Merge branch 'main' into feature-precompile_regex_pattern

Author: zhuliquan

.github/workflows/pr_comment.yml

@@ -16,6 +16,7 @@
 # under the License.
 
 [workspace]
+# datafusion-cli is excluded because of its Cargo.lock. See datafusion-cli/README.md.
 exclude = ["datafusion-cli", "dev/depcheck"]
 members = [
     "datafusion/common",
@@ -33,7 +34,6 @@ members = [
     "datafusion/optimizer",
     "datafusion/physical-expr",
     "datafusion/physical-expr-common",
-    "datafusion/physical-expr-functions-aggregate",
     "datafusion/physical-optimizer",
     "datafusion/physical-plan",
     "datafusion/proto",
@@ -106,7 +106,6 @@ datafusion-functions-window = { path = "datafusion/functions-window", version =
 datafusion-optimizer = { path = "datafusion/optimizer", version = "41.0.0", default-features = false }
 datafusion-physical-expr = { path = "datafusion/physical-expr", version = "41.0.0", default-features = false }
 datafusion-physical-expr-common = { path = "datafusion/physical-expr-common", version = "41.0.0", default-features = false }
-datafusion-physical-expr-functions-aggregate = { path = "datafusion/physical-expr-functions-aggregate", version = "41.0.0" }
 datafusion-physical-optimizer = { path = "datafusion/physical-optimizer", version = "41.0.0" }
 datafusion-physical-plan = { path = "datafusion/physical-plan", version = "41.0.0" }
 datafusion-proto = { path = "datafusion/proto", version = "41.0.0" }

Cargo.toml

@@ -58,6 +58,21 @@ LIMIT 10;
 ```
 
 
+### Q3: What is the income distribution for users in specific regions
+
+**Question**: "What regions and social networks have the highest variance of parameter price 
+
+**Important Query Properties**: STDDEV and VAR aggregation functions, GROUP BY multiple small ints
+
+```sql
+SELECT "SocialSourceNetworkID", "RegionID", COUNT(*), AVG("Age"), AVG("ParamPrice"), STDDEV("ParamPrice") as s, VAR("ParamPrice") 
+FROM 'hits.parquet' 
+GROUP BY "SocialSourceNetworkID", "RegionID"  
+HAVING s IS NOT NULL
+ORDER BY s DESC 
+LIMIT 10;
+```
+
 ## Data Notes
 
 Here are some interesting statistics about the data used in the queries

benchmarks/queries/clickbench/README.md

@@ -1,3 +1,4 @@
 SELECT COUNT(DISTINCT "SearchPhrase"), COUNT(DISTINCT "MobilePhone"), COUNT(DISTINCT "MobilePhoneModel") FROM hits;
 SELECT COUNT(DISTINCT "HitColor"), COUNT(DISTINCT "BrowserCountry"), COUNT(DISTINCT "BrowserLanguage")  FROM hits;
-SELECT "BrowserCountry",  COUNT(DISTINCT "SocialNetwork"), COUNT(DISTINCT "HitColor"), COUNT(DISTINCT "BrowserLanguage"), COUNT(DISTINCT "SocialAction") FROM hits GROUP BY 1 ORDER BY 2 DESC LIMIT 10;
+SELECT "BrowserCountry",  COUNT(DISTINCT "SocialNetwork"), COUNT(DISTINCT "HitColor"), COUNT(DISTINCT "BrowserLanguage"), COUNT(DISTINCT "SocialAction") FROM hits GROUP BY 1 ORDER BY 2 DESC LIMIT 10;
+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;