diff --git a/doc/conf.py b/doc/conf.py
index 13767f4afaa7933fc68b87a2a16d14ffd3a78537..ceb2f7adc16fe71729c75f4d4eafe4164a56e665 100644
--- a/doc/conf.py
+++ b/doc/conf.py
@@ -22,7 +22,7 @@ sys.path.insert(0, os.path.abspath('sphinxext'))
# Add any Sphinx extension module names here, as strings. They can be extensions
# coming with Sphinx (named 'sphinx.ext.*') or your custom ones.
-extensions = ['sphinx.ext.autodoc', 'sphinx.ext.autosummary',
+extensions = ['sphinx.ext.autodoc', 'sphinx.ext.autosummary',
'sphinx.ext.pngmath',
'gen_rst']
try:
diff --git a/doc/sphinxext/gen_rst.py b/doc/sphinxext/gen_rst.py
index 3deadb9a2b637152a4a73bb52e207c79629cb480..b575bf8d878c762d2cf236dabb86244c6afde8f8 100644
--- a/doc/sphinxext/gen_rst.py
+++ b/doc/sphinxext/gen_rst.py
@@ -16,7 +16,7 @@ fileList = []
import matplotlib
matplotlib.use('Agg')
-import token, tokenize
+import token, tokenize
rst_template = """
@@ -59,14 +59,14 @@ def extract_docstring(filename):
first_par = ''
tokens = tokenize.generate_tokens(lines.__iter__().next)
for tok_type, tok_content, _, (erow, _), _ in tokens:
- tok_type = token.tok_name[tok_type]
+ tok_type = token.tok_name[tok_type]
if tok_type in ('NEWLINE', 'COMMENT', 'NL', 'INDENT', 'DEDENT'):
continue
elif tok_type == 'STRING':
docstring = eval(tok_content)
# If the docstring is formatted with several paragraphs, extract
# the first one:
- paragraphs = '\n'.join(line.rstrip()
+ paragraphs = '\n'.join(line.rstrip()
for line in docstring.split('\n')).split('\n\n')
if len(paragraphs) > 0:
first_par = paragraphs[0]
@@ -77,7 +77,7 @@ def extract_docstring(filename):
def generate_example_rst(app):
""" Generate the list of examples, as well as the contents of
examples.
- """
+ """
root_dir = os.path.join(app.builder.srcdir, 'auto_examples')
example_dir = os.path.abspath(app.builder.srcdir + '/../' + 'examples')
if not os.path.exists(example_dir):
@@ -114,7 +114,7 @@ def generate_dir_rst(dir, fhindex, example_dir, root_dir):
target_dir = os.path.join(root_dir, dir)
src_dir = os.path.join(example_dir, dir)
if not os.path.exists(os.path.join(src_dir, 'README.txt')):
- raise IOError('Example directory %s does not have a README.txt file'
+ raise IOError('Example directory %s does not have a README.txt file'
% src_dir)
fhindex.write("""
@@ -126,7 +126,7 @@ def generate_dir_rst(dir, fhindex, example_dir, root_dir):
if not os.path.exists(target_dir):
os.makedirs(target_dir)
for fname in sorted(os.listdir(src_dir)):
- if fname.endswith('py'):
+ if fname.endswith('py'):
generate_file_rst(fname, target_dir, src_dir)
fhindex.write(' %s\n' % (os.path.join(dir, fname[:-3])))
@@ -154,7 +154,7 @@ def generate_file_rst(fname, target_dir, src_dir):
os.makedirs(os.path.join(target_dir, 'images'))
image_file = os.path.join(target_dir, 'images', image_name)
if (not os.path.exists(image_file) or
- os.stat(image_file).st_mtime <=
+ os.stat(image_file).st_mtime <=
os.stat(src_file).st_mtime):
print 'plotting %s' % fname
import matplotlib.pyplot as plt
diff --git a/doc/sphinxext/numpy_ext_old/docscrape.py b/doc/sphinxext/numpy_ext_old/docscrape.py
index 904270a52a1aa88ee895bf3e8bcf3d53da06d510..a4b7c21bc88280f43252a5cf286f3ce7da77d920 100644
--- a/doc/sphinxext/numpy_ext_old/docscrape.py
+++ b/doc/sphinxext/numpy_ext_old/docscrape.py
@@ -183,7 +183,7 @@ class NumpyDocString(object):
return params
-
+
_name_rgx = re.compile(r"^\s*(:(?P<role>\w+):`(?P<name>[a-zA-Z0-9_.-]+)`|"
r" (?P<name2>[a-zA-Z0-9_.-]+))\s*", re.X)
def _parse_see_also(self, content):
@@ -216,7 +216,7 @@ class NumpyDocString(object):
current_func = None
rest = []
-
+
for line in content:
if not line.strip(): continue
@@ -258,7 +258,7 @@ class NumpyDocString(object):
if len(line) > 2:
out[line[1]] = strip_each_in(line[2].split(','))
return out
-
+
def _parse_summary(self):
"""Grab signature (if given) and summary"""
if self._is_at_section():
@@ -275,7 +275,7 @@ class NumpyDocString(object):
if not self._is_at_section():
self['Extended Summary'] = self._read_to_next_section()
-
+
def _parse(self):
self._doc.reset()
self._parse_summary()
@@ -438,7 +438,7 @@ class FunctionDoc(NumpyDocString):
else:
func = self._f
return func, func_name
-
+
def __str__(self):
out = ''
diff --git a/doc/sphinxext/numpy_ext_old/numpydoc.py b/doc/sphinxext/numpy_ext_old/numpydoc.py
index 2ea41fbb7a282b8d199fa1254cbc757a49cdfb18..5e979ea9c837edb8ab6ce4380fabb91a1ce71c41 100644
--- a/doc/sphinxext/numpy_ext_old/numpydoc.py
+++ b/doc/sphinxext/numpy_ext_old/numpydoc.py
@@ -83,7 +83,7 @@ def initialize(app):
def setup(app, get_doc_object_=get_doc_object):
global get_doc_object
get_doc_object = get_doc_object_
-
+
app.connect('autodoc-process-docstring', mangle_docstrings)
app.connect('builder-inited', initialize)
app.add_config_value('numpydoc_edit_link', None, True)
diff --git a/examples/cluster/plot_segmentation_toy.py b/examples/cluster/plot_segmentation_toy.py
index 26eefccd73b5173965e2544e3d37b69ece8e6947..20f98ef79d617c6a31a3da3fd59e9c13fa8e99ea 100644
--- a/examples/cluster/plot_segmentation_toy.py
+++ b/examples/cluster/plot_segmentation_toy.py
@@ -4,12 +4,12 @@ Spectral clustering for image segmentation
===========================================
In this example, an image with connected circles is generated and
-spectral clustering is used to separate the circles.
+spectral clustering is used to separate the circles.
In these settings, the spectral clustering approach solves the problem
know as 'normalized graph cuts': the image is seen as a graph of
connected voxels, and the spectral clustering algorithm amounts to
-choosing graph cuts defining regions while minimizing the ratio of the
+choosing graph cuts defining regions while minimizing the ratio of the
gradient along the cut, and the volume of the region.
As the algorithm tries to balance the volume (ie balance the region
diff --git a/examples/feature_selection_pipeline.py b/examples/feature_selection_pipeline.py
index 8daf0b82c4f25f81fb072180d68e9390c340cda7..46aeedd174b615353c79a63800fc9b1ff6284de2 100644
--- a/examples/feature_selection_pipeline.py
+++ b/examples/feature_selection_pipeline.py
@@ -17,7 +17,7 @@ from scikits.learn.pipeline import Pipeline
X, y = samples_generator.test_dataset_classif(k=5)
# ANOVA SVM-C
-# 1) anova filter, take 5 best ranked features
+# 1) anova filter, take 5 best ranked features
anova_filter = SelectKBest(f_regression, k=5)
# 2) svm
clf = svm.SVC(kernel='linear')
diff --git a/examples/gmm/plot_gmm_classifier.py b/examples/gmm/plot_gmm_classifier.py
index cab5894faac771504dc3a13b2c6caf9a23bb851f..edf7d12e2d587b123fafc9f2fb3f8b8a3463e79c 100644
--- a/examples/gmm/plot_gmm_classifier.py
+++ b/examples/gmm/plot_gmm_classifier.py
@@ -15,7 +15,7 @@ overfitting on small datasets and does not generalize well to held out
test data.
On the plots, train data is shown as dots, while test data is shown as
-crosses. The iris dataset is four-dimensional. Only the first two
+crosses. The iris dataset is four-dimensional. Only the first two
dimensions are shown here, and thus some points are separated in other
dimensions.
"""
@@ -88,7 +88,7 @@ for index, (name, classifier) in enumerate(classifiers.iteritems()):
for n, color in enumerate('rgb'):
data = iris.data[iris.target == n]
- pl.scatter(data[:,0], data[:, 1], 0.8, color=color,
+ pl.scatter(data[:,0], data[:, 1], 0.8, color=color,
label=iris.target_names[n])
# Plot the test data with crosses
for n, color in enumerate('rgb'):
@@ -110,6 +110,6 @@ for index, (name, classifier) in enumerate(classifiers.iteritems()):
pl.title(name)
pl.legend(loc='lower right', prop=dict(size=12))
-
+
pl.show()
diff --git a/examples/gmm/plot_gmm_pdf.py b/examples/gmm/plot_gmm_pdf.py
index 8ef4ea041dc320de12796714b6e3e22a36ccadb8..cec1ec0df75022e4ab551b76c84c1c30d0de0d28 100644
--- a/examples/gmm/plot_gmm_pdf.py
+++ b/examples/gmm/plot_gmm_pdf.py
@@ -23,8 +23,8 @@ X_train = np.r_[np.dot(np.random.randn(n_samples, 2), C),
clf = gmm.GMM(n_states=2, cvtype='full')
clf.fit(X_train)
-x = np.linspace(-20.0, 30.0)
-y = np.linspace(-20.0, 40.0)
+x = np.linspace(-20.0, 30.0)
+y = np.linspace(-20.0, 40.0)
X, Y = np.meshgrid(x, y)
XX = np.c_[X.ravel(), Y.ravel()]
Z = np.log(-clf.eval(XX)[0])
diff --git a/examples/mlcomp_sparse_document_classification.py b/examples/mlcomp_sparse_document_classification.py
index b10570bdf88350386c694e225c2280a5b5c8f369..4413eded26b6005e4838659cebc67105e0ada62d 100644
--- a/examples/mlcomp_sparse_document_classification.py
+++ b/examples/mlcomp_sparse_document_classification.py
@@ -19,7 +19,7 @@ Once downloaded unzip the arhive somewhere on your filesystem. For instance in::
% unzip /path/to/dataset-379-20news-18828_XXXXX.zip
You should get a folder ``~/data/mlcomp/379`` with a file named ``metadata`` and
-subfolders ``raw``, ``train`` and ``test`` holding the text documents organized
+subfolders ``raw``, ``train`` and ``test`` holding the text documents organized
by newsgroups.
Then set the ``MLCOMP_DATASETS_HOME`` environment variable pointing to
diff --git a/examples/plot_classification_probability.py b/examples/plot_classification_probability.py
index 96881661539fbe5ad30dec4b9865341f523493f7..fffac1ff79f752c652aa31c4a53acac0c87e6772 100644
--- a/examples/plot_classification_probability.py
+++ b/examples/plot_classification_probability.py
@@ -62,12 +62,12 @@ for index, (name, classifier) in enumerate(classifiers.iteritems()):
pl.title("Class %d" % k)
if k == 0:
pl.ylabel(name)
- imshow_handle = pl.imshow(probas[:, k].reshape((100, 100)),
+ imshow_handle = pl.imshow(probas[:, k].reshape((100, 100)),
extent=(3, 9, 1, 5), origin='lower')
pl.xticks(())
pl.yticks(())
idx = (y_pred == k)
- if idx.any():
+ if idx.any():
pl.scatter(X[idx, 0], X[idx, 1], marker='o', c='k')
ax = pl.axes([0.15, 0.04, 0.7, 0.05])
diff --git a/examples/plot_lda_qda.py b/examples/plot_lda_qda.py
index a054b391818f27611988a83e45168a33aaf319a3..9e035bb3abf19a8625e23ddf9aaa2827fa3edec2 100644
--- a/examples/plot_lda_qda.py
+++ b/examples/plot_lda_qda.py
@@ -68,7 +68,7 @@ def plot_data(lda, X, y, y_pred, fig_index):
xmin, xmax = X[:, 0].min(), X[:, 0].max()
ymin, ymax = X[:, 1].min(), X[:, 1].max()
- # class 0: dots
+ # class 0: dots
pl.plot(X0_tp[:, 0], X0_tp[:, 1], 'o', color='red')
pl.plot(X0_fp[:, 0], X0_fp[:, 1], '.', color='#990000') # dark red
diff --git a/examples/sgd/plot_loss_functions.py b/examples/sgd/plot_loss_functions.py
index 3cdd603434f7eb3c85e78844197ec3d261c812ee..814fa84217e4752c735f3a03aa5727d2ad868aa7 100644
--- a/examples/sgd/plot_loss_functions.py
+++ b/examples/sgd/plot_loss_functions.py
@@ -3,7 +3,7 @@
SGD: Convex Loss Functions
==========================
-Plot the convex loss functions supported by `scikits.learn.sgd`.
+Plot the convex loss functions supported by `scikits.learn.sgd`.
"""
print __doc__
diff --git a/examples/sgd/plot_separating_hyperplane.py b/examples/sgd/plot_separating_hyperplane.py
index 0c540d4b56bfd2d9a0e7de5947139dcacab889af..56d0dd2cdc396753b064e7e502d22cd2b89c122b 100644
--- a/examples/sgd/plot_separating_hyperplane.py
+++ b/examples/sgd/plot_separating_hyperplane.py
@@ -9,7 +9,7 @@ trained using SGD.
NOTE: Due to the decreased learning rate of the intercept
the hyperplane is forced to run through the origin, thus,
-the plotted HP is not the max margin HP.
+the plotted HP is not the max margin HP.
"""
print __doc__
diff --git a/examples/svm/plot_custom_kernel.py b/examples/svm/plot_custom_kernel.py
index 872d7e32e91f680685096c8b31daf3accfe85746..a33670f58198071b2bc9524e35532df6dfbe7990 100644
--- a/examples/svm/plot_custom_kernel.py
+++ b/examples/svm/plot_custom_kernel.py
@@ -30,11 +30,11 @@ def my_kernel(x, y):
"""
M = np.array([[2, 0], [0, 1.0]])
return np.dot(np.dot(x, M), y.T)
-
+
h=.02 # step size in the mesh
-# we create an instance of SVM and fit out data.
+# we create an instance of SVM and fit out data.
clf = svm.SVC(kernel=my_kernel)
clf.fit(X, Y)
diff --git a/scikits/learn/__init__.py b/scikits/learn/__init__.py
index 34ff317e212c9cd9b82f551aff806c53b04664d8..cd4b9d65b9782911942108ec9335b3014870485c 100644
--- a/scikits/learn/__init__.py
+++ b/scikits/learn/__init__.py
@@ -32,19 +32,19 @@ try:
class NoseTester(nosetester.NoseTester):
""" Subclass numpy's NoseTester to add doctests by default
"""
- def test(self, label='fast', verbose=1, extra_argv=['--exe'],
+ def test(self, label='fast', verbose=1, extra_argv=['--exe'],
doctests=True, coverage=False):
return super(NoseTester, self).test(label=label, verbose=verbose,
extra_argv=extra_argv,
doctests=doctests, coverage=coverage)
-
+
test = NoseTester().test
del nosetester
except:
pass
__all__ = ['cross_val', 'ball_tree', 'cluster', 'covariance', 'datasets', 'gmm', 'glm',
- 'logistic', 'lda', 'metrics', 'svm', 'features', 'clone',
+ 'logistic', 'lda', 'metrics', 'svm', 'features', 'clone',
'test', 'sgd']
__version__ = '0.6.git'
diff --git a/scikits/learn/base.py b/scikits/learn/base.py
index 58db218cf48e917d64ad48a388ae92a81ade86fe..bf2219f75427cd23d8e5826a9545e45286d52000 100644
--- a/scikits/learn/base.py
+++ b/scikits/learn/base.py
@@ -46,7 +46,7 @@ def clone(estimator, safe=True):
for name, param in new_object_params.iteritems():
new_object_params[name] = clone(param, safe=False)
new_object = klass(**new_object_params)
-
+
return new_object
@@ -69,7 +69,7 @@ def _pprint(params, offset=0, printer=repr):
np.set_printoptions(precision=5, threshold=64, edgeitems=2)
params_list = list()
this_line_length = offset
- line_sep = ',\n' + (1+offset/2)*' '
+ line_sep = ',\n' + (1 + offset / 2) * ' '
for i, (k, v) in enumerate(params.iteritems()):
if type(v) is float:
# use str for representing floating point numbers
@@ -79,7 +79,7 @@ def _pprint(params, offset=0, printer=repr):
else:
# use repr of the rest
this_repr = '%s=%s' % (k, printer(v))
- if i > 0:
+ if i > 0:
if (this_line_length + len(this_repr) >= 75
or '\n' in this_repr):
params_list.append(line_sep)
@@ -94,7 +94,7 @@ def _pprint(params, offset=0, printer=repr):
lines = ''.join(params_list)
# Strip trailing space to avoid nightmare in doctests
lines = '\n'.join(l.rstrip(' ') for l in lines.split('\n'))
- return lines
+ return lines
################################################################################
@@ -109,7 +109,7 @@ class BaseEstimator(object):
"""
- @classmethod
+ @classmethod
def _get_param_names(cls):
""" Get parameter names for the estimator
"""
@@ -156,7 +156,7 @@ class BaseEstimator(object):
"""
if not params:
# Simple optimisation to gain speed (inspect is slow)
- return
+ return
valid_params = self._get_params(deep=True)
for key, value in params.iteritems():
split = key.split('__', 1)
@@ -263,6 +263,6 @@ def _get_sub_estimator(estimator):
def is_classifier(estimator):
""" Returns True if the given estimator is (probably) a classifier.
"""
- estimator = _get_sub_estimator(estimator)
+ estimator = _get_sub_estimator(estimator)
return isinstance(estimator, ClassifierMixin)
diff --git a/scikits/learn/benchmarks/bench_balltree.py b/scikits/learn/benchmarks/bench_balltree.py
index edc02a559f4b5d1f402785e231f6430f34ca9e5b..100d3e28b069e320a406eabe001766f46bebf416 100644
--- a/scikits/learn/benchmarks/bench_balltree.py
+++ b/scikits/learn/benchmarks/bench_balltree.py
@@ -1,5 +1,5 @@
"""
-This script compares the performance of the Ball Tree code with
+This script compares the performance of the Ball Tree code with
scipy.spatial.cKDTree.
Then run the simple timings script:
@@ -28,7 +28,7 @@ def compare_nbrs(nbrs1,nbrs2):
elif(nbrs1.ndim == 1):
N = len(nbrs1)
return numpy.all(nbrs1 == nbrs2)
-
+
def test_time(N=1000, D=100, ls=1, k=20):
M = numpy.random.random([N,D])
@@ -37,7 +37,7 @@ def test_time(N=1000, D=100, ls=1, k=20):
print "%i neighbors of %i points in %i dimensions:" % (k,N,D)
print " (leaf size = %i)" % ls
print " -------------"
-
+
t0 = time()
BT = BallTree(M,ls)
print " Ball Tree construction : %.3g sec" % ( time()-t0 )
@@ -45,14 +45,14 @@ def test_time(N=1000, D=100, ls=1, k=20):
print " total (construction+query) : %.3g sec" % ( time()-t0 )
print " -------------"
-
+
t0 = time()
KDT = cKDTree(M,ls)
print " KD tree construction : %.3g sec" % ( time()-t0 )
d,nbrs2 = KDT.query(M,k)
print " total (construction+query) : %.3g sec" % ( time()-t0 )
print " -------------"
-
+
print " neighbors match: ",
print ( compare_nbrs(nbrs1,nbrs2) )
print " -------------"
@@ -62,20 +62,20 @@ if __name__ == '__main__':
N,D = map(int,sys.argv[1:])
ls = 20
k = min(20,N)
-
+
elif len(sys.argv)==4:
N,D,ls = map(int,sys.argv[1:])
k = min(20,N)
elif len(sys.argv)==5:
N,D,ls,k = map(int,sys.argv[1:])
-
+
else:
print "usage: bench_balltree.py N D [leafsize=20], [k=20]"
exit()
-
-
+
+
test_time(N,D,ls,k)
-
-
-
+
+
+
diff --git a/scikits/learn/benchmarks/bench_plot_balltree.py b/scikits/learn/benchmarks/bench_plot_balltree.py
index 4fcf56cc71226bb3e7382f93d353c78fe568a1ab..e0a54ba03dc27346a7348dbff45e69c37915e707 100644
--- a/scikits/learn/benchmarks/bench_plot_balltree.py
+++ b/scikits/learn/benchmarks/bench_plot_balltree.py
@@ -55,4 +55,4 @@ pl.xlabel('number of dimensions')
pl.ylabel('time (seconds)')
pl.legend()
pl.show()
-
+
diff --git a/scikits/learn/cluster/affinity_propagation_.py b/scikits/learn/cluster/affinity_propagation_.py
index 53035a1980b53445bed44eed38edb7c2e0ae7175..aede3a09ad6f9bb1a7b675bc88a30ef96f0b8a6d 100644
--- a/scikits/learn/cluster/affinity_propagation_.py
+++ b/scikits/learn/cluster/affinity_propagation_.py
@@ -1,4 +1,4 @@
-""" Algorithms for clustering : Meanshift, Affinity propagation and spectral
+""" Algorithms for clustering : Meanshift, Affinity propagation and spectral
clustering.
"""
@@ -198,7 +198,7 @@ class AffinityPropagation(BaseEstimator):
Between Data Points", Science Feb. 2007
The algorithmic complexity of affinity propagation is quadratic
- in the number of points.
+ in the number of points.
"""
def __init__(self, damping=.5, maxit=200, convit=30, copy=True):
diff --git a/scikits/learn/cluster/mean_shift_.py b/scikits/learn/cluster/mean_shift_.py
index 6088b66f8883dc7b2c609aa0c0921add5b4adbc7..1b9934d09880c6fbd13162fcc569dd90d59ef129 100644
--- a/scikits/learn/cluster/mean_shift_.py
+++ b/scikits/learn/cluster/mean_shift_.py
@@ -1,4 +1,4 @@
-""" Algorithms for clustering : Meanshift, Affinity propagation and spectral
+""" Algorithms for clustering : Meanshift, Affinity propagation and spectral
clustering.
Author: Alexandre Gramfort alexandre.gramfort@inria.fr
@@ -223,7 +223,7 @@ class MeanShift(BaseEstimator):
def fit(self, X, **params):
""" Compute MeanShift
-
+
Parameters
-----------
X : array [n_samples, n_features]
diff --git a/scikits/learn/cluster/spectral.py b/scikits/learn/cluster/spectral.py
index e484b1fe613c173f3eb21460e4c6895ff4698949..920c2ac5fc95adb89d27d6541906c17d00262e4d 100644
--- a/scikits/learn/cluster/spectral.py
+++ b/scikits/learn/cluster/spectral.py
@@ -15,7 +15,7 @@ from .k_means_ import k_means
def spectral_embedding(adjacency, k=8, mode=None):
""" Spectral embedding: project the sample on the k first
- eigen vectors of the graph laplacian.
+ eigen vectors of the graph laplacian.
Parameters
-----------
@@ -46,7 +46,7 @@ def spectral_embedding(adjacency, k=8, mode=None):
from pyamg import smoothed_aggregation_solver
amg_loaded = True
except ImportError:
- amg_loaded = False
+ amg_loaded = False
n_nodes = adjacency.shape[0]
# XXX: Should we check that the matrices given is symmetric
@@ -56,9 +56,9 @@ def spectral_embedding(adjacency, k=8, mode=None):
mode = ('amg' if amg_loaded else 'arpack')
laplacian, dd = graph_laplacian(adjacency,
normed=True, return_diag=True)
- if (mode == 'arpack'
+ if (mode == 'arpack'
or not sparse.isspmatrix(laplacian)
- or n_nodes < 5*k # This is the threshold under which lobpcg has bugs
+ or n_nodes < 5*k # This is the threshold under which lobpcg has bugs
):
# We need to put the diagonal at zero
if not sparse.isspmatrix(laplacian):
@@ -88,7 +88,7 @@ def spectral_embedding(adjacency, k=8, mode=None):
X = np.random.rand(laplacian.shape[0], k)
X[:, 0] = 1. / dd.ravel()
M = ml.aspreconditioner()
- lambdas, diffusion_map = lobpcg(laplacian, X, M=M, tol=1.e-12,
+ lambdas, diffusion_map = lobpcg(laplacian, X, M=M, tol=1.e-12,
largest=False)
embedding = diffusion_map.T * dd
if embedding.shape[0] == 1: raise ValueError
@@ -98,7 +98,7 @@ def spectral_embedding(adjacency, k=8, mode=None):
def spectral_clustering(adjacency, k=8, mode=None):
- """ Spectral clustering: apply k-means to a projection of the
+ """ Spectral clustering: apply k-means to a projection of the
graph laplacian, finds normalized graph cuts.
Parameters
@@ -132,7 +132,7 @@ def spectral_clustering(adjacency, k=8, mode=None):
################################################################################
class SpectralClustering(BaseEstimator):
- """ Spectral clustering: apply k-means to a projection of the
+ """ Spectral clustering: apply k-means to a projection of the
graph laplacian, finds normalized graph cuts.
Parameters
@@ -148,7 +148,7 @@ class SpectralClustering(BaseEstimator):
-------
fit(X):
- Compute spectral clustering
+ Compute spectral clustering
Attributes
----------
@@ -163,11 +163,11 @@ class SpectralClustering(BaseEstimator):
self.k = k
self.mode = mode
-
+
def fit(self, X, **params):
""" Compute the spectral clustering from the adjacency matrix of
the graph.
-
+
Parameters
-----------
X: array-like or sparse matrix, shape: (p, p)
@@ -179,7 +179,7 @@ class SpectralClustering(BaseEstimator):
greatly speeds up computation.
"""
self._set_params(**params)
- self.labels_ = spectral_clustering(X,
+ self.labels_ = spectral_clustering(X,
k=self.k, mode=self.mode)
return self
diff --git a/scikits/learn/cluster/tests/common.py b/scikits/learn/cluster/tests/common.py
index f64458737cb89fe9b16e75a22331bb90b0851804..ba6bac04f52b6fbafa584710e795743fc858515b 100644
--- a/scikits/learn/cluster/tests/common.py
+++ b/scikits/learn/cluster/tests/common.py
@@ -13,15 +13,15 @@ def generate_clustered_data(seed=0, n_clusters=3, n_features=2,
n_samples_per_cluster=20, std=.4):
prng = np.random.RandomState(seed)
- means = np.array([[ 1, 1, 1, 0],
- [-1, -1, 0, 1],
+ means = np.array([[ 1, 1, 1, 0],
+ [-1, -1, 0, 1],
[ 1, -1, 1, 1],
[ -1, 1, 1, 0],
])
X = np.empty((0, n_features))
for i in range(n_clusters):
- X = np.r_[X, means[i][:n_features]
+ X = np.r_[X, means[i][:n_features]
+ std*prng.randn(n_samples_per_cluster, n_features)]
return X
diff --git a/scikits/learn/datasets/base.py b/scikits/learn/datasets/base.py
index a87a65cbe63b1037ca176172fc4f082dfc5cb506..74570e2b8f052a341299b89e25f013a0b32cdcd0 100644
--- a/scikits/learn/datasets/base.py
+++ b/scikits/learn/datasets/base.py
@@ -124,9 +124,8 @@ def load_iris():
>>> data = load_iris()
>>> data.target[[10, 25, 50]]
array([0, 0, 1])
- >>> data.target_names
- array(['setosa', 'versicolor', 'virginica'],
- dtype='|S10')
+ >>> list(data.target_names)
+ ['setosa', 'versicolor', 'virginica']
"""
diff --git a/scikits/learn/datasets/samples_generator.py b/scikits/learn/datasets/samples_generator.py
index 8eae1ed7f4dc30067477ebf1606a853910adefc8..dcac19f7af4757c7a463cb4b3f640f3d908e7606 100644
--- a/scikits/learn/datasets/samples_generator.py
+++ b/scikits/learn/datasets/samples_generator.py
@@ -138,7 +138,7 @@ def sparse_uncorrelated(nb_samples=100, nb_features=10):
def friedman(nb_samples=100, nb_features=10,noise_std=1):
"""
- Function creating simulated data with non linearities
+ Function creating simulated data with non linearities
(cf.Friedman 1993)
X = NR.normal(0,1)
Y = 10*sin(X[:,0]*X[:,1]) + 20*(X[:,2]-0.5)**2 + 10*X[:,3] + 5*X[:,4]
diff --git a/scikits/learn/externals/joblib/__init__.py b/scikits/learn/externals/joblib/__init__.py
index d415fb9502d74dfcb314ac8d7d6a44c67d95af81..66a971ea533a91d7fe557b01488a96cb76035617 100644
--- a/scikits/learn/externals/joblib/__init__.py
+++ b/scikits/learn/externals/joblib/__init__.py
@@ -15,9 +15,9 @@ data and has specific optimizations for `numpy` arrays. It is
============================== ==============================================
**User documentation**: http://packages.python.org/joblib
-
+
**Download packages**: http://pypi.python.org/pypi/joblib#downloads
-
+
**Source code**: http://github.com/joblib/joblib
**Report issues**: http://github.com/joblib/joblib/issues
@@ -36,7 +36,7 @@ solution.
over, for instance when prototyping computational-heavy jobs (as in
scientific development), but hand-crafted solution to aleviate this
issue is error-prone and often leads to unreproducible results
-
+
* **Persist to disk transparently**: persisting in an efficient way
arbitrary objects containing large data is hard. In addition,
hand-written persistence does not link easily the file on disk to the
@@ -46,7 +46,7 @@ solution.
It strives to address these problems while **leaving your code and your
flow control as unmodified as possible** (no framework, no new
-paradigms).
+paradigms).
Main features
------------------
@@ -75,7 +75,7 @@ Main features
>>> c = square(a)
>>> # The above call did not trigger an evaluation
-2) **Embarrassingly parallel helper:** to make is easy to write readable
+2) **Embarrassingly parallel helper:** to make is easy to write readable
parallel code and debug it quickly:
>>> from joblib import Parallel, delayed
@@ -88,10 +88,10 @@ Main features
progressively acquire better logging mechanism to help track what
has been ran, and capture I/O easily. In addition, Joblib will
provide a few I/O primitives, to easily define define logging and
- display streams, and provide a way of compiling a report.
+ display streams, and provide a way of compiling a report.
We want to be able to quickly inspect what has been run.
-..
+..
>>> import shutil ; shutil.rmtree('/tmp/joblib/')
"""
diff --git a/scikits/learn/externals/joblib/disk.py b/scikits/learn/externals/joblib/disk.py
index d2b267f44404a2d24703b9e94250c69f2eb23a51..b7b7846a6ebd91530765298437c7326f07ec9ac3 100644
--- a/scikits/learn/externals/joblib/disk.py
+++ b/scikits/learn/externals/joblib/disk.py
@@ -2,7 +2,7 @@
Disk management utilities.
"""
-# Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>
+# Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>
# Copyright (c) 2010 Gael Varoquaux
# License: BSD Style, 3 clauses.
@@ -12,7 +12,7 @@ import os
import shutil
def disk_used(path):
- """ Return the disk usage in a directory.
+ """ Return the disk usage in a directory.
"""
size = 0
for file in os.listdir(path) + ['.']:
@@ -60,7 +60,7 @@ def rm_subdirs(path, onerror=None):
names = os.listdir(path)
except os.error, err:
onerror(os.listdir, path, sys.exc_info())
-
+
for name in names:
fullname = os.path.join(path, name)
if os.path.isdir(fullname):
diff --git a/scikits/learn/externals/joblib/format_stack.py b/scikits/learn/externals/joblib/format_stack.py
index 246db3fb1fb38a01d6a6b8341423746bc0c68fa1..c01795e6f27bf361aeb7d5479554a159139e15a4 100644
--- a/scikits/learn/externals/joblib/format_stack.py
+++ b/scikits/learn/externals/joblib/format_stack.py
@@ -63,7 +63,7 @@ def safe_repr(value):
except:
return 'UNRECOVERABLE REPR FAILURE'
-def eq_repr(value, repr=safe_repr):
+def eq_repr(value, repr=safe_repr):
return '=%s' % repr(value)
@@ -92,7 +92,7 @@ def uniq_stable(elems):
################################################################################
def fix_frame_records_filenames(records):
"""Try to fix the filenames in each record from inspect.getinnerframes().
-
+
Particularly, modules loaded from within zip files have useless filenames
attached to their code object, and inspect.getinnerframes() just uses it.
"""
@@ -106,7 +106,7 @@ def fix_frame_records_filenames(records):
# __file__. It might also be None if the error occurred during
# import.
filename = better_fn
- fixed_records.append((frame, filename, line_no, func_name, lines, index))
+ fixed_records.append((frame, filename, line_no, func_name, lines, index))
return fixed_records
@@ -158,7 +158,7 @@ def _format_traceback_lines(lnum, index, lines, lvals=None):
if pad >= 3:
marker = '-'*(pad-3) + '-> '
elif pad == 2:
- marker = '> '
+ marker = '> '
elif pad == 1:
marker = '>'
else:
@@ -196,7 +196,7 @@ def format_records(records): #, print_globals=False):
# able to remove this try/except when 2.4 becomes a
# requirement. Bug details at http://python.org/sf/1005466
print "\nJoblib's exception reporting continues...\n"
-
+
if func == '?':
call = ''
else:
@@ -228,7 +228,7 @@ def format_records(records): #, print_globals=False):
there is no way to disambguate partial dotted structures until
the full list is known. The caller is responsible for pruning
the final list of duplicates before using it."""
-
+
# build composite names
if token == '.':
try:
@@ -275,7 +275,7 @@ def format_records(records): #, print_globals=False):
print ("An unexpected error occurred while tokenizing input\n"
"The following traceback may be corrupted or invalid\n"
"The error message is: %s\n" % msg)
-
+
# prune names list of duplicates, but keep the right order
unique_names = uniq_stable(names)
@@ -315,14 +315,14 @@ def format_records(records): #, print_globals=False):
else:
frames.append('%s%s' % (level,''.join(
_format_traceback_lines(lnum, index, lines, lvals))))
-
+
return frames
################################################################################
def format_exc(etype, evalue, etb, context=5, tb_offset=0):
""" Return a nice text document describing the traceback.
-
+
Parameters
-----------
etype, evalue, etb: as returned by sys.exc_info
@@ -340,7 +340,7 @@ def format_exc(etype, evalue, etb, context=5, tb_offset=0):
pyver = 'Python ' + string.split(sys.version)[0] + ': ' + sys.executable
date = time.ctime(time.time())
pid = 'PID: %i' % os.getpid()
-
+
head = '%s%s%s\n%s%s%s' % (etype, ' '*(75-len(str(etype))-len(date)),
date, pid, ' '*(75-len(str(pid))-len(pyver)),
pyver)
@@ -407,7 +407,7 @@ def format_outer_frames(context=5, stack_start=None, stack_end=None,
filename = filename[:-4] + '.py'
if ignore_ipython:
# Hack to avoid printing the interals of IPython
- if (os.path.basename(filename) == 'iplib.py'
+ if (os.path.basename(filename) == 'iplib.py'
and func_name in ('safe_execfile', 'runcode')):
break
maybeStart = line_no -1 - context//2
diff --git a/scikits/learn/externals/joblib/func_inspect.py b/scikits/learn/externals/joblib/func_inspect.py
index 5ea13f94424fe60d9ddbb801b64c20ee15492048..af0ff95daf9522e391e84f444166f147c5555f52 100644
--- a/scikits/learn/externals/joblib/func_inspect.py
+++ b/scikits/learn/externals/joblib/func_inspect.py
@@ -2,7 +2,7 @@
My own variation on function-specific inspect-like features.
"""
-# Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>
+# Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>
# Copyright (c) 2009 Gael Varoquaux
# License: BSD Style, 3 clauses.
@@ -13,7 +13,7 @@ import os
def get_func_code(func):
""" Attempts to retrieve a reliable function code hash.
-
+
The reason we don't use inspect.getsource is that it caches the
source, whereas we want this to be modified on the fly when the
function is modified.
@@ -54,7 +54,7 @@ def get_func_code(func):
return repr(func), source_file, -1
-def get_func_name(func, resolv_alias=True, win_characters=True):
+def get_func_name(func, resolv_alias=True, win_characters=True):
""" Return the function import path (as a list of module names), and
a name for the function.
@@ -94,7 +94,7 @@ def get_func_name(func, resolv_alias=True, win_characters=True):
module = module.split('.')
if hasattr(func, 'func_name'):
name = func.func_name
- elif hasattr(func, '__name__'):
+ elif hasattr(func, '__name__'):
name = func.__name__
else:
name = 'unknown'
@@ -105,7 +105,7 @@ def get_func_name(func, resolv_alias=True, win_characters=True):
if not func.func_globals[name] is func:
name = '%s-alias' % name
if inspect.ismethod(func):
- # We need to add the name of the class
+ # We need to add the name of the class
if hasattr(func, 'im_class'):
klass = func.im_class
module.append(klass.__name__)
@@ -126,7 +126,7 @@ def filter_args(func, ignore_lst, *args, **kwargs):
func: callable
Function giving the argument specification
ignore_lst: list of strings
- List of arguments to ignore (either a name of an argument
+ List of arguments to ignore (either a name of an argument
in the function spec, or '*', or '**')
*args: list
Positional arguments passed to the function.
@@ -146,7 +146,7 @@ def filter_args(func, ignore_lst, *args, **kwargs):
raise ValueError('ignore_lst must be a list of parameters to ignore '
'%s (type %s) was given' % (ignore_lst, type(ignore_lst)))
# Special case for functools.partial objects
- if (not inspect.ismethod(func) and not inspect.isfunction(func)):
+ if (not inspect.ismethod(func) and not inspect.isfunction(func)):
if ignore_lst:
warnings.warn('Cannot inspect object %s, ignore list will '
'not work.' % func, stacklevel=2)
@@ -165,7 +165,7 @@ def filter_args(func, ignore_lst, *args, **kwargs):
# First argument is 'self', it has been removed by Python
# we need to add it back:
args = [func.im_self, ] + args
- # XXX: Maybe I need an inspect.isbuiltin to detect C-level methods, such
+ # XXX: Maybe I need an inspect.isbuiltin to detect C-level methods, such
# as on ndarrays.
_, name = get_func_name(func, resolv_alias=False)
@@ -186,15 +186,15 @@ def filter_args(func, ignore_lst, *args, **kwargs):
# Missing argument
raise ValueError('Wrong number of arguments for %s%s:\n'
' %s(%s, %s) was called.'
- % (name,
+ % (name,
inspect.formatargspec(*inspect.getargspec(func)),
name,
repr(args)[1:-1],
- ', '.join('%s=%s' % (k, v)
+ ', '.join('%s=%s' % (k, v)
for k, v in kwargs.iteritems())
)
)
-
+
varkwargs = dict()
@@ -219,7 +219,7 @@ def filter_args(func, ignore_lst, *args, **kwargs):
arg_dict.pop(item)
else:
raise ValueError("Ignore list: argument '%s' is not defined for "
- "function %s%s" %
+ "function %s%s" %
(item, name,
inspect.formatargspec(arg_names,
arg_varargs,
@@ -227,5 +227,5 @@ def filter_args(func, ignore_lst, *args, **kwargs):
arg_defaults,
)))
# XXX: Return a sorted list of pairs?
- return arg_dict
+ return arg_dict
diff --git a/scikits/learn/externals/joblib/hashing.py b/scikits/learn/externals/joblib/hashing.py
index e00a70768105f43c9bfb109631b0637acefa5332..8183382ce2d0b1427684d084e86066a04e62b9db 100644
--- a/scikits/learn/externals/joblib/hashing.py
+++ b/scikits/learn/externals/joblib/hashing.py
@@ -1,9 +1,9 @@
"""
-Fast cryptographic hash of Python objects, with a special case for fast
+Fast cryptographic hash of Python objects, with a special case for fast
hashing of numpy arrays.
"""
-# Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>
+# Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>
# Copyright (c) 2009 Gael Varoquaux
# License: BSD Style, 3 clauses.
@@ -76,7 +76,7 @@ class NumpyHasher(Hasher):
# XXX: There might be a more efficient way of doing this
self._hash.update(self.np.getbuffer(obj.flatten()))
- # We store the class, to be able to distinguish between
+ # We store the class, to be able to distinguish between
# Objects with the same binary content, but different
# classes.
if self.coerce_mmap and isinstance(obj, self.np.memmap):
@@ -86,7 +86,7 @@ class NumpyHasher(Hasher):
klass = self.np.ndarray
else:
klass = obj.__class__
- # We also return the dtype and the shape, to distinguish
+ # We also return the dtype and the shape, to distinguish
# different views on the same data with different dtypes.
# The object will be pickled by the pickler hashed at the end.
@@ -95,14 +95,14 @@ class NumpyHasher(Hasher):
def hash(obj, hash_name='md5', coerce_mmap=False):
- """ Quick calculation of a hash to identify uniquely Python objects
+ """ Quick calculation of a hash to identify uniquely Python objects
containing numpy arrays.
-
+
Parameters
-----------
hash_name: 'md5' or 'sha1'
- Hashing algorithm used. sha1 is supposedly safer, but md5 is
+ Hashing algorithm used. sha1 is supposedly safer, but md5 is
faster.
coerce_mmap: boolean
Make no difference between np.memmap and np.ndarray
diff --git a/scikits/learn/externals/joblib/logger.py b/scikits/learn/externals/joblib/logger.py
index 4cf90ce4f5ad0b36ac08ec2cfd443d9e53006a61..4416c5f133655777ee1a21e4a9caaf73541c57c1 100644
--- a/scikits/learn/externals/joblib/logger.py
+++ b/scikits/learn/externals/joblib/logger.py
@@ -4,7 +4,7 @@ Helpers for logging.
This module needs much love to become useful.
"""
-# Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>
+# Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>
# Copyright (c) 2008 Gael Varoquaux
# License: BSD Style, 3 clauses.
@@ -31,7 +31,7 @@ def short_format_time(t):
class Logger(object):
""" Base class for logging messages.
"""
-
+
def __init__(self, depth=3):
"""
Parameters
@@ -87,7 +87,7 @@ class PrintTime(object):
for i in range(1, 9):
if os.path.exists(logfile+'.%i' % i):
try:
- shutil.move(logfile+'.%i' % i,
+ shutil.move(logfile+'.%i' % i,
logfile+'.%i' % (i+1))
except:
"No reason failing here"
diff --git a/scikits/learn/externals/joblib/memory.py b/scikits/learn/externals/joblib/memory.py
index b043fca3f231a2405ba194d7737d1e0b945caee0..901c4b0027718879a423f08cc10e2379b4e419e4 100644
--- a/scikits/learn/externals/joblib/memory.py
+++ b/scikits/learn/externals/joblib/memory.py
@@ -4,7 +4,7 @@ is called with the same input arguments.
"""
-# Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>
+# Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>
# Copyright (c) 2009 Gael Varoquaux
# License: BSD Style, 3 clauses.
@@ -45,10 +45,10 @@ FIRST_LINE_TEXT = "# first line:"
# object, and the interface to persist and query should be separated in
# the data store.
#
-# This would enable creating 'Memory' objects with a different logic for
+# This would enable creating 'Memory' objects with a different logic for
# pickling that would simply span a MemorizedFunc with the same
# store (or do we want to copy it to avoid cross-talks?), for instance to
-# implement HDF5 pickling.
+# implement HDF5 pickling.
# TODO: Same remark for the logger, and probably use the Python logging
# mechanism.
@@ -79,9 +79,9 @@ class JobLibCollisionWarning(UserWarning):
# class `Memory`
################################################################################
class MemorizedFunc(Logger):
- """ Callable object decorating a function for caching its return value
+ """ Callable object decorating a function for caching its return value
each time it is called.
-
+
All values are cached on the filesystem, in a deep directory
structure. Methods are provided to inspect the cache or clean it.
@@ -100,14 +100,14 @@ class MemorizedFunc(Logger):
arguments. Only used if save_npy was true when the
cache was created.
verbose: int, optional
- The verbosity flag, controls messages that are issued as
+ The verbosity flag, controls messages that are issued as
the function is revaluated.
"""
#-------------------------------------------------------------------------
# Public interface
#-------------------------------------------------------------------------
-
- def __init__(self, func, cachedir, ignore=None, save_npy=True,
+
+ def __init__(self, func, cachedir, ignore=None, save_npy=True,
mmap_mode=None, verbose=1):
"""
Parameters
@@ -127,7 +127,7 @@ class MemorizedFunc(Logger):
arguments. Only used if save_npy was true when the
cache was created.
verbose: int, optional
- Verbosity flag, controls the debug messages that are issued
+ Verbosity flag, controls the debug messages that are issued
as functions are revaluated.
"""
Logger.__init__(self)
@@ -159,7 +159,7 @@ class MemorizedFunc(Logger):
# function code has changed
output_dir, _ = self.get_output_dir(*args, **kwargs)
# FIXME: The statements below should be try/excepted
- if not (self._check_previous_func_code(stacklevel=3) and
+ if not (self._check_previous_func_code(stacklevel=3) and
os.path.exists(output_dir)):
return self.call(*args, **kwargs)
else:
@@ -179,7 +179,7 @@ class MemorizedFunc(Logger):
#-------------------------------------------------------------------------
# Private interface
#-------------------------------------------------------------------------
-
+
def _get_func_dir(self, mkdir=True):
""" Get the directory corresponding to the cache for the
function.
@@ -191,7 +191,7 @@ class MemorizedFunc(Logger):
try:
os.makedirs(func_dir)
except OSError:
- """ Dir exists: we have a race condition here, when using
+ """ Dir exists: we have a race condition here, when using
multiprocessing.
"""
# XXX: Ugly
@@ -206,12 +206,12 @@ class MemorizedFunc(Logger):
"""
coerce_mmap = (self.mmap_mode is not None)
argument_hash = hash(filter_args(self.func, self.ignore,
- *args, **kwargs),
+ *args, **kwargs),
coerce_mmap=coerce_mmap)
output_dir = os.path.join(self._get_func_dir(self.func),
argument_hash)
return output_dir, argument_hash
-
+
def _write_func_code(self, filename, func_code, first_line):
""" Write the function code and the filename to a file.
@@ -221,7 +221,7 @@ class MemorizedFunc(Logger):
def _check_previous_func_code(self, stacklevel=2):
- """
+ """
stacklevel is the depth a which this function is called, to
issue useful warnings to the user.
"""
@@ -232,7 +232,7 @@ class MemorizedFunc(Logger):
func_dir = self._get_func_dir()
func_code_file = os.path.join(func_dir, 'func_code.py')
- if not os.path.exists(func_code_file):
+ if not os.path.exists(func_code_file):
self._write_func_code(func_code_file, func_code, first_line)
return False
old_func_code, old_first_line = \
@@ -241,14 +241,14 @@ class MemorizedFunc(Logger):
return True
# We have differing code, is this because we are refering to
- # differing functions, or because the function we are refering as
+ # differing functions, or because the function we are refering as
# changed?
if old_first_line == first_line == -1:
_, func_name = get_func_name(self.func, resolv_alias=False,
win_characters=False)
if not first_line == -1:
- func_description = '%s (%s:%i)' % (func_name,
+ func_description = '%s (%s:%i)' % (func_name,
source_file, first_line)
else:
func_description = func_name
@@ -260,7 +260,7 @@ class MemorizedFunc(Logger):
# same than the code store, we have a collision: the code in the
# file has not changed, but the name we have is pointing to a new
# code block.
- if (not old_first_line == first_line
+ if (not old_first_line == first_line
and source_file is not None
and os.path.exists(source_file)):
_, func_name = get_func_name(self.func, resolv_alias=False)
@@ -272,7 +272,7 @@ class MemorizedFunc(Logger):
warnings.warn(JobLibCollisionWarning(
'Possible name collisions between functions '
"'%s' (%s:%i) and '%s' (%s:%i)" %
- (func_name, source_file, old_first_line,
+ (func_name, source_file, old_first_line,
func_name, source_file, first_line)),
stacklevel=stacklevel)
@@ -283,7 +283,7 @@ class MemorizedFunc(Logger):
def clear(self, warn=True):
- """ Empty the function's cache.
+ """ Empty the function's cache.
"""
func_dir = self._get_func_dir(mkdir=False)
if self._verbose and warn:
@@ -297,7 +297,7 @@ class MemorizedFunc(Logger):
def call(self, *args, **kwargs):
- """ Force the execution of the function with the given arguments and
+ """ Force the execution of the function with the given arguments and
persist the output values.
"""
start_time = time.time()
@@ -316,7 +316,7 @@ class MemorizedFunc(Logger):
def format_call(self, *args, **kwds):
- """ Returns a nicely formatted statement displaying the function
+ """ Returns a nicely formatted statement displaying the function
call with the given arguments.
"""
path, signature = self.format_signature(self.func, *args,
@@ -363,7 +363,7 @@ class MemorizedFunc(Logger):
filename = os.path.join(dir, 'output.pkl')
if 'numpy' in sys.modules and self.save_npy:
- numpy_pickle.dump(output, filename)
+ numpy_pickle.dump(output, filename)
else:
output_file = file(filename, 'w')
pickle.dump(output, output_file, protocol=2)
@@ -391,7 +391,7 @@ class MemorizedFunc(Logger):
"""
filename = os.path.join(output_dir, 'output.pkl')
if self.save_npy:
- return numpy_pickle.load(filename,
+ return numpy_pickle.load(filename,
mmap_mode=self.mmap_mode)
else:
output_file = file(filename, 'r')
@@ -402,7 +402,7 @@ class MemorizedFunc(Logger):
#-------------------------------------------------------------------------
# Private `object` interface
#-------------------------------------------------------------------------
-
+
def __repr__(self):
return '%s(func=%s, cachedir=%s)' % (
self.__class__.__name__,
@@ -418,7 +418,7 @@ class MemorizedFunc(Logger):
class Memory(Logger):
""" A context object for caching a function's return value each time it
is called with the same input arguments.
-
+
All values are cached on the filesystem, in a deep directory
structure.
@@ -427,7 +427,7 @@ class Memory(Logger):
#-------------------------------------------------------------------------
# Public interface
#-------------------------------------------------------------------------
-
+
def __init__(self, cachedir, save_npy=True, mmap_mode=None,
verbose=1):
"""
@@ -446,7 +446,7 @@ class Memory(Logger):
arguments. Only used if save_npy was true when the
cache was created.
verbose: int, optional
- Verbosity flag, controls the debug messages that are issued
+ Verbosity flag, controls the debug messages that are issued
as functions are revaluated.
"""
# XXX: Bad explaination of the None value of cachedir
@@ -469,13 +469,13 @@ class Memory(Logger):
Returns
-------
decorated_func: MemorizedFunc object
- The returned object is a MemorizedFunc object, that is
+ The returned object is a MemorizedFunc object, that is
callable (behaves like a function), but offers extra
methods for cache lookup and management. See the
documentation for :class:`joblib.memory.MemorizedFunc`.
"""
if func is None:
- # Partial application, to be able to specify extra keyword
+ # Partial application, to be able to specify extra keyword
# arguments in decorators
return functools.partial(self.cache, ignore=ignore)
if self.cachedir is None:
@@ -511,7 +511,7 @@ class Memory(Logger):
#-------------------------------------------------------------------------
# Private `object` interface
#-------------------------------------------------------------------------
-
+
def __repr__(self):
return '%s(cachedir=%s)' % (
self.__class__.__name__,
diff --git a/scikits/learn/externals/joblib/my_exceptions.py b/scikits/learn/externals/joblib/my_exceptions.py
index 5eee46b232de2e1c77946b7a61b6dbc521bb2b27..f8f3ffc91b9532e6a0a2f71eb8f2c8c5e2826958 100644
--- a/scikits/learn/externals/joblib/my_exceptions.py
+++ b/scikits/learn/externals/joblib/my_exceptions.py
@@ -40,7 +40,7 @@ def _mk_exception(exception, name=None):
# Avoid creating twice the same exception
this_exception = _exception_mapping[this_name]
else:
- this_exception = type(this_name, (exception, JoblibException),
+ this_exception = type(this_name, (exception, JoblibException),
dict(__repr__=JoblibException.__repr__,
__str__=JoblibException.__str__),
)
@@ -64,7 +64,7 @@ def _mk_common_exceptions():
return namespace
-# Updating module locals so that the exceptions pickle right. AFAIK this
+# Updating module locals so that the exceptions pickle right. AFAIK this
# works only at module-creation time
locals().update(_mk_common_exceptions())
diff --git a/scikits/learn/externals/joblib/numpy_pickle.py b/scikits/learn/externals/joblib/numpy_pickle.py
index bdef0cde0b53cf9daca85875ae6cccf41f70e456..1a641ac8e67e89aa3551983ffb12b729db39a7a2 100644
--- a/scikits/learn/externals/joblib/numpy_pickle.py
+++ b/scikits/learn/externals/joblib/numpy_pickle.py
@@ -2,7 +2,7 @@
A pickler to save numpy arrays in separate .npy files.
"""
-# Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>
+# Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>
# Copyright (c) 2009 Gael Varoquaux
# License: BSD Style, 3 clauses.
@@ -45,7 +45,7 @@ class NumpyPickler(pickle.Pickler):
def save(self, obj):
""" Subclass the save method, to save ndarray subclasses in npy
- files, rather than pickling them. Off course, this is a
+ files, rather than pickling them. Off course, this is a
total abuse of the Pickler class.
"""
if isinstance(obj, self.np.ndarray):
@@ -83,8 +83,8 @@ class NumpyUnpickler(pickle.Unpickler):
def load_build(self):
""" This method is called to set the state of a knewly created
- object.
-
+ object.
+
We capture it to replace our place-holder objects,
NDArrayWrapper, by the array we are interested in. We
replace directly in the stack of pickler.
@@ -111,7 +111,7 @@ class NumpyUnpickler(pickle.Unpickler):
# Utility functions
def dump(value, filename):
- """ Persist an arbitrary Python object into a filename, with numpy arrays
+ """ Persist an arbitrary Python object into a filename, with numpy arrays
saved as separate .npy files.
See Also
@@ -129,7 +129,7 @@ def dump(value, filename):
def load(filename, mmap_mode=None):
- """ Reconstruct a Python object and the numpy arrays it contains from
+ """ Reconstruct a Python object and the numpy arrays it contains from
a persisted file.
This function loads the numpy array files saved separately. If
diff --git a/scikits/learn/externals/joblib/parallel.py b/scikits/learn/externals/joblib/parallel.py
index 0e3088cb5ac9d96f26458fe0c3fb484916689b8f..fdaae353710f7c1cb0a5292a94388b7740784853 100644
--- a/scikits/learn/externals/joblib/parallel.py
+++ b/scikits/learn/externals/joblib/parallel.py
@@ -27,7 +27,7 @@ from .my_exceptions import JoblibException, _mk_exception
class SafeFunction(object):
""" Wraps a function to make it exception with full traceback in
their representation.
- Useful for parallel computing with multiprocessing, for which
+ Useful for parallel computing with multiprocessing, for which
exceptions cannot be captured.
"""
@@ -57,8 +57,8 @@ def print_progress(msg, index, total, start_time, n_jobs=1):
(total - index - 1.))
sys.stderr.write('[%s]: Done %3i out of %3i |elapsed: %s remaining: %s\n'
% (msg,
- index+1,
- total,
+ index+1,
+ total,
short_format_time(elapsed_time),
short_format_time(remaining_time),
))
@@ -103,16 +103,16 @@ class Parallel(Logger):
verbose: int, optional
The verbosity level. If 1 is given, the elapsed time as well
as the estimated remaining time are displayed.
-
+
Notes
-----
This object uses the multiprocessing module to compute in
parallel the application of a function to many different
- arguments. The main functionnality it brings in addition to
+ arguments. The main functionnality it brings in addition to
using the raw multiprocessing API are (see examples for details):
- * More readable code, in particular since it avoids
+ * More readable code, in particular since it avoids
constructing list of arguments.
* Easier debuging:
@@ -136,7 +136,7 @@ class Parallel(Logger):
Reshaping the output when the function has several return
values:
-
+
>>> from math import modf
>>> from joblib import Parallel, delayed
>>> r = Parallel(n_jobs=1)(delayed(modf)(i/2.) for i in range(10))
@@ -145,7 +145,7 @@ class Parallel(Logger):
(0.0, 0.5, 0.0, 0.5, 0.0, 0.5, 0.0, 0.5, 0.0, 0.5)
>>> i
(0.0, 0.0, 1.0, 1.0, 2.0, 2.0, 3.0, 3.0, 4.0, 4.0)
-
+
The progress meter::
>>> from time import sleep
@@ -157,9 +157,9 @@ class Parallel(Logger):
[Parallel(n_jobs=2)]: Done 7 out of 10 |elapsed: 0.4s remaining: 0.2s
[Parallel(n_jobs=2)]: Done 9 out of 10 |elapsed: 0.5s remaining: 0.1s
- Traceback example, note how the ligne of the error is indicated
+ Traceback example, note how the ligne of the error is indicated
as well as the values of the parameter passed to the function that
- triggered the exception, eventhough the traceback happens in the
+ triggered the exception, eventhough the traceback happens in the
child process::
>>> from string import atoi
@@ -167,7 +167,7 @@ class Parallel(Logger):
>>> Parallel(n_jobs=2)(delayed(atoi)(n) for n in ('1', '300', 30)) #doctest: +SKIP
#...
---------------------------------------------------------------------------
- Sub-process traceback:
+ Sub-process traceback:
---------------------------------------------------------------------------
TypeError Fri Jul 2 20:32:05 2010
PID: 4151 Python 2.6.5: /usr/bin/python
@@ -176,14 +176,14 @@ class Parallel(Logger):
398 is chosen from the leading characters of s, 0 for octal, 0x or
399 0X for hexadecimal. If base is 16, a preceding 0x or 0X is
400 accepted.
- 401
+ 401
402 """
--> 403 return _int(s, base)
- 404
- 405
+ 404
+ 405
406 # Convert string to long integer
407 def atol(s, base=10):
-
+
TypeError: int() can't convert non-string with explicit base
___________________________________________________________________________
@@ -206,7 +206,7 @@ class Parallel(Logger):
if n_jobs is None or multiprocessing is None or n_jobs == 1:
n_jobs = 1
- apply = LazyApply
+ apply = LazyApply
else:
pool = multiprocessing.Pool(n_jobs)
apply = pool.apply_async
@@ -219,7 +219,7 @@ class Parallel(Logger):
output.append(apply(function, args, kwargs))
if self.verbose and n_jobs == 1:
print '[%s]: Done job %3i | elapsed: %s' % (
- self, index,
+ self, index,
short_format_time(time.time() - start_time)
)
@@ -233,7 +233,7 @@ class Parallel(Logger):
print_progress(self, index, len(jobs), start_time,
n_jobs=n_jobs)
except JoblibException, exception:
- # Capture exception to add information on
+ # Capture exception to add information on
# the local stack in addition to the distant
# stack
this_report = format_outer_frames(
@@ -243,7 +243,7 @@ class Parallel(Logger):
report = """Multiprocessing exception:
%s
---------------------------------------------------------------------------
-Sub-process traceback:
+Sub-process traceback:
---------------------------------------------------------------------------
%s""" % (
this_report,
diff --git a/scikits/learn/externals/joblib/test/common.py b/scikits/learn/externals/joblib/test/common.py
index de6050d2d19d7f626737a70752e2c3b0494e705e..53894e3177b558a50dbd308f5786277fa467c7dd 100644
--- a/scikits/learn/externals/joblib/test/common.py
+++ b/scikits/learn/externals/joblib/test/common.py
@@ -11,7 +11,7 @@ try:
"""
return func
-except ImportError:
+except ImportError:
def with_numpy(func):
""" A decorator to skip tests requiring numpy.
"""
diff --git a/scikits/learn/externals/joblib/test/test_format_stack.py b/scikits/learn/externals/joblib/test/test_format_stack.py
index 453bd431ece80e0dd5b8f81f8c0f7309cd4b6ee1..db4102348b53760a93eaca7703526e28f17f2d23 100644
--- a/scikits/learn/externals/joblib/test/test_format_stack.py
+++ b/scikits/learn/externals/joblib/test/test_format_stack.py
@@ -2,7 +2,7 @@
Test the format_stack module.
"""
-# Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>
+# Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>
# Copyright (c) 2010 Gael Varoquaux
# License: BSD Style, 3 clauses.
@@ -18,7 +18,7 @@ class Nasty(object):
__str__ = __repr__
################################################################################
-# Test safe_repr
+# Test safe_repr
def test_safe_repr():
""" Smoke test safe_repr on a nasty class.
diff --git a/scikits/learn/externals/joblib/test/test_func_inspect.py b/scikits/learn/externals/joblib/test/test_func_inspect.py
index 820b0ebaaf35ae2aa9e68c8c79a5b29077643029..738035f6443b15f03832c39bff3914485fce656c 100644
--- a/scikits/learn/externals/joblib/test/test_func_inspect.py
+++ b/scikits/learn/externals/joblib/test/test_func_inspect.py
@@ -2,7 +2,7 @@
Test the func_inspect module.
"""
-# Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>
+# Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>
# Copyright (c) 2009 Gael Varoquaux
# License: BSD Style, 3 clauses.
@@ -13,7 +13,7 @@ from ..func_inspect import filter_args, get_func_name
from ..memory import Memory
################################################################################
-# Module-level functions, for tests
+# Module-level functions, for tests
def f(x, y=0):
pass
@@ -60,7 +60,7 @@ def test_filter_args():
def test_filter_args_method():
obj = Klass()
- nose.tools.assert_equal(filter_args(obj.f, [], 1),
+ nose.tools.assert_equal(filter_args(obj.f, [], 1),
{'x': 1, 'self': obj})
@@ -75,7 +75,7 @@ def test_filter_varargs():
{'x': 1, 'y': 2, '**':{'ee':2}}
def test_tmp():
- nose.tools.assert_equal(filter_args(j, [], 1, 2, ee=2),
+ nose.tools.assert_equal(filter_args(j, [], 1, 2, ee=2),
{'x': 1, 'y': 2, '**':{'ee':2}})
def test_func_name():
@@ -90,7 +90,7 @@ def test_bound_methods():
"""
a = Klass()
b = Klass()
- nose.tools.assert_not_equal(filter_args(a.f, [], 1),
+ nose.tools.assert_not_equal(filter_args(a.f, [], 1),
filter_args(b.f, [], 1))
diff --git a/scikits/learn/externals/joblib/test/test_hashing.py b/scikits/learn/externals/joblib/test/test_hashing.py
index eaa2172baffcbb403a9f4090468c5ec35e49447c..ab93c69e36269f9bfd061ff9021bb68503e21f10 100644
--- a/scikits/learn/externals/joblib/test/test_hashing.py
+++ b/scikits/learn/externals/joblib/test/test_hashing.py
@@ -2,7 +2,7 @@
Test the hashing module.
"""
-# Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>
+# Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>
# Copyright (c) 2009 Gael Varoquaux
# License: BSD Style, 3 clauses.
@@ -17,7 +17,7 @@ from ..hashing import hash
from .common import np, with_numpy
################################################################################
-# Helper functions for the tests
+# Helper functions for the tests
def time_func(func, *args):
""" Time function func on *args.
"""
@@ -47,7 +47,7 @@ def test_trival_hash():
""" Smoke test hash on various types.
"""
obj_list = [1, 1., 1+1j,
- 'a',
+ 'a',
(1, ), [1, ], {1:1},
None,
]
@@ -93,14 +93,14 @@ def test_hash_memmap():
a = np.asarray(m)
for coerce_mmap in (False, True):
yield (nose.tools.assert_equal,
- hash(a, coerce_mmap=coerce_mmap)
+ hash(a, coerce_mmap=coerce_mmap)
== hash(m, coerce_mmap=coerce_mmap),
coerce_mmap)
finally:
if 'm' in locals():
del m
# Force a garbage-collection cycle, to be certain that the
- # object is delete, and we don't run in a problem under
+ # object is delete, and we don't run in a problem under
# Windows with a file handle still open.
gc.collect()
try:
diff --git a/scikits/learn/externals/joblib/test/test_logger.py b/scikits/learn/externals/joblib/test/test_logger.py
index 33a44b138dc498717cb6f3a8c87aa68f55dbf5b5..0db7148bc74323d6fcc0b889fe9647ebc5cb527c 100644
--- a/scikits/learn/externals/joblib/test/test_logger.py
+++ b/scikits/learn/externals/joblib/test/test_logger.py
@@ -2,7 +2,7 @@
Test the logger module.
"""
-# Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>
+# Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>
# Copyright (c) 2009 Gael Varoquaux
# License: BSD Style, 3 clauses.
@@ -27,7 +27,7 @@ def setup():
if os.path.exists(cachedir):
shutil.rmtree(cachedir)
env['dir'] = cachedir
-
+
def teardown():
""" Test teardown.
@@ -49,7 +49,7 @@ def test_print_time():
# Create a second time, to smoke test log rotation.
print_time = PrintTime(logfile=os.path.join(env['dir'], 'test.log'))
print_time('Foo')
- # And a third time
+ # And a third time
print_time = PrintTime(logfile=os.path.join(env['dir'], 'test.log'))
print_time('Foo')
# nose.tools.assert_equal(sys.stderr.getvalue(),
diff --git a/scikits/learn/externals/joblib/test/test_memory.py b/scikits/learn/externals/joblib/test/test_memory.py
index 335ab45341d535c7877c504209d1c00c1cd03bc7..14fc3b1b5bdcc69e32ced74f5aca5e0f16f84be1 100644
--- a/scikits/learn/externals/joblib/test/test_memory.py
+++ b/scikits/learn/externals/joblib/test/test_memory.py
@@ -2,7 +2,7 @@
Test the memory module.
"""
-# Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>
+# Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>
# Copyright (c) 2009 Gael Varoquaux
# License: BSD Style, 3 clauses.
@@ -44,7 +44,7 @@ def setup_module():
print 80*'_'
print 'test_memory setup'
print 80*'_'
-
+
def _rmtree_onerror(func, path, excinfo):
print '!'*79
print 'os function failed:', repr(func)
@@ -169,7 +169,7 @@ def test_memory_name_collision():
@memory.cache
def name_collision(x):
- """ A first function called name_collision
+ """ A first function called name_collision
"""
return x
@@ -177,7 +177,7 @@ def test_memory_name_collision():
@memory.cache
def name_collision(x):
- """ A second function called name_collision
+ """ A second function called name_collision
"""
return x
@@ -221,7 +221,7 @@ def test_memory_warning_lambda_collisions():
def test_memory_warning_collision_detection():
- """ Check that collisions impossible to detect will raise appropriate
+ """ Check that collisions impossible to detect will raise appropriate
warnings.
"""
memory = Memory(cachedir=env['dir'], verbose=0)
@@ -272,7 +272,7 @@ def test_memory_eval():
def count_and_append(x=[]):
- """ A function with a side effect in its arguments.
+ """ A function with a side effect in its arguments.
Return the lenght of its argument and append one element.
"""
@@ -316,7 +316,7 @@ def test_memory_numpy():
def test_memory_exception():
- """ Smoketest the exception handling of Memory.
+ """ Smoketest the exception handling of Memory.
"""
memory = Memory(cachedir=env['dir'], verbose=0)
class MyException(Exception):
diff --git a/scikits/learn/externals/joblib/test/test_numpy_pickle.py b/scikits/learn/externals/joblib/test/test_numpy_pickle.py
index 6182c89adc99b4b200f26d8ca700604464bd76ff..0d8175c5105fb40abb0dd3ad7ab9f16a895f7412 100644
--- a/scikits/learn/externals/joblib/test/test_numpy_pickle.py
+++ b/scikits/learn/externals/joblib/test/test_numpy_pickle.py
@@ -113,7 +113,7 @@ def test_numpy_persistence():
for item in obj_:
yield nose.tools.assert_true, isinstance(item, np.ndarray)
# And finally, check that all the values are equal.
- yield nose.tools.assert_true, np.all(np.array(obj) ==
+ yield nose.tools.assert_true, np.all(np.array(obj) ==
np.array(obj_))
diff --git a/scikits/learn/externals/joblib/test/test_parallel.py b/scikits/learn/externals/joblib/test/test_parallel.py
index 808750eaeb7b3559655a0336bf67b48820428e81..a28f4d1835669cf008dac5a56a12a1a7f31e1698 100644
--- a/scikits/learn/externals/joblib/test/test_parallel.py
+++ b/scikits/learn/externals/joblib/test/test_parallel.py
@@ -2,7 +2,7 @@
Test the parallel module.
"""
-# Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>
+# Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>
# Copyright (c) 2010 Gael Varoquaux
# License: BSD Style, 3 clauses.
@@ -46,12 +46,12 @@ def test_parallel_kwargs():
"""
lst = range(10)
for n_jobs in (1, 4):
- yield (nose.tools.assert_equal,
- [f(x, y=1) for x in lst],
+ yield (nose.tools.assert_equal,
+ [f(x, y=1) for x in lst],
Parallel(n_jobs=n_jobs)(delayed(f)(x, y=1) for x in lst)
)
-
+
def test_parallel_pickling():
""" Check that pmap captures the errors when it is passed an object
that cannot be pickled.
@@ -59,7 +59,7 @@ def test_parallel_pickling():
def g(x):
return x**2
nose.tools.assert_raises(PickleError,
- Parallel(),
+ Parallel(),
(delayed(g)(x) for x in range(10))
)
diff --git a/scikits/learn/feature_extraction/image.py b/scikits/learn/feature_extraction/image.py
index ebada423dc8588301716bcb48d885c469d3295d9..4303781b6bb47e6d1c24d89fbb8589dcec6cd914 100644
--- a/scikits/learn/feature_extraction/image.py
+++ b/scikits/learn/feature_extraction/image.py
@@ -15,7 +15,7 @@ from ..utils.fixes import in1d
def _make_edges_3d(n_x, n_y, n_z=1):
""" Returns a list of edges for a 3D image.
-
+
Parameters
===========
n_x: integer
@@ -48,7 +48,7 @@ def _compute_gradient_3d(edges, img):
# XXX: Why mask the image after computing the weights?
def _mask_edges_weights(mask, edges, weights):
- """ Given a image mask and the
+ """ Given a image mask and the
"""
inds = np.arange(mask.size)
inds = inds[mask.ravel()]
@@ -71,7 +71,7 @@ def img_to_graph(img, mask=None,
img: ndarray, 2D or 3D
2D or 3D image
mask : ndarray of booleans, optional
- An optional mask of the image, to consider only part of the
+ An optional mask of the image, to consider only part of the
pixels.
return_as: np.ndarray or a sparse matrix class, optional
The class to use to build the returned adjacency matrix.
diff --git a/scikits/learn/feature_extraction/tests/test_image.py b/scikits/learn/feature_extraction/tests/test_image.py
index 40a3644b7e4a1fe65976666909404d56c94640ee..5209e6e356f4a7a14e5ecb5d1cd5c4c353c12fc1 100644
--- a/scikits/learn/feature_extraction/tests/test_image.py
+++ b/scikits/learn/feature_extraction/tests/test_image.py
@@ -19,7 +19,7 @@ def test_img_to_graph():
# Negative elements are the diagonal: the elements of the original
# image. Positive elements are the values of the gradient, they
# shoudl all be equal on grad_x and grad_y
- np.testing.assert_array_equal(grad_x.data[grad_x.data > 0],
+ np.testing.assert_array_equal(grad_x.data[grad_x.data > 0],
grad_y.data[grad_y.data > 0])
diff --git a/scikits/learn/feature_selection/tests/test_feature_select.py b/scikits/learn/feature_selection/tests/test_feature_select.py
index 656e674a1a6dc42d52f88a3bf695d303ee2856f7..002f15cf7c2a44e574ac5b52e51bcd49ba09c8ca 100644
--- a/scikits/learn/feature_selection/tests/test_feature_select.py
+++ b/scikits/learn/feature_selection/tests/test_feature_select.py
@@ -2,7 +2,7 @@
Todo: cross-check the F-value with stats model
"""
-from ..univariate_selection import (f_classif, f_regression,
+from ..univariate_selection import (f_classif, f_regression,
SelectPercentile, SelectKBest,
SelectFpr, SelectFdr, SelectFwe,
GenericUnivariateSelect)
@@ -72,7 +72,7 @@ def test_select_percentile_classif():
seed=seed)
univariate_filter = SelectPercentile(f_classif, percentile=25)
X_r = univariate_filter.fit(X, Y).transform(X)
- X_r2 = GenericUnivariateSelect(f_classif, mode='percentile',
+ X_r2 = GenericUnivariateSelect(f_classif, mode='percentile',
param=25).fit(X, Y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
@@ -94,7 +94,7 @@ def test_select_kbest_classif():
seed=seed)
univariate_filter = SelectKBest(f_classif, k=5)
X_r = univariate_filter.fit(X, Y).transform(X)
- X_r2 = GenericUnivariateSelect(f_classif, mode='k_best',
+ X_r2 = GenericUnivariateSelect(f_classif, mode='k_best',
param=5).fit(X, Y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
@@ -113,7 +113,7 @@ def test_select_fpr_classif():
seed=seed)
univariate_filter = SelectFpr(f_classif, alpha=0.0001)
X_r = univariate_filter.fit(X, Y).transform(X)
- X_r2 = GenericUnivariateSelect(f_classif, mode='fpr',
+ X_r2 = GenericUnivariateSelect(f_classif, mode='fpr',
param=0.0001).fit(X, Y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
@@ -132,7 +132,7 @@ def test_select_fdr_classif():
seed=3)
univariate_filter = SelectFdr(f_classif, alpha=0.01)
X_r = univariate_filter.fit(X, Y).transform(X)
- X_r2 = GenericUnivariateSelect(f_classif, mode='fdr',
+ X_r2 = GenericUnivariateSelect(f_classif, mode='fdr',
param=0.01).fit(X, Y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
@@ -151,7 +151,7 @@ def test_select_fwe_classif():
seed=seed)
univariate_filter = SelectFwe(f_classif, alpha=0.01)
X_r = univariate_filter.fit(X, Y).transform(X)
- X_r2 = GenericUnivariateSelect(f_classif, mode='fwe',
+ X_r2 = GenericUnivariateSelect(f_classif, mode='fwe',
param=0.01).fit(X, Y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
@@ -173,7 +173,7 @@ def test_select_percentile_regression():
seed=seed)
univariate_filter = SelectPercentile(f_regression, percentile=25)
X_r = univariate_filter.fit(X, Y).transform(X)
- X_r2 = GenericUnivariateSelect(f_regression, mode='percentile',
+ X_r2 = GenericUnivariateSelect(f_regression, mode='percentile',
param=25).fit(X, Y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
@@ -191,7 +191,7 @@ def test_select_percentile_regression_full():
seed=seed)
univariate_filter = SelectPercentile(f_regression, percentile=100)
X_r = univariate_filter.fit(X, Y).transform(X)
- X_r2 = GenericUnivariateSelect(f_regression, mode='percentile',
+ X_r2 = GenericUnivariateSelect(f_regression, mode='percentile',
param=100).fit(X, Y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
@@ -209,7 +209,7 @@ def test_select_kbest_regression():
seed=seed)
univariate_filter = SelectKBest(f_regression, k=5)
X_r = univariate_filter.fit(X, Y).transform(X)
- X_r2 = GenericUnivariateSelect(f_regression, mode='k_best',
+ X_r2 = GenericUnivariateSelect(f_regression, mode='k_best',
param=5).fit(X, Y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
@@ -228,7 +228,7 @@ def test_select_fpr_regression():
seed=seed)
univariate_filter = SelectFpr(f_regression, alpha=0.01)
X_r = univariate_filter.fit(X, Y).transform(X)
- X_r2 = GenericUnivariateSelect(f_regression, mode='fpr',
+ X_r2 = GenericUnivariateSelect(f_regression, mode='fpr',
param=0.01).fit(X, Y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
@@ -248,7 +248,7 @@ def test_select_fdr_regression():
seed=2)
univariate_filter = SelectFdr(f_regression, alpha=0.01)
X_r = univariate_filter.fit(X, Y).transform(X)
- X_r2 = GenericUnivariateSelect(f_regression, mode='fdr',
+ X_r2 = GenericUnivariateSelect(f_regression, mode='fdr',
param=0.01).fit(X, Y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
@@ -267,7 +267,7 @@ def test_select_fwe_regression():
seed=seed)
univariate_filter = SelectFwe(f_regression, alpha=0.01)
X_r = univariate_filter.fit(X, Y).transform(X)
- X_r2 = GenericUnivariateSelect(f_regression, mode='fwe',
+ X_r2 = GenericUnivariateSelect(f_regression, mode='fwe',
param=0.01).fit(X, Y).transform(X)
assert_array_equal(X_r, X_r2)
support = univariate_filter.get_support()
diff --git a/scikits/learn/glm/bayes.py b/scikits/learn/glm/bayes.py
index 17dde8731abd99d2e583ebfc7b4ed78200152cbe..afd017483fcd2c38eaf07821262bbff3d14117db 100644
--- a/scikits/learn/glm/bayes.py
+++ b/scikits/learn/glm/bayes.py
@@ -116,7 +116,7 @@ class BayesianRidge(LinearModel):
def fit(self, X, y, **params):
"""Fit the model
-
+
Parameters
----------
X : numpy array of shape [n_samples,n_features]
diff --git a/scikits/learn/glm/benchmarks/bench_bayes.py b/scikits/learn/glm/benchmarks/bench_bayes.py
index 8a7bd40424175a4f266d03468499322de6728492..665f91aaa6c748535a347aaea13fbbb814d468da 100644
--- a/scikits/learn/glm/benchmarks/bench_bayes.py
+++ b/scikits/learn/glm/benchmarks/bench_bayes.py
@@ -13,7 +13,7 @@ from scikits.learn.utils.bench import total_seconds
if __name__ == '__main__':
import pylab as pl
-
+
n_iter = 20
time_ridge = np.empty(n_iter)
@@ -24,7 +24,7 @@ if __name__ == '__main__':
n_samples, n_features = 100, 100
- X = np.random.randn(n_samples, n_features)
+ X = np.random.randn(n_samples, n_features)
y = np.random.randn(n_samples)
start = datetime.now()
diff --git a/scikits/learn/glm/benchmarks/bench_glm.py b/scikits/learn/glm/benchmarks/bench_glm.py
index 97d3d307334528a5579d64acc2c1b38c045d331c..d249bd95828924aa18261922af76ea5e8ec7905b 100644
--- a/scikits/learn/glm/benchmarks/bench_glm.py
+++ b/scikits/learn/glm/benchmarks/bench_glm.py
@@ -28,7 +28,7 @@ if __name__ == '__main__':
n, m = 10*i + 3, 10*i + 3
- X = np.random.randn (n, m)
+ X = np.random.randn (n, m)
Y = np.random.randn (n)
start = datetime.now()
@@ -47,7 +47,7 @@ if __name__ == '__main__':
lasso.fit (X, Y)
time_lasso[i] = total_seconds(datetime.now() - start)
-
+
pl.xlabel ('Dimesions')
pl.ylabel ('Time (in seconds)')
diff --git a/scikits/learn/glm/tests/test_ridge.py b/scikits/learn/glm/tests/test_ridge.py
index 99e08efa3814a1fecb655c0f73c1ddff36546111..b27bd0fabfbc365e58772a2cde8a46b49e997555 100644
--- a/scikits/learn/glm/tests/test_ridge.py
+++ b/scikits/learn/glm/tests/test_ridge.py
@@ -12,17 +12,17 @@ def test_ridge():
of np.random.
"""
alpha = 1.0
-
+
# With more samples than features
n_samples, n_features = 6, 5
np.random.seed(0)
y = np.random.randn(n_samples)
X = np.random.randn(n_samples, n_features)
-
+
ridge = Ridge(alpha=alpha)
ridge.fit(X, y)
assert ridge.score (X, y) > 0.5
-
+
# With more features than samples
n_samples, n_features = 5, 10
np.random.seed(0)
@@ -59,7 +59,7 @@ def test_ridge_vs_lstsq():
ridge = Ridge(alpha=0.)
ols = LinearRegression()
-
+
ridge.fit(X, y)
ols.fit (X, y)
assert np.linalg.norm (ridge.coef_ - ols.coef_) < 1e-10
diff --git a/scikits/learn/hmm.py b/scikits/learn/hmm.py
index f760e2c19205aea23411c68e3fbe28187c12967c..b851762384bc2620c84047a040112daf0a08fd85 100644
--- a/scikits/learn/hmm.py
+++ b/scikits/learn/hmm.py
@@ -808,7 +808,7 @@ class MultinomialHMM(_BaseHMM):
[ 0.5, 0.5]]),
startprob_prior=1.0, n_states=2, startprob=array([ 0.5, 0.5]),
transmat_prior=1.0)
-
+
See Also
--------
GaussianHMM : HMM with Gaussian emissions
@@ -923,9 +923,9 @@ class GMMHMM(_BaseHMM):
... # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE
GMMHMM(n_mix=10, cvtype='diag', n_states=2, startprob_prior=1.0,
startprob=array([ 0.5, 0.5]),
- transmat=array([[ 0.5, 0.5],
- [ 0.5, 0.5]]),
- transmat_prior=1.0,
+ transmat=array([[ 0.5, 0.5],
+ [ 0.5, 0.5]]),
+ transmat_prior=1.0,
gmms=[GMM(cvtype='diag', n_states=10), GMM(cvtype='diag', n_states=10)])
See Also
diff --git a/scikits/learn/lda.py b/scikits/learn/lda.py
index 192f5a1013d7a070d0f21a073492a541d9afba34..34936416957ec944ff80672f8724d58c48137058 100644
--- a/scikits/learn/lda.py
+++ b/scikits/learn/lda.py
@@ -125,7 +125,7 @@ class LDA(BaseEstimator, ClassifierMixin):
if store_covariance:
cov /= (n_samples - n_classes)
self.covariance_ = cov
-
+
means = np.asarray(means)
Xc = np.concatenate(Xc, 0)
diff --git a/scikits/learn/neighbors.py b/scikits/learn/neighbors.py
index 06385b50ff324fab34e2aea5e2d86bf88f3097bd..31230b5d285d0ab1a767a398b469598fa9363f69 100644
--- a/scikits/learn/neighbors.py
+++ b/scikits/learn/neighbors.py
@@ -96,7 +96,7 @@ class Neighbors(BaseEstimator, ClassifierMixin):
(array([ 0.5 , 1.11803399]), array([1, 2]))
"""
- if k is None:
+ if k is None:
k=self.k
return self.ball_tree.query(data, k=k)
@@ -132,7 +132,7 @@ class Neighbors(BaseEstimator, ClassifierMixin):
[0 1]
"""
T = np.asanyarray(T)
- if k is None:
+ if k is None:
k=self.k
return _predict_from_BallTree(self.ball_tree, self.Y, T, k=k)
diff --git a/scikits/learn/pca.py b/scikits/learn/pca.py
index f9722138060783efc236bb00befac7055d7d726b..c1455f4b3ee53510c6ad1c15fb2b3ccff3933e24 100644
--- a/scikits/learn/pca.py
+++ b/scikits/learn/pca.py
@@ -16,16 +16,16 @@ def _assess_dimension_(spect, rk, n_samples, dim):
----------
spect: array of shape (n)
data spectrum
- rk: int,
+ rk: int,
tested rank value
- n_samples: int,
+ n_samples: int,
number of samples
- dim: int,
+ dim: int,
embedding/emprical dimension
Returns
-------
- ll: float,
+ ll: float,
The log-likelihood
Notes
@@ -174,7 +174,7 @@ class ProbabilisticPCA(PCA):
Parameters
----------
- X: array of shape(n_samples, n_dim)
+ X: array of shape(n_samples, n_dim)
The data to fit
homoscedastic: bool, optional,
If True, average variance across remaining dimensions
diff --git a/scikits/learn/sgd/base.py b/scikits/learn/sgd/base.py
index 5f3051a8006c02fbd155ec21dbe435c7453c09f9..d06ff1f8c6a2fe0ce4b62c0c8244ded87ea751f9 100644
--- a/scikits/learn/sgd/base.py
+++ b/scikits/learn/sgd/base.py
@@ -16,7 +16,7 @@ class LinearModel(BaseEstimator):
Parameters
----------
loss : str, ('hinge'|'log'|'modifiedhuber')
- The loss function to be used. Defaults to 'hinge'.
+ The loss function to be used. Defaults to 'hinge'.
penalty : str, ('l2'|'l1'|'elasticnet')
The penalty (aka regularization term) to be used. Defaults to 'l2'.
alpha : float
@@ -33,7 +33,7 @@ class LinearModel(BaseEstimator):
data is assumed to be already centered. Defaults to True.
n_iter: int
The number of passes over the training data (aka epochs).
- Defaults to 5.
+ Defaults to 5.
shuffle: bool
Whether or not the training data should be shuffled after each epoch.
Defaults to False.
diff --git a/scikits/learn/sgd/setup.py b/scikits/learn/sgd/setup.py
index 7f26520788bd12df0c06d8baae3f2dc1635eb550..5b05589e17a8330241f86af580d597e90ab15b62 100644
--- a/scikits/learn/sgd/setup.py
+++ b/scikits/learn/sgd/setup.py
@@ -7,7 +7,7 @@ def configuration(parent_package='', top_path=None):
site_cfg = ConfigParser()
site_cfg.read(get_standard_file('site.cfg'))
-
+
# add other directories
config.add_subpackage('tests')
config.add_subpackage('sparse')
diff --git a/scikits/learn/sgd/sparse/sgd.py b/scikits/learn/sgd/sparse/sgd.py
index b4a3862c288c78a5f985f56ac8234c7046868b86..af1ab392191c6de60195911b8da0280b2c44e74c 100644
--- a/scikits/learn/sgd/sparse/sgd.py
+++ b/scikits/learn/sgd/sparse/sgd.py
@@ -21,7 +21,7 @@ class SGD(LinearModel, ClassifierMixin):
Parameters
----------
loss : str, ('hinge'|'log'|'modifiedhuber')
- The loss function to be used. Defaults to 'hinge'.
+ The loss function to be used. Defaults to 'hinge'.
penalty : str, ('l2'|'l1'|'elasticnet')
The penalty (aka regularization term) to be used. Defaults to 'l2'.
alpha : float
@@ -38,7 +38,7 @@ class SGD(LinearModel, ClassifierMixin):
data is assumed to be already centered. Defaults to True.
n_iter: int
The number of passes over the training data (aka epochs).
- Defaults to 5.
+ Defaults to 5.
shuffle: bool
Whether or not the training data should be shuffled after each epoch.
Defaults to False.
@@ -169,7 +169,7 @@ class SGD(LinearModel, ClassifierMixin):
if self.coef_.shape != (n_classes, n_features):
raise ValueError("Provided coef_ does not match dataset. ")
coef_ = self.coef_
-
+
if self.intercept_ is None \
or isinstance(self.intercept_, float):
intercept_ = np.zeros(n_classes, dtype=np.float64,
@@ -187,13 +187,13 @@ class SGD(LinearModel, ClassifierMixin):
res = Parallel(n_jobs=self.n_jobs, verbose=self.verbose)(
delayed(_train_ova_classifier)(i, c, X_data, X_indices,
- X_indptr, Y, self)
+ X_indptr, Y, self)
for i, c in enumerate(self.classes))
for i, coef, intercept in res:
coef_[i] = coef
intercept_[i] = intercept
-
+
self._set_coef(coef_)
self.intercept_ = intercept_
@@ -260,7 +260,7 @@ class SGD(LinearModel, ClassifierMixin):
This is important
for joblib because otherwise it will crash trying to pickle
- the external loss function object.
+ the external loss function object.
"""
return SGD,(self.loss, self.penalty, self.alpha, self.rho, self.coef_,
self.intercept_, self.fit_intercept, self.n_iter,
diff --git a/scikits/learn/sgd/tests/test_sparse.py b/scikits/learn/sgd/tests/test_sparse.py
index c5811a3834cc6fc2b45a8696c02f4cf634879bd3..d7f560baff7cd3d7532dce5d423e8cbddfa047b7 100644
--- a/scikits/learn/sgd/tests/test_sparse.py
+++ b/scikits/learn/sgd/tests/test_sparse.py
@@ -115,7 +115,7 @@ def test_set_coef():
pass
else:
assert False
-
+
clf = sgd.sparse.SGD()
clf._set_coef(None)
assert clf.sparse_coef_ == None
@@ -154,7 +154,7 @@ def test_sgd_multiclass_njobs():
def test_set_coef_multiclass():
"""Checks coef_ and intercept_ shape for
- the warm starts for multi-class problems.
+ the warm starts for multi-class problems.
"""
# Provided coef_ does not match dataset.
try:
diff --git a/scikits/learn/svm/sparse/libsvm.py b/scikits/learn/svm/sparse/libsvm.py
index 34be970222bc6d925f3f0906b6bbbc67fecf0c44..cb1dc9047cedf90600aef68f85af24e53d20c609 100644
--- a/scikits/learn/svm/sparse/libsvm.py
+++ b/scikits/learn/svm/sparse/libsvm.py
@@ -89,12 +89,12 @@ class OneClassSVM (SparseBaseLibSVM):
"""
def __init__(self, kernel='rbf', degree=3, gamma=0.0, coef0=0.0,
- cache_size=100.0, eps=1e-3, C=1.0,
+ cache_size=100.0, eps=1e-3, C=1.0,
nu=0.5, p=0.1, shrinking=True, probability=False):
SparseBaseLibSVM.__init__(self, 'one_class', kernel, degree,
gamma, coef0, cache_size, eps, C, nu, p,
shrinking, probability)
-
+
def fit(self, X):
super(OneClassSVM, self).fit(X, [])
diff --git a/scikits/learn/tests/test_base.py b/scikits/learn/tests/test_base.py
index de7808bd5c94dd7c614950dd16e4cfdf53d323ba..074c70bb2c0202ff309afe4b2f2f87d8e3b20329 100644
--- a/scikits/learn/tests/test_base.py
+++ b/scikits/learn/tests/test_base.py
@@ -41,7 +41,7 @@ def test_clone():
new_selector = clone(selector)
assert_true(selector is not new_selector)
assert_equal(selector._get_params(), new_selector._get_params())
-
+
def test_clone_2():
"""Tests that clone doesn't copy everything.
@@ -49,7 +49,7 @@ def test_clone_2():
We first create an estimator, give it an own attribute, and
make a copy of its original state. Then we check that the copy doesn't have
the specific attribute we manually added to the initial estimator.
-
+
"""
from scikits.learn.feature_selection import SelectFpr, f_classif
@@ -57,21 +57,21 @@ def test_clone_2():
selector.own_attribute = "test"
new_selector = clone(selector)
assert_false(hasattr(new_selector, "own_attribute"))
-
+
def test_repr():
- """ Smoke test the repr of the
+ """ Smoke test the repr of the
"""
my_estimator = MyEstimator()
repr(my_estimator)
test = T(K(), K())
- assert_equal(repr(test),
+ assert_equal(repr(test),
"T(a=K(c=None, d=None), b=K(c=None, d=None))"
)
def test_str():
- """ Smoke test the str of the
+ """ Smoke test the str of the
"""
my_estimator = MyEstimator()
str(my_estimator)
@@ -96,6 +96,6 @@ def test_is_classifier():
assert_true(is_classifier(svc))
assert_true(is_classifier(GridSearchCV(svc, {'C': [0.1, 1]})))
assert_true(is_classifier(Pipeline([('svc', svc)])))
- assert_true(is_classifier(Pipeline([('svc_cv',
+ assert_true(is_classifier(Pipeline([('svc_cv',
GridSearchCV(svc, {'C': [0.1, 1]}))])))
diff --git a/scikits/learn/tests/test_cross_val.py b/scikits/learn/tests/test_cross_val.py
index 667de59b8d7b2010f7232f3bf12694d7bc707bbe..871fc76d368a367979126e6aa52344ff03795ab7 100644
--- a/scikits/learn/tests/test_cross_val.py
+++ b/scikits/learn/tests/test_cross_val.py
@@ -10,7 +10,7 @@ from .. import cross_val
class MockClassifier(BaseEstimator):
"""Dummy classifier to test the cross-validation
-
+
"""
def __init__(self, a=0):
self.a = a
diff --git a/scikits/learn/tests/test_fastica.py b/scikits/learn/tests/test_fastica.py
index 2d937023372a650c6404709ab256d4ca12d9249b..a3fad0acdb22ef336aa40a842daf38db2a9cf9a3 100644
--- a/scikits/learn/tests/test_fastica.py
+++ b/scikits/learn/tests/test_fastica.py
@@ -13,7 +13,7 @@ def center_and_norm(x, axis=-1):
Parameters
-----------
x: ndarray
- Array with an axis of observations (statistical units) measured on
+ Array with an axis of observations (statistical units) measured on
random variables.
axis: int, optionnal
Axis along which the mean and variance are calculated.
@@ -53,13 +53,13 @@ def test_fastica(add_noise=False):
# Mixing angle
phi = 0.6
- mixing = np.array([[np.cos(phi), np.sin(phi)],
+ mixing = np.array([[np.cos(phi), np.sin(phi)],
[np.sin(phi), -np.cos(phi)]])
m = np.dot(mixing, s)
if add_noise:
- m += 0.1*np.random.randn(2, 1000)
-
+ m += 0.1*np.random.randn(2, 1000)
+
center_and_norm(m)
algorithm = ['parallel', 'deflation']
@@ -118,14 +118,14 @@ def test_non_square_fastica(add_noise=False):
if add_noise:
m += 0.1*np.random.randn(6, n_samples)
-
+
center_and_norm(m)
k_, mixing_, s_ = fastica.fastica(m, n_comp=2)
# Check that the mixing model described in the docstring holds:
np.testing.assert_almost_equal(s_, np.dot(np.dot(mixing_, k_), m))
-
+
center_and_norm(s_)
s1_, s2_ = s_
# Check to see if the sources have been estimated
diff --git a/scikits/learn/tests/test_gmm.py b/scikits/learn/tests/test_gmm.py
index 46d514e10d72a662588c4b4751e92de8fd6e3784..215944efe5c26f30ef87596d5f3f2d81ef59b5e5 100644
--- a/scikits/learn/tests/test_gmm.py
+++ b/scikits/learn/tests/test_gmm.py
@@ -54,7 +54,7 @@ def test_sample_gaussian():
Test sample generation from gmm.sample_gaussian where covariance
is diagonal, spherical and full
"""
-
+
n_dim, n_samples = 2, 300
axis = 1
mu = np.random.randint(10) * np.random.rand(n_dim)
diff --git a/scikits/learn/tests/test_hmm.py b/scikits/learn/tests/test_hmm.py
index b19a5d44f4327182a7708f45a96a346186fc2cdd..69c9bdf74ead513c30a9416c72f332d33befddda 100644
--- a/scikits/learn/tests/test_hmm.py
+++ b/scikits/learn/tests/test_hmm.py
@@ -204,7 +204,7 @@ class TestBaseHMM(SeedRandomNumberGeneratorTestCase):
np.zeros((n_states - 2, n_states)))
-def train_hmm_and_keep_track_of_log_likelihood(hmm, obs, n_iter=1, **kwargs):
+def train_hmm_and_keep_track_of_log_likelihood(hmm, obs, n_iter=1, **kwargs):
hmm.fit(obs, n_iter=1, **kwargs)
loglikelihoods = []
for n in xrange(n_iter):
diff --git a/scikits/learn/tests/test_neighbors.py b/scikits/learn/tests/test_neighbors.py
index 05bd276b8604d6496cd12b6bb019739da5a3a023..a7dbc990fcd1a15a1ac87147b8a176a51e79be13 100644
--- a/scikits/learn/tests/test_neighbors.py
+++ b/scikits/learn/tests/test_neighbors.py
@@ -48,4 +48,4 @@ def test_neighbors_2D():
prediction = knn.predict([[0, .1], [0, -.1], [.1, 0], [-.1, 0]])
assert_array_equal(prediction, [0, 1, 0, 1])
-
+
diff --git a/scikits/learn/tests/test_pipeline.py b/scikits/learn/tests/test_pipeline.py
index 9e8bdbdbdfb60a83d870b46df9d4ffe3f1f69f9e..edec37420c6492d11523f8c9a93d1309bee88d01 100644
--- a/scikits/learn/tests/test_pipeline.py
+++ b/scikits/learn/tests/test_pipeline.py
@@ -26,12 +26,12 @@ def test_pipeline_init():
assert_raises(TypeError, Pipeline)
# Check that we can't instantiate pipelines with objects without fit
# method
- pipe = assert_raises(AssertionError, Pipeline,
+ pipe = assert_raises(AssertionError, Pipeline,
[('svc', IncorrectT)])
# Smoke test with only an estimator
clf = T()
pipe = Pipeline([('svc', clf)])
- assert_equal(pipe._get_params(deep=True),
+ assert_equal(pipe._get_params(deep=True),
dict(svc__a=None, svc__b=None, svc=clf))
# Check that params are set
@@ -39,7 +39,7 @@ def test_pipeline_init():
assert_equal(clf.a, 0.1)
# Smoke test the repr:
repr(pipe)
-
+
# Test with two objects
clf = SVC()
filter1 = SelectKBest(f_classif)
diff --git a/scikits/learn/utils/_csgraph.py b/scikits/learn/utils/_csgraph.py
index 535ac4cd473a42046a8bbfd73c63f735dde7b4a0..e395c6b1d8ad73fa76c468d9c633717a57e7bdf9 100644
--- a/scikits/learn/utils/_csgraph.py
+++ b/scikits/learn/utils/_csgraph.py
@@ -54,7 +54,7 @@ def cs_graph_components(x):
>>> D[0,1] = D[1,0] = 1
>>> cs_graph_components(D)
(3, array([0, 0, 1, 2]))
- >>> from scipy.sparse import dok_matrix
+ >>> from scipy.sparse import dok_matrix
>>> cs_graph_components(dok_matrix(D))
(3, array([0, 0, 1, 2]))
@@ -63,7 +63,7 @@ def cs_graph_components(x):
shape = x.shape
except AttributeError:
raise ValueError(_msg0)
-
+
if not ((len(x.shape) == 2) and (x.shape[0] == x.shape[1])):
raise ValueError(_msg1 % x.shape)
@@ -71,7 +71,7 @@ def cs_graph_components(x):
x = x.tocsr()
else:
x = csr_matrix(x)
-
+
label = np.empty((shape[0],), dtype=x.indptr.dtype)
n_comp = _cs_graph_components(shape[0], x.indptr, x.indices, label)
diff --git a/scikits/learn/utils/bench.py b/scikits/learn/utils/bench.py
index f1984019ef21ae2277c20c4a3e8535822648147b..40f1f2a9ec36786fc0eaaf9cce4aae3ee5a802e0 100644
--- a/scikits/learn/utils/bench.py
+++ b/scikits/learn/utils/bench.py
@@ -14,4 +14,4 @@ def total_seconds(delta):
return delta.seconds + delta.microseconds * mu_sec
-
+
diff --git a/scikits/learn/utils/fixes.py b/scikits/learn/utils/fixes.py
index 9bb5a872d8019e62ea6a719946d016a59dcb1ad4..52557f62fe66c224ac9fba0b800db852fdb8562a 100644
--- a/scikits/learn/utils/fixes.py
+++ b/scikits/learn/utils/fixes.py
@@ -18,15 +18,15 @@ def _unique(ar, return_index=False, return_inverse=False):
return np.asarray(items)
else:
ar = np.asanyarray(ar).flatten()
-
+
if ar.size == 0:
if return_inverse and return_index:
return ar, np.empty(0, np.bool), np.empty(0, np.bool)
elif return_inverse or return_index:
return ar, np.empty(0, np.bool)
- else:
+ else:
return ar
-
+
if return_inverse or return_index:
perm = ar.argsort()
aux = ar[perm]
diff --git a/scikits/learn/utils/graph.py b/scikits/learn/utils/graph.py
index f3b94957ed52c99241445767a649ad6af889838f..00269ed24909a17fc4509fd0c5beed842df9b5ee 100644
--- a/scikits/learn/utils/graph.py
+++ b/scikits/learn/utils/graph.py
@@ -1,11 +1,11 @@
"""
Graph utilities and algorithms
-Graphs are represented with their adjacency matrices, preferably using
+Graphs are represented with their adjacency matrices, preferably using
sparse matrices.
"""
-# Authors: Aric Hagberg <hagberg@lanl.gov>
+# Authors: Aric Hagberg <hagberg@lanl.gov>
# Gael Varoquaux <gael.varoquaux@normalesup.org>
# License: BSD
@@ -55,12 +55,12 @@ def single_source_shortest_path_length(graph, source, cutoff=None):
this_level = next_level # advance to next level
next_level = set() # and start a new list (fringe)
for v in this_level:
- if v not in seen:
+ if v not in seen:
seen[v] = level # set the level of vertex v
neighbors = np.array(graph.rows[v])
# Restrict to the upper triangle
neighbors = neighbors[neighbors > v]
- next_level.update(neighbors)
+ next_level.update(neighbors)
if cutoff is not None and cutoff <= level:
break
level += 1
@@ -131,7 +131,7 @@ def _graph_laplacian_dense(graph, normed=False, return_diag=False):
if return_diag:
return lap, w
return lap
-
+
def graph_laplacian(graph, normed=False, return_diag=False):
""" Return the Laplacian of the given graph.
@@ -146,4 +146,4 @@ def graph_laplacian(graph, normed=False, return_diag=False):
# We have a numpy array
return _graph_laplacian_dense(graph, normed=normed,
return_diag=return_diag)
-
+
diff --git a/scikits/learn/utils/sparsetools/setup.py b/scikits/learn/utils/sparsetools/setup.py
index 57ca85201ed39f6e25860dccd518f429af772318..d9cbe508c8256dba6361cec6d1437e9fc90f10d3 100644
--- a/scikits/learn/utils/sparsetools/setup.py
+++ b/scikits/learn/utils/sparsetools/setup.py
@@ -8,7 +8,7 @@ def configuration(parent_package='',top_path=None):
sources = [ fmt + '_wrap.cxx' ]
depends = [ fmt + '.h' ]
config.add_extension('_' + fmt, sources=sources,
- define_macros=[('__STDC_FORMAT_MACROS', 1)],
+ define_macros=[('__STDC_FORMAT_MACROS', 1)],
depends=depends)
return config
diff --git a/setup.py b/setup.py
index 408c2211f55b433ab9727f2fd3a194bd5492894f..daa16909d1e1064028cc672626e5c56c05cb2f21 100644
--- a/setup.py
+++ b/setup.py
@@ -8,7 +8,7 @@ descr = """A set of python modules for machine learning and data mining"""
import os
-DISTNAME = 'scikits.learn'
+DISTNAME = 'scikits.learn'
DESCRIPTION = 'A set of python modules for machine learning and data mining'
LONG_DESCRIPTION = descr
MAINTAINER = 'Fabian Pedregosa'
@@ -46,7 +46,7 @@ if __name__ == "__main__":
download_url = DOWNLOAD_URL,
long_description = LONG_DESCRIPTION,
zip_safe=False, # the package can run out of an .egg file
- classifiers =
+ classifiers =
['Intended Audience :: Science/Research',
'Intended Audience :: Developers',
'License :: OSI Approved',