DevTalks Reimagined 2020 - Funnel Analysis with Spark and Druid
- 46. @ItaiYaffe
"inputSpec": {"type": " multi",
"children": [
{"type": " dataSource",
"ingestionSpec": {
"intervals": ["2020-01-01/2020-01-29"],
"dataSource": "campaign_1472", ...}},
{"type": " static",
"Paths": "s3://<BUCKET_NAME>/date=2020-01-28/campaign=1472",
...},
...
- 63. @ItaiYaffe
SELECT THETA_SKETCH_NOT(65536,
THETA_SKETCH_INTERSECT(65536,a,b), THETA_SKETCH_UNION(65536,c,d,e)
) as online_ad_596
FROM (
SELECT
DS_THETA("user_id_sketch") FILTER (WHERE stage = 'homepage') as a,
DS_THETA("user_id_sketch") FILTER (WHERE tactic = 'online_ad') as b,
DS_THETA("user_id_sketch") FILTER (WHERE stage = 'productX_page') as c,
DS_THETA("user_id_sketch") FILTER (WHERE stage = 'add_to_cart') as d,
DS_THETA("user_id_sketch") FILTER (WHERE stage = 'checkout') as e
FROM campaign_1472
WHERE stage in ('homepage','productX_page','checkout','add_to_cart')
AND tactic = 'online_ad') subquery