Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- Feature: Symbolic regression scoring against x+6 dataset
- In order to evaluate how well a Pile script models a given dataset
- As a symbolic regression modeler
- I want the score of a given script against a dataset to be the RSS value
- Scenario: score for a perfect program should be 0.0
- Given the Pile script "x 6.0 +"
- And the training data is "x_plus_6.csv"
- When I score the script
- Then the score should be 0.0
- Scenario: score is summed squared errors
- Given the Pile script "x 8.0 +"
- And the training data is "x_plus_6.csv"
- When I score the script
- Then the score should be 36.0
- Scenario: missing return value is important
- Given the Pile script "foo bar"
- And the training data is "x_plus_6.csv"
- When I score the script
- Then the score should be close to 10^18
Add Comment
Please, Sign In to add comment