Weijun-H commented on code in PR #15773:
URL: https://github.com/apache/datafusion/pull/15773#discussion_r2051622969
##########
benchmarks/queries/clickbench/README.md:
##########
@@ -155,7 +155,7 @@ WHERE
THEN split_part(split_part("URL", 'resolution=', 2), '&', 1)::INT
ELSE 0
END > 1920 -- Extract and validate resolution parameter
- AND levenshtein("UTMSource", "UTMCampaign") < 3 -- Verify UTM parameter
similarity
+ AND levenshtein(CAST("UTMSource" AS STRING), CAST("UTMCampaign" AS
STRING)) < 3 -- Verify UTM parameter similarity
Review Comment:
```suggestion
AND levenshtein('UTMSource', 'UTMCampaign') < 3 -- Verify UTM parameter
similarity
```
##########
benchmarks/queries/clickbench/extended.sql:
##########
@@ -4,4 +4,4 @@ SELECT "BrowserCountry", COUNT(DISTINCT "SocialNetwork"),
COUNT(DISTINCT "HitCo
SELECT "SocialSourceNetworkID", "RegionID", COUNT(*), AVG("Age"),
AVG("ParamPrice"), STDDEV("ParamPrice") as s, VAR("ParamPrice") FROM hits
GROUP BY "SocialSourceNetworkID", "RegionID" HAVING s IS NOT NULL ORDER BY s
DESC LIMIT 10;
SELECT "ClientIP", "WatchID", COUNT(*) c, MIN("ResponseStartTiming") tmin,
MEDIAN("ResponseStartTiming") tmed, MAX("ResponseStartTiming") tmax FROM hits
WHERE "JavaEnable" = 0 GROUP BY "ClientIP", "WatchID" HAVING c > 1 ORDER BY
tmed DESC LIMIT 10;
SELECT "ClientIP", "WatchID", COUNT(*) c, MIN("ResponseStartTiming") tmin,
APPROX_PERCENTILE_CONT("ResponseStartTiming", 0.95) tp95,
MAX("ResponseStartTiming") tmax FROM 'hits' WHERE "JavaEnable" = 0 GROUP BY
"ClientIP", "WatchID" HAVING c > 1 ORDER BY tp95 DESC LIMIT 10;
-SELECT COUNT(*) AS ShareCount FROM hits WHERE "IsMobile" = 1 AND
"MobilePhoneModel" LIKE 'iPhone%' AND "SocialAction" = 'share' AND
"SocialSourceNetworkID" IN (5, 12) AND "ClientTimeZone" BETWEEN -5 AND 5 AND
regexp_match("Referer", '\/campaign\/(spring|summer)_promo') IS NOT NULL AND
CASE WHEN split_part(split_part("URL", 'resolution=', 2), '&', 1) ~ '^\d+$'
THEN split_part(split_part("URL", 'resolution=', 2), '&', 1)::INT ELSE 0 END >
1920 AND levenshtein("UTMSource", "UTMCampaign") < 3;
\ No newline at end of file
+SELECT COUNT(*) AS ShareCount FROM hits WHERE "IsMobile" = 1 AND
"MobilePhoneModel" LIKE 'iPhone%' AND "SocialAction" = 'share' AND
"SocialSourceNetworkID" IN (5, 12) AND "ClientTimeZone" BETWEEN -5 AND 5 AND
regexp_match("Referer", '\/campaign\/(spring|summer)_promo') IS NOT NULL AND
CASE WHEN split_part(split_part("URL", 'resolution=', 2), '&', 1) ~ '^\d+$'
THEN split_part(split_part("URL", 'resolution=', 2), '&', 1)::INT ELSE 0 END >
1920 AND levenshtein(CAST("UTMSource" AS STRING), CAST("UTMCampaign" AS
STRING)) < 3;
Review Comment:
```suggestion
SELECT COUNT(*) AS ShareCount FROM hits WHERE "IsMobile" = 1 AND
"MobilePhoneModel" LIKE 'iPhone%' AND "SocialAction" = 'share' AND
"SocialSourceNetworkID" IN (5, 12) AND "ClientTimeZone" BETWEEN -5 AND 5 AND
regexp_match("Referer", '\/campaign\/(spring|summer)_promo') IS NOT NULL AND
CASE WHEN split_part(split_part("URL", 'resolution=', 2), '&', 1) ~ '^\d+$'
THEN split_part(split_part("URL", 'resolution=', 2), '&', 1)::INT ELSE 0 END >
1920 AND levenshtein('UTMSource', 'UTMCampaign') < 3;
```
--
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: github-unsubscr...@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For additional commands, e-mail: github-h...@datafusion.apache.org
