 # How many cohorts (days/weeks/months)
# to track.
'grouping_key': 'user'}, # What key in an event should we tie
# to a key in the action stream?
'action':
{'stream': CohortTest.FRONTPAGE_STREAM, # Stream users take actions on.
'transform': lambda x: x # Transformations on the stream.
'unit': DateUnit.XX, # Track events in day/week/months.
'repetitions': 14 # How many days/weeks/months to track.
'grouping_key': 'user_id'} # What key in an event should we tie
# to a key in the action stream?
}
Output:
A metis-compatible query plan to return a cohort analysis.
"""
cohort = plan['cohort']
action = plan['action']
source = plan['source']
# Calculate the start and end dates, in Kronos time, of the
# beginning and end of the cohort and action streams that will be
# relevant.
cohort_start = datetime_to_kronos_time(_date_to_datetime(cohort['start']))
cohort_span = timedelta(**{cohort['unit']: cohort['cohorts']})
cohort_end = cohort['start'] + cohort_span
action_span = timedelta(**{action['unit']: action['repetitions']})
action_end = cohort_end + action_span
cohort_end = datetime_to_kronos_time(_date_to_datetime(cohort_end)) + 1
action_end = datetime_to_kronos_time(_date_to_datetime(action_end)) + 1
left = _cohort_stream_transform(source,
cohort['stream'], cohort_start, cohort_end,
cohort.get('transform'),
cohort['grouping_key'], cohort['unit'])
right = _cohort_stream_transform(source,
action['stream'], cohort_start, action_end,
action.get('transform'),
action['grouping_key'], action['unit'])
additional_action_time = (DateUnit.unit_to_kronos_time(action['unit']) *
action['repetitions'])
left.alias = 'cohort'
right.alias = 'action'
joined = Join(left,
right,
(Condition(Condition.Op.EQ,
Property('cohort.%s' % cohort['grouping_key']),
Property('action.%s' % action['grouping_key'])) &
Condition(Condition.Op.GTE,
Property('action.%s' % TIMESTAMP_FIELD),
Property('cohort.%s' % TIMESTAMP_FIELD)) &
Condition(Condition.Op.LT,
Property('action.%s' % TIMESTAMP_FIELD),
Add([Property('cohort.%s' % TIMESTAMP_FIELD),
Constant(additional_action_time)]))))
user_aggregated = Aggregate(
joined,
GroupBy([Property('cohort.date', alias=TIMESTAMP_FIELD),
Property('cohort.%s' % cohort['grouping_key'], alias='group'),
Floor([Subtract([Property('action.%s' % TIMESTAMP_FIELD),
Property('cohort.%s' % TIMESTAMP_FIELD)]),
Constant(DateUnit.unit_to_kronos_time(action['unit']))],
alias='action_step')]),
[Count([], alias='count')]
)
aggregated = Aggregate(
user_aggregated,
GroupBy([Property(TIMESTAMP_FIELD, alias=TIMESTAMP_FIELD),
Property('action_step', alias='action_step')]),
[Count([], alias='cohort_actions')])
# TODO(marcua): Also sum up the cohort sizes, join with the plan.
return aggregated.to_dict()
def test_join_eq(self):
for i in xrange(200):
self.kronos_client.put({
self.stream + '1': [{constants.TIMESTAMP_FIELD: random.randint(0, 999),
'a': i,
'b': i + 1}]
})
for i in xrange(200):
self.kronos_client.put({
self.stream + '2': [{constants.TIMESTAMP_FIELD: random.randint(0, 999),
'a': i + 1,
'b': i + 2}]
})
# 1-1 join with property.
events = self.query(Join(KronosStream('http://localhost:9191',
self.stream + '1',
0,
1000),
KronosStream('http://localhost:9191',
self.stream + '2',
0,
1000),
# left.a == right.b
Condition(Condition.Op.EQ,
Property('left.b'),
Property('right.a'))).to_dict())
self.assertEqual(len(events), 200)
for event in events:
self.assertEqual(event['left.b'], event['right.a'])
# 1-1 join with function.
events = self.query(Join(KronosStream('http://localhost:9191',
self.stream + '1',
0,
1000),
KronosStream('http://localhost:9191',
self.stream + '2',
0,
1000),
# left.a == (right.a - 1)
Condition(Condition.Op.EQ,
Property('left.a'),
Subtract([Property('right.a'),
Constant(1)]))).to_dict())
self.assertEqual(len(events), 200)
for event in events:
self.assertEqual(event['left.a'], event['right.a'] - 1)
# 1-1 eqjoin with filtering.
events = self.query(
Join(KronosStream('http://localhost:9191',
self.stream + '1',
0,
1000),
KronosStream('http://localhost:9191',
self.stream + '2',
0,
1000),
(Condition(Condition.Op.EQ,
Property('left.b'),
Property('right.a')) &
Condition(Condition.Op.GT,
Property('left.%s' %
constants.TIMESTAMP_FIELD),
Add([Property('right.%s' %
constants.TIMESTAMP_FIELD),
Constant(10)])))).to_dict())
self.assertTrue(len(events) > 0)
self.assertTrue(len(events) < 200)
for event in events:
self.assertEqual(event['left.b'], event['right.a'])
self.assertTrue(event['left.%s' % constants.TIMESTAMP_FIELD] >
event['right.%s' % constants.TIMESTAMP_FIELD] + 10)