Skip to content

Apache DataFusion SQL Query Engine

chore: fix malformed example tables in aggregate function docs (#24503)

Advit Arora5c1211439efd
diff --git a/datafusion/functions-aggregate/src/approx_percentile_cont_with_weight.rs b/datafusion/functions-aggregate/src/approx_percentile_cont_with_weight.rs
index 6ada47fb38..90b24dc3c6 100644
--- a/datafusion/functions-aggregate/src/approx_percentile_cont_with_weight.rs
+++ b/datafusion/functions-aggregate/src/approx_percentile_cont_with_weight.rs
@@ -90,11 +90,11 @@ An alternative syntax is also supported:
```sql
> SELECT approx_percentile_cont_with_weight(column_name, weight_column, 0.90) FROM table_name;
-+--------------------------------------------------+
++----------------------------------------------------------------------+
| approx_percentile_cont_with_weight(column_name, weight_column, 0.90) |
-+--------------------------------------------------+
-| 78.5 |
-+--------------------------------------------------+
++----------------------------------------------------------------------+
+| 78.5 |
++----------------------------------------------------------------------+
```"#,
standard_argument(name = "expression", prefix = "The"),
argument(
diff --git a/datafusion/functions-aggregate/src/array_agg.rs b/datafusion/functions-aggregate/src/array_agg.rs
index 0e02ff1186..97a2520eb2 100644
--- a/datafusion/functions-aggregate/src/array_agg.rs
+++ b/datafusion/functions-aggregate/src/array_agg.rs
@@ -77,7 +77,7 @@ This aggregation function can only mix DISTINCT and ORDER BY if the ordering exp
+-----------------------------------------------+
> SELECT array_agg(DISTINCT column_name ORDER BY column_name) FROM table_name;
+--------------------------------------------------------+
-| array_agg(DISTINCT column_name ORDER BY column_name) |
+| array_agg(DISTINCT column_name ORDER BY column_name) |
+--------------------------------------------------------+
| [element1, element2, element3] |
+--------------------------------------------------------+
diff --git a/datafusion/functions-aggregate/src/average.rs b/datafusion/functions-aggregate/src/average.rs
index 89b6330852..8601d93c11 100644
--- a/datafusion/functions-aggregate/src/average.rs
+++ b/datafusion/functions-aggregate/src/average.rs
@@ -83,9 +83,9 @@ pub fn avg_distinct(expr: Expr) -> Expr {
sql_example = r#"```sql
> SELECT avg(column_name) FROM table_name;
+---------------------------+
-| avg(column_name) |
+| avg(column_name) |
+---------------------------+
-| 42.75 |
+| 42.75 |
+---------------------------+
```"#,
standard_argument(name = "expression",)
diff --git a/datafusion/functions-aggregate/src/bool_and_or.rs b/datafusion/functions-aggregate/src/bool_and_or.rs
index 3b900f1655..5f37def71b 100644
--- a/datafusion/functions-aggregate/src/bool_and_or.rs
+++ b/datafusion/functions-aggregate/src/bool_and_or.rs
@@ -97,9 +97,9 @@ make_udaf_expr_and_func!(
sql_example = r#"```sql
> SELECT bool_and(column_name) FROM table_name;
+----------------------------+
-| bool_and(column_name) |
+| bool_and(column_name) |
+----------------------------+
-| true |
+| true |
+----------------------------+
```"#,
standard_argument(name = "expression", prefix = "The")
@@ -226,9 +226,9 @@ impl Accumulator for BoolAndAccumulator {
sql_example = r#"```sql
> SELECT bool_and(column_name) FROM table_name;
+----------------------------+
-| bool_and(column_name) |
+| bool_and(column_name) |
+----------------------------+
-| true |
+| true |
+----------------------------+
```"#,
standard_argument(name = "expression", prefix = "The")
diff --git a/datafusion/functions-aggregate/src/count.rs b/datafusion/functions-aggregate/src/count.rs
index 1e72d8ac3d..87d3adeca2 100644
--- a/datafusion/functions-aggregate/src/count.rs
+++ b/datafusion/functions-aggregate/src/count.rs
@@ -139,7 +139,7 @@ pub fn count_all_window() -> Expr {
sql_example = r#"```sql
> SELECT count(column_name) FROM table_name;
+-----------------------+
-| count(column_name) |
+| count(column_name) |
+-----------------------+
| 100 |
+-----------------------+
diff --git a/datafusion/functions-aggregate/src/grouping.rs b/datafusion/functions-aggregate/src/grouping.rs
index a170a7e0c9..720a63aab6 100644
--- a/datafusion/functions-aggregate/src/grouping.rs
+++ b/datafusion/functions-aggregate/src/grouping.rs
@@ -44,13 +44,13 @@ make_udaf_expr_and_func!(
> SELECT column_name, GROUPING(column_name) AS group_column
FROM table_name
GROUP BY GROUPING SETS ((column_name), ());
-+-------------+-------------+
++-------------+--------------+
| column_name | group_column |
-+-------------+-------------+
-| value1 | 0 |
-| value2 | 0 |
-| NULL | 1 |
-+-------------+-------------+
++-------------+--------------+
+| value1 | 0 |
+| value2 | 0 |
+| NULL | 1 |
++-------------+--------------+
```"#,
argument(
name = "expression",
diff --git a/datafusion/functions-aggregate/src/median.rs b/datafusion/functions-aggregate/src/median.rs
index fb74da87c7..2a2adfdc98 100644
--- a/datafusion/functions-aggregate/src/median.rs
+++ b/datafusion/functions-aggregate/src/median.rs
@@ -73,7 +73,7 @@ make_udaf_expr_and_func!(
sql_example = r#"```sql
> SELECT median(column_name) FROM table_name;
+----------------------+
-| median(column_name) |
+| median(column_name) |
+----------------------+
| 45.5 |
+----------------------+
diff --git a/datafusion/functions-aggregate/src/min_max.rs b/datafusion/functions-aggregate/src/min_max.rs
index 41643747e8..400956af0e 100644
--- a/datafusion/functions-aggregate/src/min_max.rs
+++ b/datafusion/functions-aggregate/src/min_max.rs
@@ -84,7 +84,7 @@ fn get_min_max_result_type(input_types: &[DataType]) -> Result<Vec<DataType>> {
sql_example = r#"```sql
> SELECT max(column_name) FROM table_name;
+----------------------+
-| max(column_name) |
+| max(column_name) |
+----------------------+
| 150 |
+----------------------+
@@ -456,7 +456,7 @@ impl Accumulator for SlidingMaxAccumulator {
sql_example = r#"```sql
> SELECT min(column_name) FROM table_name;
+----------------------+
-| min(column_name) |
+| min(column_name) |
+----------------------+
| 12 |
+----------------------+
diff --git a/datafusion/functions-aggregate/src/percentile_cont.rs b/datafusion/functions-aggregate/src/percentile_cont.rs
index 3a98900bbb..c026a3d3a5 100644
--- a/datafusion/functions-aggregate/src/percentile_cont.rs
+++ b/datafusion/functions-aggregate/src/percentile_cont.rs
@@ -99,11 +99,11 @@ pub fn percentile_cont(order_by: Sort, percentile: Expr) -> Expr {
syntax_example = "percentile_cont(percentile) WITHIN GROUP (ORDER BY expression)",
sql_example = r#"```sql
> SELECT percentile_cont(0.75) WITHIN GROUP (ORDER BY column_name) FROM table_name;
-+----------------------------------------------------------+
++-----------------------------------------------------------+
| percentile_cont(0.75) WITHIN GROUP (ORDER BY column_name) |
-+----------------------------------------------------------+
-| 45.5 |
-+----------------------------------------------------------+
++-----------------------------------------------------------+
+| 45.5 |
++-----------------------------------------------------------+
```
An alternate syntax is also supported:
diff --git a/datafusion/functions-aggregate/src/regr.rs b/datafusion/functions-aggregate/src/regr.rs
index 3d5bbf1eda..0065f1b876 100644
--- a/datafusion/functions-aggregate/src/regr.rs
+++ b/datafusion/functions-aggregate/src/regr.rs
@@ -170,7 +170,7 @@ create table weekly_performance(week int, productivity_score int) as values (1,6
select * from weekly_performance;
+------+---------------------+
| week | productivity_score |
-| ---- | ------------------- |
++------+---------------------+
| 1 | 60 |
| 2 | 65 |
| 3 | 70 |
@@ -179,12 +179,11 @@ select * from weekly_performance;
+------+---------------------+
SELECT regr_intercept(productivity_score, week) AS intercept FROM weekly_performance;
-+----------+
-|intercept|
-|intercept |
-+----------+
-| 55 |
-+----------+
++-----------+
+| intercept |
++-----------+
+| 55 |
++-----------+
```
"#
)
@@ -206,7 +205,7 @@ create table daily_metrics(day int, user_signups int) as values (1,100), (2,120)
select * from daily_metrics;
+-----+---------------+
| day | user_signups |
-| --- | ------------- |
++-----+---------------+
| 1 | 100 |
| 2 | 120 |
| 3 | NULL |
@@ -250,11 +249,11 @@ select * from weekly_performance;
+-----+--------------+
SELECT regr_r2(user_signups, day) AS r_squared FROM weekly_performance;
-+---------+
-|r_squared|
-+---------+
-| 1.0 |
-+---------+
++-----------+
+| r_squared |
++-----------+
+| 1.0 |
++-----------+
```
"#
)
@@ -276,7 +275,7 @@ create table daily_sales(day int, total_sales int) as values (1,100), (2,150), (
select * from daily_sales;
+-----+-------------+
| day | total_sales |
-| --- | ----------- |
++-----+-------------+
| 1 | 100 |
| 2 | 150 |
| 3 | 200 |
@@ -311,7 +310,7 @@ create table daily_temperature(day int, temperature int) as values (1,30), (2,32
select * from daily_temperature;
+-----+-------------+
| day | temperature |
-| --- | ----------- |
++-----+-------------+
| 1 | 30 |
| 2 | 32 |
| 3 | NULL |
diff --git a/datafusion/functions-aggregate/src/stddev.rs b/datafusion/functions-aggregate/src/stddev.rs
index 15511bf4a5..3485a50629 100644
--- a/datafusion/functions-aggregate/src/stddev.rs
+++ b/datafusion/functions-aggregate/src/stddev.rs
@@ -53,7 +53,7 @@ make_udaf_expr_and_func!(
sql_example = r#"```sql
> SELECT stddev(column_name) FROM table_name;
+----------------------+
-| stddev(column_name) |
+| stddev(column_name) |
+----------------------+
| 12.34 |
+----------------------+
@@ -157,7 +157,7 @@ make_udaf_expr_and_func!(
sql_example = r#"```sql
> SELECT stddev_pop(column_name) FROM table_name;
+--------------------------+
-| stddev_pop(column_name) |
+| stddev_pop(column_name) |
+--------------------------+
| 10.56 |
+--------------------------+
diff --git a/datafusion/functions-aggregate/src/string_agg.rs b/datafusion/functions-aggregate/src/string_agg.rs
index 3fe2b0a186..bfb07183d9 100644
--- a/datafusion/functions-aggregate/src/string_agg.rs
+++ b/datafusion/functions-aggregate/src/string_agg.rs
@@ -74,7 +74,7 @@ This aggregation function can only mix DISTINCT and ORDER BY if the ordering exp
+--------------------------+
| names_list |
+--------------------------+
-| Charlie, Bob, Alice |
+| Charlie, Bob, Alice |
+--------------------------+
```"#,
argument(
diff --git a/datafusion/functions-aggregate/src/sum.rs b/datafusion/functions-aggregate/src/sum.rs
index 20bfe064e5..e2f9f1ec67 100644
--- a/datafusion/functions-aggregate/src/sum.rs
+++ b/datafusion/functions-aggregate/src/sum.rs
@@ -153,7 +153,7 @@ macro_rules! downcast_sum {
sql_example = r#"```sql
> SELECT sum(column_name) FROM table_name;
+-----------------------+
-| sum(column_name) |
+| sum(column_name) |
+-----------------------+
| 12345 |
+-----------------------+
diff --git a/docs/source/user-guide/sql/aggregate_functions.md b/docs/source/user-guide/sql/aggregate_functions.md
index c681ccb28e..4f130d4008 100644
--- a/docs/source/user-guide/sql/aggregate_functions.md
+++ b/docs/source/user-guide/sql/aggregate_functions.md
@@ -153,7 +153,7 @@ array_agg(expression [ORDER BY expression])
+-----------------------------------------------+
> SELECT array_agg(DISTINCT column_name ORDER BY column_name) FROM table_name;
+--------------------------------------------------------+
-| array_agg(DISTINCT column_name ORDER BY column_name) |
+| array_agg(DISTINCT column_name ORDER BY column_name) |
+--------------------------------------------------------+
| [element1, element2, element3] |
+--------------------------------------------------------+
@@ -176,9 +176,9 @@ avg(expression)
```sql
> SELECT avg(column_name) FROM table_name;
+---------------------------+
-| avg(column_name) |
+| avg(column_name) |
+---------------------------+
-| 42.75 |
+| 42.75 |
+---------------------------+
```
@@ -239,9 +239,9 @@ bool_and(expression)
```sql
> SELECT bool_and(column_name) FROM table_name;
+----------------------------+
-| bool_and(column_name) |
+| bool_and(column_name) |
+----------------------------+
-| true |
+| true |
+----------------------------+
```
@@ -262,9 +262,9 @@ bool_and(expression)
```sql
> SELECT bool_and(column_name) FROM table_name;
+----------------------------+
-| bool_and(column_name) |
+| bool_and(column_name) |
+----------------------------+
-| true |
+| true |
+----------------------------+
```
@@ -285,7 +285,7 @@ count(expression)
```sql
> SELECT count(column_name) FROM table_name;
+-----------------------+
-| count(column_name) |
+| count(column_name) |
+-----------------------+
| 100 |
+-----------------------+
@@ -339,13 +339,13 @@ grouping(expression)
> SELECT column_name, GROUPING(column_name) AS group_column
FROM table_name
GROUP BY GROUPING SETS ((column_name), ());
-+-------------+-------------+
++-------------+--------------+
| column_name | group_column |
-+-------------+-------------+
-| value1 | 0 |
-| value2 | 0 |
-| NULL | 1 |
-+-------------+-------------+
++-------------+--------------+
+| value1 | 0 |
+| value2 | 0 |
+| NULL | 1 |
++-------------+--------------+
```
### `last_value`
@@ -388,7 +388,7 @@ max(expression)
```sql
> SELECT max(column_name) FROM table_name;
+----------------------+
-| max(column_name) |
+| max(column_name) |
+----------------------+
| 150 |
+----------------------+
@@ -415,7 +415,7 @@ median(expression)
```sql
> SELECT median(column_name) FROM table_name;
+----------------------+
-| median(column_name) |
+| median(column_name) |
+----------------------+
| 45.5 |
+----------------------+
@@ -438,7 +438,7 @@ min(expression)
```sql
> SELECT min(column_name) FROM table_name;
+----------------------+
-| min(column_name) |
+| min(column_name) |
+----------------------+
| 12 |
+----------------------+
@@ -461,11 +461,11 @@ percentile_cont(percentile) WITHIN GROUP (ORDER BY expression)
```sql
> SELECT percentile_cont(0.75) WITHIN GROUP (ORDER BY column_name) FROM table_name;
-+----------------------------------------------------------+
++-----------------------------------------------------------+
| percentile_cont(0.75) WITHIN GROUP (ORDER BY column_name) |
-+----------------------------------------------------------+
-| 45.5 |
-+----------------------------------------------------------+
++-----------------------------------------------------------+
+| 45.5 |
++-----------------------------------------------------------+
```
An alternate syntax is also supported:
@@ -522,7 +522,7 @@ string_agg([DISTINCT] expression, delimiter [ORDER BY expression])
+--------------------------+
| names_list |
+--------------------------+
-| Charlie, Bob, Alice |
+| Charlie, Bob, Alice |
+--------------------------+
```
@@ -543,7 +543,7 @@ sum(expression)
```sql
> SELECT sum(column_name) FROM table_name;
+-----------------------+
-| sum(column_name) |
+| sum(column_name) |
+-----------------------+
| 12345 |
+-----------------------+
@@ -743,7 +743,7 @@ create table daily_sales(day int, total_sales int) as values (1,100), (2,150), (
select * from daily_sales;
+-----+-------------+
| day | total_sales |
-| --- | ----------- |
++-----+-------------+
| 1 | 100 |
| 2 | 150 |
| 3 | 200 |
@@ -779,7 +779,7 @@ create table daily_temperature(day int, temperature int) as values (1,30), (2,32
select * from daily_temperature;
+-----+-------------+
| day | temperature |
-| --- | ----------- |
++-----+-------------+
| 1 | 30 |
| 2 | 32 |
| 3 | NULL |
@@ -816,7 +816,7 @@ create table daily_metrics(day int, user_signups int) as values (1,100), (2,120)
select * from daily_metrics;
+-----+---------------+
| day | user_signups |
-| --- | ------------- |
++-----+---------------+
| 1 | 100 |
| 2 | 120 |
| 3 | NULL |
@@ -852,7 +852,7 @@ create table weekly_performance(week int, productivity_score int) as values (1,6
select * from weekly_performance;
+------+---------------------+
| week | productivity_score |
-| ---- | ------------------- |
++------+---------------------+
| 1 | 60 |
| 2 | 65 |
| 3 | 70 |
@@ -861,12 +861,11 @@ select * from weekly_performance;
+------+---------------------+
SELECT regr_intercept(productivity_score, week) AS intercept FROM weekly_performance;
-+----------+
-|intercept|
-|intercept |
-+----------+
-| 55 |
-+----------+
++-----------+
+| intercept |
++-----------+
+| 55 |
++-----------+
```
### `regr_r2`
@@ -898,11 +897,11 @@ select * from weekly_performance;
+-----+--------------+
SELECT regr_r2(user_signups, day) AS r_squared FROM weekly_performance;
-+---------+
-|r_squared|
-+---------+
-| 1.0 |
-+---------+
++-----------+
+| r_squared |
++-----------+
+| 1.0 |
++-----------+
```
### `regr_slope`
@@ -1062,7 +1061,7 @@ stddev(expression)
```sql
> SELECT stddev(column_name) FROM table_name;
+----------------------+
-| stddev(column_name) |
+| stddev(column_name) |
+----------------------+
| 12.34 |
+----------------------+
@@ -1089,7 +1088,7 @@ stddev_pop(expression)
```sql
> SELECT stddev_pop(column_name) FROM table_name;
+--------------------------+
-| stddev_pop(column_name) |
+| stddev_pop(column_name) |
+--------------------------+
| 10.56 |
+--------------------------+
@@ -1237,9 +1236,9 @@ An alternative syntax is also supported:
```sql
> SELECT approx_percentile_cont_with_weight(column_name, weight_column, 0.90) FROM table_name;
-+--------------------------------------------------+
++----------------------------------------------------------------------+
| approx_percentile_cont_with_weight(column_name, weight_column, 0.90) |
-+--------------------------------------------------+
-| 78.5 |
-+--------------------------------------------------+
++----------------------------------------------------------------------+
+| 78.5 |
++----------------------------------------------------------------------+
```