Skip to content

Added Example for Statistical Functions in Docs #16927

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 17 commits into from
Jul 31, 2025
Merged

Added Example for Statistical Functions in Docs #16927

Show file tree
Hide file tree
Changes from 14 commits
Commits
Show all changes
17 commits
Select commit Hold shift + click to select a range
5888f11
Update aggregate_functions.md
Adez017 Jul 26, 2025
5bf7b6d
Merge branch 'apache:main' into Adez017---updatesblogs
Adez017 Jul 28, 2025
5b778d3
Update aggregate_functions.md
Adez017 Jul 28, 2025
aa28dd1
formating fix
Adez017 Jul 28, 2025
613b594
Update aggregate_functions.md
Adez017 Jul 28, 2025
f886f32
Update docs/source/user-guide/sql/aggregate_functions.md
Adez017 Jul 29, 2025
49a3793
Update docs/source/user-guide/sql/aggregate_functions.md
Adez017 Jul 29, 2025
af66dc9
Update docs/source/user-guide/sql/aggregate_functions.md
Adez017 Jul 29, 2025
8481ef0
Update aggregate_functions.md
Adez017 Jul 29, 2025
461c3c0
Update aggregate_functions.md
Adez017 Jul 29, 2025
77ecc4a
Update aggregate_functions.md
Adez017 Jul 29, 2025
852de4b
Add examples to code
alamb Jul 29, 2025
3f9afdd
Alamb Update
Adez017 Jul 30, 2025
a4cf6a8
Updated docs , build
Adez017 Jul 30, 2025
4c7522d
prettier
alamb Jul 30, 2025
3e94ab4
Merge remote-tracking branch 'apache/main' into Adez017---updatesblogs
alamb Jul 30, 2025
04684d7
Updates + prettier
alamb Jul 30, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
214 changes: 214 additions & 0 deletions datafusion/functions-aggregate/src/regr.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -144,6 +144,30 @@ static DOCUMENTATION: LazyLock<HashMap<RegrType, Documentation>> = LazyLock::new
Given input column Y and X: regr_slope(Y, X) returns the slope (k in Y = k*X + b) using minimal RSS fitting.",

"regr_slope(expression_y, expression_x)")
.with_sql_example(
r#"```sql
create table weekly_performance(day int,user_signups int) as values (1,60), (2,65), (3, 70), (4,75), (5,80);

select * from weekly_performance;
+------+---------------------+
| week | productivity_score |
| ---- | ------------------- |
| 1 | 60 |
| 2 | 65 |
| 3 | 70 |
| 4 | 75 |
| 5 | 80 |
+------+---------------------+

SELECT regr_slope(user_signups, day) AS slope FROM weekly_performance;
+--------+
| slope |
+--------+
| 5.0 |
+--------+
```
"#
)
.with_standard_argument("expression_y", Some("Dependent variable"))
.with_standard_argument("expression_x", Some("Independent variable"))
.build()
Expand All @@ -157,6 +181,31 @@ static DOCUMENTATION: LazyLock<HashMap<RegrType, Documentation>> = LazyLock::new
this function returns b.",

"regr_intercept(expression_y, expression_x)")
.with_sql_example(
r#"```sql
create table weekly_performances(week int, productivity_score int) as values (1,60), (2,65), (3, 70), (4,75), (5,80);
select * from weekly_performances;
+------+---------------------+
| week | productivity_score |
| ---- | ------------------- |
| 1 | 60 |
| 2 | 65 |
| 3 | 70 |
| 4 | 75 |
| 5 | 80 |
+------+---------------------+

SELECT regr_intercept(productivity_score, week) AS intercept
FROM weekly_performance;
+----------+
|intercept|
|intercept |
+----------+
| 55 |
+----------+
```
"#
)
.with_standard_argument("expression_y", Some("Dependent variable"))
.with_standard_argument("expression_x", Some("Independent variable"))
.build()
Expand All @@ -169,6 +218,30 @@ static DOCUMENTATION: LazyLock<HashMap<RegrType, Documentation>> = LazyLock::new
"Counts the number of non-null paired data points.",
"regr_count(expression_y, expression_x)",
)
.with_sql_example(
r#"```sql
create table daily_metrics(day int, user_signups int) as values (1,100), (2,120), (3, NULL), (4,110), (5,NULL);
select * from daily_metrics;
+-----+---------------+
| day | user_signups |
| --- | ------------- |
| 1 | 100 |
| 2 | 120 |
| 3 | NULL |
| 4 | 110 |
| 5 | NULL |
+-----+---------------+

SELECT regr_count(user_signups, day) AS valid_pairs
FROM daily_metrics;
+-------------+
| valid_pairs |
+-------------+
| 3 |
+-------------+
```
"#
)
.with_standard_argument("expression_y", Some("Dependent variable"))
.with_standard_argument("expression_x", Some("Independent variable"))
.build(),
Expand All @@ -181,6 +254,30 @@ static DOCUMENTATION: LazyLock<HashMap<RegrType, Documentation>> = LazyLock::new
"Computes the square of the correlation coefficient between the independent and dependent variables.",

"regr_r2(expression_y, expression_x)")
.with_sql_example(
r#"```sql
create table weekly_performances(day int ,user_signups int) as values (1,60), (2,65), (3, 70), (4,75), (5,80);
select * from weekly_performances;
+------+---------------------+
| week | productivity_score |
| ---- | ------------------- |
| 1 | 60 |
| 2 | 65 |
| 3 | 70 |
| 4 | 75 |
| 5 | 80 |
+------+---------------------+

SELECT regr_r2(productivity_score, week) AS r_squared
FROM weekly_performance;
+---------+
|r_squared|
+---------+
| 1.0 |
+---------+
```
"#
)
.with_standard_argument("expression_y", Some("Dependent variable"))
.with_standard_argument("expression_x", Some("Independent variable"))
.build()
Expand All @@ -193,6 +290,31 @@ static DOCUMENTATION: LazyLock<HashMap<RegrType, Documentation>> = LazyLock::new
"Computes the average of the independent variable (input) expression_x for the non-null paired data points.",

"regr_avgx(expression_y, expression_x)")
.with_sql_example(
r#"```sql
> create table daily_sales(day int, temperature int) as values (1,35), (2,36), (3, NULL), (4,37), (5,38);
> select * from daily_sales;
+-----+-------------+
| day | total_sales |
| --- | ----------- |
| 1 | 100 |
| 2 | 150 |
| 3 | 200 |
| 4 | NULL |
| 5 | 250 |
+-----+-------------+

SELECT regr_avgx(total_sales, day) AS avg_day
FROM daily_sales; --output = (1+2+3+5)/4 = 2.75
+----------+
| avg_day |
+----------+
| 2.75 |
+----------+

```
"#
)
.with_standard_argument("expression_y", Some("Dependent variable"))
.with_standard_argument("expression_x", Some("Independent variable"))
.build()
Expand All @@ -205,6 +327,30 @@ static DOCUMENTATION: LazyLock<HashMap<RegrType, Documentation>> = LazyLock::new
"Computes the average of the dependent variable (output) expression_y for the non-null paired data points.",

"regr_avgy(expression_y, expression_x)")
.with_sql_example(
r#"```sql
create table daily_temperature(day int, temperature int) as values (1,30), (2,32), (3, NULL), (4,35), (5,36);
select * from daily_temperature;
+-----+-------------+
| day | temperature |
| --- | ----------- |
| 1 | 30 |
| 2 | 32 |
| 3 | NULL |
| 4 | 35 |
| 5 | 36 |
+-----+-------------+

SELECT regr_avgy(temperature, day) AS avg_temperature --temperature as Dependent Variable(Y)
FROM daily_temperature;
+-----------------+
| avg_temperature |
+-----------------+
| 33.25 |
+-----------------+
```
"#
)
.with_standard_argument("expression_y", Some("Dependent variable"))
.with_standard_argument("expression_x", Some("Independent variable"))
.build()
Expand All @@ -217,6 +363,30 @@ static DOCUMENTATION: LazyLock<HashMap<RegrType, Documentation>> = LazyLock::new
"Computes the sum of squares of the independent variable.",
"regr_sxx(expression_y, expression_x)",
)
.with_sql_example(
r#"```sql
create table study_hours(int student_id, int hours,int test_score) as values(1,2,55),(2,4,65) , (3,6,75),(4,8,85),(5,10,95);
select * from study_hours;
+-------------+-----------+-----------------+
| student_id | hours (x) | test_score (y) |
| ----------- | --------- | --------------- |
| 1 | 2 | 55 |
| 2 | 4 | 65 |
| 3 | 6 | 75 |
| 4 | 8 | 85 |
| 5 | 10 | 95 |
+-------------+-----------+-----------------+

SELECT regr_sxx(test_score, hours) AS sxx
FROM study_hours; --Output - 40
+-------+
| sxx |
+-------+
| 40 |
+-------+
```
"#
)
.with_standard_argument("expression_y", Some("Dependent variable"))
.with_standard_argument("expression_x", Some("Independent variable"))
.build(),
Expand All @@ -229,6 +399,28 @@ static DOCUMENTATION: LazyLock<HashMap<RegrType, Documentation>> = LazyLock::new
"Computes the sum of squares of the dependent variable.",
"regr_syy(expression_y, expression_x)",
)
.with_sql_example(
r#"```sql
create table employee_productivity(int week,int productivity_score) as values(1,60) , (2,65), (3,70);
select * from employee_productivity;
+-------+---------------------+
| week | Procutivity_score |
+-------+---------------------+
| 1 | 65 |
| 2 | 70 |
| 3 | 75 |
+-------+---------------------+

SELECT regr_syy(productivity_score, week) AS sum_squares_y
FROM employee_productivity;
+---------------+
| sum_squares_y |
+---------------+
| 50.0 |
+---------------+
```
"#
)
.with_standard_argument("expression_y", Some("Dependent variable"))
.with_standard_argument("expression_x", Some("Independent variable"))
.build(),
Expand All @@ -241,6 +433,28 @@ static DOCUMENTATION: LazyLock<HashMap<RegrType, Documentation>> = LazyLock::new
"Computes the sum of products of paired data points.",
"regr_sxy(expression_y, expression_x)",
)
.with_sql_example(
r#"```sql
create table employee_productivity(int week,int productivity_score) as values(1,60) , (2,65), (3,70);
select * from employee_productivity;
+-------+---------------------+
| week | Procutivity_score |
+-------+---------------------+
| 1 | 65 |
| 2 | 70 |
| 3 | 75 |
+-------+---------------------+

SELECT regr_sxy(productivity_score, week) AS sum_product_deviations
FROM employee_productivity;
+------------------------+
| sum_product_deviations |
+------------------------+
| 10.0 |
+------------------------+
```
"#
)
.with_standard_argument("expression_y", Some("Dependent variable"))
.with_standard_argument("expression_x", Some("Independent variable"))
.build(),
Expand Down
Loading
Loading