Output Table Schema
| Column | Data Type | Description |
|---|---|---|
| iternum | INTEGER | Iteration number. NULL for baseline rmse. |
| rmse | DOUBLE PRECISION | Root mean square error after iteration. |
WeightModelTable Schema
| Column | Data Type | Description |
|---|---|---|
| itemid | INTEGER | Item identifier. |
| weights | VARBYTE(n) | Interpolation weights for item, in compressed binary format. Column size depends on RatingTable size and may be very large. If any cell of this column exceeds 64 KB, you cannot use WeightModelTable with KNNRecommenderPredict function.
|
BiasModelTable Schema
| Column | Data Type | Description | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| label | CHARACTER(1) | One of the following values:
|
||||||||
| id | INTEGER | Item identifier or user identifier. | ||||||||
| value | DOUBLE PRECISION | One of the following values:
|
NearestItemsTable Schema
This table appears only with the NearestItemsTable argument.
| Column | Data Type | Description |
|---|---|---|
| itemi | INTEGER | Item identifier of item i. |
| itemj | INTEGER | Item identifier of item j. |
| sij | DOUBLE PRECISION | Calculated similarity between item i and item j. |