Single Dataset Performance#
This notebook provides an overview for using and understanding single dataset performance check.
What is the purpose of the check?#
This check is designed for evaluating a model’s performance on a labeled dataset based on a scorer or multiple scorers.
Scorers are a convention of sklearn to evaluate a model, it is a function which accepts (model, X, y_true) and returns a float result which is the score. A sklearn convention is that higher scores are better than lower scores. For additional details see scorers documentation.
The default scorers that are used are F1, Percision, and Recall for Classification and Negative Root Mean Square Error, Negative Mean Absolute Error, and R2 for Regression.
Generate data & model#
Run the check#
You can select which scorers to use by passing either a list or a dict of scorers to the check, the full list of possible scorers can be seen at scorers.py.
Define a condition#
We can define on our check a condition to validate that the different metric scores are above a certain threshold.
class_mode argument we can define select a sub set of the classes to use for the condition.
Let’s add a condition to the check and see what happens when it fails:
We detected that the Recall score is below specified threshold in at least one of the classes.
Using a custom scorer#
In addition to the built-in scorers, we can define our own scorer based on sklearn api and run it using the check alongside other scorers:
Total running time of the script: ( 0 minutes 3.357 seconds)