Since the time of writing this post scikit-learn has updated and made my answer obsolete, see the much cleaner solution below
You can write your own scoring function to capture all three pieces of information, however a scoring function for cross validation must only return a single number in scikit-learn
(this is likely for compatibility reasons). Below is an example where each of the scores for each cross validation slice prints to the console, and the returned value is just the sum of the three metrics. If you want to return all these values, you're going to have to make some changes to cross_val_score
(line 1351 of cross_validation.py) and _score
(line 1601 or the same file).
from sklearn.svm import SVC
from sklearn.naive_bayes import GaussianNB
from sklearn.tree import DecisionTreeClassifier
from sklearn.cross_validation import cross_val_score
import time
from sklearn.datasets import load_iris
from sklearn.metrics import accuracy_score, precision_score, recall_score
iris = load_iris()
models = [GaussianNB(), DecisionTreeClassifier(), SVC()]
names = ["Naive Bayes", "Decision Tree", "SVM"]
def getScores(estimator, x, y):
yPred = estimator.predict(x)
return (accuracy_score(y, yPred),
precision_score(y, yPred, pos_label=3, average='macro'),
recall_score(y, yPred, pos_label=3, average='macro'))
def my_scorer(estimator, x, y):
a, p, r = getScores(estimator, x, y)
print a, p, r
return a+p+r
for model, name in zip(models, names):
print name
start = time.time()
m = cross_val_score(model, iris.data, iris.target,scoring=my_scorer, cv=10).mean()
print '
Sum:',m, '
'
print 'time', time.time() - start, '
'
Which gives:
Naive Bayes
0.933333333333 0.944444444444 0.933333333333
0.933333333333 0.944444444444 0.933333333333
1.0 1.0 1.0
0.933333333333 0.944444444444 0.933333333333
0.933333333333 0.944444444444 0.933333333333
0.933333333333 0.944444444444 0.933333333333
0.866666666667 0.904761904762 0.866666666667
1.0 1.0 1.0
1.0 1.0 1.0
1.0 1.0 1.0
Sum: 2.86936507937
time 0.0249638557434
Decision Tree
1.0 1.0 1.0
0.933333333333 0.944444444444 0.933333333333
1.0 1.0 1.0
0.933333333333 0.944444444444 0.933333333333
0.933333333333 0.944444444444 0.933333333333
0.866666666667 0.866666666667 0.866666666667
0.933333333333 0.944444444444 0.933333333333
0.933333333333 0.944444444444 0.933333333333
1.0 1.0 1.0
1.0 1.0 1.0
Sum: 2.86555555556
time 0.0237860679626
SVM
1.0 1.0 1.0
0.933333333333 0.944444444444 0.933333333333
1.0 1.0 1.0
1.0 1.0 1.0
1.0 1.0 1.0
0.933333333333 0.944444444444 0.933333333333
0.933333333333 0.944444444444 0.933333333333
1.0 1.0 1.0
1.0 1.0 1.0
1.0 1.0 1.0
Sum: 2.94333333333
time 0.043044090271
As of scikit-learn 0.19.0 the solution becomes much easier
from sklearn.model_selection import cross_validate
from sklearn.datasets import load_iris
from sklearn.svm import SVC
iris = load_iris()
clf = SVC()
scoring = {'acc': 'accuracy',
'prec_macro': 'precision_macro',
'rec_micro': 'recall_macro'}
scores = cross_validate(clf, iris.data, iris.target, scoring=scoring,
cv=5, return_train_score=True)
print(scores.keys())
print(scores['test_acc'])
Which gives:
['test_acc', 'score_time', 'train_acc', 'fit_time', 'test_rec_micro', 'train_rec_micro', 'train_prec_macro', 'test_prec_macro']
[ 0.96666667 1. 0.96666667 0.96666667 1. ]