def _parse(result: List) -> List:
_, seconds_in_interval, _ = get_time_diff(filter.interval,
filter.date_from,
filter.date_to,
team_id=team_id)
time_range = enumerate_time_range(filter, seconds_in_interval)
filter_params = filter.to_params()
extra_params = {
"entity_id": entity.id,
"entity_type": entity.type,
"entity_math": entity.math
}
parsed_params: Dict[str, str] = encode_get_request_params({
**filter_params,
**extra_params
})
return [{
"aggregated_value":
result[0][0] if result and len(result) else 0,
"days":
time_range,
"filter":
filter_params,
"persons": {
"filter":
extra_params,
"url":
f"api/projects/{team_id}/actions/people/?{urllib.parse.urlencode(parsed_params)}",
},
}]
def _get_date_filter(self) -> Tuple[str, Dict]:
date_filter = ""
date_params: Dict[str, Any] = {}
interval_annotation = get_trunc_func_ch(self._filter.interval)
_, _, round_interval = get_time_diff(self._filter.interval or "day",
self._filter.date_from,
self._filter.date_to,
team_id=self._team_id)
_, parsed_date_to, date_params = parse_timestamps(
filter=self._filter, team_id=self._team_id)
parsed_date_from = date_from_clause(interval_annotation,
round_interval)
self.parsed_date_from = parsed_date_from
self.parsed_date_to = parsed_date_to
if self._entity.math in [WEEKLY_ACTIVE, MONTHLY_ACTIVE]:
date_filter = "{parsed_date_from_prev_range} {parsed_date_to}"
format_params = get_active_user_params(self._filter, self._entity,
self._team_id)
self.active_user_params = format_params
date_filter = date_filter.format(**format_params,
parsed_date_to=parsed_date_to)
else:
date_filter = "{parsed_date_from} {parsed_date_to}".format(
parsed_date_from=parsed_date_from,
parsed_date_to=parsed_date_to)
return date_filter, date_params
def _format_lifecycle_query(self, entity: Entity, filter: Filter,
team_id: int) -> Tuple[str, Dict, Callable]:
date_from = filter.date_from
if not date_from:
date_from = get_earliest_timestamp(team_id)
interval = filter.interval or "day"
num_intervals, seconds_in_interval, _ = get_time_diff(
interval, filter.date_from, filter.date_to, team_id)
interval_increment, interval_string, sub_interval_string = self.get_interval(
interval)
trunc_func = get_trunc_func_ch(interval)
event_query = ""
event_params: Dict[str, Any] = {}
props_to_filter = [*filter.properties, *entity.properties]
prop_filters, prop_filter_params = parse_prop_clauses(
props_to_filter,
team_id,
filter_test_accounts=filter.filter_test_accounts)
_, _, date_params = parse_timestamps(filter=filter, team_id=team_id)
if entity.type == TREND_FILTER_TYPE_ACTIONS:
try:
action = entity.get_action()
event_query, event_params = format_action_filter(action)
except:
return "", {}, self._parse_result(filter, entity)
else:
event_query = "event = %(event)s"
event_params = {"event": entity.id}
return (
LIFECYCLE_SQL.format(
interval=interval_string,
trunc_func=trunc_func,
event_query=event_query,
filters=prop_filters,
sub_interval=sub_interval_string,
GET_TEAM_PERSON_DISTINCT_IDS=GET_TEAM_PERSON_DISTINCT_IDS,
),
{
"team_id":
team_id,
"prev_date_from":
(date_from - interval_increment).strftime("%Y-%m-%d{}".format(
" %H:%M:%S" if filter.interval == "hour"
or filter.interval == "minute" else " 00:00:00")),
"num_intervals":
num_intervals,
"seconds_in_interval":
seconds_in_interval,
**event_params,
**date_params,
**prop_filter_params,
},
self._parse_result(filter, entity),
)
def _total_volume_query(self, entity: Entity, filter: Filter, team_id: int) -> Tuple[str, Dict, Callable]:
interval_annotation = get_trunc_func_ch(filter.interval)
num_intervals, seconds_in_interval, _ = get_time_diff(
filter.interval or "day", filter.date_from, filter.date_to, team_id=team_id
)
aggregate_operation, join_condition, math_params = process_math(entity)
trend_event_query = TrendsEventQuery(
filter=filter,
entity=entity,
team_id=team_id,
should_join_distinct_ids=True
if join_condition != "" or entity.math in [WEEKLY_ACTIVE, MONTHLY_ACTIVE]
else False,
)
event_query, event_query_params = trend_event_query.get_query()
content_sql_params = {
"aggregate_operation": aggregate_operation,
"timestamp": "e.timestamp",
"interval": interval_annotation,
}
params: Dict = {"team_id": team_id}
params = {**params, **math_params, **event_query_params}
if filter.display in TRENDS_DISPLAY_BY_VALUE:
content_sql = VOLUME_TOTAL_AGGREGATE_SQL.format(event_query=event_query, **content_sql_params)
time_range = enumerate_time_range(filter, seconds_in_interval)
return (
content_sql,
params,
lambda result: [
{"aggregated_value": result[0][0] if result and len(result) else 0, "days": time_range}
],
)
else:
if entity.math in [WEEKLY_ACTIVE, MONTHLY_ACTIVE]:
content_sql = ACTIVE_USER_SQL.format(
event_query=event_query,
**content_sql_params,
parsed_date_to=trend_event_query.parsed_date_to,
parsed_date_from=trend_event_query.parsed_date_from,
**trend_event_query.active_user_params
)
else:
content_sql = VOLUME_SQL.format(event_query=event_query, **content_sql_params)
null_sql = NULL_SQL.format(
interval=interval_annotation,
seconds_in_interval=seconds_in_interval,
num_intervals=num_intervals,
date_to=filter.date_to.strftime("%Y-%m-%d %H:%M:%S"),
)
final_query = AGGREGATE_SQL.format(null_sql=null_sql, content_sql=content_sql)
return final_query, params, self._parse_total_volume_result(filter)
def calculate_avg(self, filter: Filter, team: Team):
parsed_date_from, parsed_date_to, _ = parse_timestamps(filter, team.pk)
filters, params = parse_prop_clauses(
filter.properties, team.pk, filter_test_accounts=filter.filter_test_accounts
)
interval_notation = get_trunc_func_ch(filter.interval)
num_intervals, seconds_in_interval, _ = get_time_diff(
filter.interval or "day", filter.date_from, filter.date_to, team.pk
)
entity_conditions, entity_params = entity_query_conditions(filter, team)
if not entity_conditions:
entity_conditions = ["event != '$feature_flag_called'"] # default conditino
params = {**params, **entity_params}
entity_query = " OR ".join(entity_conditions)
avg_query = SESSIONS_NO_EVENTS_SQL.format(
team_id=team.pk,
date_from=parsed_date_from,
date_to=parsed_date_to,
filters=filters,
sessions_limit="",
entity_filter=f"AND ({entity_query})",
)
per_period_query = AVERAGE_PER_PERIOD_SQL.format(sessions=avg_query, interval=interval_notation)
null_sql = NULL_SQL.format(
date_to=filter.date_to.strftime("%Y-%m-%d 00:00:00"),
interval=interval_notation,
num_intervals=num_intervals,
seconds_in_interval=seconds_in_interval,
)
final_query = AVERAGE_SQL.format(sessions=per_period_query, null_sql=null_sql)
params = {**params, "team_id": team.pk}
response = sync_execute(final_query, params)
values = self.clean_values(filter, response)
time_series_data = append_data(values, interval=filter.interval, math=None)
scaled_data, _ = scale_time_series(time_series_data["data"])
time_series_data.update({"data": scaled_data})
# calculate average
total = sum(val[1] for val in values)
if total == 0:
return []
valid_days = sum(1 if val[1] else 0 for val in values)
overall_average = (total / valid_days) if valid_days else 0
result = self._format_avg(overall_average)
time_series_data.update(result)
return [time_series_data]
def calculate_avg(self, filter: Filter, team: Team):
# format default dates
if not filter._date_from:
filter._date_from = relative_date_parse("-7d")
if not filter._date_to:
filter._date_to = timezone.now()
parsed_date_from, parsed_date_to = parse_timestamps(filter)
filters, params = parse_prop_clauses("uuid", filter.properties, team)
interval_notation = get_interval_annotation_ch(filter.interval)
num_intervals, seconds_in_interval = get_time_diff(
filter.interval or "day", filter.date_from, filter.date_to)
avg_query = SESSIONS_NO_EVENTS_SQL.format(
team_id=team.pk,
date_from=parsed_date_from,
date_to=parsed_date_to,
filters="{}".format(filters) if filter.properties else "",
sessions_limit="",
)
per_period_query = AVERAGE_PER_PERIOD_SQL.format(
sessions=avg_query, interval=interval_notation)
null_sql = NULL_SQL.format(
date_to=(filter.date_to
or timezone.now()).strftime("%Y-%m-%d 00:00:00"),
interval=interval_notation,
num_intervals=num_intervals,
seconds_in_interval=seconds_in_interval,
)
final_query = AVERAGE_SQL.format(sessions=per_period_query,
null_sql=null_sql)
params = {**params, "team_id": team.pk}
response = sync_execute(final_query, params)
values = self.clean_values(filter, response)
time_series_data = append_data(values,
interval=filter.interval,
math=None)
# calculate average
total = sum(val[1] for val in values)
if total == 0:
return []
valid_days = sum(1 if val[1] else 0 for val in values)
overall_average = (total / valid_days) if valid_days else 0
result = self._format_avg(overall_average)
time_series_data.update(result)
return [time_series_data]
def _get_funnel_trend_null_sql(self):
interval_annotation = get_trunc_func_ch(self._filter.interval)
num_intervals, seconds_in_interval, round_interval = get_time_diff(
self._filter.interval or "day", self._filter.date_from, self._filter.date_to, team_id=self._team.id
)
funnel_trend_null_sql = NULL_SQL_FUNNEL_TRENDS.format(
interval=interval_annotation,
seconds_in_interval=seconds_in_interval,
num_intervals=num_intervals,
date_to=self._filter.date_to.strftime("%Y-%m-%d %H:%M:%S"),
)
return funnel_trend_null_sql
def get_query(self) -> str:
steps_per_person_query = self.funnel_order.get_step_counts_without_aggregation_query(
)
# expects multiple rows for same person, first event time, steps taken.
self.params.update(self.funnel_order.params)
num_intervals, seconds_in_interval, _ = get_time_diff(
self._filter.interval or "day",
self._filter.date_from,
self._filter.date_to,
team_id=self._team.pk)
interval_method = get_trunc_func_ch(self._filter.interval)
# How many steps must have been done to count for the denominator
from_step = self._filter.funnel_from_step or 1
# How many steps must have been done to count for the numerator
to_step = self._filter.funnel_to_step or len(self._filter.entities)
reached_from_step_count_condition = f"steps_completed >= {from_step}"
reached_to_step_count_condition = f"steps_completed >= {to_step}"
query = f"""
SELECT
entrance_period_start,
reached_from_step_count,
reached_to_step_count,
if(reached_from_step_count > 0, round(reached_to_step_count / reached_from_step_count * 100, 2), 0) AS conversion_rate
FROM (
SELECT
entrance_period_start,
countIf({reached_from_step_count_condition}) AS reached_from_step_count,
countIf({reached_to_step_count_condition}) AS reached_to_step_count
FROM (
SELECT
person_id,
{interval_method}(timestamp) AS entrance_period_start,
max(steps) AS steps_completed
FROM (
{steps_per_person_query}
) GROUP BY person_id, entrance_period_start
) GROUP BY entrance_period_start
) data
RIGHT JOIN (
SELECT
{interval_method}(toDateTime('{self._filter.date_from.strftime(TIMESTAMP_FORMAT)}') + number * {seconds_in_interval}) AS entrance_period_start
FROM numbers({num_intervals}) AS period_offsets
) fill
USING (entrance_period_start)
ORDER BY entrance_period_start ASC
SETTINGS allow_experimental_window_functions = 1"""
return query
def _normal_query(self, entity: Entity, filter: Filter, team_id: int) -> Tuple[str, Dict, Callable]:
interval_annotation = get_trunc_func_ch(filter.interval)
num_intervals, seconds_in_interval, round_interval = get_time_diff(
filter.interval or "day", filter.date_from, filter.date_to, team_id=team_id
)
_, parsed_date_to, date_params = parse_timestamps(filter=filter, team_id=team_id)
props_to_filter = [*filter.properties, *entity.properties]
prop_filters, prop_filter_params = parse_prop_clauses(props_to_filter, team_id)
aggregate_operation, join_condition, math_params = process_math(entity)
params: Dict = {"team_id": team_id}
params = {**params, **prop_filter_params, **math_params, **date_params}
content_sql_params = {
"interval": interval_annotation,
"parsed_date_from": date_from_clause(interval_annotation, round_interval),
"parsed_date_to": parsed_date_to,
"timestamp": "timestamp",
"team_id": team_id,
"filters": prop_filters,
"event_join": join_condition,
"aggregate_operation": aggregate_operation,
}
entity_params, entity_format_params = self._populate_entity_params(entity)
params = {**params, **entity_params}
content_sql_params = {**content_sql_params, **entity_format_params}
if filter.display in TRENDS_DISPLAY_BY_VALUE:
agg_query = self._determine_single_aggregate_query(filter, entity)
content_sql = agg_query.format(**content_sql_params)
return (
content_sql,
params,
lambda result: [{"aggregated_value": result[0][0] if result and len(result) else 0}],
)
else:
content_sql = self._determine_trend_aggregate_query(filter, entity)
content_sql = content_sql.format(**content_sql_params)
null_sql = NULL_SQL.format(
interval=interval_annotation,
seconds_in_interval=seconds_in_interval,
num_intervals=num_intervals,
date_to=filter.date_to.strftime("%Y-%m-%d %H:%M:%S"),
)
final_query = AGGREGATE_SQL.format(null_sql=null_sql, content_sql=content_sql)
return final_query, params, self._parse_normal_result(filter)
def get_query(self) -> str:
step_counts = self.get_step_counts_without_aggregation_query()
# Expects multiple rows for same person, first event time, steps taken.
self.params.update(self.funnel_order.params)
reached_from_step_count_condition, reached_to_step_count_condition, _ = self.get_steps_reached_conditions(
)
interval_method = get_trunc_func_ch(self._filter.interval)
num_intervals, seconds_in_interval, _ = get_time_diff(
self._filter.interval or "day",
self._filter.date_from,
self._filter.date_to,
team_id=self._team.pk)
breakdown_clause = self._get_breakdown_prop()
query = f"""
SELECT
entrance_period_start,
reached_from_step_count,
reached_to_step_count,
if(reached_from_step_count > 0, round(reached_to_step_count / reached_from_step_count * 100, 2), 0) AS conversion_rate
{breakdown_clause}
FROM (
SELECT
entrance_period_start,
countIf({reached_from_step_count_condition}) AS reached_from_step_count,
countIf({reached_to_step_count_condition}) AS reached_to_step_count
{breakdown_clause}
FROM (
{step_counts}
) GROUP BY entrance_period_start {breakdown_clause}
) data
RIGHT OUTER JOIN (
SELECT
{interval_method}(toDateTime('{self._filter.date_from.strftime(TIMESTAMP_FORMAT)}') + number * {seconds_in_interval}) AS entrance_period_start
{', breakdown_value as prop' if breakdown_clause else ''}
FROM numbers({num_intervals}) AS period_offsets
{'ARRAY JOIN (%(breakdown_values)s) AS breakdown_value' if breakdown_clause else ''}
) fill
USING (entrance_period_start {breakdown_clause})
ORDER BY entrance_period_start ASC
SETTINGS allow_experimental_window_functions = 1"""
return query
def _format_breakdown_query(self, entity: Entity, filter: Filter,
team: Team) -> List[Dict[str, Any]]:
params = {"team_id": team.pk}
inteval_annotation = get_interval_annotation_ch(filter.interval)
num_intervals, seconds_in_interval = get_time_diff(
filter.interval or "day", filter.date_from, filter.date_to)
parsed_date_from, parsed_date_to = parse_timestamps(filter=filter)
action_query = ""
action_params: Dict = {}
top_elements_array = []
if entity.type == TREND_FILTER_TYPE_ACTIONS:
action = Action.objects.get(pk=entity.id)
action_query, action_params = format_action_filter(action)
null_sql = NULL_BREAKDOWN_SQL.format(
interval=inteval_annotation,
seconds_in_interval=seconds_in_interval,
num_intervals=num_intervals,
date_to=((filter.date_to or timezone.now()) +
timedelta(days=1)).strftime("%Y-%m-%d 00:00:00"),
)
aggregate_operation, join_condition, math_params = self._process_math(
entity)
params = {**params, **math_params}
if filter.breakdown_type == "cohort":
breakdown = filter.breakdown if filter.breakdown and isinstance(
filter.breakdown, list) else []
if "all" in breakdown:
params = {
**params,
"event": entity.id,
**action_params,
}
null_sql = NULL_SQL.format(
interval=inteval_annotation,
seconds_in_interval=seconds_in_interval,
num_intervals=num_intervals,
date_to=((filter.date_to or timezone.now()) +
timedelta(days=1)).strftime("%Y-%m-%d 00:00:00"),
)
conditions = BREAKDOWN_CONDITIONS_SQL.format(
parsed_date_from=parsed_date_from,
parsed_date_to=parsed_date_to,
actions_query="and uuid IN ({})".format(action_query)
if action_query else "",
event_filter="AND event = %(event)s"
if not action_query else "",
)
breakdown_query = BREAKDOWN_DEFAULT_SQL.format(
null_sql=null_sql,
conditions=conditions,
event_join=join_condition,
aggregate_operation=aggregate_operation,
)
else:
cohort_queries, cohort_ids = self._format_breakdown_cohort_join_query(
breakdown, team)
params = {
**params,
"values": cohort_ids,
"event": entity.id,
**action_params,
}
breakdown_filter = BREAKDOWN_COHORT_JOIN_SQL.format(
cohort_queries=cohort_queries,
parsed_date_from=parsed_date_from,
parsed_date_to=parsed_date_to,
actions_query="and uuid IN ({})".format(action_query)
if action_query else "",
event_filter="AND event = %(event)s"
if not action_query else "",
)
breakdown_query = BREAKDOWN_QUERY_SQL.format(
null_sql=null_sql,
breakdown_filter=breakdown_filter,
event_join=join_condition,
aggregate_operation=aggregate_operation,
)
elif filter.breakdown_type == "person":
pass
else:
element_params = {**params, "key": filter.breakdown, "limit": 20}
element_query = TOP_ELEMENTS_ARRAY_OF_KEY_SQL.format(
parsed_date_from=parsed_date_from,
parsed_date_to=parsed_date_to)
try:
top_elements_array_result = sync_execute(
element_query, element_params)
top_elements_array = top_elements_array_result[0][0]
except:
top_elements_array = []
params = {
**params,
"values": top_elements_array,
"key": filter.breakdown,
"event": entity.id,
**action_params,
}
breakdown_filter = BREAKDOWN_PROP_JOIN_SQL.format(
parsed_date_from=parsed_date_from,
parsed_date_to=parsed_date_to,
actions_query="and uuid IN ({})".format(action_query)
if action_query else "",
event_filter="AND event = %(event)s"
if not action_query else "",
)
breakdown_query = BREAKDOWN_QUERY_SQL.format(
null_sql=null_sql,
breakdown_filter=breakdown_filter,
event_join=join_condition,
aggregate_operation=aggregate_operation,
)
try:
result = sync_execute(breakdown_query, params)
except:
result = []
parsed_results = []
for idx, stats in enumerate(result):
extra_label = self._determine_breakdown_label(
idx, filter.breakdown_type, filter.breakdown,
top_elements_array)
label = "{} - {}".format(entity.name, extra_label)
additional_values = {
"label":
label,
"breakdown_value":
filter.breakdown[idx]
if isinstance(filter.breakdown, list) else filter.breakdown if
filter.breakdown_type == "cohort" else top_elements_array[idx],
}
parsed_result = self._parse_response(stats, filter,
additional_values)
parsed_results.append(parsed_result)
return parsed_results
def get_people(
self,
filter: Filter,
team_id: int,
target_date: datetime,
lifecycle_type: str,
request: Request,
limit: int = 100,
):
entity = filter.entities[0]
date_from = filter.date_from
if not date_from:
date_from = get_earliest_timestamp(team_id)
interval = filter.interval or "day"
num_intervals, seconds_in_interval, _ = get_time_diff(interval,
filter.date_from,
filter.date_to,
team_id=team_id)
interval_increment, interval_string, sub_interval_string = self.get_interval(
interval)
trunc_func = get_trunc_func_ch(interval)
event_query = ""
event_params: Dict[str, Any] = {}
_, _, date_params = parse_timestamps(filter=filter, team_id=team_id)
if entity.type == TREND_FILTER_TYPE_ACTIONS:
try:
action = entity.get_action()
event_query, event_params = format_action_filter(action)
except:
return []
else:
event_query = "event = %(event)s"
event_params = {"event": entity.id}
props_to_filter = [*filter.properties, *entity.properties]
prop_filters, prop_filter_params = parse_prop_clauses(
props_to_filter,
team_id,
filter_test_accounts=filter.filter_test_accounts)
result = sync_execute(
LIFECYCLE_PEOPLE_SQL.format(
interval=interval_string,
trunc_func=trunc_func,
event_query=event_query,
filters=prop_filters,
sub_interval=sub_interval_string,
GET_TEAM_PERSON_DISTINCT_IDS=GET_TEAM_PERSON_DISTINCT_IDS,
),
{
"team_id":
team_id,
"prev_date_from":
(date_from - interval_increment).strftime("%Y-%m-%d{}".format(
" %H:%M:%S" if filter.interval == "hour"
or filter.interval == "minute" else " 00:00:00")),
"num_intervals":
num_intervals,
"seconds_in_interval":
seconds_in_interval,
**event_params,
**date_params,
**prop_filter_params,
"status":
lifecycle_type,
"target_date":
target_date.strftime("%Y-%m-%d{}".format(
" %H:%M:%S" if filter.interval == "hour"
or filter.interval == "minute" else " 00:00:00")),
"offset":
filter.offset,
"limit":
limit,
},
)
people = get_persons_by_uuids(team_id=team_id,
uuids=[p[0] for p in result])
people = people.prefetch_related(
Prefetch("persondistinctid_set", to_attr="distinct_ids_cache"))
from posthog.api.person import PersonSerializer
return PersonSerializer(people, many=True).data
def _format_normal_query(self, entity: Entity, filter: Filter,
team_id: int) -> List[Dict[str, Any]]:
interval_annotation = get_trunc_func_ch(filter.interval)
num_intervals, seconds_in_interval = get_time_diff(filter.interval
or "day",
filter.date_from,
filter.date_to,
team_id=team_id)
parsed_date_from, parsed_date_to, _ = parse_timestamps(filter=filter,
team_id=team_id)
props_to_filter = [*filter.properties, *entity.properties]
prop_filters, prop_filter_params = parse_prop_clauses(
props_to_filter, team_id)
aggregate_operation, join_condition, math_params = process_math(entity)
params: Dict = {"team_id": team_id}
params = {**params, **prop_filter_params, **math_params}
content_sql_params = {
"interval": interval_annotation,
"timestamp": "timestamp",
"team_id": team_id,
"parsed_date_from": parsed_date_from,
"parsed_date_to": parsed_date_to,
"filters": prop_filters,
"event_join": join_condition,
"aggregate_operation": aggregate_operation,
}
entity_params, entity_format_params = self._populate_entity_params(
entity)
params = {**params, **entity_params}
content_sql_params = {**content_sql_params, **entity_format_params}
if filter.display == TRENDS_TABLE or filter.display == TRENDS_PIE:
agg_query = self._determine_single_aggregate_query(filter, entity)
content_sql = agg_query.format(**content_sql_params)
try:
result = sync_execute(content_sql, params)
except:
result = []
return [{
"aggregated_value":
result[0][0] if result and len(result) else 0
}]
else:
content_sql = self._determine_trend_aggregate_query(filter, entity)
content_sql = content_sql.format(**content_sql_params)
null_sql = NULL_SQL.format(
interval=interval_annotation,
seconds_in_interval=seconds_in_interval,
num_intervals=num_intervals,
date_to=filter.date_to.strftime("%Y-%m-%d %H:%M:%S"),
)
final_query = AGGREGATE_SQL.format(null_sql=null_sql,
content_sql=content_sql)
try:
result = sync_execute(final_query, params)
except:
result = []
parsed_results = []
for _, stats in enumerate(result):
parsed_result = parse_response(stats, filter)
parsed_results.append(parsed_result)
return parsed_results
def _format_breakdown_query(self, entity: Entity, filter: Filter,
team_id: int) -> Tuple[str, Dict, Callable]:
# process params
params: Dict[str, Any] = {"team_id": team_id}
interval_annotation = get_trunc_func_ch(filter.interval)
num_intervals, seconds_in_interval, round_interval = get_time_diff(
filter.interval or "day", filter.date_from, filter.date_to,
team_id)
_, parsed_date_to, date_params = parse_timestamps(filter=filter,
team_id=team_id)
props_to_filter = [*filter.properties, *entity.properties]
prop_filters, prop_filter_params = parse_prop_clauses(
props_to_filter,
team_id,
table_name="e",
filter_test_accounts=filter.filter_test_accounts)
aggregate_operation, _, math_params = process_math(entity)
if entity.math == "dau" or filter.breakdown_type == "person":
join_condition = EVENT_JOIN_PERSON_SQL
else:
join_condition = ""
action_query = ""
action_params: Dict = {}
if entity.type == TREND_FILTER_TYPE_ACTIONS:
action = Action.objects.get(pk=entity.id)
action_query, action_params = format_action_filter(action)
null_sql = NULL_BREAKDOWN_SQL.format(
interval=interval_annotation,
seconds_in_interval=seconds_in_interval,
num_intervals=num_intervals,
date_to=(filter.date_to).strftime("%Y-%m-%d %H:%M:%S"),
)
params = {
**params,
**math_params,
**prop_filter_params,
**action_params,
"event": entity.id,
"key": filter.breakdown,
**date_params,
}
breakdown_filter_params = {
"parsed_date_from":
date_from_clause(interval_annotation, round_interval),
"parsed_date_to":
parsed_date_to,
"actions_query":
"AND {}".format(action_query) if action_query else "",
"event_filter":
"AND event = %(event)s" if not action_query else "",
"filters":
prop_filters if props_to_filter else "",
}
breakdown_query = self._get_breakdown_query(filter)
_params, _breakdown_filter_params = {}, {}
if filter.breakdown_type == "cohort":
_params, breakdown_filter, _breakdown_filter_params, breakdown_value = self._breakdown_cohort_params(
team_id, filter, entity)
elif filter.breakdown_type == "person":
_params, breakdown_filter, _breakdown_filter_params, breakdown_value = self._breakdown_person_params(
filter, team_id)
else:
_params, breakdown_filter, _breakdown_filter_params, breakdown_value = self._breakdown_prop_params(
filter, team_id)
if len(_params["values"]) == 0:
return "SELECT 1", {}, lambda _: []
params = {**params, **_params}
breakdown_filter_params = {
**breakdown_filter_params,
**_breakdown_filter_params
}
if filter.display in TRENDS_DISPLAY_BY_VALUE:
breakdown_filter = breakdown_filter.format(
**breakdown_filter_params)
content_sql = breakdown_query.format(
breakdown_filter=breakdown_filter,
event_join=join_condition,
aggregate_operation=aggregate_operation,
breakdown_value=breakdown_value,
)
return content_sql, params, self._parse_single_aggregate_result(
filter, entity)
else:
null_sql = null_sql.format(
interval=interval_annotation,
seconds_in_interval=seconds_in_interval,
num_intervals=num_intervals,
date_to=(filter.date_to).strftime("%Y-%m-%d %H:%M:%S"),
)
breakdown_filter = breakdown_filter.format(
**breakdown_filter_params)
breakdown_query = breakdown_query.format(
null_sql=null_sql,
breakdown_filter=breakdown_filter,
event_join=join_condition,
aggregate_operation=aggregate_operation,
interval_annotation=interval_annotation,
breakdown_value=breakdown_value,
)
return breakdown_query, params, self._parse_trend_result(
filter, entity)
def get_query(self) -> Tuple[str, Dict, Callable]:
interval_annotation = get_trunc_func_ch(self.filter.interval)
num_intervals, seconds_in_interval, round_interval = get_time_diff(
self.filter.interval, self.filter.date_from, self.filter.date_to,
self.team_id)
_, parsed_date_to, date_params = parse_timestamps(filter=self.filter,
team_id=self.team_id)
props_to_filter = self.filter.property_groups.combine_property_group(
PropertyOperatorType.AND, self.entity.property_groups)
outer_properties = self.column_optimizer.property_optimizer.parse_property_groups(
props_to_filter).outer
prop_filters, prop_filter_params = parse_prop_grouped_clauses(
team_id=self.team_id,
property_group=outer_properties,
table_name="e",
person_properties_mode=PersonPropertiesMode.
USING_PERSON_PROPERTIES_COLUMN,
)
aggregate_operation, _, math_params = process_math(self.entity)
action_query = ""
action_params: Dict = {}
if self.entity.type == TREND_FILTER_TYPE_ACTIONS:
action = self.entity.get_action()
action_query, action_params = format_action_filter(
team_id=self.team_id, action=action, table_name="e")
self.params = {
**self.params,
**math_params,
**prop_filter_params,
**action_params,
"event": self.entity.id,
"key": self.filter.breakdown,
**date_params,
}
breakdown_filter_params = {
"parsed_date_from":
date_from_clause(interval_annotation, round_interval),
"parsed_date_to":
parsed_date_to,
"actions_query":
"AND {}".format(action_query) if action_query else "",
"event_filter":
"AND event = %(event)s" if not action_query else "",
"filters":
prop_filters if props_to_filter.values else "",
}
_params, _breakdown_filter_params = {}, {}
if self.filter.breakdown_type == "cohort":
_params, breakdown_filter, _breakdown_filter_params, breakdown_value = self._breakdown_cohort_params(
)
else:
_params, breakdown_filter, _breakdown_filter_params, breakdown_value = self._breakdown_prop_params(
"count(*)"
if self.entity.math == "dau" else aggregate_operation,
math_params,
)
if len(_params["values"]) == 0:
# If there are no breakdown values, we are sure that there's no relevant events, so instead of adjusting
# a "real" SELECT for this, we only include the below dummy SELECT.
# It's a drop-in replacement for a "real" one, simply always returning 0 rows.
# See https://github.com/PostHog/posthog/pull/5674 for context.
return (
"SELECT [now()] AS date, [0] AS data, '' AS breakdown_value LIMIT 0",
{},
lambda _: [],
)
person_join_condition, person_join_params = self._person_join_condition(
)
groups_join_condition, groups_join_params = GroupsJoinQuery(
self.filter, self.team_id, self.column_optimizer).get_join_query()
self.params = {
**self.params,
**_params,
**person_join_params,
**groups_join_params
}
breakdown_filter_params = {
**breakdown_filter_params,
**_breakdown_filter_params
}
if self.filter.display in TRENDS_DISPLAY_BY_VALUE:
breakdown_filter = breakdown_filter.format(
**breakdown_filter_params)
content_sql = BREAKDOWN_AGGREGATE_QUERY_SQL.format(
breakdown_filter=breakdown_filter,
person_join=person_join_condition,
groups_join=groups_join_condition,
aggregate_operation=aggregate_operation,
breakdown_value=breakdown_value,
)
time_range = enumerate_time_range(self.filter, seconds_in_interval)
return (
content_sql,
self.params,
self._parse_single_aggregate_result(self.filter, self.entity,
{"days": time_range}),
)
else:
breakdown_filter = breakdown_filter.format(
**breakdown_filter_params)
if self.entity.math in [WEEKLY_ACTIVE, MONTHLY_ACTIVE]:
active_user_params = get_active_user_params(
self.filter, self.entity, self.team_id)
conditions = BREAKDOWN_ACTIVE_USER_CONDITIONS_SQL.format(
**breakdown_filter_params, **active_user_params)
inner_sql = BREAKDOWN_ACTIVE_USER_INNER_SQL.format(
breakdown_filter=breakdown_filter,
person_join=person_join_condition,
groups_join=groups_join_condition,
aggregate_operation=aggregate_operation,
interval_annotation=interval_annotation,
breakdown_value=breakdown_value,
conditions=conditions,
GET_TEAM_PERSON_DISTINCT_IDS=get_team_distinct_ids_query(
self.team_id),
**active_user_params,
**breakdown_filter_params,
)
elif self.filter.display == TRENDS_CUMULATIVE and self.entity.math == "dau":
inner_sql = BREAKDOWN_CUMULATIVE_INNER_SQL.format(
breakdown_filter=breakdown_filter,
person_join=person_join_condition,
groups_join=groups_join_condition,
aggregate_operation=aggregate_operation,
interval_annotation=interval_annotation,
breakdown_value=breakdown_value,
**breakdown_filter_params,
)
else:
inner_sql = BREAKDOWN_INNER_SQL.format(
breakdown_filter=breakdown_filter,
person_join=person_join_condition,
groups_join=groups_join_condition,
aggregate_operation=aggregate_operation,
interval_annotation=interval_annotation,
breakdown_value=breakdown_value,
)
breakdown_query = BREAKDOWN_QUERY_SQL.format(
interval=interval_annotation,
num_intervals=num_intervals,
inner_sql=inner_sql,
)
self.params.update({
"seconds_in_interval": seconds_in_interval,
"num_intervals": num_intervals,
})
return breakdown_query, self.params, self._parse_trend_result(
self.filter, self.entity)
def _format_breakdown_query(self, entity: Entity, filter: Filter,
team_id: int) -> Tuple[str, Dict, Callable]:
# process params
params: Dict[str, Any] = {"team_id": team_id}
interval_annotation = get_trunc_func_ch(filter.interval)
num_intervals, seconds_in_interval, round_interval = get_time_diff(
filter.interval or "day", filter.date_from, filter.date_to,
team_id)
_, parsed_date_to, date_params = parse_timestamps(filter=filter,
team_id=team_id)
props_to_filter = [*filter.properties, *entity.properties]
prop_filters, prop_filter_params = parse_prop_clauses(
props_to_filter,
team_id,
table_name="e",
filter_test_accounts=filter.filter_test_accounts)
aggregate_operation, _, math_params = process_math(entity)
if entity.math == "dau" or filter.breakdown_type == "person":
join_condition = EVENT_JOIN_PERSON_SQL
else:
join_condition = ""
action_query = ""
action_params: Dict = {}
if entity.type == TREND_FILTER_TYPE_ACTIONS:
action = entity.get_action()
action_query, action_params = format_action_filter(action,
table_name="e")
params = {
**params,
**math_params,
**prop_filter_params,
**action_params,
"event": entity.id,
"key": filter.breakdown,
**date_params,
}
breakdown_filter_params = {
"parsed_date_from":
date_from_clause(interval_annotation, round_interval),
"parsed_date_to":
parsed_date_to,
"actions_query":
"AND {}".format(action_query) if action_query else "",
"event_filter":
"AND event = %(event)s" if not action_query else "",
"filters":
prop_filters if props_to_filter else "",
}
_params, _breakdown_filter_params = {}, {}
if filter.breakdown_type == "cohort":
_params, breakdown_filter, _breakdown_filter_params, breakdown_value = self._breakdown_cohort_params(
team_id, filter, entity)
elif filter.breakdown_type == "person":
(
_params,
breakdown_filter,
_breakdown_filter_params,
breakdown_value,
) = self._breakdown_person_params(
"count(*)" if entity.math == "dau" else aggregate_operation,
entity, filter, team_id)
else:
(
_params,
breakdown_filter,
_breakdown_filter_params,
breakdown_value,
) = self._breakdown_prop_params(
"count(*)" if entity.math == "dau" else aggregate_operation,
entity, filter, team_id)
if len(_params["values"]) == 0:
return "SELECT 1", {}, lambda _: []
params = {**params, **_params}
breakdown_filter_params = {
**breakdown_filter_params,
**_breakdown_filter_params
}
if filter.display in TRENDS_DISPLAY_BY_VALUE:
breakdown_filter = breakdown_filter.format(
**breakdown_filter_params)
content_sql = BREAKDOWN_AGGREGATE_QUERY_SQL.format(
breakdown_filter=breakdown_filter,
event_join=join_condition,
aggregate_operation=aggregate_operation,
breakdown_value=breakdown_value,
)
time_range = enumerate_time_range(filter, seconds_in_interval)
return content_sql, params, self._parse_single_aggregate_result(
filter, entity, {"days": time_range})
else:
breakdown_filter = breakdown_filter.format(
**breakdown_filter_params)
if entity.math in [WEEKLY_ACTIVE, MONTHLY_ACTIVE]:
active_user_params = get_active_user_params(
filter, entity, team_id)
conditions = BREAKDOWN_ACTIVE_USER_CONDITIONS_SQL.format(
**breakdown_filter_params, **active_user_params)
inner_sql = BREAKDOWN_ACTIVE_USER_INNER_SQL.format(
breakdown_filter=breakdown_filter,
event_join=join_condition,
aggregate_operation=aggregate_operation,
interval_annotation=interval_annotation,
breakdown_value=breakdown_value,
conditions=conditions,
GET_TEAM_PERSON_DISTINCT_IDS=GET_TEAM_PERSON_DISTINCT_IDS,
**active_user_params,
**breakdown_filter_params)
else:
inner_sql = BREAKDOWN_INNER_SQL.format(
breakdown_filter=breakdown_filter,
event_join=join_condition,
aggregate_operation=aggregate_operation,
interval_annotation=interval_annotation,
breakdown_value=breakdown_value,
)
breakdown_query = BREAKDOWN_QUERY_SQL.format(
interval=interval_annotation,
num_intervals=num_intervals,
inner_sql=inner_sql,
)
params.update({
"date_to":
filter.date_to.strftime("%Y-%m-%d %H:%M:%S"),
"seconds_in_interval":
seconds_in_interval,
"num_intervals":
num_intervals,
})
return breakdown_query, params, self._parse_trend_result(
filter, entity)
def _format_breakdown_query(self, entity: Entity, filter: Filter,
team: Team) -> List[Dict[str, Any]]:
params = {"team_id": team.pk}
interval_annotation = get_interval_annotation_ch(filter.interval)
num_intervals, seconds_in_interval = get_time_diff(
filter.interval or "day", filter.date_from, filter.date_to)
parsed_date_from, parsed_date_to = parse_timestamps(filter=filter)
props_to_filter = [*filter.properties, *entity.properties]
prop_filters, prop_filter_params = parse_prop_clauses(
props_to_filter, team)
aggregate_operation, join_condition, math_params = self._process_math(
entity)
action_query = ""
action_params: Dict = {}
if entity.type == TREND_FILTER_TYPE_ACTIONS:
action = Action.objects.get(pk=entity.id)
action_query, action_params = format_action_filter(action)
null_sql = NULL_BREAKDOWN_SQL.format(
interval=interval_annotation,
seconds_in_interval=seconds_in_interval,
num_intervals=num_intervals,
date_to=((filter.date_to
or timezone.now())).strftime("%Y-%m-%d %H:%M:%S"),
)
params = {**params, **math_params, **prop_filter_params}
top_elements_array = []
if filter.breakdown_type == "cohort":
breakdown = filter.breakdown if filter.breakdown and isinstance(
filter.breakdown, list) else []
if "all" in breakdown:
params = {**params, "event": entity.id, **action_params}
null_sql = NULL_SQL.format(
interval=interval_annotation,
seconds_in_interval=seconds_in_interval,
num_intervals=num_intervals,
date_to=((filter.date_to or
timezone.now())).strftime("%Y-%m-%d %H:%M:%S"),
)
conditions = BREAKDOWN_CONDITIONS_SQL.format(
parsed_date_from=parsed_date_from,
parsed_date_to=parsed_date_to,
actions_query="AND {}".format(action_query)
if action_query else "",
event_filter="AND event = %(event)s"
if not action_query else "",
filters="{filters}".format(
filters=prop_filters) if props_to_filter else "",
)
breakdown_query = BREAKDOWN_DEFAULT_SQL.format(
null_sql=null_sql,
conditions=conditions,
event_join=join_condition,
aggregate_operation=aggregate_operation,
interval_annotation=interval_annotation,
)
else:
cohort_queries, cohort_ids, cohort_params = self._format_breakdown_cohort_join_query(
breakdown, team)
params = {
**params, "values": cohort_ids,
"event": entity.id,
**action_params,
**cohort_params
}
breakdown_filter = BREAKDOWN_COHORT_JOIN_SQL.format(
cohort_queries=cohort_queries,
parsed_date_from=parsed_date_from,
parsed_date_to=parsed_date_to,
actions_query="AND {}".format(action_query)
if action_query else "",
event_filter="AND event = %(event)s"
if not action_query else "",
filters="{filters}".format(
filters=prop_filters) if props_to_filter else "",
)
breakdown_query = BREAKDOWN_QUERY_SQL.format(
null_sql=null_sql,
breakdown_filter=breakdown_filter,
event_join=join_condition,
aggregate_operation=aggregate_operation,
interval_annotation=interval_annotation,
)
elif filter.breakdown_type == "person":
elements_query = TOP_PERSON_PROPS_ARRAY_OF_KEY_SQL.format(
parsed_date_from=parsed_date_from,
parsed_date_to=parsed_date_to,
latest_person_sql=GET_LATEST_PERSON_SQL.format(query=""),
)
top_elements_array = self._get_top_elements(
elements_query, filter, team)
params = {
**params,
"values": top_elements_array,
"key": filter.breakdown,
"event": entity.id,
**action_params,
}
breakdown_filter = BREAKDOWN_PERSON_PROP_JOIN_SQL.format(
parsed_date_from=parsed_date_from,
parsed_date_to=parsed_date_to,
actions_query="AND {}".format(action_query)
if action_query else "",
event_filter="AND event = %(event)s"
if not action_query else "",
latest_person_sql=GET_LATEST_PERSON_SQL.format(query=""),
)
breakdown_query = BREAKDOWN_QUERY_SQL.format(
null_sql=null_sql,
breakdown_filter=breakdown_filter,
event_join=join_condition,
aggregate_operation=aggregate_operation,
interval_annotation=interval_annotation,
)
else:
elements_query = TOP_ELEMENTS_ARRAY_OF_KEY_SQL.format(
parsed_date_from=parsed_date_from,
parsed_date_to=parsed_date_to)
top_elements_array = self._get_top_elements(
elements_query, filter, team)
params = {
**params,
"values": top_elements_array,
"key": filter.breakdown,
"event": entity.id,
**action_params,
}
breakdown_filter = BREAKDOWN_PROP_JOIN_SQL.format(
parsed_date_from=parsed_date_from,
parsed_date_to=parsed_date_to,
actions_query="AND {}".format(action_query)
if action_query else "",
event_filter="AND event = %(event)s"
if not action_query else "",
filters="{filters}".format(
filters=prop_filters) if props_to_filter else "",
)
breakdown_query = BREAKDOWN_QUERY_SQL.format(
null_sql=null_sql,
breakdown_filter=breakdown_filter,
event_join=join_condition,
aggregate_operation=aggregate_operation,
interval_annotation=interval_annotation,
)
try:
result = sync_execute(breakdown_query, params)
except:
result = []
parsed_results = []
for idx, stats in enumerate(result):
breakdown_value = stats[
2] if not filter.breakdown_type == "cohort" else ""
stripped_value = breakdown_value.strip('"') if isinstance(
breakdown_value, str) else breakdown_value
extra_label = self._determine_breakdown_label(
idx, filter.breakdown_type, filter.breakdown, stripped_value)
label = "{} - {}".format(entity.name, extra_label)
additional_values = {
"label":
label,
"breakdown_value":
filter.breakdown[idx]
if isinstance(filter.breakdown, list) else filter.breakdown
if filter.breakdown_type == "cohort" else stripped_value,
}
parsed_result = self._parse_response(stats, filter,
additional_values)
parsed_results.append(parsed_result)
return parsed_results
def _serialize_lifecycle(self, entity: Entity, filter: Filter,
team_id: int) -> List[Dict[str, Any]]:
date_from = filter.date_from
if not date_from:
date_from = get_earliest_timestamp(team_id)
interval = filter.interval or "day"
num_intervals, seconds_in_interval, _ = get_time_diff(
interval, filter.date_from, filter.date_to, team_id)
interval_increment, interval_string, sub_interval_string = self.get_interval(
interval)
trunc_func = get_trunc_func_ch(interval)
event_query = ""
event_params: Dict[str, Any] = {}
props_to_filter = [*filter.properties, *entity.properties]
prop_filters, prop_filter_params = parse_prop_clauses(
props_to_filter, team_id)
_, _, date_params = parse_timestamps(filter=filter, team_id=team_id)
if entity.type == TREND_FILTER_TYPE_ACTIONS:
try:
action = Action.objects.get(pk=entity.id)
event_query, event_params = format_action_filter(action)
except:
return []
else:
event_query = "event = %(event)s"
event_params = {"event": entity.id}
result = sync_execute(
LIFECYCLE_SQL.format(
interval=interval_string,
trunc_func=trunc_func,
event_query=event_query,
filters=prop_filters,
sub_interval=sub_interval_string,
),
{
"team_id":
team_id,
"prev_date_from":
(date_from - interval_increment).strftime("%Y-%m-%d{}".format(
" %H:%M:%S" if filter.interval == "hour"
or filter.interval == "minute" else " 00:00:00")),
"num_intervals":
num_intervals,
"seconds_in_interval":
seconds_in_interval,
**event_params,
**date_params,
**prop_filter_params,
},
)
res = []
for val in result:
label = "{} - {}".format(entity.name, val[2])
additional_values = {"label": label, "status": val[2]}
parsed_result = parse_response(val, filter, additional_values)
res.append(parsed_result)
return res
def _format_normal_query(self, entity: Entity, filter: Filter,
team: Team) -> List[Dict[str, Any]]:
inteval_annotation = get_interval_annotation_ch(filter.interval)
num_intervals, seconds_in_interval = get_time_diff(
filter.interval or "day", filter.date_from, filter.date_to)
parsed_date_from, parsed_date_to = parse_timestamps(filter=filter)
prop_filters, prop_filter_params = parse_prop_clauses(
"uuid", filter.properties, team)
aggregate_operation, join_condition, math_params = self._process_math(
entity)
params: Dict = {"team_id": team.pk}
params = {**params, **prop_filter_params, **math_params}
if entity.type == TREND_FILTER_TYPE_ACTIONS:
try:
action = Action.objects.get(pk=entity.id)
action_query, action_params = format_action_filter(action)
params = {**params, **action_params}
content_sql = VOLUME_ACTIONS_SQL.format(
interval=inteval_annotation,
timestamp="timestamp",
team_id=team.pk,
actions_query=action_query,
parsed_date_from=(parsed_date_from or ""),
parsed_date_to=(parsed_date_to or ""),
filters="{filters}".format(
filters=prop_filters) if filter.properties else "",
event_join=join_condition,
aggregate_operation=aggregate_operation,
)
except:
return []
else:
content_sql = VOLUME_SQL.format(
interval=inteval_annotation,
timestamp="timestamp",
team_id=team.pk,
parsed_date_from=(parsed_date_from or ""),
parsed_date_to=(parsed_date_to or ""),
filters="{filters}".format(
filters=prop_filters) if filter.properties else "",
event_join=join_condition,
aggregate_operation=aggregate_operation,
)
params = {**params, "event": entity.id}
null_sql = NULL_SQL.format(
interval=inteval_annotation,
seconds_in_interval=seconds_in_interval,
num_intervals=num_intervals,
date_to=((filter.date_to
or timezone.now())).strftime("%Y-%m-%d %H:%M:%S"),
)
final_query = AGGREGATE_SQL.format(null_sql=null_sql,
content_sql=content_sql)
try:
result = sync_execute(final_query, params)
except:
result = []
parsed_results = []
for _, stats in enumerate(result):
parsed_result = self._parse_response(stats, filter)
parsed_results.append(parsed_result)
return parsed_results
def _normal_query(self, entity: Entity, filter: Filter,
team_id: int) -> Tuple[str, Dict, Callable]:
interval_annotation = get_trunc_func_ch(filter.interval)
num_intervals, seconds_in_interval, round_interval = get_time_diff(
filter.interval or "day",
filter.date_from,
filter.date_to,
team_id=team_id)
_, parsed_date_to, date_params = parse_timestamps(filter=filter,
team_id=team_id)
props_to_filter = [*filter.properties, *entity.properties]
prop_filters, prop_filter_params = parse_prop_clauses(
props_to_filter,
team_id,
filter_test_accounts=filter.filter_test_accounts)
aggregate_operation, join_condition, math_params = process_math(entity)
params: Dict = {"team_id": team_id}
params = {**params, **prop_filter_params, **math_params, **date_params}
content_sql_params = {
"interval":
interval_annotation,
"parsed_date_from":
date_from_clause(interval_annotation, round_interval),
"parsed_date_to":
parsed_date_to,
"timestamp":
"timestamp",
"filters":
prop_filters,
"event_join":
join_condition,
"aggregate_operation":
aggregate_operation,
"entity_query":
"AND {actions_query}" if entity.type == TREND_FILTER_TYPE_ACTIONS
else "AND event = %(event)s",
}
entity_params, entity_format_params = self._populate_entity_params(
entity)
params = {**params, **entity_params}
if filter.display in TRENDS_DISPLAY_BY_VALUE:
content_sql = VOLUME_TOTAL_AGGREGATE_SQL.format(
**content_sql_params).format(**entity_format_params)
time_range = self._enumerate_time_range(filter,
seconds_in_interval)
return (
content_sql,
params,
lambda result: [{
"aggregated_value":
result[0][0] if result and len(result) else 0,
"days":
time_range
}],
)
else:
if entity.math in [WEEKLY_ACTIVE, MONTHLY_ACTIVE]:
sql_params = get_active_user_params(filter, entity, team_id)
content_sql = ACTIVE_USER_SQL.format(
**content_sql_params,
**sql_params).format(**entity_format_params)
else:
# entity_format_params depends on format clause from content_sql_params
content_sql = VOLUME_SQL.format(**content_sql_params).format(
**entity_format_params)
null_sql = NULL_SQL.format(
interval=interval_annotation,
seconds_in_interval=seconds_in_interval,
num_intervals=num_intervals,
date_to=filter.date_to.strftime("%Y-%m-%d %H:%M:%S"),
)
final_query = AGGREGATE_SQL.format(null_sql=null_sql,
content_sql=content_sql)
return final_query, params, self._parse_normal_result(filter)
def _format_normal_query(self, entity: Entity, filter: Filter,
team_id: int) -> List[Dict[str, Any]]:
interval_annotation = get_interval_annotation_ch(filter.interval)
num_intervals, seconds_in_interval = get_time_diff(
filter.interval or "day", filter.date_from, filter.date_to)
parsed_date_from, parsed_date_to = parse_timestamps(filter=filter)
props_to_filter = [*filter.properties, *entity.properties]
prop_filters, prop_filter_params = parse_prop_clauses(
props_to_filter, team_id)
aggregate_operation, join_condition, math_params = process_math(entity)
params: Dict = {"team_id": team_id}
params = {**params, **prop_filter_params, **math_params}
content_sql_params = {
"interval": interval_annotation,
"timestamp": "timestamp",
"team_id": team_id,
"parsed_date_from": parsed_date_from,
"parsed_date_to": parsed_date_to,
"filters": prop_filters,
"event_join": join_condition,
"aggregate_operation": aggregate_operation,
}
if entity.type == TREND_FILTER_TYPE_ACTIONS:
try:
action = Action.objects.get(pk=entity.id)
action_query, action_params = format_action_filter(action)
params = {**params, **action_params}
content_sql = VOLUME_ACTIONS_SQL
content_sql_params = {
**content_sql_params, "actions_query": action_query
}
except:
return []
else:
content_sql = VOLUME_SQL
params = {**params, "event": entity.id}
null_sql = NULL_SQL.format(
interval=interval_annotation,
seconds_in_interval=seconds_in_interval,
num_intervals=num_intervals,
date_to=filter.date_to.strftime("%Y-%m-%d %H:%M:%S"),
)
content_sql = content_sql.format(**content_sql_params)
final_query = AGGREGATE_SQL.format(null_sql=null_sql,
content_sql=content_sql)
try:
result = sync_execute(final_query, params)
except:
result = []
parsed_results = []
for _, stats in enumerate(result):
parsed_result = parse_response(stats, filter)
parsed_results.append(parsed_result)
return parsed_results
def _format_breakdown_query(
self, entity: Entity, filter: Filter, breakdown: List, team_id: int
) -> List[Dict[str, Any]]:
# process params
params: Dict[str, Any] = {"team_id": team_id}
interval_annotation = get_trunc_func_ch(filter.interval)
num_intervals, seconds_in_interval, round_interval = get_time_diff(
filter.interval or "day", filter.date_from, filter.date_to, team_id
)
_, parsed_date_to, date_params = parse_timestamps(filter=filter, team_id=team_id)
props_to_filter = [*filter.properties, *entity.properties]
prop_filters, prop_filter_params = parse_prop_clauses(props_to_filter, team_id, table_name="e")
aggregate_operation, _, math_params = process_math(entity)
if entity.math == "dau" or filter.breakdown_type == "person":
join_condition = EVENT_JOIN_PERSON_SQL
else:
join_condition = ""
action_query = ""
action_params: Dict = {}
if entity.type == TREND_FILTER_TYPE_ACTIONS:
action = Action.objects.get(pk=entity.id)
action_query, action_params = format_action_filter(action)
null_sql = NULL_BREAKDOWN_SQL.format(
interval=interval_annotation,
seconds_in_interval=seconds_in_interval,
num_intervals=num_intervals,
date_to=(filter.date_to).strftime("%Y-%m-%d %H:%M:%S"),
)
params = {
**params,
**math_params,
**prop_filter_params,
**action_params,
"event": entity.id,
"key": filter.breakdown,
**date_params,
}
breakdown_filter_params = {
"parsed_date_from": date_from_clause(interval_annotation, round_interval),
"parsed_date_to": parsed_date_to,
"actions_query": "AND {}".format(action_query) if action_query else "",
"event_filter": "AND event = %(event)s" if not action_query else "",
"filters": prop_filters if props_to_filter else "",
}
breakdown_query = self._get_breakdown_query(filter, breakdown)
_params, _breakdown_filter_params = {}, {}
if filter.breakdown_type == "cohort":
if "all" in breakdown:
null_sql = NULL_SQL
breakdown_filter = BREAKDOWN_CONDITIONS_SQL
breakdown_value = ""
else:
_params, breakdown_filter, _breakdown_filter_params, breakdown_value = self._breakdown_cohort_params(
breakdown, team_id
)
elif filter.breakdown_type == "person":
_params, breakdown_filter, _breakdown_filter_params, breakdown_value = self._breakdown_person_params(
filter, team_id
)
else:
_params, breakdown_filter, _breakdown_filter_params, breakdown_value = self._breakdown_prop_params(
filter, team_id
)
params = {**params, **_params}
breakdown_filter_params = {**breakdown_filter_params, **_breakdown_filter_params}
if filter.display == TRENDS_TABLE or filter.display == TRENDS_PIE:
breakdown_filter = breakdown_filter.format(**breakdown_filter_params)
content_sql = breakdown_query.format(
breakdown_filter=breakdown_filter,
event_join=join_condition,
aggregate_operation=aggregate_operation,
breakdown_value=breakdown_value,
)
result = sync_execute(content_sql, params)
parsed_results = self._parse_single_aggregate_result(result, filter, entity, breakdown)
return parsed_results
else:
null_sql = null_sql.format(
interval=interval_annotation,
seconds_in_interval=seconds_in_interval,
num_intervals=num_intervals,
date_to=(filter.date_to).strftime("%Y-%m-%d %H:%M:%S"),
)
breakdown_filter = breakdown_filter.format(**breakdown_filter_params)
breakdown_query = breakdown_query.format(
null_sql=null_sql,
breakdown_filter=breakdown_filter,
event_join=join_condition,
aggregate_operation=aggregate_operation,
interval_annotation=interval_annotation,
breakdown_value=breakdown_value,
)
try:
result = sync_execute(breakdown_query, params)
except:
result = []
parsed_results = self._parse_trend_result(result, filter, entity, breakdown)
return parsed_results
