GROUP BY Clause

Description

The GROUP BY clause is used to group the rows based on a set of specified grouping expressions and compute aggregations on the group of rows based on one or more specified aggregate functions. Spark also supports advanced aggregations to do multiple aggregations for the same input record set via GROUPING SETS, CUBE, ROLLUP clauses. When a FILTER clause is attached to an aggregate function, only the matching rows are passed to that function.

Syntax

GROUP BY group_expression [ , group_expression [ , ... ] ]
    [ { WITH ROLLUP | WITH CUBE | GROUPING SETS (grouping_set [ , ...]) } ]

GROUP BY GROUPING SETS (grouping_set [ , ...])

While aggregate functions are defined as

aggregate_name ( [ DISTINCT ] expression [ , ... ] ) [ FILTER ( WHERE boolean_expression ) ]

Parameters

Examples

CREATE TABLE dealer (id INT, city STRING, car_model STRING, quantity INT);
INSERT INTO dealer VALUES
    (100, 'Fremont', 'Honda Civic', 10),
    (100, 'Fremont', 'Honda Accord', 15),
    (100, 'Fremont', 'Honda CRV', 7),
    (200, 'Dublin', 'Honda Civic', 20),
    (200, 'Dublin', 'Honda Accord', 10),
    (200, 'Dublin', 'Honda CRV', 3),
    (300, 'San Jose', 'Honda Civic', 5),
    (300, 'San Jose', 'Honda Accord', 8);

-- Sum of quantity per dealership. Group by `id`.
SELECT id, sum(quantity) FROM dealer GROUP BY id ORDER BY id;
+---+-------------+
| id|sum(quantity)|
+---+-------------+
|100|           32|
|200|           33|
|300|           13|
+---+-------------+

-- Use column position in GROUP by clause.
SELECT id, sum(quantity) FROM dealer GROUP BY 1 ORDER BY 1;
+---+-------------+
| id|sum(quantity)|
+---+-------------+
|100|           32|
|200|           33|
|300|           13|
+---+-------------+

-- Multiple aggregations.
-- 1. Sum of quantity per dealership.
-- 2. Max quantity per dealership.
SELECT id, sum(quantity) AS sum, max(quantity) AS max FROM dealer GROUP BY id ORDER BY id;
+---+---+---+
| id|sum|max|
+---+---+---+
|100| 32| 15|
|200| 33| 20|
|300| 13|  8|
+---+---+---+

-- Count the number of distinct dealer cities per car_model.
SELECT car_model, count(DISTINCT city) AS count FROM dealer GROUP BY car_model;
+------------+-----+
|   car_model|count|
+------------+-----+
| Honda Civic|    3|
|   Honda CRV|    2|
|Honda Accord|    3|
+------------+-----+

-- Sum of only 'Honda Civic' and 'Honda CRV' quantities per dealership.
SELECT id, sum(quantity) FILTER (
            WHERE car_model IN ('Honda Civic', 'Honda CRV')
        ) AS `sum(quantity)` FROM dealer
    GROUP BY id ORDER BY id;
+---+-------------+
| id|sum(quantity)|
+---+-------------+
|100|           17|
|200|           23|
|300|            5|
+---+-------------+

-- Aggregations using multiple sets of grouping columns in a single statement.
-- Following performs aggregations based on four sets of grouping columns.
-- 1. city, car_model
-- 2. city
-- 3. car_model
-- 4. Empty grouping set. Returns quantities for all city and car models.
SELECT city, car_model, sum(quantity) AS sum FROM dealer
    GROUP BY GROUPING SETS ((city, car_model), (city), (car_model), ())
    ORDER BY city;
+---------+------------+---+
|     city|   car_model|sum|
+---------+------------+---+
|     null|        null| 78|
|     null| HondaAccord| 33|
|     null|    HondaCRV| 10|
|     null|  HondaCivic| 35|
|   Dublin|        null| 33|
|   Dublin| HondaAccord| 10|
|   Dublin|    HondaCRV|  3|
|   Dublin|  HondaCivic| 20|
|  Fremont|        null| 32|
|  Fremont| HondaAccord| 15|
|  Fremont|    HondaCRV|  7|
|  Fremont|  HondaCivic| 10|
| San Jose|        null| 13|
| San Jose| HondaAccord|  8|
| San Jose|  HondaCivic|  5|
+---------+------------+---+

-- Alternate syntax for `GROUPING SETS` in which both `GROUP BY` and `GROUPING SETS`
-- specifications are present.
SELECT city, car_model, sum(quantity) AS sum FROM dealer
    GROUP BY city, car_model GROUPING SETS ((city, car_model), (city), (car_model), ())
    ORDER BY city, car_model;
+---------+------------+---+
|     city|   car_model|sum|
+---------+------------+---+
|     null|        null| 78|
|     null| HondaAccord| 33|
|     null|    HondaCRV| 10|
|     null|  HondaCivic| 35|
|   Dublin|        null| 33|
|   Dublin| HondaAccord| 10|
|   Dublin|    HondaCRV|  3|
|   Dublin|  HondaCivic| 20|
|  Fremont|        null| 32|
|  Fremont| HondaAccord| 15|
|  Fremont|    HondaCRV|  7|
|  Fremont|  HondaCivic| 10|
| San Jose|        null| 13|
| San Jose| HondaAccord|  8|
| San Jose|  HondaCivic|  5|
+---------+------------+---+

-- Group by processing with `ROLLUP` clause.
-- Equivalent GROUP BY GROUPING SETS ((city, car_model), (city), ())
SELECT city, car_model, sum(quantity) AS sum FROM dealer
    GROUP BY city, car_model WITH ROLLUP
    ORDER BY city, car_model;
+---------+------------+---+
|     city|   car_model|sum|
+---------+------------+---+
|     null|        null| 78|
|   Dublin|        null| 33|
|   Dublin| HondaAccord| 10|
|   Dublin|    HondaCRV|  3|
|   Dublin|  HondaCivic| 20|
|  Fremont|        null| 32|
|  Fremont| HondaAccord| 15|
|  Fremont|    HondaCRV|  7|
|  Fremont|  HondaCivic| 10|
| San Jose|        null| 13|
| San Jose| HondaAccord|  8|
| San Jose|  HondaCivic|  5|
+---------+------------+---+

-- Group by processing with `CUBE` clause.
-- Equivalent GROUP BY GROUPING SETS ((city, car_model), (city), (car_model), ())
SELECT city, car_model, sum(quantity) AS sum FROM dealer
    GROUP BY city, car_model WITH CUBE
    ORDER BY city, car_model;
+---------+------------+---+
|     city|   car_model|sum|
+---------+------------+---+
|     null|        null| 78|
|     null| HondaAccord| 33|
|     null|    HondaCRV| 10|
|     null|  HondaCivic| 35|
|   Dublin|        null| 33|
|   Dublin| HondaAccord| 10|
|   Dublin|    HondaCRV|  3|
|   Dublin|  HondaCivic| 20|
|  Fremont|        null| 32|
|  Fremont| HondaAccord| 15|
|  Fremont|    HondaCRV|  7|
|  Fremont|  HondaCivic| 10|
| San Jose|        null| 13|
| San Jose| HondaAccord|  8|
| San Jose|  HondaCivic|  5|
+---------+------------+---+

--Prepare data for ignore nulls example
CREATE TABLE person (id INT, name STRING, age INT);
INSERT INTO person VALUES
    (100, 'Mary', NULL),
    (200, 'John', 30),
    (300, 'Mike', 80),
    (400, 'Dan', 50);

--Select the first row in cloumn age
SELECT FIRST(age) FROM person;
+--------------------+
| first(age, false)  |
+--------------------+
| NULL               |
+--------------------+

--Get the first row in cloumn `age` ignore nulls,last row in column `id` and sum of cloumn `id`.
SELECT FIRST(age IGNORE NULLS), LAST(id), SUM(id) FROM person;
+-------------------+------------------+----------+
| first(age, true)  | last(id, false)  | sum(id)  |
+-------------------+------------------+----------+
| 30                | 400              | 1000     |
+-------------------+------------------+----------+