COSMIT pep8

Author: larsmans

sklearn/datasets/tests/test_svmlight_format.py

@@ -260,7 +260,8 @@ def test_dump_concise():
     dump_svmlight_file(X, y, f)
     f.seek(0)
     # make sure it's using the most concise format possible
-    assert_equal(f.readline(), b("1 0:1 1:2.1 2:3.01 3:1.000000000000001 4:1\n"))
+    assert_equal(f.readline(),
+                 b("1 0:1 1:2.1 2:3.01 3:1.000000000000001 4:1\n"))
     assert_equal(f.readline(), b("2.1 0:1000000000 1:2e+18 2:3e+27\n"))
     assert_equal(f.readline(), b("3.01 \n"))
     assert_equal(f.readline(), b("1.000000000000001 \n"))

sklearn/decomposition/nmf.py

@@ -97,7 +97,7 @@ def _initialize_nmf(X, n_components, variant=None, eps=1e-6,
     initialization: A head start for nonnegative
     matrix factorization - Pattern Recognition, 2008
 
-    http://scgroup.hpclab.ceid.upatras.gr/faculty/stratis/Papers/HPCLAB020107.pdf
+    http://tinyurl.com/nndsvd
     """
     check_non_negative(X, "NMF initialization")
     if variant not in (None, 'a', 'ar'):
@@ -359,8 +359,7 @@ class ProjectedGradientNMF(BaseEstimator, TransformerMixin):
     C. Boutsidis, E. Gallopoulos: SVD based
     initialization: A head start for nonnegative
     matrix factorization - Pattern Recognition, 2008
-    http://scgroup.hpclab.ceid.upatras.gr/faculty/stratis/Papers/HPCLAB020107.pdf
-
+    http://tinyurl.com/nndsvd
     """
 
     def __init__(self, n_components=None, init=None, sparseness=None, beta=1,

sklearn/feature_extraction/image.py

@@ -215,6 +215,7 @@ def _compute_n_patches(i_h, i_w, p_h, p_w, max_patches=None):
     else:
         return all_patches
 
+
 def extract_patches(arr, patch_shape=8, extraction_step=1):
     """Extracts patches of any n-dimensional array in place using strides.
 

sklearn/feature_extraction/tests/test_image.py

@@ -186,13 +186,16 @@ def test_patch_extractor_max_patches():
 
     max_patches = 100
     expected_n_patches = len(lenas) * max_patches
-    extr = PatchExtractor(patch_size=(p_h, p_w), max_patches=max_patches, random_state=0)
+    extr = PatchExtractor(patch_size=(p_h, p_w), max_patches=max_patches,
+                          random_state=0)
     patches = extr.transform(lenas)
     assert_true(patches.shape == (expected_n_patches, p_h, p_w))
 
     max_patches = 0.5
-    expected_n_patches = len(lenas) * int((i_h - p_h + 1) * (i_w - p_w + 1) * max_patches)
-    extr = PatchExtractor(patch_size=(p_h, p_w), max_patches=max_patches, random_state=0)
+    expected_n_patches = len(lenas) * int((i_h - p_h + 1) * (i_w - p_w + 1)
+                                          * max_patches)
+    extr = PatchExtractor(patch_size=(p_h, p_w), max_patches=max_patches,
+                          random_state=0)
     patches = extr.transform(lenas)
     assert_true(patches.shape == (expected_n_patches, p_h, p_w))
 

sklearn/feature_selection/base.py

@@ -113,4 +113,3 @@ def inverse_transform(self, X):
         Xt = np.zeros((X.shape[0], support.size), dtype=X.dtype)
         Xt[:, support] = X
         return Xt
-

sklearn/linear_model/ridge.py

@@ -124,8 +124,7 @@ def _solve_dense_cholesky_kernel(K, y, alpha, sample_weight=None):
         # Only one penalty, we can solve multi-target problems in one time.
         K.flat[::n_samples + 1] += alpha[0]
 
-        dual_coef = linalg.solve(K, y,
-                             sym_pos=True, overwrite_a=True)
+        dual_coef = linalg.solve(K, y, sym_pos=True, overwrite_a=True)
 
         # K is expensive to compute and store in memory so change it back in
         # case it was user-given.
@@ -196,7 +195,8 @@ def ridge_regression(X, y, alpha, sample_weight=1.0, solver='auto',
         - 'auto' chooses the solver automatically based on the type of data.
 
         - 'svd' uses a Singular Value Decomposition of X to compute the Ridge
-          coefficients. More stable for singular matrices than 'dense_cholesky'.
+          coefficients. More stable for singular matrices than
+          'dense_cholesky'.
 
         - 'dense_cholesky' uses the standard scipy.linalg.solve function to
           obtain a closed-form solution via a Cholesky decomposition of
@@ -266,7 +266,8 @@ def ridge_regression(X, y, alpha, sample_weight=1.0, solver='auto',
     alpha = safe_asarray(alpha).ravel()
     if alpha.size not in [1, n_targets]:
         raise ValueError("Number of targets and number of penalties "
-                    "do not correspond: %d != %d" % (alpha.size, n_targets))
+                         "do not correspond: %d != %d"
+                         % (alpha.size, n_targets))
 
     if alpha.size == 1 and n_targets > 1:
         alpha = np.repeat(alpha, n_targets)
@@ -293,7 +294,7 @@ def ridge_regression(X, y, alpha, sample_weight=1.0, solver='auto',
             coef = safe_sparse_dot(X.T, dual_coef, dense_output=True).T
         else:
             try:
-                coef =_solve_dense_cholesky(X, y, alpha)
+                coef = _solve_dense_cholesky(X, y, alpha)
             except linalg.LinAlgError:
                 # use SVD solver if matrix is singular
                 solver = 'svd'
@@ -379,7 +380,8 @@ class Ridge(_BaseRidge, RegressorMixin):
         - 'auto' chooses the solver automatically based on the type of data.
 
         - 'svd' uses a Singular Value Decomposition of X to compute the Ridge
-          coefficients. More stable for singular matrices than 'dense_cholesky'.
+          coefficients. More stable for singular matrices than
+          'dense_cholesky'.
 
         - 'dense_cholesky' uses the standard scipy.linalg.solve function to
           obtain a closed-form solution.

sklearn/metrics/metrics.py

@@ -193,8 +193,8 @@ def _check_clf_targets(y_true, y_pred):
 def auc(x, y, reorder=False):
     """Compute Area Under the Curve (AUC) using the trapezoidal rule
 
-    This is a general function, given points on a curve.  For computing the area
-    under the ROC-curve, see :func:`auc_score`.
+    This is a general function, given points on a curve.  For computing the
+    area under the ROC-curve, see :func:`auc_score`.
 
     Parameters
     ----------

sklearn/tests/test_common.py

@@ -111,6 +111,7 @@ def test_all_estimators():
                 else:
                     assert_equal(params[arg], default)
 
+
 def test_estimators_sparse_data():
     # All estimators should either deal with sparse data, or raise an
     # intelligible error message
@@ -990,8 +991,9 @@ def test_cluster_overwrite_params():
 def test_import_all_consistency():
     # Smoke test to check that any name in a __all__ list is actually defined
     # in the namespace of the module or package.
-    for importer, modname, ispkg in pkgutil.walk_packages(
-        path=sklearn.__path__, prefix='sklearn.', onerror=lambda x: None):
+    pkgs = pkgutil.walk_packages(path=sklearn.__path__, prefix='sklearn.',
+                                 onerror=lambda _: None)
+    for importer, modname, ispkg in pkgs:
         if ".tests." in modname:
             continue
         package = __import__(modname, fromlist="dummy")

sklearn/utils/extmath.py

@@ -414,7 +414,7 @@ def cartesian(arrays, out=None):
 
     References
     ----------
-    http://stackoverflow.com/questions/1208118/using-numpy-to-build-an-array-of-all-combinations-of-two-arrays
+    http://stackoverflow.com/q/1208118
 
     """
     arrays = [np.asarray(x).ravel() for x in arrays]

sklearn/utils/mst/_graph_validation.py

@@ -7,6 +7,7 @@
 
 DTYPE = np.float64
 
+
 def validate_graph(csgraph, directed, dtype=DTYPE,
                    csr_output=True, dense_output=True,
                    copy_if_dense=False, copy_if_sparse=False,