56 lines
1.8 KiB
Python
56 lines
1.8 KiB
Python
"""
|
|
=========================================
|
|
Feature importances with forests of trees
|
|
=========================================
|
|
|
|
This examples shows the use of forests of trees to evaluate the importance of
|
|
features on an artifical classification task. The red bars are the feature
|
|
importances of the forest, along with their inter-trees variability.
|
|
|
|
As expected, the plot suggests that 3 features are informative, while the
|
|
remaining are not.
|
|
"""
|
|
print __doc__
|
|
|
|
import numpy as np
|
|
|
|
from sklearn.datasets import make_classification
|
|
from sklearn.ensemble import ExtraTreesClassifier
|
|
|
|
# Build a classification task using 3 informative features
|
|
X, y = make_classification(n_samples=1000,
|
|
n_features=10,
|
|
n_informative=3,
|
|
n_redundant=0,
|
|
n_repeated=0,
|
|
n_classes=2,
|
|
random_state=0,
|
|
shuffle=False)
|
|
|
|
# Build a forest and compute the feature importances
|
|
forest = ExtraTreesClassifier(n_estimators=250,
|
|
compute_importances=True,
|
|
random_state=0)
|
|
|
|
forest.fit(X, y)
|
|
importances = forest.feature_importances_
|
|
std = np.std([tree.feature_importances_ for tree in forest.estimators_],
|
|
axis=0)
|
|
indices = np.argsort(importances)[::-1]
|
|
|
|
# Print the feature ranking
|
|
print "Feature ranking:"
|
|
|
|
for f in xrange(10):
|
|
print "%d. feature %d (%f)" % (f + 1, indices[f], importances[indices[f]])
|
|
|
|
# Plot the feature importances of the forest
|
|
import pylab as pl
|
|
pl.figure()
|
|
pl.title("Feature importances")
|
|
pl.bar(xrange(10), importances[indices],
|
|
color="r", yerr=std[indices], align="center")
|
|
pl.xticks(xrange(10), indices)
|
|
pl.xlim([-1, 10])
|
|
pl.show()
|