COSMIT pep8

Author: amueller

sklearn/cluster/spectral.py

@@ -288,7 +288,7 @@ class SpectralClustering(BaseEstimator, ClusterMixin):
     If affinity is the adjacency matrix of a graph, this method can be
     used to find normalized graph cuts.
 
-    When calling ``fit``, an affinity matrix is constructed using either 
+    When calling ``fit``, an affinity matrix is constructed using either
     kernel function such the Gaussian (aka RBF) kernel of the euclidean
     distanced ``d(X, X)``::
 
@@ -486,5 +486,3 @@ def mode(self):
                 " 0.15.")
     def k(self):
         return self.n_clusters
-
-

sklearn/datasets/lfw.py

@@ -319,7 +319,7 @@ def _fetch_lfw_pairs(index_file_path, data_folder_path, slice_=None,
             try:
                 person_folder = join(data_folder_path, name)
             except TypeError:
-                person_folder = join(data_folder_path, str(name,'UTF-8'))
+                person_folder = join(data_folder_path, str(name, 'UTF-8'))
             filenames = list(sorted(listdir(person_folder)))
             file_path = join(person_folder, filenames[idx])
             file_paths.append(file_path)

sklearn/datasets/svmlight_format.py

@@ -57,7 +57,7 @@ def load_svmlight_file(f, n_features=None, dtype=np.float64,
     when using pairwise loss functions (as is the case in some
     learning to rank problems) so that only pairs with the same
     query_id value are considered.
-    
+
     This implementation is written in Cython and is reasonably fast.
     However, a faster API-compatible loader is also available at:
 
@@ -246,7 +246,8 @@ def _dump_svmlight(X, y, f, one_based, comment, query_id):
     if comment:
         f.write(b("# Generated by dump_svmlight_file from scikit-learn %s\n"
                 % __version__))
-        f.write(b("# Column indices are %s-based\n" % ["zero", "one"][one_based]))
+        f.write(b("# Column indices are %s-based\n"
+                  % ["zero", "one"][one_based]))
 
         f.write(b("#\n"))
         f.writelines(b("# %s\n" % line) for line in comment.splitlines())

sklearn/datasets/tests/test_lfw.py

@@ -94,7 +94,7 @@ def setup_module():
             first_index = random_state.choice(np.arange(counts[first_name]))
             second_index = random_state.choice(np.arange(counts[second_name]))
             f.write(six.b('%s\t%d\t%s\t%d\n' % (first_name, first_index,
-                                          second_name, second_index)))
+                                                second_name, second_index)))
 
     with open(os.path.join(LFW_HOME, 'pairsDevTest.txt'), 'wb') as f:
         f.write(six.b("Fake place holder that won't be tested"))

sklearn/datasets/tests/test_mldata.py

@@ -128,8 +128,7 @@ def test_fetch_multiple_column():
         dataname = 'threecol-order'
         datasets.mldata.urlopen = mock_mldata_urlopen({
             dataname: ({'y': y, 'x': x, 'z': z},
-                       ['y', 'x', 'z']),
-            })
+                       ['y', 'x', 'z']), })
 
         dset = fetch_mldata(dataname, data_home=tmpdir)
         for n in ["COL_NAMES", "DESCR", "target", "data", "z"]:

sklearn/decomposition/tests/test_kernel_pca.py

@@ -126,7 +126,6 @@ def test_remove_zero_eig():
     assert_equal(Xt.shape, (3, 0))
 
 
-
 def test_kernel_pca_precomputed():
     rng = np.random.RandomState(0)
     X_fit = rng.random_sample((5, 4))

sklearn/ensemble/partial_dependence.py

@@ -335,7 +335,7 @@ def convert_feature(fx):
     n_rows = int(np.ceil(len(features) / float(n_cols)))
     axs = []
     for i, fx, name, (pdp, axes) in zip(count(), features, names,
-                                         pd_result):
+                                        pd_result):
         ax = fig.add_subplot(n_rows, n_cols, i + 1)
 
         if len(axes) == 1:

sklearn/feature_extraction/dict_vectorizer.py

@@ -2,7 +2,7 @@
 # License: BSD-style.
 
 from array import array
-from collections import Mapping, Sequence
+from collections import Mapping
 from operator import itemgetter
 
 import numpy as np

sklearn/feature_extraction/text.py

@@ -717,15 +717,17 @@ def fit_transform(self, raw_documents, y=None):
             max_df = self.max_df
             min_df = self.min_df
 
-            max_doc_count = (max_df if isinstance(max_df, numbers.Integral)
-                                    else max_df * n_doc)
-            min_doc_count = (min_df if isinstance(min_df, numbers.Integral)
-                                    else min_df * n_doc)
+            max_doc_count = (max_df
+                             if isinstance(max_df, numbers.Integral)
+                             else max_df * n_doc)
+            min_doc_count = (min_df
+                             if isinstance(min_df, numbers.Integral)
+                             else min_df * n_doc)
 
             # filter out stop words: terms that occur in almost all documents
             if max_doc_count < n_doc or min_doc_count > 1:
                 stop_words = set(t for t, dc in six.iteritems(document_counts)
-                                   if not min_doc_count <= dc <= max_doc_count)
+                                 if not min_doc_count <= dc <= max_doc_count)
             else:
                 stop_words = set()
 

sklearn/feature_selection/selector_mixin.py

@@ -97,7 +97,8 @@ def transform(self, X, threshold=None):
         try:
             mask = importances >= threshold
         except TypeError:
-            # Fails in Python 3.x when threshold is str; result is array of True
+            # Fails in Python 3.x when threshold is str;
+            # result is array of True
             raise ValueError("Invalid threshold: all features are discarded.")
 
         if np.any(mask):