Python Machine Learning Cookbook - Second Edition

How to do it...

Let's see how to evaluate model accuracy using cross-validation metrics:

1. We will use the classifier just used in the Building a Naive Bayes classifier recipe (load the naive_bayes.py file). We will start with the accuracy measure:

from sklearn import model_selectionnum_validations = 5accuracy = model_selection.cross_val_score(classifier_gaussiannb,        X, y, scoring='accuracy', cv=num_validations)print "Accuracy: " + str(round(100*accuracy.mean(), 2)) + "%"

2. We will use the preceding function to compute precision, recall, and the F1 score as well:

f1 = model_selection.cross_val_score(classifier_gaussiannb, X, y, scoring='f1_weighted', cv=num_validations)print "F1: " + str(round(100*f1.mean(), 2)) + "%"precision = model_selection.cross_val_score(classifier_gaussiannb, ...