Last active
October 8, 2018 21:02
-
-
Save samgqroberts/248530623731441e1218633e4afe1582 to your computer and use it in GitHub Desktop.
working thesis for golden attribute API input formats
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"clusterDataset": { | |
"name": "my_dedup_project_published_clusters_with_data", | |
"groupingKey": "published_id", | |
}, | |
"overrideRules": { | |
"default": { | |
"type": "PRIORITY", | |
"overrideDatasets": ["manual_overrides", "suggestions"], // defaults to rule output | |
"default": true, | |
}, | |
"noSuggestions": { | |
"type": "PRIORITY", | |
"overrideDatasets": ["manual_overrides"], | |
}, | |
}, | |
"goldenAttributes": [ | |
{ | |
"attributeName": "ga_spend", | |
"consolidationRule": { | |
"type": "SUM", | |
"attribute": "spend" | |
}, // GROUP sum(to_double(spend)) BY published_id | |
"overrideRule": "default", // OPTIONAL b/c "default" is marked as default | |
}, | |
{ | |
"attributeName": "ga_address", | |
"consolidationRule": { | |
"type": "CUSTOM", | |
"expr": "mode(address_1) || mode(address_2)", | |
}, | |
// overrideRule is the "default" rule | |
{ | |
"attributeName": "ga_marital_status", | |
"consolidationRule": { | |
"type": "MOST_RECENT", | |
"dateAttribute": "date", | |
"valueAttribute": "marital_status", | |
}, // GROUP firstBy(marital_status, date) BY published_id (syntax is pending output of DEV-9345 | |
"overrideRule": "noSuggestions", | |
}, | |
{ | |
// authoritative source ?? "same as" ?? | |
}, | |
] | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment