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_parsing_and_to_dict(self):
_property = {'type': 'property', 'name': 'x'}
constant = {'type': 'constant', 'value': 1}
function = {'type': 'function', 'name': 'add',
'arguments': [deepcopy(_property), deepcopy(constant)]}
self.assertEqual(Value.parse(deepcopy(constant)).to_dict(), constant)
self.assertEqual(Value.parse(deepcopy(_property)).to_dict(), _property)
self.assertEqual(Value.parse(deepcopy(function)).to_dict(), function)
kronos = {'type': 'kronos', 'host': 'localhost', 'stream': 'mystream',
'start_time': 100, 'end_time': 200}
self.assertEqual(Stream.parse(deepcopy(kronos)).to_dict(), kronos)
condition_lt = {'op': 'lt', 'left': deepcopy(_property),
'right': deepcopy(constant)}
condition_eq = {'op': 'eq', 'left': deepcopy(function),
'right': deepcopy(_property)}
condition_or = {'type': 'or', 'conditions': [deepcopy(condition_lt),
deepcopy(condition_eq)]}
self.assertEqual(Condition.parse(deepcopy(condition_lt)).to_dict(),
condition_lt)
self.assertEqual(Condition.parse(deepcopy(condition_eq)).to_dict(),
condition_eq)
self.assertEqual(Condition.parse(deepcopy(condition_or)).to_dict(),
condition_or)
avg = {'op': 'avg', 'arguments': [deepcopy(_property)], 'alias': 'myavg'}
count = {'op': 'count', 'alias': 'mycount'}
self.assertEqual(Aggregator.parse(deepcopy(avg)).to_dict(), avg)
self.assertEqual(Aggregator.parse(deepcopy(count)).to_dict(), count)
group_by = deepcopy(function)
group_by['alias'] = 'mygroup'
group_by = [group_by]
self.assertEqual(GroupBy.parse(deepcopy(group_by)).to_dict(), group_by)
project = {'type': 'project', 'fields': [deepcopy(_property)],
'stream': deepcopy(kronos)}
_filter = {'type': 'filter', 'condition': condition_lt,
'stream': deepcopy(project)}
aggregate = {'type': 'aggregate',
'group_by': deepcopy(group_by),
'aggregates': [deepcopy(avg), deepcopy(count)],
'stream': deepcopy(_filter)}
join = {'type': 'join', 'left': deepcopy(aggregate),
'right': deepcopy(project), 'condition': deepcopy(condition_or)}
self.assertEqual(Transform.parse(deepcopy(project)).to_dict(), project)
self.assertEqual(Transform.parse(deepcopy(_filter)).to_dict(), _filter)
self.assertEqual(Transform.parse(deepcopy(aggregate)).to_dict(), aggregate)
self.assertEqual(Transform.parse(deepcopy(join)).to_dict(), join)
def test_parsing_and_to_dict(self):
_property = {'type': 'property', 'name': 'x'}
constant = {'type': 'constant', 'value': 1}
function = {'type': 'function', 'name': 'add',
'arguments': [deepcopy(_property), deepcopy(constant)]}
self.assertEqual(Value.parse(deepcopy(constant)).to_dict(), constant)
self.assertEqual(Value.parse(deepcopy(_property)).to_dict(), _property)
self.assertEqual(Value.parse(deepcopy(function)).to_dict(), function)
kronos = {'type': 'data_access', 'source': 'kronos', 'stream': 'mystream',
'start_time': 100, 'end_time': 200}
self.assertEqual(Operator.parse(deepcopy(kronos)).to_dict(), kronos)
condition_lt = {'op': 'lt', 'left': deepcopy(_property),
'right': deepcopy(constant)}
condition_eq = {'op': 'eq', 'left': deepcopy(function),
'right': deepcopy(_property)}
condition_or = {'type': 'or', 'conditions': [deepcopy(condition_lt),
deepcopy(condition_eq)]}
self.assertEqual(Condition.parse(deepcopy(condition_lt)).to_dict(),
condition_lt)
self.assertEqual(Condition.parse(deepcopy(condition_eq)).to_dict(),
condition_eq)
self.assertEqual(Condition.parse(deepcopy(condition_or)).to_dict(),
condition_or)
avg = {'op': 'avg', 'arguments': [deepcopy(_property)], 'alias': 'myavg'}
count = {'op': 'count', 'alias': 'mycount'}
self.assertEqual(Aggregator.parse(deepcopy(avg)).to_dict(), avg)
self.assertEqual(Aggregator.parse(deepcopy(count)).to_dict(), count)
group_by = deepcopy(function)
group_by['alias'] = 'mygroup'
group_by = [group_by]
self.assertEqual(GroupBy.parse(deepcopy(group_by)).to_dict(), group_by)
project = {'type': 'project', 'fields': [deepcopy(_property)],
'source': deepcopy(kronos)}
_filter = {'type': 'filter', 'condition': condition_lt,
'source': deepcopy(project)}
aggregate = {'type': 'aggregate',
'group_by': deepcopy(group_by),
'aggregates': [deepcopy(avg), deepcopy(count)],
'source': deepcopy(_filter)}
join = {'type': 'join', 'left': deepcopy(aggregate),
'right': deepcopy(project), 'condition': deepcopy(condition_or)}
self.assertEqual(Operator.parse(deepcopy(project)).to_dict(), project)
self.assertEqual(Operator.parse(deepcopy(_filter)).to_dict(), _filter)
self.assertEqual(Operator.parse(deepcopy(aggregate)).to_dict(), aggregate)
self.assertEqual(Operator.parse(deepcopy(join)).to_dict(), join)
def test_join(self):
for i in xrange(100):
self.kronos_client.put({
self.stream + '1': [{constants.TIMESTAMP_FIELD: i,
'a': random.randint(0, 2),
'b': random.randint(0, 5)}]
})
for i in xrange(100):
self.kronos_client.put({
self.stream + '2': [{constants.TIMESTAMP_FIELD: i,
'a': random.randint(0, 2),
'b': random.randint(0, 5)}]
})
events = self.query(Join(KronosStream('http://localhost:9191',
self.stream + '1',
0,
200,
alias='j1'),
KronosStream('http://localhost:9191',
self.stream + '2',
0,
200),
(Condition(Condition.Op.EQ,
Property('j1.a'),
Property('right.a')) &
Condition(Condition.Op.GT,
Property('j1.b'),
Property('right.b')))).to_dict())
self.assertTrue(len(events) > 0)
for event in events:
self.assertEqual(event['j1.a'], event['right.a'])
self.assertTrue(event['j1.b'] > event['right.b'])
self.assertEqual(set(event),
{'j1.%s' % constants.TIMESTAMP_FIELD,
'right.%s' % constants.TIMESTAMP_FIELD,
'j1.%s' % constants.ID_FIELD,
'right.%s' % constants.ID_FIELD,
'j1.a', 'right.a',
'j1.b', 'right.b'})
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 parse(self, _dict):
_dict['condition'] = Condition.parse(_dict['condition'])
return Filter(**_dict)
def parse(self, _dict):
_dict['left'] = _parse_stream_or_transform(_dict['left'])
_dict['right'] = _parse_stream_or_transform(_dict['right'])
_dict['condition'] = Condition.parse(_dict['condition'])
return Join(**_dict)
def parse(self, _dict): _dict['left'] = Operator.parse(_dict['left']) _dict['right'] = Operator.parse(_dict['right']) _dict['condition'] = Condition.parse(_dict['condition']) return Join(**_dict)
def parse(self, _dict): _dict['condition'] = Condition.parse(_dict['condition']) return Filter(**_dict)
def filter(query_plan, operands):
condition = Condition(operands['op'], cpf(operands['lhs']),
cpf(operands['rhs']))
return Filter(query_plan, condition)
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)
def parse(self, _dict): _dict['left'] = _parse_stream_or_transform(_dict['left']) _dict['right'] = _parse_stream_or_transform(_dict['right']) _dict['condition'] = Condition.parse(_dict['condition']) return Join(**_dict)
