BUG fix whitespace in error messages

Partial fix for scikit-learn#2380.

Signed-off-by: Lars Buitinck <[email protected]>

benchmarks/bench_random_projections.py

@@ -102,7 +102,7 @@ def print_row(clf_type, time_fit, time_transform):
     op.add_option("--n-components",
                   dest="n_components", default="auto",
                   help="Size of the random subspace."
-                       "('auto' or int > 0)")
+                       " ('auto' or int > 0)")
 
     op.add_option("--ratio-nonzeros",
                   dest="ratio_nonzeros", default=10 ** -3, type=float,
@@ -119,7 +119,7 @@ def print_row(clf_type, time_fit, time_transform):
     op.add_option("--density",
                   dest="density", default=1 / 3,
                   help="Density used by the sparse random projection."
-                       "('auto' or float (0.0, 1.0]")
+                       " ('auto' or float (0.0, 1.0]")
 
     op.add_option("--eps",
                   dest="eps", default=0.5, type=float,

doc/sphinxext/gen_rst.py

@@ -203,7 +203,7 @@ def __init__(self, doc_url, searchindex='searchindex.js',
         if os.name.lower() == 'nt' and not doc_url.startswith('http://'):
             if not relative:
                 raise ValueError('You have to use relative=True for the local'
-                                 'package on a Windows system.')
+                                 ' package on a Windows system.')
             self._is_windows = True
         else:
             self._is_windows = False

examples/document_clustering.py

@@ -91,7 +91,7 @@
               help="Use a hashing feature vectorizer")
 op.add_option("--n-features", type=int, default=10000,
               help="Maximum number of features (dimensions)"
-                   "to extract from text.")
+                   " to extract from text.")
 op.add_option("--verbose",
               action="store_true", dest="verbose", default=False,
               help="Print progress reports inside k-means algorithm.")

sklearn/cluster/k_means_.py

@@ -941,7 +941,7 @@ def _mini_batch_convergence(model, iteration_idx, n_iter, tol,
     if verbose:
         progress_msg = (
             'Minibatch iteration %d/%d:'
-            'mean batch inertia: %f, ewa inertia: %f ' % (
+            ' mean batch inertia: %f, ewa inertia: %f ' % (
                 iteration_idx + 1, n_iter, batch_inertia,
                 ewa_inertia))
         print(progress_msg)

sklearn/covariance/graph_lasso_.py

@@ -211,7 +211,7 @@ def graph_lasso(emp_cov, alpha, cov_init=None, mode='cd', tol=1e-4,
                                          'too ill-conditioned for this solver')
         else:
             warnings.warn('graph_lasso: did not converge after %i iteration:'
-                          'dual gap: %.3e' % (max_iter, d_gap),
+                          ' dual gap: %.3e' % (max_iter, d_gap),
                           ConvergenceWarning)
     except FloatingPointError as e:
         e.args = (e.args[0]

sklearn/covariance/robust_covariance.py

@@ -138,7 +138,7 @@ def c_step(X, n_support, remaining_iterations=30, initial_estimates=None,
         # c_step procedure converged
         if verbose:
             print("Optimal couple (location, covariance) found before"
-                  "ending iterations (%d left)" % (remaining_iterations))
+                  " ending iterations (%d left)" % (remaining_iterations))
         results = location, covariance, det, support, dist
     elif det > previous_det:
         # determinant has increased (should not happen)

sklearn/cross_validation.py

@@ -248,7 +248,7 @@ def __init__(self, n, n_folds, indices):
         if n_folds > self.n:
             raise ValueError(
                 ("Cannot have number of folds n_folds={0} greater"
-                 "than the number of samples: {1}.").format(n_folds, n))
+                 " than the number of samples: {1}.").format(n_folds, n))
 
 
 class KFold(_BaseKFold):

sklearn/datasets/lfw.py

@@ -118,7 +118,7 @@ def _load_imgs(file_paths, slice_, color, resize):
         from scipy.misc import imresize
     except ImportError:
         raise ImportError("The Python Imaging Library (PIL)"
-                          "is required to load data from jpeg files")
+                          " is required to load data from jpeg files")
 
     # compute the portion of the images to load to respect the slice_ parameter
     # given by the caller

sklearn/datasets/samples_generator.py

@@ -119,7 +119,7 @@ def make_classification(n_samples=100, n_features=20, n_informative=2,
                          " 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.")

sklearn/ensemble/gradient_boosting.py

@@ -733,7 +733,7 @@ def feature_importances_(self):
     @property
     def oob_score_(self):
         warn("The oob_score_ argument is replaced by oob_improvement_"
-             "as of version 0.14 and will be removed in 0.16.",
+             " as of version 0.14 and will be removed in 0.16.",
              DeprecationWarning)
         try:
             return self._oob_score_

sklearn/externals/joblib/numpy_pickle.py

@@ -68,7 +68,7 @@ def read_zfile(file_handle):
     data = zlib.decompress(file_handle.read(), 15, length)
     assert len(data) == length, (
         "Incorrect data length while decompressing %s."
-        "The file could be corrupted." % file_handle)
+        " The file could be corrupted." % file_handle)
     return data
 
 

sklearn/linear_model/ridge.py

@@ -1018,7 +1018,7 @@ def fit(self, X, y, sample_weight=1.0, class_weight=None):
             class_weight = self.class_weight
         else:
             warnings.warn("'class_weight' is now an initialization parameter."
-                          "Using it in the 'fit' method is deprecated and "
+                          " Using it in the 'fit' method is deprecated and "
                           "will be removed in 0.15.", DeprecationWarning,
                           stacklevel=2)
 

sklearn/linear_model/stochastic_gradient.py

@@ -384,7 +384,7 @@ def _fit(self, X, y, alpha, C, loss, learning_rate,
 
         if class_weight is not None:
             warnings.warn("Using 'class_weight' as a parameter to the 'fit'"
-                          "method is deprecated and will be removed in 0.13. "
+                          " method is deprecated and will be removed in 0.13. "
                           "Set it on initialization instead.",
                           DeprecationWarning, stacklevel=2)
 

sklearn/manifold/mds.py

@@ -376,7 +376,7 @@ def fit_transform(self, X, init=None, y=None):
         """
         if X.shape[0] == X.shape[1] and self.dissimilarity != "precomputed":
             warnings.warn("The MDS API has changed. ``fit`` now constructs an"
-                          "dissimilarity matrix from data. To use a custom "
+                          " dissimilarity matrix from data. To use a custom "
                           "dissimilarity matrix, set "
                           "``dissimilarity=precomputed``.")
 

sklearn/metrics/metrics.py

@@ -841,7 +841,7 @@ def zero_one_loss(y_true, y_pred, normalize=True):
 
 @deprecated("Function 'zero_one' has been renamed to "
             "'zero_one_loss' and will be removed in release 0.15."
-            "Default behavior is changed from 'normalize=False' to "
+            " Default behavior is changed from 'normalize=False' to "
             "'normalize=True'")
 def zero_one(y_true, y_pred, normalize=False):
     """Zero-One classification loss
@@ -1494,7 +1494,7 @@ def precision_recall_fscore_support(y_true, y_pred, beta=1.0, labels=None,
         else:
             raise ValueError("Example-based precision, recall, fscore is "
                              "not meaningful outside of multilabel"
-                             "classification. Use accuracy_score instead.")
+                             " classification. Use accuracy_score instead.")
 
         warning_msg = ""
         if np.any(size_pred == 0):

sklearn/metrics/scorer.py

@@ -154,14 +154,14 @@ def _deprecate_loss_and_score_funcs(
         if loss_func is not None:
             warn("Passing a loss function is "
                  "deprecated and will be removed in 0.15. "
-                 "Either use strings or score objects."
+                 "Either use strings or score objects. "
                  "The relevant new parameter is called ''scoring''. ",
                  category=DeprecationWarning, stacklevel=2)
             scorer = make_scorer(loss_func, greater_is_better=False)
         if score_func is not None:
             warn("Passing function as ``score_func`` is "
                  "deprecated and will be removed in 0.15. "
-                 "Either use strings or score objects."
+                 "Either use strings or score objects. "
                  "The relevant new parameter is called ''scoring''.",
                  category=DeprecationWarning, stacklevel=2)
             if loss_func is None or score_overrides_loss:

sklearn/metrics/tests/test_metrics.py

@@ -1236,7 +1236,7 @@ def test_multioutput_regression_invariance_to_dimension_shuffling():
             perm = rng.permutation(n_dims)
             assert_almost_equal(metric(y_true[:, perm], y_pred[:, perm]),
                                 error,
-                                err_msg="%s is not dimension shuffling"
+                                err_msg="%s is not dimension shuffling "
                                         "invariant" % name)
 
 

sklearn/mixture/gmm.py

@@ -634,7 +634,7 @@ def _validate_covars(covars, covariance_type, n_components):
                              "positive-definite")
     elif covariance_type == 'diag':
         if len(covars.shape) != 2:
-            raise ValueError("'diag' covars must have shape"
+            raise ValueError("'diag' covars must have shape "
                              "(n_components, n_dim)")
         elif np.any(covars <= 0):
             raise ValueError("'diag' covars must be non-negative")

sklearn/neighbors/base.py

@@ -607,8 +607,8 @@ def fit(self, X, y):
 
         if y.ndim == 1 or y.ndim == 2 and y.shape[1] == 1:
             if y.ndim != 1:
-                warnings.warn("A column-vector y was passed when a 1d array"
-                              "was expected. Please change the shape of y to"
+		    warnings.warn("A column-vector y was passed when a 1d array "
+                              "was expected. Please change the shape of y to "
                               "(n_samples, ), for example using ravel().",
                               DataConversionWarning, stacklevel=2)
 

sklearn/pipeline.py

@@ -89,7 +89,7 @@ def __init__(self, steps):
             if (not (hasattr(t, "fit") or hasattr(t, "fit_transform")) or not
                     hasattr(t, "transform")):
                 raise TypeError("All intermediate steps a the chain should "
-                                "be transforms and implement fit and transform"
+                                "be transforms and implement fit and transform "
                                 "'%s' (type %s) doesn't)" % (t, type(t)))
 
         if not hasattr(estimator, "fit"):

sklearn/preprocessing/label.py

@@ -401,7 +401,7 @@ def label_binarize(y, classes, multilabel=False, neg_label=0, pos_label=1):
 
     if multilabel:
         if not y_is_multilabel:
-            raise ValueError("y should be a list of label lists/tuples,"
+            raise ValueError("y should be a list of label lists/tuples, "
                              "got %r" % (y,))
 
         # inverse map: label => column index

sklearn/random_projection.py

@@ -408,7 +408,7 @@ def transform(self, X, y=None):
         if X.shape[1] != self.components_.shape[1]:
             raise ValueError(
                 'Impossible to perform projection:'
-                'X at fit stage had a different number of features.'
+                'X at fit stage had a different number of features. '
                 '(%s != %s)' % (X.shape[1], self.components_.shape[1]))
 
         if not sp.issparse(X):

sklearn/svm/base.py

@@ -154,7 +154,7 @@ def fit(self, X, y, sample_weight=None):
             raise ValueError("X.shape[0] should be equal to X.shape[1]")
 
         if sample_weight.shape[0] > 0 and sample_weight.shape[0] != X.shape[0]:
-            raise ValueError("sample_weight and X have incompatible shapes:"
+            raise ValueError("sample_weight and X have incompatible shapes: "
                              "%r vs %r\n"
                              "Note: Sparse matrices cannot be indexed w/"
                              "boolean masks (use `indices=True` in CV)."

sklearn/utils/arpack.py

@@ -138,7 +138,7 @@
        "increase the size of the arrays DR and DI to have "
        "dimension at least dimension NCV and allocate at least NCV "
        "columns for Z. NOTE: Not necessary if Z and V share "
-       "the same space. Please notify the authors if this error"
+       "the same space. Please notify the authors if this error "
        "occurs.",
     -1: "N must be positive.",
     -2: "NEV must be positive.",

sklearn/utils/testing.py

@@ -128,7 +128,7 @@ def _assert_allclose(actual, desired, rtol=1e-7, atol=0,
     actual, desired = np.asanyarray(actual), np.asanyarray(desired)
     if np.allclose(actual, desired, rtol=rtol, atol=atol):
         return
-    msg = ('Array not equal to tolerance rtol=%g, atol=%g:'
+    msg = ('Array not equal to tolerance rtol=%g, atol=%g: '
            'actual %s, desired %s') % (rtol, atol, actual, desired)
     raise AssertionError(msg)