The KNN function has two input tables, a training table and a test table.
The following table describes the required training table column. The training table can have additional columns, but the function ignores them.
| Column Name | Data Type | Description |
|---|---|---|
| id_column | Any | Contains unique row identifiers. |
| df_column | INTEGER, BIGINT, SMALLINT, or NUMERIC | Column that the function uses to compute the distance between a test object and the training objects. The testing table must have a column with the same name and data type. |
| response_column | VARCHAR | Column that contains the class label or classification of the classified data objects. |
The following table describes the required test table column. The test table can have additional columns, but the function ignores them.
| Column Name | Data Type | Description |
|---|---|---|
| df_column | INTEGER, BIGINT, SMALLINT, or NUMERIC | Column that the function uses to compute the distance between a test object and the training objects. The training table must have a column with the same name and data type. |
| test_id_column | Any | Contains unique test data object identifiers. |