Data Splitting#
The lenskit.splitting package implements data splitting support for
evaluation.
Output Types#
|
A train-test set from splitting or other sources. |
Temporal Splitting#
Global temporal train-test split. |
User-Based Splitting#
Partition a dataset user-by-user for user-based cross-validation. |
|
Create train-test splits by sampling users. |
|
Select a fraction of test rows per user/item. |
|
Select a fixed number of test rows per user/item, based on ordering by a field. |
|
Randomly select a fraction of test rows per user/item. |
|
Randomly select a fixed number of test rows per user/item. |
Record-Based Splitting#
Partition a dataset by records into cross-fold partitions. |
|
Create a train-test split of data by randomly sampling individual interactions. |