def test_load_fake_lfw_people():
lfw_people = load_lfw_people(data_home=SCIKIT_LEARN_DATA,
min_faces_per_person=3)
# The data is croped around the center as a rectangular bounding box
# arounthe the face. Colors are converted to gray levels:
assert_equal(lfw_people.data.shape, (10, 62, 47))
# the target is array of person integer ids
assert_array_equal(lfw_people.target, [2, 0, 1, 0, 2, 0, 2, 1, 1, 2])
# names of the persons can be found using the target_names array
expected_classes = ['Abdelatif Smith', 'Abhati Kepler', 'Onur Lopez']
assert_array_equal(lfw_people.target_names, expected_classes)
# It is possible to ask for the original data without any croping or color
# conversion and not limit on the number of picture per person
lfw_people = load_lfw_people(data_home=SCIKIT_LEARN_DATA,
resize=None, slice_=None, color=True)
assert_equal(lfw_people.data.shape, (17, 250, 250, 3))
# the ids and class names are the same as previously
assert_array_equal(lfw_people.target,
[0, 0, 1, 6, 5, 6, 3, 6, 0, 3, 6, 1, 2, 4, 5, 1, 2])
assert_array_equal(lfw_people.target_names,
['Abdelatif Smith', 'Abhati Kepler', 'Camara Alvaro',
'Chen Dupont', 'John Lee', 'Lin Bauman', 'Onur Lopez'])
def test_load_fake_lfw_people():
lfw_people = load_lfw_people(data_home=SCIKIT_LEARN_DATA,
min_faces_per_person=3)
# The data is croped around the center as a rectangular bounding box
# arounthe the face. Colors are converted to gray levels:
assert_equal(lfw_people.data.shape, (10, 62, 47))
# the target is array of person integer ids
assert_array_equal(lfw_people.target, [2, 0, 1, 0, 2, 0, 2, 1, 1, 2])
# names of the persons can be found using the target_names array
expected_classes = ['Abdelatif Smith', 'Abhati Kepler', 'Onur Lopez']
assert_array_equal(lfw_people.target_names, expected_classes)
# It is possible to ask for the original data without any croping or color
# conversion
lfw_people = load_lfw_people(data_home=SCIKIT_LEARN_DATA,
min_faces_per_person=3,
resize=None,
slice_=None,
color=True)
assert_equal(lfw_people.data.shape, (10, 250, 250, 3))
# the ids and class names are the same as previously
assert_array_equal(lfw_people.target, [2, 0, 1, 0, 2, 0, 2, 1, 1, 2])
assert_array_equal(lfw_people.target_names, expected_classes)
def test_load_lfw_people():
if not os.path.exists(os.path.join(get_data_home(), 'lfw_home')):
# skip this test is the data has not already been previously
# downloaded to avoid having tests rely on the availability of a
# fast internet connection
# to download the data, run the face recognition / verification
# examples or call fetch_lfw_people function from an interactive shell
# for instance
raise SkipTest
lfw_people = load_lfw_people(min_faces_per_person=100)
# only 5 person have more than 100 pictures each in the dataset
top_classes = [
'Colin Powell', 'Donald Rumsfeld', 'George W Bush',
'Gerhard Schroeder', 'Tony Blair'
]
assert_array_equal(lfw_people.target_names, top_classes)
# default slice is a rectangular shape around the face, removing
# most of the background
assert_equal(lfw_people.data.shape, (1140, 62, 47))
# person ids have been shuffled to avoid having the photo ordered by
# alphabetical ordering as in the default tarball layout
assert_equal(lfw_people.target.shape, (1140, ))
assert_array_equal(lfw_people.target[:5], [2, 3, 1, 4, 1])
# it is possible to slice the data in different ways and to resize the
# outpout without changing the width / heigh ratio
lfw_people = load_lfw_people(min_faces_per_person=100,
slice_=(slice(50, 200), slice(50, 200)),
resize=0.1)
assert_equal(lfw_people.data.shape, (1140, 15, 15))
# it is also possible to load the color version of the data, in that
# case the color channels are stored in the last dimension of the data
lfw_people = load_lfw_people(min_faces_per_person=100, color=True)
assert_equal(lfw_people.data.shape, (1140, 62, 47, 3))
def test_load_lfw_people():
if not os.path.exists(os.path.join(get_data_home(), 'lfw_home')):
# skip this test is the data has not already been previously
# downloaded to avoid having tests rely on the availability of a
# fast internet connection
# to download the data, run the face recognition / verification
# examples or call fetch_lfw_people function from an interactive shell
# for instance
raise SkipTest
lfw_people = load_lfw_people(min_faces_per_person=100)
# only 5 person have more than 100 pictures each in the dataset
top_classes = ['Colin Powell', 'Donald Rumsfeld', 'George W Bush',
'Gerhard Schroeder', 'Tony Blair']
assert_array_equal(lfw_people.target_names, top_classes)
# default slice is a rectangular shape around the face, removing
# most of the background
assert_equal(lfw_people.data.shape, (1140, 62, 47))
# person ids have been shuffled to avoid having the photo ordered by
# alphabetical ordering as in the default tarball layout
assert_equal(lfw_people.target.shape, (1140,))
assert_array_equal(lfw_people.target[:5], [2, 3, 1, 4, 1])
# it is possible to slice the data in different ways and to resize the
# outpout without changing the width / heigh ratio
lfw_people = load_lfw_people(min_faces_per_person=100,
slice_=(slice(50, 200), slice(50, 200)),
resize=0.1)
assert_equal(lfw_people.data.shape, (1140, 15, 15))
# it is also possible to load the color version of the data, in that
# case the color channels are stored in the last dimension of the data
lfw_people = load_lfw_people(min_faces_per_person=100, color=True)
assert_equal(lfw_people.data.shape, (1140, 62, 47, 3))
def test_load_fake_lfw_people_too_restrictive():
load_lfw_people(data_home=SCIKIT_LEARN_DATA, min_faces_per_person=100)
def test_load_empty_lfw_people():
lfw_people = load_lfw_people(data_home=SCIKIT_LEARN_EMPTY_DATA)
from scikits.learn.cross_val import StratifiedKFold
from scikits.learn.datasets import load_lfw_people
from scikits.learn.grid_search import GridSearchCV
from scikits.learn.metrics import classification_report
from scikits.learn.metrics import confusion_matrix
from scikits.learn.pca import RandomizedPCA
from scikits.learn.svm import SVC
# Display progress logs on stdout
logging.basicConfig(level=logging.INFO,
format='%(asctime)s %(levelname)s %(message)s')
################################################################################
# Download the data, if not already on disk and load it as numpy arrays
lfw_people = load_lfw_people(min_faces_per_person=70, resize=0.4)
# reshape the data using the traditional (n_samples, n_features) shape
faces = lfw_people.data
n_samples, h, w = faces.shape
X = faces.reshape((n_samples, h * w))
n_features = X.shape[1]
# the label to predict is the id of the person
y = lfw_people.target
target_names = lfw_people.target_names
n_classes = target_names.shape[0]
print "Total dataset size:"
print "n_samples: %d" % n_samples
from scikits.learn.metrics import classification_report
from scikits.learn.metrics import confusion_matrix
from scikits.learn.pca import RandomizedPCA
from scikits.learn.svm import SVC
# Display progress logs on stdout
logging.basicConfig(level=logging.INFO,
format='%(asctime)s %(levelname)s %(message)s')
################################################################################
# Download the data, if not already on disk and load it as numpy arrays
download_if_missing = '--download' in sys.argv
try:
lfw_people = load_lfw_people(min_faces_per_person=70, resize=0.4,
download_if_missing=download_if_missing)
except IOError:
print "This example needs more than 200MB of data not locally available:"
print "re-run this script with '--download' to download it explicitly"
print sys.exit(0)
# reshape the data using the traditional (n_samples, n_features) shape
faces = lfw_people.data
n_samples, h, w = faces.shape
X = faces.reshape((n_samples, h * w))
n_features = X.shape[1]
# the label to predict is the id of the person
y = lfw_people.target
target_names = lfw_people.target_names
def test_load_fake_lfw_people_too_restrictive():
load_lfw_people(data_home=SCIKIT_LEARN_DATA, min_faces_per_person=100)
def test_load_empty_lfw_people():
lfw_people = load_lfw_people(data_home=SCIKIT_LEARN_EMPTY_DATA)
from scikits.learn.datasets import load_lfw_people
from scikits.learn.grid_search import GridSearchCV
from scikits.learn.metrics import classification_report
from scikits.learn.metrics import confusion_matrix
from scikits.learn.pca import RandomizedPCA
from scikits.learn.svm import SVC
# Display progress logs on stdout
logging.basicConfig(level=logging.INFO,
format='%(asctime)s %(levelname)s %(message)s')
################################################################################
# Download the data, if not already on disk and load it as numpy arrays
lfw_people = load_lfw_people(min_faces_per_person=70, resize=0.4)
# reshape the data using the traditional (n_samples, n_features) shape
faces = lfw_people.data
n_samples, h, w = faces.shape
X = faces.reshape((n_samples, h * w))
n_features = X.shape[1]
# the label to predict is the id of the person
y = lfw_people.target
target_names = lfw_people.target_names
n_classes = target_names.shape[0]
print "Total dataset size:"
print "n_samples: %d" % n_samples
