walterddr commented on code in PR #10120:
URL: https://github.com/apache/pinot/pull/10120#discussion_r1073985700


##########
pinot-query-runtime/src/test/resources/queries/Skew.json:
##########
@@ -0,0 +1,79 @@
+{
+  "skew": {
+    "tables": {
+      "tbl": {
+        "schema": [
+          {"name": "groupingCol", "type": "STRING"},
+          {"name": "partitionCol", "type": "STRING"},
+          {"name": "val", "type": "INT"}
+        ],
+        "inputs": [
+          ["a", "key1", 1],
+          ["a", "key2", 2],
+          ["a", "key3", 3],
+          ["a", "key1", 4],
+          ["a", "key2", 4],
+          ["a", "key3", 4],
+          ["a", "key1", 7],
+          ["a", "key2", 9],
+          ["b", "key3", 1],
+          ["b", "key1", 2],
+          ["b", "key2", 3],
+          ["b", "key3", 4],
+          ["b", "key1", 4],
+          ["b", "key2", 4],
+          ["b", "key3", 7],
+          ["b", "key1", 9]
+        ],
+        "partitionColumns": [
+          "partitionCol"
+        ]
+      },
+      "tbl2": {
+        "schema": [
+          {"name": "groupingCol", "type": "STRING"},
+          {"name": "partitionCol", "type": "STRING"},
+          {"name": "val", "type": "INT"}
+        ],
+        "inputs": [
+          ["a", "key1", 1],
+          ["a", "key2", 2],
+          ["a", "key3", 3],
+          ["a", "key1", 4],
+          ["a", "key2", 4],
+          ["a", "key3", 4],
+          ["a", "key1", 7],
+          ["a", "key2", 9],
+          ["b", "key3", 1],
+          ["b", "key1", 2],
+          ["b", "key2", 3],
+          ["b", "key3", 4],
+          ["b", "key1", 4],
+          ["b", "key2", 4],
+          ["b", "key3", 7],
+          ["b", "key1", 9]
+        ],
+        "partitionColumns": [
+          "partitionCol"
+        ]
+      }
+    },
+    "queries": [
+      {
+        "description": "skew for int column",
+        "sql": "SELECT groupingCol, SKEWNESS(val), KURTOSIS(val) FROM {tbl} 
GROUP BY groupingCol",

Review Comment:
   current framework compares as bag of records. i believe most of the order by 
query have order by limit so that it make sure the results are correct



-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to