Note
Click here to download the full example code
Pixel importances with a parallel forest of trees¶
This example shows the use of forests of trees to evaluate the impurity-based importance of the pixels in an image classification task (faces). The hotter the pixel, the more important.
The code below also illustrates how the construction and the computation of the predictions can be parallelized within multiple jobs.
Traceback (most recent call last):
File "/build/scikit-learn-0.23.2/examples/ensemble/plot_forest_importances_faces.py", line 25, in <module>
data = fetch_olivetti_faces()
File "/build/scikit-learn-0.23.2/.pybuild/cpython3_3.9/build/sklearn/utils/validation.py", line 72, in inner_f
return f(**kwargs)
File "/build/scikit-learn-0.23.2/.pybuild/cpython3_3.9/build/sklearn/datasets/_olivetti_faces.py", line 111, in fetch_olivetti_faces
mat_path = _fetch_remote(FACES, dirname=data_home)
File "/build/scikit-learn-0.23.2/.pybuild/cpython3_3.9/build/sklearn/datasets/_base.py", line 1181, in _fetch_remote
urlretrieve(remote.url, file_path)
File "/usr/lib/python3.9/urllib/request.py", line 239, in urlretrieve
with contextlib.closing(urlopen(url, data)) as fp:
File "/usr/lib/python3.9/urllib/request.py", line 214, in urlopen
return opener.open(url, data, timeout)
File "/usr/lib/python3.9/urllib/request.py", line 517, in open
response = self._open(req, data)
File "/usr/lib/python3.9/urllib/request.py", line 534, in _open
result = self._call_chain(self.handle_open, protocol, protocol +
File "/usr/lib/python3.9/urllib/request.py", line 494, in _call_chain
result = func(*args)
File "/usr/lib/python3.9/urllib/request.py", line 1389, in https_open
return self.do_open(http.client.HTTPSConnection, req,
File "/usr/lib/python3.9/urllib/request.py", line 1349, in do_open
raise URLError(err)
urllib.error.URLError: <urlopen error [Errno -2] Name or service not known>
print(__doc__)
from time import time
import matplotlib.pyplot as plt
from sklearn.datasets import fetch_olivetti_faces
from sklearn.ensemble import ExtraTreesClassifier
# Number of cores to use to perform parallel fitting of the forest model
n_jobs = 1
# Load the faces dataset
data = fetch_olivetti_faces()
X, y = data.data, data.target
mask = y < 5 # Limit to 5 classes
X = X[mask]
y = y[mask]
# Build a forest and compute the pixel importances
print("Fitting ExtraTreesClassifier on faces data with %d cores..." % n_jobs)
t0 = time()
forest = ExtraTreesClassifier(n_estimators=1000,
max_features=128,
n_jobs=n_jobs,
random_state=0)
forest.fit(X, y)
print("done in %0.3fs" % (time() - t0))
importances = forest.feature_importances_
importances = importances.reshape(data.images[0].shape)
# Plot pixel importances
plt.matshow(importances, cmap=plt.cm.hot)
plt.title("Pixel importances with forests of trees")
plt.show()
Total running time of the script: ( 0 minutes 0.004 seconds)