diff --git a/benchmarks/bench_glmnet.py b/benchmarks/bench_glmnet.py
index c8779d9c93557a3a6ab6b665ba24c3d06187000d..2b866eb09b9cfd4e71b6e373ea7b270ce1193cb2 100644
--- a/benchmarks/bench_glmnet.py
+++ b/benchmarks/bench_glmnet.py
@@ -63,7 +63,7 @@ if __name__ == '__main__':
print '=================='
X, Y, coef_ = make_regression(
- n_samples=(i * step) + n_test_samples, n_features=n_features,
+ n_samples=(i * step) + n_test_samples, n_features=n_features,
noise=0.1, n_informative=n_informative, coef=True)
X_test = X[-n_test_samples:]
@@ -103,7 +103,7 @@ if __name__ == '__main__':
n_informative = n_features / 10
X, Y, coef_ = make_regression(
- n_samples=(i * step) + n_test_samples, n_features=n_features,
+ n_samples=(i * step) + n_test_samples, n_features=n_features,
noise=0.1, n_informative=n_informative, coef=True)
X_test = X[-n_test_samples:]
diff --git a/benchmarks/bench_lasso.py b/benchmarks/bench_lasso.py
index f8f1f24e75d6b35aa65ec866b13822444a053005..b54e6bdeb1e239fdcc927aa82719cb91958644f0 100644
--- a/benchmarks/bench_lasso.py
+++ b/benchmarks/bench_lasso.py
@@ -34,8 +34,8 @@ def compute_bench(alpha, n_samples, n_features, precompute):
len(n_features)))
print '=================='
n_informative = nf // 10
- X, Y, coef_ = make_regression(n_samples=ns, n_features=nf,
- n_informative=n_informative,
+ X, Y, coef_ = make_regression(n_samples=ns, n_features=nf,
+ n_informative=n_informative,
noise=0.1, coef=True)
X /= np.sqrt(np.sum(X**2, axis=0)) # Normalize data
diff --git a/benchmarks/bench_sgd_regression.py b/benchmarks/bench_sgd_regression.py
index 3e5259096cdc8e1b86bf1d027eb1e27769c56c7e..df84c2d1aa90455fbad69a393705779c4ce83c7c 100644
--- a/benchmarks/bench_sgd_regression.py
+++ b/benchmarks/bench_sgd_regression.py
@@ -33,9 +33,9 @@ if __name__ == "__main__":
for i, n_train in enumerate(list_n_samples):
for j, n_features in enumerate(list_n_features):
X, y, coef = make_regression(
- n_samples=n_train + n_test, n_features=n_features,
+ n_samples=n_train + n_test, n_features=n_features,
noise=noise, coef=True)
-
+
X_train = X[:n_train]
y_train = y[:n_train]
X_test = X[n_train:]
diff --git a/examples/decomposition/plot_faces_decomposition.py b/examples/decomposition/plot_faces_decomposition.py
index e3aebb64ea29b96feb498786aa8582dccb55b05a..397b865df700a94b4e708b1293278031d396da4e 100644
--- a/examples/decomposition/plot_faces_decomposition.py
+++ b/examples/decomposition/plot_faces_decomposition.py
@@ -69,7 +69,7 @@ estimators = [
True, False),
('Non-negative components - NMF',
- decomposition.NMF(n_components=n_components, init='nndsvda', beta=5.0,
+ decomposition.NMF(n_components=n_components, init='nndsvda', beta=5.0,
tol=5e-3, sparseness='components'),
False, False),
@@ -78,7 +78,7 @@ estimators = [
True, True),
('Sparse comp. - MiniBatchSparsePCA',
- decomposition.MiniBatchSparsePCA(n_components=n_components, alpha=1e-3,
+ decomposition.MiniBatchSparsePCA(n_components=n_components, alpha=1e-3,
n_iter=100, chunk_size=3),
True, False),
diff --git a/examples/feature_selection_pipeline.py b/examples/feature_selection_pipeline.py
index 025e2c4d671feeddb392c33f293a1db7254ef3c3..8c5454e13d89d1acba42f19646c12b1af2e13ef8 100644
--- a/examples/feature_selection_pipeline.py
+++ b/examples/feature_selection_pipeline.py
@@ -15,7 +15,7 @@ from sklearn.pipeline import Pipeline
# import some data to play with
X, y = samples_generator.make_classification(
- n_features=20, n_informative=3, n_redundant=0,
+ n_features=20, n_informative=3, n_redundant=0,
n_classes=4, n_clusters_per_class=2)
# ANOVA SVM-C
diff --git a/examples/linear_model/plot_bayesian_ridge.py b/examples/linear_model/plot_bayesian_ridge.py
index 7296bb02a21df8baf9ae34148aad3bf4057a5952..e3fad8daa5bb283ca4696468a5a344d2b47c5f8e 100644
--- a/examples/linear_model/plot_bayesian_ridge.py
+++ b/examples/linear_model/plot_bayesian_ridge.py
@@ -62,7 +62,7 @@ pl.legend(loc="best", prop=dict(size=12))
pl.figure(figsize=(6, 5))
pl.title("Histogram of the weights")
pl.hist(clf.coef_, bins=n_features, log=True)
-pl.plot(clf.coef_[relevant_features], 5*np.ones(len(relevant_features)),
+pl.plot(clf.coef_[relevant_features], 5*np.ones(len(relevant_features)),
'ro', label="Relevant features")
pl.ylabel("Features")
pl.xlabel("Values of the weights")
diff --git a/examples/linear_model/plot_lasso_model_selection.py b/examples/linear_model/plot_lasso_model_selection.py
index 133cfa67114cb0a24e8530f154c85cbdb062cbd5..3a10e2563d939283876ee26679088ee493839a4b 100644
--- a/examples/linear_model/plot_lasso_model_selection.py
+++ b/examples/linear_model/plot_lasso_model_selection.py
@@ -82,7 +82,7 @@ def plot_ic_criterion(model, name, color):
alpha_ = model.alpha_
alphas_ = model.alphas_
criterion_ = model.criterion_
- pl.plot(-np.log10(alphas_), criterion_, '--', color=color,
+ pl.plot(-np.log10(alphas_), criterion_, '--', color=color,
linewidth=3, label='%s criterion' % name)
pl.axvline(-np.log10(alpha_), color=color,
linewidth=3, label='alpha: %s estimate' % name)
diff --git a/examples/manifold/plot_compare_methods.py b/examples/manifold/plot_compare_methods.py
index 8be3de5d40323cf48638e948f0d122e100e50d0c..0d4c3b2e4247daa7cc47484b0751c28f0b5f1142 100644
--- a/examples/manifold/plot_compare_methods.py
+++ b/examples/manifold/plot_compare_methods.py
@@ -41,7 +41,7 @@ except:
pl.scatter(X[:, 0], X[:, 2], c=color, cmap=pl.cm.Spectral)
methods = ['standard', 'ltsa', 'hessian', 'modified']
-labels = ['LLE', 'LTSA', 'Hessian LLE', 'Modified LLE']
+labels = ['LLE', 'LTSA', 'Hessian LLE', 'Modified LLE']
for i, method in enumerate(methods):
t0 = time()
diff --git a/examples/manifold/plot_lle_digits.py b/examples/manifold/plot_lle_digits.py
index c0e7eb230d2187d6822a37d6e1555468a82ea4b2..9e4298b5c411902c732313e156bfd8c669f602f4 100644
--- a/examples/manifold/plot_lle_digits.py
+++ b/examples/manifold/plot_lle_digits.py
@@ -88,8 +88,8 @@ plot_embedding(X_projected, "Random Projection of the digits")
print "Computing PCA projection"
t0 = time()
X_pca = decomposition.RandomizedPCA(n_components=2).fit_transform(X)
-plot_embedding(X_pca,
- "Principal Components projection of the digits (time %.2fs)" %
+plot_embedding(X_pca,
+ "Principal Components projection of the digits (time %.2fs)" %
(time() - t0))
#----------------------------------------------------------------------
@@ -100,8 +100,8 @@ X2 = X.copy()
X2.flat[::X.shape[1] + 1] += 0.01 # Make X invertible
t0 = time()
X_lda = lda.LDA(n_components=2).fit_transform(X2, y)
-plot_embedding(X_lda,
- "Linear Discriminant projection of the digits (time %.2fs)" %
+plot_embedding(X_lda,
+ "Linear Discriminant projection of the digits (time %.2fs)" %
(time() - t0))
@@ -111,8 +111,8 @@ print "Computing Isomap embedding"
t0 = time()
X_iso = manifold.Isomap(n_neighbors, out_dim=2).fit_transform(X)
print "Done."
-plot_embedding(X_iso,
- "Isomap projection of the digits (time %.2fs)" %
+plot_embedding(X_iso,
+ "Isomap projection of the digits (time %.2fs)" %
(time() - t0))
@@ -124,8 +124,8 @@ clf = manifold.LocallyLinearEmbedding(n_neighbors, out_dim=2,
t0 = time()
X_lle = clf.fit_transform(X)
print "Done. Reconstruction error: %g" % clf.reconstruction_error_
-plot_embedding(X_lle,
- "Locally Linear Embedding of the digits (time %.2fs)" %
+plot_embedding(X_lle,
+ "Locally Linear Embedding of the digits (time %.2fs)" %
(time() - t0))
@@ -137,8 +137,8 @@ clf = manifold.LocallyLinearEmbedding(n_neighbors, out_dim=2,
t0 = time()
X_mlle = clf.fit_transform(X)
print "Done. Reconstruction error: %g" % clf.reconstruction_error_
-plot_embedding(X_mlle,
- "Modified Locally Linear Embedding of the digits (time %.2fs)" %
+plot_embedding(X_mlle,
+ "Modified Locally Linear Embedding of the digits (time %.2fs)" %
(time() - t0))
@@ -150,8 +150,8 @@ clf = manifold.LocallyLinearEmbedding(n_neighbors, out_dim=2,
t0 = time()
X_hlle = clf.fit_transform(X)
print "Done. Reconstruction error: %g" % clf.reconstruction_error_
-plot_embedding(X_hlle,
- "Hessian Locally Linear Embedding of the digits (time %.2fs)" %
+plot_embedding(X_hlle,
+ "Hessian Locally Linear Embedding of the digits (time %.2fs)" %
(time() - t0))
@@ -164,7 +164,7 @@ t0 = time()
X_ltsa = clf.fit_transform(X)
print "Done. Reconstruction error: %g" % clf.reconstruction_error_
plot_embedding(X_ltsa,
- "Local Tangent Space Alignment of the digits (time %.2fs)" %
+ "Local Tangent Space Alignment of the digits (time %.2fs)" %
(time() - t0))
pl.show()
diff --git a/examples/mlcomp_sparse_document_classification.py b/examples/mlcomp_sparse_document_classification.py
index 48b9d6125c6cda858862019865dd9fa08160c20a..4ac6839538d3b21915d6e8cc200338cec63980c9 100644
--- a/examples/mlcomp_sparse_document_classification.py
+++ b/examples/mlcomp_sparse_document_classification.py
@@ -105,22 +105,22 @@ def benchmark(clf_class, params, name):
t0 = time()
pred = clf.predict(X_test)
print "done in %fs" % (time() - t0)
-
+
print "Classification report on test set for classifier:"
print clf
print
print classification_report(y_test, pred, target_names=news_test.target_names)
-
+
cm = confusion_matrix(y_test, pred)
print "Confusion matrix:"
print cm
-
+
# Show confusion matrix
pl.matshow(cm)
pl.title('Confusion matrix of the %s classifier' % name)
pl.colorbar()
-
-
+
+
print "Testbenching a linear classifier..."
parameters = {
'loss': 'hinge',
diff --git a/examples/plot_digits_classification.py b/examples/plot_digits_classification.py
index 67da225d19b4f773d2f1725408f4f516298dc1f5..e1fc6e300d46abcf65f4b9d3d6b314c1736158c2 100644
--- a/examples/plot_digits_classification.py
+++ b/examples/plot_digits_classification.py
@@ -6,7 +6,7 @@ Recognizing hand-written digits
An example showing how the scikit-learn can be used to recognize images of
hand-written digits.
-This example is commented in the
+This example is commented in the
:ref:`tutorial section of the user manual <getting_started>`.
"""
@@ -27,7 +27,7 @@ digits = datasets.load_digits()
# The data that we are interested in is made of 8x8 images of digits,
# let's have a look at the first 3 images, stored in the `images`
# attribute of the dataset. If we were working from image files, we
-# could load them using pylab.imread. For these images know which
+# could load them using pylab.imread. For these images know which
# digit they represent: it is given in the 'target' of the dataset.
for index, (image, label) in enumerate(zip(digits.images, digits.target)[:4]):
pl.subplot(2, 4, index+1)
diff --git a/sklearn/base.py b/sklearn/base.py
index 7f85b2fb475b37f1bf5e086916e1c205af6ea891..5248a3f9b34278e63776387831be3d523baf21d3 100644
--- a/sklearn/base.py
+++ b/sklearn/base.py
@@ -52,12 +52,12 @@ def clone(estimator, safe=True):
param2 = params_set[name]
if isinstance(param1, np.ndarray):
# For ndarrays, we do not test for complete equality
- equality_test = (param1.shape == param2.shape
- and param1.dtype == param2.dtype
- and param1[0] == param2[0]
+ equality_test = (param1.shape == param2.shape
+ and param1.dtype == param2.dtype
+ and param1[0] == param2[0]
and param1[-1] == param2[-1])
elif sparse.issparse(param1):
- # For sparse matrices equality doesn't work
+ # For sparse matrices equality doesn't work
equality_test = (param1.__class__ == param2.__class__
and param1.data[0] == param2.data[0]
and param1.data[-1] == param2.data[-1]
diff --git a/sklearn/check_build/setup.py b/sklearn/check_build/setup.py
index 685d375401769f0b8179d250830b3b02793fa4f3..41fe65fd286d2d9ed5d79b9a7579991a3f455ab6 100644
--- a/sklearn/check_build/setup.py
+++ b/sklearn/check_build/setup.py
@@ -11,7 +11,7 @@ def configuration(parent_package='', top_path=None):
config.add_extension('_check_build',
sources=['_check_build.c'],
include_dirs=[numpy.get_include()])
-
+
return config
if __name__ == '__main__':
diff --git a/sklearn/cluster/setup.py b/sklearn/cluster/setup.py
index afbf73daad4d7874cee8cd96d321eaa9aa92e3b0..b7c3e75cacbeb0c2ade270ff7e6a3d8f395c1653 100644
--- a/sklearn/cluster/setup.py
+++ b/sklearn/cluster/setup.py
@@ -15,7 +15,7 @@ def configuration(parent_package='', top_path=None):
sources=['_k_means.c'],
include_dirs=[numpy.get_include()]
)
-
+
return config
if __name__ == '__main__':
diff --git a/sklearn/cluster/tests/test_mean_shift.py b/sklearn/cluster/tests/test_mean_shift.py
index d725a0e86bffe8b3628f3e0931687e836c6ab29b..3d3b972831265599b1ac1833c0546c939c67c69d 100644
--- a/sklearn/cluster/tests/test_mean_shift.py
+++ b/sklearn/cluster/tests/test_mean_shift.py
@@ -43,13 +43,13 @@ def test_bin_seeds():
# Data is just 6 points in the plane
X = np.array([[1., 1.], [1.5, 1.5], [1.8, 1.2],
[2., 1.], [2.1, 1.1], [0., 0.]])
-
+
# With a bin coarseness of 1.0 and min_bin_freq of 1, 3 bins should be found
ground_truth = set([(1.,1.), (2.,1.), (0.,0.)])
test_bins = get_bin_seeds(X, 1, 1)
test_result = set([tuple(p) for p in test_bins])
assert_true(len(ground_truth.symmetric_difference(test_result)) == 0)
-
+
# With a bin coarseness of 1.0 and min_bin_freq of 2, 2 bins should be found
ground_truth = set([(1.,1.), (2.,1.)])
test_bins = get_bin_seeds(X, 1, 2)
@@ -61,4 +61,4 @@ def test_bin_seeds():
test_result = set([tuple(p) for p in test_bins])
assert_true(len(test_result) == 6)
-
+
diff --git a/sklearn/covariance/empirical_covariance_.py b/sklearn/covariance/empirical_covariance_.py
index ff488a9ce85fb3ec692c1c1f5b3fe9b003ab63af..fc270be2576e15fe4ff8aacfe46f9275b7dade4c 100644
--- a/sklearn/covariance/empirical_covariance_.py
+++ b/sklearn/covariance/empirical_covariance_.py
@@ -210,5 +210,5 @@ class EmpiricalCovariance(BaseEstimator):
result = squared_norm
else:
result = np.sqrt(squared_norm)
-
+
return result
diff --git a/sklearn/datasets/olivetti_faces.py b/sklearn/datasets/olivetti_faces.py
index ed33eb15d23437ee3e9f9c4e79ee9d3d2a7868ba..6ce33ebfd19d5c40b4d65f4d4826f6b75f46547d 100644
--- a/sklearn/datasets/olivetti_faces.py
+++ b/sklearn/datasets/olivetti_faces.py
@@ -52,7 +52,7 @@ def fetch_olivetti_faces(data_home=None, shuffle=False, random_state=0,
all scikit learn data is stored in '~/scikit_learn_data' subfolders.
shuffle : boolean, optional
- If True the order of the dataset is shuffled to avoid having
+ If True the order of the dataset is shuffled to avoid having
images of the same person grouped.
download_if_missing: optional, True by default
diff --git a/sklearn/datasets/twenty_newsgroups.py b/sklearn/datasets/twenty_newsgroups.py
index a103750fb8a491854abf1489cc347e1ea6621317..cd06b6aafb832d6c042a61108d76e31b5630725f 100644
--- a/sklearn/datasets/twenty_newsgroups.py
+++ b/sklearn/datasets/twenty_newsgroups.py
@@ -142,7 +142,7 @@ def fetch_20newsgroups(data_home=None, subset='train', categories=None,
cache_path=cache_path)
else:
raise IOError('20Newsgroups dataset not found')
-
+
if subset in ('train', 'test'):
data = cache[subset]
elif subset == 'all':
diff --git a/sklearn/externals/joblib/__init__.py b/sklearn/externals/joblib/__init__.py
index 581a4d506378782f56962c6d7893226008efcdc1..a6117d133e1ae2dc55af66d0d3316209a027c1e2 100755
--- a/sklearn/externals/joblib/__init__.py
+++ b/sklearn/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 sklearn.externals.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/sklearn/externals/joblib/disk.py b/sklearn/externals/joblib/disk.py
index 79f6797715b912549deb1a8f35919c5e395a55f9..8b026af05ee74b8887d82a79dd831fe99add5899 100755
--- a/sklearn/externals/joblib/disk.py
+++ b/sklearn/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.
@@ -13,7 +13,7 @@ import shutil
import time
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) + ['.']:
@@ -49,7 +49,7 @@ RM_SUBDIRS_RETRY_TIME = 0.1
def rm_subdirs(path, onerror=None):
"""Remove all subdirectories in this path.
-
+
The directory indicated by `path` is left in place, and its subdirectories
are erased.
diff --git a/sklearn/externals/joblib/format_stack.py b/sklearn/externals/joblib/format_stack.py
index 246db3fb1fb38a01d6a6b8341423746bc0c68fa1..c01795e6f27bf361aeb7d5479554a159139e15a4 100755
--- a/sklearn/externals/joblib/format_stack.py
+++ b/sklearn/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/sklearn/externals/joblib/func_inspect.py b/sklearn/externals/joblib/func_inspect.py
index 7899e14d620335b4e3c14903aac0098ed04d029b..c6d0a9214504cabe51099524fe32e6011d3c29eb 100755
--- a/sklearn/externals/joblib/func_inspect.py
+++ b/sklearn/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)
@@ -186,11 +186,11 @@ 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())
)
)
@@ -218,7 +218,7 @@ 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,
@@ -226,5 +226,5 @@ 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/sklearn/externals/joblib/hashing.py b/sklearn/externals/joblib/hashing.py
index e00a70768105f43c9bfb109631b0637acefa5332..8183382ce2d0b1427684d084e86066a04e62b9db 100755
--- a/sklearn/externals/joblib/hashing.py
+++ b/sklearn/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/sklearn/externals/joblib/logger.py b/sklearn/externals/joblib/logger.py
index eed6baeb76c0075f1d6a613e7070a93d08668bae..368e52a188fe85cc33272fb1b164e398c55869e6 100755
--- a/sklearn/externals/joblib/logger.py
+++ b/sklearn/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.
@@ -43,7 +43,7 @@ def short_format_time(t):
class Logger(object):
""" Base class for logging messages.
"""
-
+
def __init__(self, depth=3):
"""
Parameters
@@ -99,7 +99,7 @@ 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/sklearn/externals/joblib/memory.py b/sklearn/externals/joblib/memory.py
index d7c22eb404298bc5ede54d822687147acefa3c7d..7486ccc4b830f62536cdd30429a4d0cb15a1f97b 100755
--- a/sklearn/externals/joblib/memory.py
+++ b/sklearn/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.
@@ -76,9 +76,9 @@ class JobLibCollisionWarning(UserWarning):
# class `MemorizedFunc`
################################################################################
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.
@@ -97,14 +97,14 @@ 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, timestamp=None):
"""
Parameters
@@ -124,7 +124,7 @@ 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. The higher, the more verbose
timestamp: float, optional
The reference time from which times in tracing messages
@@ -162,7 +162,7 @@ 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:
@@ -192,13 +192,13 @@ class MemorizedFunc(Logger):
depending from it.
In addition, when unpickling, we run the __init__
"""
- return (self.__class__, (self.func, self.cachedir, self.ignore,
+ return (self.__class__, (self.func, self.cachedir, self.ignore,
self.save_npy, self.mmap_mode, self._verbose))
#-------------------------------------------------------------------------
# Private interface
#-------------------------------------------------------------------------
-
+
def _get_func_dir(self, mkdir=True):
""" Get the directory corresponding to the cache for the
function.
@@ -210,7 +210,7 @@ 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
@@ -225,12 +225,12 @@ 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.
@@ -240,7 +240,7 @@ 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.
"""
@@ -252,7 +252,7 @@ class MemorizedFunc(Logger):
func_code_file = os.path.join(func_dir, 'func_code.py')
try:
- if not os.path.exists(func_code_file):
+ if not os.path.exists(func_code_file):
raise IOError
old_func_code, old_first_line = \
extract_first_line(file(func_code_file).read())
@@ -263,14 +263,14 @@ 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
@@ -282,7 +282,7 @@ 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)
@@ -294,7 +294,7 @@ 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)
@@ -305,7 +305,7 @@ 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:
@@ -323,7 +323,7 @@ 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()
@@ -342,7 +342,7 @@ 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,
@@ -390,7 +390,7 @@ 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)
@@ -433,7 +433,7 @@ 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')
@@ -444,7 +444,7 @@ class MemorizedFunc(Logger):
#-------------------------------------------------------------------------
# Private `object` interface
#-------------------------------------------------------------------------
-
+
def __repr__(self):
return '%s(func=%s, cachedir=%s)' % (
self.__class__.__name__,
@@ -460,7 +460,7 @@ 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.
@@ -469,7 +469,7 @@ class Memory(Logger):
#-------------------------------------------------------------------------
# Public interface
#-------------------------------------------------------------------------
-
+
def __init__(self, cachedir, save_npy=True, mmap_mode=None,
verbose=1):
"""
@@ -488,7 +488,7 @@ 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
@@ -527,13 +527,13 @@ 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:
@@ -576,7 +576,7 @@ class Memory(Logger):
#-------------------------------------------------------------------------
# Private `object` interface
#-------------------------------------------------------------------------
-
+
def __repr__(self):
return '%s(cachedir=%s)' % (
self.__class__.__name__,
@@ -590,7 +590,7 @@ class Memory(Logger):
In addition, when unpickling, we run the __init__
"""
# We need to remove 'joblib' from the end of cachedir
- return (self.__class__, (self.cachedir[:-7],
+ return (self.__class__, (self.cachedir[:-7],
self.save_npy, self.mmap_mode, self._verbose))
diff --git a/sklearn/externals/joblib/my_exceptions.py b/sklearn/externals/joblib/my_exceptions.py
index 9f7c9edac8956e10df939dd0494d4c9e08775fa5..f81b149b05de89ec70061569a5c0322313357870 100755
--- a/sklearn/externals/joblib/my_exceptions.py
+++ b/sklearn/externals/joblib/my_exceptions.py
@@ -32,7 +32,7 @@ class TransportableException(JoblibException):
""" An exception containing all the info to wrap an original
exception and recreate it.
"""
-
+
def __init__(self, message, etype):
self.message = message
self.etype = etype
@@ -41,7 +41,7 @@ class TransportableException(JoblibException):
# For pickling
return self.__class__, (self.message, self.etype), {}
-
+
_exception_mapping = dict()
@@ -55,7 +55,7 @@ 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__),
)
@@ -88,7 +88,7 @@ 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/sklearn/externals/joblib/numpy_pickle.py b/sklearn/externals/joblib/numpy_pickle.py
index 54bc938d26ae08cbc24eea354cc006f5431a4d33..111b90d52ec219cc7b45ead494ab8ec8dd7d65b4 100755
--- a/sklearn/externals/joblib/numpy_pickle.py
+++ b/sklearn/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.
@@ -50,7 +50,7 @@ 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):
@@ -88,8 +88,8 @@ class NumpyUnpickler(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.
@@ -116,7 +116,7 @@ class NumpyUnpickler(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
@@ -134,7 +134,7 @@ 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/sklearn/externals/joblib/parallel.py b/sklearn/externals/joblib/parallel.py
index 312f4ee9a8d6da82843db71151125b7f0c8d2471..5a66abff078a674293de771d959332a6b32d255e 100755
--- a/sklearn/externals/joblib/parallel.py
+++ b/sklearn/externals/joblib/parallel.py
@@ -54,7 +54,7 @@ class WorkerInterrupt(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.
"""
@@ -109,7 +109,7 @@ class ImmediateApply(object):
################################################################################
class CallBack(object):
- """ Callback used by parallel: it is used for progress reporting, and
+ """ Callback used by parallel: it is used for progress reporting, and
to add data to be processed
"""
def __init__(self, index, parallel):
@@ -145,8 +145,8 @@ class CallBack(object):
writer = sys.stdout.write
writer('[%s]: Done %3i out of %s |elapsed: %s remaining: %s\n'
% (self.parallel,
- self.index+1,
- total,
+ self.index+1,
+ total,
short_format_time(elapsed_time),
short_format_time(remaining_time),
))
@@ -214,7 +214,7 @@ 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
@@ -236,7 +236,7 @@ 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
@@ -245,14 +245,14 @@ 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
___________________________________________________________________________
@@ -269,7 +269,7 @@ class Parallel(Logger):
... for i in range(6):
... print 'Produced %s' % i
... yield i
-
+
>>> out = Parallel(n_jobs=2, verbose=100, pre_dispatch='1.5*n_jobs')(
... delayed(sqrt)(i) for i in producer()) #doctest: +SKIP
Produced 0
@@ -294,7 +294,7 @@ class Parallel(Logger):
def dispatch(self, func, args, kwargs):
- """ Queue the function for computing, with or without multiprocessing
+ """ Queue the function for computing, with or without multiprocessing
"""
if self._pool is None:
job = ImmediateApply(func, args, kwargs)
@@ -325,7 +325,7 @@ class Parallel(Logger):
self._dispatch_amount += 1
while self._dispatch_amount:
try:
- # XXX: possible race condition shuffling the order of
+ # XXX: possible race condition shuffling the order of
# dispatchs in the next two lines.
func, args, kwargs = self._iterable.next()
self.dispatch(func, args, kwargs)
@@ -352,7 +352,7 @@ class Parallel(Logger):
try:
self._output.append(job.get())
except tuple(self.exceptions), exception:
- if isinstance(exception,
+ if isinstance(exception,
(KeyboardInterrupt, WorkerInterrupt)):
# We have captured a user interruption, clean up
# everything
@@ -361,7 +361,7 @@ class Parallel(Logger):
self._pool.terminate()
raise exception
elif isinstance(exception, TransportableException):
- # 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(
@@ -371,7 +371,7 @@ class Parallel(Logger):
report = """Multiprocessing exception:
%s
---------------------------------------------------------------------------
-Sub-process traceback:
+Sub-process traceback:
---------------------------------------------------------------------------
%s""" % (
this_report,
@@ -418,7 +418,7 @@ Sub-process traceback:
try:
for function, args, kwargs in iterable:
self.dispatch(function, args, kwargs)
-
+
self.retrieve()
finally:
if n_jobs > 1:
diff --git a/sklearn/externals/joblib/test/common.py b/sklearn/externals/joblib/test/common.py
index de6050d2d19d7f626737a70752e2c3b0494e705e..53894e3177b558a50dbd308f5786277fa467c7dd 100755
--- a/sklearn/externals/joblib/test/common.py
+++ b/sklearn/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/sklearn/externals/joblib/test/test_format_stack.py b/sklearn/externals/joblib/test/test_format_stack.py
index 39ee599b0e7910061204e8468f47d7d7a99bbbae..31292ac69c66c476a0ce2f7f6fe7ce48d91398f5 100755
--- a/sklearn/externals/joblib/test/test_format_stack.py
+++ b/sklearn/externals/joblib/test/test_format_stack.py
@@ -1,8 +1,8 @@
"""
-Unit tests for the stack formatting utilities
+Unit tests for the stack formatting 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.
diff --git a/sklearn/externals/joblib/test/test_func_inspect.py b/sklearn/externals/joblib/test/test_func_inspect.py
index a52adf51f2878aa01aca1df4762da3eafa8f2fad..12872ace0108901452af5338cd610626bf7bff4b 100755
--- a/sklearn/externals/joblib/test/test_func_inspect.py
+++ b/sklearn/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.
@@ -14,7 +14,7 @@ from ..func_inspect import filter_args, get_func_name, get_func_code
from ..memory import Memory
################################################################################
-# Module-level functions, for tests
+# Module-level functions, for tests
def f(x, y=0):
pass
@@ -65,7 +65,7 @@ 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})
@@ -81,24 +81,24 @@ def test_filter_varargs():
def test_filter_kwargs():
- nose.tools.assert_equal(filter_args(k, [], 1, 2, ee=2),
+ nose.tools.assert_equal(filter_args(k, [], 1, 2, ee=2),
{'*': [1, 2], '**':{'ee':2}})
- nose.tools.assert_equal(filter_args(k, [], 3, 4),
+ nose.tools.assert_equal(filter_args(k, [], 3, 4),
{'*': [3, 4], '**':{}})
def test_filter_args_2():
- 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}})
-
+
nose.tools.assert_raises(ValueError, filter_args, f, 'a', None)
# Check that we capture an undefined argument
nose.tools.assert_raises(ValueError, filter_args, f, ['a'], None)
ff = functools.partial(f, 1)
# filter_args has to special-case partial
- nose.tools.assert_equal(filter_args(ff, [], 1),
+ nose.tools.assert_equal(filter_args(ff, [], 1),
{'*': [1], '**':{}})
- nose.tools.assert_equal(filter_args(ff, ['y'], 1),
+ nose.tools.assert_equal(filter_args(ff, ['y'], 1),
{'*': [1], '**':{}})
@@ -114,15 +114,15 @@ def test_func_inspect_errors():
nose.tools.assert_equal(get_func_name('a'.lower)[-1], 'lower')
nose.tools.assert_equal(get_func_code('a'.lower)[1:], (None, -1))
ff = lambda x: x
- nose.tools.assert_equal(get_func_name(ff, win_characters=False)[-1],
+ nose.tools.assert_equal(get_func_name(ff, win_characters=False)[-1],
'<lambda>')
- nose.tools.assert_equal(get_func_code(ff)[1],
+ nose.tools.assert_equal(get_func_code(ff)[1],
__file__.replace('.pyc', '.py'))
# Simulate a function defined in __main__
ff.__module__ = '__main__'
- nose.tools.assert_equal(get_func_name(ff, win_characters=False)[-1],
+ nose.tools.assert_equal(get_func_name(ff, win_characters=False)[-1],
'<lambda>')
- nose.tools.assert_equal(get_func_code(ff)[1],
+ nose.tools.assert_equal(get_func_code(ff)[1],
__file__.replace('.pyc', '.py'))
@@ -133,7 +133,7 @@ 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/sklearn/externals/joblib/test/test_logger.py b/sklearn/externals/joblib/test/test_logger.py
index ac85a89d14a5cbabafe00c84192014d898300611..187066360dacba8a895770bd3d1a6caae62e7fea 100755
--- a/sklearn/externals/joblib/test/test_logger.py
+++ b/sklearn/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.
@@ -28,7 +28,7 @@ def setup():
if os.path.exists(cachedir):
shutil.rmtree(cachedir)
env['dir'] = cachedir
-
+
def teardown():
""" Test teardown.
@@ -50,14 +50,14 @@ 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')
printed_text = sys.stderr.getvalue()
# Use regexps to be robust to time variations
match = r"Foo: 0\..s, 0\.0min\nFoo: 0\..s, 0.0min\nFoo: .\..s, 0.0min\n"
if not re.match(match, printed_text):
- raise AssertionError('Excepted %s, got %s' %
+ raise AssertionError('Excepted %s, got %s' %
(match, printed_text))
finally:
sys.stderr = orig_stderr
diff --git a/sklearn/externals/joblib/test/test_memory.py b/sklearn/externals/joblib/test/test_memory.py
index 335ab45341d535c7877c504209d1c00c1cd03bc7..14fc3b1b5bdcc69e32ced74f5aca5e0f16f84be1 100755
--- a/sklearn/externals/joblib/test/test_memory.py
+++ b/sklearn/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/sklearn/externals/joblib/test/test_my_exceptions.py b/sklearn/externals/joblib/test/test_my_exceptions.py
index 0728a599babe738729f256e173b88dd9a3be84d1..3c9202e57d9db1ed8f8c3245c005b3087d12552d 100755
--- a/sklearn/externals/joblib/test/test_my_exceptions.py
+++ b/sklearn/externals/joblib/test/test_my_exceptions.py
@@ -7,7 +7,7 @@ from .. import my_exceptions
def test_inheritance():
assert_true(isinstance(my_exceptions.JoblibNameError(), NameError))
- assert_true(isinstance(my_exceptions.JoblibNameError(),
+ assert_true(isinstance(my_exceptions.JoblibNameError(),
my_exceptions.JoblibException))
assert_true(my_exceptions.JoblibNameError is
my_exceptions._mk_exception(NameError)[0])
diff --git a/sklearn/externals/joblib/test/test_numpy_pickle.py b/sklearn/externals/joblib/test/test_numpy_pickle.py
index 6182c89adc99b4b200f26d8ca700604464bd76ff..0d8175c5105fb40abb0dd3ad7ab9f16a895f7412 100755
--- a/sklearn/externals/joblib/test/test_numpy_pickle.py
+++ b/sklearn/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/sklearn/externals/joblib/test/test_parallel.py b/sklearn/externals/joblib/test/test_parallel.py
index 834d7273cb9cfd6525d0cd35b6b45e2819a2cf9f..2599acb393439c3a178716305fcaa0591e02449e 100755
--- a/sklearn/externals/joblib/test/test_parallel.py
+++ b/sklearn/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) 2010-2011 Gael Varoquaux
# License: BSD Style, 3 clauses.
@@ -61,12 +61,12 @@ 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.
@@ -74,7 +74,7 @@ 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))
)
@@ -135,12 +135,12 @@ def test_dispatch_one_job():
yield i
Parallel(n_jobs=1)(delayed(consumer)(queue, x) for x in producer())
- nose.tools.assert_equal(queue,
- ['Produced 0', 'Consumed 0',
- 'Produced 1', 'Consumed 1',
- 'Produced 2', 'Consumed 2',
- 'Produced 3', 'Consumed 3',
- 'Produced 4', 'Consumed 4',
+ nose.tools.assert_equal(queue,
+ ['Produced 0', 'Consumed 0',
+ 'Produced 1', 'Consumed 1',
+ 'Produced 2', 'Consumed 2',
+ 'Produced 3', 'Consumed 3',
+ 'Produced 4', 'Consumed 4',
'Produced 5', 'Consumed 5']
)
nose.tools.assert_equal(len(queue), 12)
@@ -161,8 +161,8 @@ def test_dispatch_multiprocessing():
Parallel(n_jobs=2, pre_dispatch=3)(delayed(consumer)(queue, i)
for i in producer())
- nose.tools.assert_equal(list(queue)[:4],
- ['Produced 0', 'Produced 1', 'Produced 2',
+ nose.tools.assert_equal(list(queue)[:4],
+ ['Produced 0', 'Produced 1', 'Produced 2',
'Consumed 0', ])
nose.tools.assert_equal(len(queue), 12)
diff --git a/sklearn/feature_selection/tests/test_feature_select.py b/sklearn/feature_selection/tests/test_feature_select.py
index 4d4771665af1b3e6832b28719bdeff3f022a699c..4214225e1cf8a6965a7c52fff3f1de666b375254 100644
--- a/sklearn/feature_selection/tests/test_feature_select.py
+++ b/sklearn/feature_selection/tests/test_feature_select.py
@@ -30,9 +30,9 @@ def test_f_classif():
Test whether the F test yields meaningful results
on a simple simulated classification problem
"""
- X, Y = make_classification(n_samples=200, n_features=20,
- n_informative=3, n_redundant=2,
- n_repeated=0, n_classes=8,
+ X, Y = make_classification(n_samples=200, n_features=20,
+ n_informative=3, n_redundant=2,
+ n_repeated=0, n_classes=8,
n_clusters_per_class=1, flip_y=0.0,
class_sep=10, shuffle=False, random_state=0)
@@ -49,7 +49,7 @@ def test_f_regression():
Test whether the F test yields meaningful results
on a simple simulated regression problem
"""
- X, Y = make_regression(n_samples=200, n_features=20,
+ X, Y = make_regression(n_samples=200, n_features=20,
n_informative=5, shuffle=False, random_state=0)
F, pv = f_regression(X, Y)
@@ -65,9 +65,9 @@ def test_f_classif_multi_class():
Test whether the F test yields meaningful results
on a simple simulated classification problem
"""
- X, Y = make_classification(n_samples=200, n_features=20,
- n_informative=3, n_redundant=2,
- n_repeated=0, n_classes=8,
+ X, Y = make_classification(n_samples=200, n_features=20,
+ n_informative=3, n_redundant=2,
+ n_repeated=0, n_classes=8,
n_clusters_per_class=1, flip_y=0.0,
class_sep=10, shuffle=False, random_state=0)
@@ -85,9 +85,9 @@ def test_select_percentile_classif():
gets the correct items in a simple classification problem
with the percentile heuristic
"""
- X, Y = make_classification(n_samples=200, n_features=20,
- n_informative=3, n_redundant=2,
- n_repeated=0, n_classes=8,
+ X, Y = make_classification(n_samples=200, n_features=20,
+ n_informative=3, n_redundant=2,
+ n_repeated=0, n_classes=8,
n_clusters_per_class=1, flip_y=0.0,
class_sep=10, shuffle=False, random_state=0)
@@ -110,9 +110,9 @@ def test_select_kbest_classif():
gets the correct items in a simple classification problem
with the k best heuristic
"""
- X, Y = make_classification(n_samples=200, n_features=20,
- n_informative=3, n_redundant=2,
- n_repeated=0, n_classes=8,
+ X, Y = make_classification(n_samples=200, n_features=20,
+ n_informative=3, n_redundant=2,
+ n_repeated=0, n_classes=8,
n_clusters_per_class=1, flip_y=0.0,
class_sep=10, shuffle=False, random_state=0)
@@ -133,9 +133,9 @@ def test_select_fpr_classif():
gets the correct items in a simple classification problem
with the fpr heuristic
"""
- X, Y = make_classification(n_samples=200, n_features=20,
- n_informative=3, n_redundant=2,
- n_repeated=0, n_classes=8,
+ X, Y = make_classification(n_samples=200, n_features=20,
+ n_informative=3, n_redundant=2,
+ n_repeated=0, n_classes=8,
n_clusters_per_class=1, flip_y=0.0,
class_sep=10, shuffle=False, random_state=0)
@@ -156,9 +156,9 @@ def test_select_fdr_classif():
gets the correct items in a simple classification problem
with the fpr heuristic
"""
- X, Y = make_classification(n_samples=200, n_features=20,
- n_informative=3, n_redundant=2,
- n_repeated=0, n_classes=8,
+ X, Y = make_classification(n_samples=200, n_features=20,
+ n_informative=3, n_redundant=2,
+ n_repeated=0, n_classes=8,
n_clusters_per_class=1, flip_y=0.0,
class_sep=10, shuffle=False, random_state=0)
@@ -179,9 +179,9 @@ def test_select_fwe_classif():
gets the correct items in a simple classification problem
with the fpr heuristic
"""
- X, Y = make_classification(n_samples=200, n_features=20,
- n_informative=3, n_redundant=2,
- n_repeated=0, n_classes=8,
+ X, Y = make_classification(n_samples=200, n_features=20,
+ n_informative=3, n_redundant=2,
+ n_repeated=0, n_classes=8,
n_clusters_per_class=1, flip_y=0.0,
class_sep=10, shuffle=False, random_state=0)
@@ -205,7 +205,7 @@ def test_select_percentile_regression():
gets the correct items in a simple regression problem
with the percentile heuristic
"""
- X, Y = make_regression(n_samples=200, n_features=20,
+ X, Y = make_regression(n_samples=200, n_features=20,
n_informative=5, shuffle=False, random_state=0)
univariate_filter = SelectPercentile(f_regression, percentile=25)
@@ -227,7 +227,7 @@ def test_select_percentile_regression_full():
Test whether the relative univariate feature selection
selects all features when '100%' is asked.
"""
- X, Y = make_regression(n_samples=200, n_features=20,
+ X, Y = make_regression(n_samples=200, n_features=20,
n_informative=5, shuffle=False, random_state=0)
univariate_filter = SelectPercentile(f_regression, percentile=100)
@@ -246,7 +246,7 @@ def test_select_kbest_regression():
gets the correct items in a simple regression problem
with the k best heuristic
"""
- X, Y = make_regression(n_samples=200, n_features=20,
+ X, Y = make_regression(n_samples=200, n_features=20,
n_informative=5, shuffle=False, random_state=0)
univariate_filter = SelectKBest(f_regression, k=5)
@@ -266,7 +266,7 @@ def test_select_fpr_regression():
gets the correct items in a simple regression problem
with the fpr heuristic
"""
- X, Y = make_regression(n_samples=200, n_features=20,
+ X, Y = make_regression(n_samples=200, n_features=20,
n_informative=5, shuffle=False, random_state=0)
univariate_filter = SelectFpr(f_regression, alpha=0.01)
@@ -287,7 +287,7 @@ def test_select_fdr_regression():
gets the correct items in a simple regression problem
with the fdr heuristic
"""
- X, Y = make_regression(n_samples=200, n_features=20,
+ X, Y = make_regression(n_samples=200, n_features=20,
n_informative=5, shuffle=False, random_state=0)
univariate_filter = SelectFdr(f_regression, alpha=0.01)
@@ -307,7 +307,7 @@ def test_select_fwe_regression():
gets the correct items in a simple regression problem
with the fwe heuristic
"""
- X, Y = make_regression(n_samples=200, n_features=20,
+ X, Y = make_regression(n_samples=200, n_features=20,
n_informative=5, shuffle=False, random_state=0)
univariate_filter = SelectFwe(f_regression, alpha=0.01)
diff --git a/sklearn/feature_selection/univariate_selection.py b/sklearn/feature_selection/univariate_selection.py
index 3350795ea2f90c9269dcc5e981e5daedd7002d85..2b9c9ea6def8a32584f5dc7a6eccb0c84b23970f 100644
--- a/sklearn/feature_selection/univariate_selection.py
+++ b/sklearn/feature_selection/univariate_selection.py
@@ -379,7 +379,7 @@ class SelectFdr(_AbstractUnivariateFilter):
class SelectFwe(_AbstractUnivariateFilter):
"""
- Filter : Select the p-values corresponding to Family-wise error rate: a
+ Filter : Select the p-values corresponding to Family-wise error rate: a
corrected p-value of alpha
"""
diff --git a/sklearn/grid_search.py b/sklearn/grid_search.py
index 1c92572cb5273c4cdeaa65cdd90bf15898d033ea..c4a756ca2eac9a9b9f549443991156f4d36f7e6e 100644
--- a/sklearn/grid_search.py
+++ b/sklearn/grid_search.py
@@ -182,7 +182,7 @@ class GridSearchCV(BaseEstimator):
cv : integer or crossvalidation generator, optional
If an integer is passed, it is the number of fold (default 3).
- Specific crossvalidation objects can be passed, see
+ Specific crossvalidation objects can be passed, see
sklearn.cross_validation module for the list of possible objects
refit: boolean
diff --git a/sklearn/linear_model/bayes.py b/sklearn/linear_model/bayes.py
index 374f6fcf31374376c48b115ccf464ab57b070001..ba2b2f157c5c9e37da1da4b49e7ec5962bca30d1 100644
--- a/sklearn/linear_model/bayes.py
+++ b/sklearn/linear_model/bayes.py
@@ -120,7 +120,7 @@ class BayesianRidge(LinearModel):
fit_intercept=True, normalize=False,
overwrite_X=False, verbose=False):
self.n_iter = n_iter
- self.tol = tol
+ self.tol = tol
self.alpha_1 = alpha_1
self.alpha_2 = alpha_2
self.lambda_1 = lambda_1
diff --git a/sklearn/manifold/tests/test_locally_linear.py b/sklearn/manifold/tests/test_locally_linear.py
index 1a89516d623458f657edf623006265f9e8e45ec2..9344bff69aed37a3fa72979c64a7df151c1718e0 100644
--- a/sklearn/manifold/tests/test_locally_linear.py
+++ b/sklearn/manifold/tests/test_locally_linear.py
@@ -62,7 +62,7 @@ def test_lle_manifold():
assert_lower(reconstruction_error, tol)
for solver in eigen_solvers:
- clf.set_params(eigen_solver=solver)
+ clf.set_params(eigen_solver=solver)
clf.fit(X)
assert clf.embedding_.shape[1] == out_dim
reconstruction_error = np.linalg.norm(
diff --git a/sklearn/metrics/pairwise.py b/sklearn/metrics/pairwise.py
index 667ec7533cafc1e4483f39e32ed05faadc4396a3..2c513bbdb86dfb261d0f15e1298d92ec75e29d7d 100644
--- a/sklearn/metrics/pairwise.py
+++ b/sklearn/metrics/pairwise.py
@@ -155,8 +155,8 @@ def euclidean_distances(X, Y=None, Y_norm_squared=None, squared=False):
distances = np.maximum(distances, 0)
if X is Y:
- # Ensure that distances between vectors and themselves are set to 0.0.
- # This may not be the case due to floating point rounding errors.
+ # Ensure that distances between vectors and themselves are set to 0.0.
+ # This may not be the case due to floating point rounding errors.
distances.flat[::distances.shape[0] + 1] = 0.0
return distances if squared else np.sqrt(distances)
diff --git a/sklearn/svm/tests/test_sparse.py b/sklearn/svm/tests/test_sparse.py
index fd5f3335e8881da7e2b81fa8ce310c4a7c352786..57ed8655358ae8e426de73ef8627337c2b063eb8 100644
--- a/sklearn/svm/tests/test_sparse.py
+++ b/sklearn/svm/tests/test_sparse.py
@@ -133,7 +133,7 @@ def test_weight():
Test class weights
"""
- X_, y_ = make_classification(n_samples=200, n_features=100,
+ X_, y_ = make_classification(n_samples=200, n_features=100,
weights=[0.833, 0.167], random_state=0)
X_ = scipy.sparse.csr_matrix(X_)
diff --git a/sklearn/svm/tests/test_svm.py b/sklearn/svm/tests/test_svm.py
index 2f9d42bd7f05c104f3389aafa790b724da3b818f..17813589a5e62209663d0ded3ad0a9e5cc3b26e7 100644
--- a/sklearn/svm/tests/test_svm.py
+++ b/sklearn/svm/tests/test_svm.py
@@ -254,9 +254,9 @@ def test_weight():
# so all predicted values belong to class 2
assert_array_almost_equal(clf.predict(X), [2] * 6)
- X_, y_ = make_classification(n_samples=200, n_features=100,
+ X_, y_ = make_classification(n_samples=200, n_features=100,
weights=[0.833, 0.167], random_state=0)
-
+
for clf in (linear_model.LogisticRegression(), svm.LinearSVC(), svm.SVC()):
clf.fit(X_[: 180], y_[: 180], class_weight={0: 5})
y_pred = clf.predict(X_[180:])
diff --git a/sklearn/utils/setup.py b/sklearn/utils/setup.py
index be9d635020f20f818358fbc765e701774f6f526b..da5909ffa2cf33fe513f82da5eeb378e59137d9f 100644
--- a/sklearn/utils/setup.py
+++ b/sklearn/utils/setup.py
@@ -31,7 +31,7 @@ def configuration(parent_package='', top_path=None):
**blas_info
)
-
+
config.add_extension('graph_shortest_path',
sources=['graph_shortest_path.c'],
include_dirs=[numpy.get_include()])
diff --git a/sklearn/utils/tests/test_svd.py b/sklearn/utils/tests/test_svd.py
index 2c10e5c43de519a464ddb482dfb55197d688dd13..41f26e4f30252456bbd801edcebcc066df50c69b 100644
--- a/sklearn/utils/tests/test_svd.py
+++ b/sklearn/utils/tests/test_svd.py
@@ -21,7 +21,7 @@ def test_fast_svd_low_rank():
# generate a matrix X of approximate effective rank `rank` and no noise
# component (very structured signal):
- X = make_low_rank_matrix(n_samples=n_samples, n_features=n_features,
+ X = make_low_rank_matrix(n_samples=n_samples, n_features=n_features,
effective_rank=rank, tail_strength=0.0, random_state=0)
assert_equal(X.shape, (n_samples, n_features))
@@ -58,7 +58,7 @@ def test_fast_svd_low_rank_with_noise():
# generate a matrix X wity structure approximate rank `rank` and an
# important noisy component
- X = make_low_rank_matrix(n_samples=n_samples, n_features=n_features,
+ X = make_low_rank_matrix(n_samples=n_samples, n_features=n_features,
effective_rank=rank, tail_strength=0.5, random_state=0)
assert_equal(X.shape, (n_samples, n_features))
@@ -89,7 +89,7 @@ def test_fast_svd_infinite_rank():
# let us try again without 'low_rank component': just regularly but slowly
# decreasing singular values: the rank of the data matrix is infinite
- X = make_low_rank_matrix(n_samples=n_samples, n_features=n_features,
+ X = make_low_rank_matrix(n_samples=n_samples, n_features=n_features,
effective_rank=rank, tail_strength=1.0, random_state=0)
assert_equal(X.shape, (n_samples, n_features))
@@ -119,7 +119,7 @@ def test_fast_svd_transpose_consistency():
rank = 4
k = 10
- X = make_low_rank_matrix(n_samples=n_samples, n_features=n_features,
+ X = make_low_rank_matrix(n_samples=n_samples, n_features=n_features,
effective_rank=rank, tail_strength=0.5, random_state=0)
assert_equal(X.shape, (n_samples, n_features))