ItemTable Schema
This table contains all pairs of items bought together. Typically, the CFilter function outputs this table.
Column | Data Type | Description |
---|---|---|
item1_column | VARCHAR | First item (item1). Column by which table is partitioned. The database handles NULL values in partitioning columns. You need not exclude them with a WHERE clause. |
item2_column | VARCHAR | Second item (item2). |
similarity_column | INTEGER or DOUBLE PRECISION | Similarity score for item1 and item2 (number of times item1_column co-occurs with item2_column). To compute this score, use CFilter (ML Engine) function. |
accumulate_item_column | Any | [Column appears once for each specified accumulate_item_column.] Column to copy to output table. |
This table must be symmetric with respect to item1_column and item2_column. That is, if a row has 'apple' in item1_column and 'bread' in item2_column, then another row must have 'bread' in item1_column and 'apple' in item2_column, and these two rows must have the same value in similarity_column.
UserTable Schema
This table contains the user preference for each item. The function recalculates these preferences, using the preferences of other items and how many times the item was bought with those items.
Column | Data Type | Description |
---|---|---|
item_column | VARCHAR | Name of item that user viewed or bought. Column by which table is partitioned. The database handles NULL values in partitioning columns. You need not exclude them with a WHERE clause. |
user_column | VARCHAR | User identifier. |
preference_column | INTEGER | User preference score for item, which must be greater than 0. |
accumulate_user_column | Any | [Column appears once for each specified accumulate_user_column.] Column to copy to output table. |