Introduction to Scikit-learn
Chapter 6: Classification
Making predictions
Once your model has been fitted, you can perform predictions on unseen test data in just one line, with the predict() method of your classifier!
>>> predictions = knn_classifier.predict(x_test)
>>> print(predictions)
[1 0 2 1 1 0 1 2 1 1 2 0 0 0 0 1 2 1 1 2 0 2 0 2 2 2 2 2 0 0]
You can also obtain the probability of predictions across classes, with the predict_proba() method. This is useful if you need multiple predictions per class, or just want to know the classifier’s confidence towards its predictions.
>>> probs = knn_classifier.predict_proba(x_test)
>>> print(probs)
[[0. 1. 0. ]
[1. 0. 0. ]
[0. 0. 1. ]
[0. 1. 0. ]
[0. 1. 0. ]
[1. 0. 0. ]
[0. 1. 0. ]
[0. 0. 1. ]
[0. 0.6 0.4]
[0. 1. 0. ]
[0. 0.2 0.8]
...
[0. 0. 1. ]
[1. 0. 0. ]
[1. 0. 0. ]]
Scikit-learn’s implementation of classifiers is also very good example of OOP polymorphism in action. This is also known as duck typing. Scikit-learn does not care what classifier you use, as long as the classifier implements a .fit() and a .predict() method. As you can see, this makes it very flexible as we can simply swap classifiers without having to change a lot of code!