Face completion with a multi-output estimators

This example shows the use of multi-output estimator to complete images. The goal is to predict the lower half of a face given its upper half.

The first column of images shows true faces. The next columns illustrate how extremely randomized trees, k nearest neighbors, linear regression and ridge regression complete the lower half of those faces.

Traceback (most recent call last):
  File "/usr/lib/python3/dist-packages/sphinx_gallery/gen_gallery.py", line 159, in call_memory
    return 0., func()
  File "/usr/lib/python3/dist-packages/sphinx_gallery/gen_rst.py", line 466, in __call__
    exec(self.code, self.fake_main.__dict__)
  File "/build/scikit-learn-4qMeVF/scikit-learn-0.23.2/examples/miscellaneous/plot_multioutput_face_completion.py", line 28, in <module>
    data, targets = fetch_olivetti_faces(return_X_y=True)
  File "/build/scikit-learn-4qMeVF/scikit-learn-0.23.2/.pybuild/cpython3_3.8/build/sklearn/utils/validation.py", line 72, in inner_f
    return f(**kwargs)
  File "/build/scikit-learn-4qMeVF/scikit-learn-0.23.2/.pybuild/cpython3_3.8/build/sklearn/datasets/_olivetti_faces.py", line 111, in fetch_olivetti_faces
    mat_path = _fetch_remote(FACES, dirname=data_home)
  File "/build/scikit-learn-4qMeVF/scikit-learn-0.23.2/.pybuild/cpython3_3.8/build/sklearn/datasets/_base.py", line 1181, in _fetch_remote
    urlretrieve(remote.url, file_path)
  File "/usr/lib/python3.8/urllib/request.py", line 247, in urlretrieve
    with contextlib.closing(urlopen(url, data)) as fp:
  File "/usr/lib/python3.8/urllib/request.py", line 222, in urlopen
    return opener.open(url, data, timeout)
  File "/usr/lib/python3.8/urllib/request.py", line 525, in open
    response = self._open(req, data)
  File "/usr/lib/python3.8/urllib/request.py", line 542, in _open
    result = self._call_chain(self.handle_open, protocol, protocol +
  File "/usr/lib/python3.8/urllib/request.py", line 502, in _call_chain
    result = func(*args)
  File "/usr/lib/python3.8/urllib/request.py", line 1393, in https_open
    return self.do_open(http.client.HTTPSConnection, req,
  File "/usr/lib/python3.8/urllib/request.py", line 1353, in do_open
    raise URLError(err)
urllib.error.URLError: <urlopen error [Errno -2] Name or service not known>

print(__doc__)

import numpy as np
import matplotlib.pyplot as plt

from sklearn.datasets import fetch_olivetti_faces
from sklearn.utils.validation import check_random_state

from sklearn.ensemble import ExtraTreesRegressor
from sklearn.neighbors import KNeighborsRegressor
from sklearn.linear_model import LinearRegression
from sklearn.linear_model import RidgeCV

# Load the faces datasets
data, targets = fetch_olivetti_faces(return_X_y=True)

train = data[targets < 30]
test = data[targets >= 30]  # Test on independent people

# Test on a subset of people
n_faces = 5
rng = check_random_state(4)
face_ids = rng.randint(test.shape[0], size=(n_faces, ))
test = test[face_ids, :]

n_pixels = data.shape[1]
# Upper half of the faces
X_train = train[:, :(n_pixels + 1) // 2]
# Lower half of the faces
y_train = train[:, n_pixels // 2:]
X_test = test[:, :(n_pixels + 1) // 2]
y_test = test[:, n_pixels // 2:]

# Fit estimators
ESTIMATORS = {
    "Extra trees": ExtraTreesRegressor(n_estimators=10, max_features=32,
                                       random_state=0),
    "K-nn": KNeighborsRegressor(),
    "Linear regression": LinearRegression(),
    "Ridge": RidgeCV(),
}

y_test_predict = dict()
for name, estimator in ESTIMATORS.items():
    estimator.fit(X_train, y_train)
    y_test_predict[name] = estimator.predict(X_test)

# Plot the completed faces
image_shape = (64, 64)

n_cols = 1 + len(ESTIMATORS)
plt.figure(figsize=(2. * n_cols, 2.26 * n_faces))
plt.suptitle("Face completion with multi-output estimators", size=16)

for i in range(n_faces):
    true_face = np.hstack((X_test[i], y_test[i]))

    if i:
        sub = plt.subplot(n_faces, n_cols, i * n_cols + 1)
    else:
        sub = plt.subplot(n_faces, n_cols, i * n_cols + 1,
                          title="true faces")

    sub.axis("off")
    sub.imshow(true_face.reshape(image_shape),
               cmap=plt.cm.gray,
               interpolation="nearest")

    for j, est in enumerate(sorted(ESTIMATORS)):
        completed_face = np.hstack((X_test[i], y_test_predict[est][i]))

        if i:
            sub = plt.subplot(n_faces, n_cols, i * n_cols + 2 + j)

        else:
            sub = plt.subplot(n_faces, n_cols, i * n_cols + 2 + j,
                              title=est)

        sub.axis("off")
        sub.imshow(completed_face.reshape(image_shape),
                   cmap=plt.cm.gray,
                   interpolation="nearest")

plt.show()

Total running time of the script: ( 0 minutes 0.005 seconds)

Gallery generated by Sphinx-Gallery