COSMIT pep8

Author: amueller

sklearn/covariance/outlier_detection.py

@@ -13,7 +13,7 @@
 # License: BSD Style.
 
 import numpy as np
-import  scipy as sp
+import scipy as sp
 from . import MinCovDet
 from ..utils import deprecated
 from ..base import ClassifierMixin

sklearn/datasets/base.py

@@ -50,7 +50,7 @@ def get_data_home(data_home=None):
     """
     if data_home is None:
         data_home = environ.get('SCIKIT_LEARN_DATA',
-                               join('~', 'scikit_learn_data'))
+                                join('~', 'scikit_learn_data'))
     data_home = expanduser(data_home)
     if not exists(data_home):
         makedirs(data_home)

sklearn/datasets/lfw.py

@@ -167,7 +167,7 @@ def _load_imgs(file_paths, slice_, color, resize):
 #
 
 def _fetch_lfw_people(data_folder_path, slice_=None, color=False, resize=None,
-                     min_faces_per_person=0):
+                      min_faces_per_person=0):
     """Perform the actual data loading for the lfw people dataset
 
     This operation is meant to be cached by a joblib wrapper.
@@ -208,9 +208,9 @@ def _fetch_lfw_people(data_folder_path, slice_=None, color=False, resize=None,
 
 
 def fetch_lfw_people(data_home=None, funneled=True, resize=0.5,
-                    min_faces_per_person=None, color=False,
-                    slice_=(slice(70, 195), slice(78, 172)),
-                    download_if_missing=True):
+                     min_faces_per_person=None, color=False,
+                     slice_=(slice(70, 195), slice(78, 172)),
+                     download_if_missing=True):
     """Loader for the Labeled Faces in the Wild (LFW) people dataset
 
     This dataset is a collection of JPEG pictures of famous people
@@ -283,7 +283,7 @@ def fetch_lfw_people(data_home=None, funneled=True, resize=0.5,
 
 
 def _fetch_lfw_pairs(index_file_path, data_folder_path, slice_=None,
-                    color=False, resize=None):
+                     color=False, resize=None):
     """Perform the actual data loading for the LFW pairs dataset
 
     This operation is meant to be cached by a joblib wrapper.
@@ -339,7 +339,7 @@ def load_lfw_people(download_if_missing=False, **kwargs):
 
 
 def fetch_lfw_pairs(subset='train', data_home=None, funneled=True, resize=0.5,
-                   color=False, slice_=(slice(70, 195), slice(78, 172)),
+                    color=False, slice_=(slice(70, 195), slice(78, 172)),
                     download_if_missing=True):
     """Loader for the Labeled Faces in the Wild (LFW) pairs dataset
 

sklearn/datasets/olivetti_faces.py

@@ -83,8 +83,8 @@ def fetch_olivetti_faces(data_home=None, shuffle=False, random_state=0,
     if not exists(data_home):
         makedirs(data_home)
     if not exists(join(data_home, TARGET_FILENAME)):
-        print 'downloading Olivetti faces from %s to %s' % (DATA_URL,
-                            data_home)
+        print('downloading Olivetti faces from %s to %s'
+              % (DATA_URL, data_home))
         fhandle = urllib2.urlopen(DATA_URL)
         buf = StringIO(fhandle.read())
         mfile = loadmat(buf)

sklearn/datasets/samples_generator.py

@@ -112,13 +112,14 @@ def make_classification(n_samples=100, n_features=20, n_informative=2,
     # Count features, clusters and samples
     if n_informative + n_redundant + n_repeated > n_features:
         raise ValueError("Number of informative, redundant and repeated "
-            "features must sum to less than the number of total features")
+                         "features must sum to less than the number of total"
+                         " features")
     if 2 ** n_informative < n_classes * n_clusters_per_class:
         raise ValueError("n_classes * n_clusters_per_class must"
-            "be smaller or equal 2 ** n_informative")
+                         "be smaller or equal 2 ** n_informative")
     if weights and len(weights) not in [n_classes, n_classes - 1]:
         raise ValueError("Weights specified but incompatible with number "
-                "of classes.")
+                         "of classes.")
 
     n_useless = n_features - n_informative - n_redundant - n_repeated
     n_clusters = n_classes * n_clusters_per_class
@@ -186,7 +187,7 @@ def make_classification(n_samples=100, n_features=20, n_informative=2,
     if n_redundant > 0:
         B = 2 * generator.rand(n_informative, n_redundant) - 1
         X[:, n_informative:n_informative + n_redundant] = \
-                                            np.dot(X[:, :n_informative], B)
+            np.dot(X[:, :n_informative], B)
 
     # Repeat some features
     if n_repeated > 0:
@@ -485,7 +486,7 @@ def make_regression(n_samples=100, n_features=100, n_informative=10,
 
 
 def make_circles(n_samples=100, shuffle=True, noise=None, random_state=None,
-        factor=.8):
+                 factor=.8):
     """Make a large circle containing a smaller circle in 2d.
 
     A simple toy dataset to visualize clustering and classification
@@ -526,8 +527,8 @@ def make_circles(n_samples=100, shuffle=True, noise=None, random_state=None,
     inner_circ_x = outer_circ_x * factor
     inner_circ_y = outer_circ_y * factor
 
-    X = np.vstack((np.append(outer_circ_x, inner_circ_x),\
-           np.append(outer_circ_y, inner_circ_y))).T
+    X = np.vstack((np.append(outer_circ_x, inner_circ_x),
+                   np.append(outer_circ_y, inner_circ_y))).T
     y = np.hstack([np.zeros(n_samples / 2), np.ones(n_samples / 2)])
     if shuffle:
         X, y = util_shuffle(X, y, random_state=generator)
@@ -574,8 +575,8 @@ def make_moons(n_samples=100, shuffle=True, noise=None, random_state=None):
     inner_circ_x = 1 - np.cos(np.linspace(0, np.pi, n_samples_in))
     inner_circ_y = 1 - np.sin(np.linspace(0, np.pi, n_samples_in)) - .5
 
-    X = np.vstack((np.append(outer_circ_x, inner_circ_x),\
-           np.append(outer_circ_y, inner_circ_y))).T
+    X = np.vstack((np.append(outer_circ_x, inner_circ_x),
+                   np.append(outer_circ_y, inner_circ_y))).T
     y = np.hstack([np.zeros(n_samples_in), np.ones(n_samples_out)])
 
     if shuffle:
@@ -793,7 +794,7 @@ def make_friedman2(n_samples=100, noise=0.0, random_state=None):
     X[:, 3] += 1
 
     y = (X[:, 0] ** 2
-            + (X[:, 1] * X[:, 2] - 1 / (X[:, 1] * X[:, 3])) ** 2) ** 0.5 \
+         + (X[:, 1] * X[:, 2] - 1 / (X[:, 1] * X[:, 3])) ** 2) ** 0.5 \
         + noise * generator.randn(n_samples)
 
     return X, y
@@ -924,8 +925,8 @@ def make_low_rank_matrix(n_samples=100, n_features=100, effective_rank=10,
     singular_ind = np.arange(n, dtype=np.float64)
 
     # Build the singular profile by assembling signal and noise components
-    low_rank = (1 - tail_strength) * \
-               np.exp(-1.0 * (singular_ind / effective_rank) ** 2)
+    low_rank = ((1 - tail_strength) *
+                np.exp(-1.0 * (singular_ind / effective_rank) ** 2))
     tail = tail_strength * np.exp(-0.1 * singular_ind / effective_rank)
     s = np.identity(n) * (low_rank + tail)
 
@@ -1105,7 +1106,7 @@ def make_sparse_spd_matrix(dim=1, alpha=0.95, norm_diag=False,
     aux[aux < alpha] = 0
     aux[aux > alpha] = (smallest_coef
                         + (largest_coef - smallest_coef)
-                          * random_state.rand(np.sum(aux > alpha)))
+                        * random_state.rand(np.sum(aux > alpha)))
     aux = np.tril(aux, k=-1)
 
     # Permute the lines: we don't want to have assymetries in the final

sklearn/datasets/species_distributions.py

@@ -57,7 +57,7 @@
 
 
 def _load_coverage(F, header_length=6,
-                  dtype=np.int16):
+                   dtype=np.int16):
     """
     load a coverage file.
     This will return a numpy array of the given dtype

sklearn/datasets/svmlight_format.py

@@ -205,8 +205,8 @@ def load_svmlight_files(files, n_features=None, dtype=np.float64,
     r = [_open_and_load(f, dtype, multilabel, bool(zero_based), bool(query_id))
          for f in files]
 
-    if zero_based is False \
-     or zero_based == "auto" and all(np.min(tmp[1]) > 0 for tmp in r):
+    if (zero_based is False
+            or zero_based == "auto" and all(np.min(tmp[1]) > 0 for tmp in r)):
         for ind in r:
             indices = ind[1]
             indices -= 1

sklearn/datasets/tests/test_20news.py

@@ -11,16 +11,14 @@
 
 def test_20news():
     try:
-        data = datasets.fetch_20newsgroups(subset='all',
-                        download_if_missing=False,
-                        shuffle=False)
+        data = datasets.fetch_20newsgroups(
+            subset='all', download_if_missing=False, shuffle=False)
     except IOError:
         raise SkipTest("Download 20 newsgroups to run this test")
 
     # Extract a reduced dataset
-    data2cats = datasets.fetch_20newsgroups(subset='all',
-                            categories=data.target_names[-1:-3:-1],
-                            shuffle=False)
+    data2cats = datasets.fetch_20newsgroups(
+        subset='all', categories=data.target_names[-1:-3:-1], shuffle=False)
     # Check that the ordering of the target_names is the same
     # as the ordering in the full dataset
     assert_equal(data2cats.target_names,

sklearn/datasets/tests/test_lfw.py

@@ -141,8 +141,8 @@ def test_load_fake_lfw_people():
     assert_array_equal(lfw_people.target,
                        [0, 0, 1, 6, 5, 6, 3, 6, 0, 3, 6, 1, 2, 4, 5, 1, 2])
     assert_array_equal(lfw_people.target_names,
-                      ['Abdelatif Smith', 'Abhati Kepler', 'Camara Alvaro',
-                       'Chen Dupont', 'John Lee', 'Lin Bauman', 'Onur Lopez'])
+                       ['Abdelatif Smith', 'Abhati Kepler', 'Camara Alvaro',
+                        'Chen Dupont', 'John Lee', 'Lin Bauman', 'Onur Lopez'])
 
 
 @raises(ValueError)

sklearn/datasets/tests/test_samples_generator.py

@@ -78,7 +78,8 @@ def test_make_regression_multitarget():
     assert_equal(X.shape, (100, 10), "X shape mismatch")
     assert_equal(y.shape, (100, 3), "y shape mismatch")
     assert_equal(c.shape, (10, 3), "coef shape mismatch")
-    assert_array_equal(sum(c != 0.0), 3, "Unexpected number of informative features")
+    assert_array_equal(sum(c != 0.0), 3,
+                       "Unexpected number of informative features")
 
     # Test that y ~= np.dot(X, c) + bias + N(0, 1.0)
     assert_almost_equal(np.std(y - np.dot(X, c)), 1.0, decimal=1)
@@ -102,7 +103,7 @@ def test_make_friedman1():
     assert_equal(y.shape, (5,), "y shape mismatch")
 
     assert_array_almost_equal(y, 10 * np.sin(np.pi * X[:, 0] * X[:, 1])
-                                 + 20 * (X[:, 2] - 0.5) ** 2 \
+                                 + 20 * (X[:, 2] - 0.5) ** 2
                                  + 10 * X[:, 3] + 5 * X[:, 4])
 
 
@@ -112,9 +113,10 @@ def test_make_friedman2():
     assert_equal(X.shape, (5, 4), "X shape mismatch")
     assert_equal(y.shape, (5,), "y shape mismatch")
 
-    assert_array_almost_equal(y, (X[:, 0] ** 2
-                                 + (X[:, 1] * X[:, 2]
-                                    - 1 / (X[:, 1] * X[:, 3])) ** 2) ** 0.5)
+    assert_array_almost_equal(y,
+                              (X[:, 0] ** 2
+                               + (X[:, 1] * X[:, 2] - 1
+                                  / (X[:, 1] * X[:, 3])) ** 2) ** 0.5)
 
 
 def test_make_friedman3():
@@ -141,8 +143,8 @@ def test_make_low_rank_matrix():
 
 def test_make_sparse_coded_signal():
     Y, D, X = make_sparse_coded_signal(n_samples=5, n_components=8,
-                                           n_features=10, n_nonzero_coefs=3,
-                                           random_state=0)
+                                       n_features=10, n_nonzero_coefs=3,
+                                       random_state=0)
     assert_equal(Y.shape, (10, 5), "Y shape mismatch")
     assert_equal(D.shape, (10, 8), "D shape mismatch")
     assert_equal(X.shape, (8, 5), "X shape mismatch")