diff --git a/sklearn/cluster/hierarchical.py b/sklearn/cluster/hierarchical.py
index 8c75ef7c696024ed028ff99476ac775f1bdfa121..7ae174cc45ef648b0b347c6f9ce1da1ae16c4ebd 100644
--- a/sklearn/cluster/hierarchical.py
+++ b/sklearn/cluster/hierarchical.py
@@ -713,7 +713,7 @@ class AgglomerativeClustering(BaseEstimator, ClusterMixin):
-------
self
"""
- X = check_array(X, ensure_min_samples=2)
+ X = check_array(X, ensure_min_samples=2, estimator=self)
memory = self.memory
if isinstance(memory, six.string_types):
memory = Memory(cachedir=memory, verbose=0)
@@ -870,7 +870,7 @@ class FeatureAgglomeration(AgglomerativeClustering, AgglomerationTransform):
self
"""
X = check_array(X, accept_sparse=['csr', 'csc', 'coo'],
- ensure_min_features=2)
+ ensure_min_features=2, estimator=self)
return AgglomerativeClustering.fit(self, X.T, **params)
@property
diff --git a/sklearn/covariance/graph_lasso_.py b/sklearn/covariance/graph_lasso_.py
index 6957507a336a01851edd2b04275ad66f6d76b1c0..9e8e07063399d77a2b6438d69bf52de0acd99534 100644
--- a/sklearn/covariance/graph_lasso_.py
+++ b/sklearn/covariance/graph_lasso_.py
@@ -336,7 +336,8 @@ class GraphLasso(EmpiricalCovariance):
def fit(self, X, y=None):
# Covariance does not make sense for a single feature
- X = check_array(X, ensure_min_features=2, ensure_min_samples=2)
+ X = check_array(X, ensure_min_features=2, ensure_min_samples=2,
+ estimator=self)
if self.assume_centered:
self.location_ = np.zeros(X.shape[1])
@@ -570,7 +571,7 @@ class GraphLassoCV(GraphLasso):
Data from which to compute the covariance estimate
"""
# Covariance does not make sense for a single feature
- X = check_array(X, ensure_min_features=2)
+ X = check_array(X, ensure_min_features=2, estimator=self)
if self.assume_centered:
self.location_ = np.zeros(X.shape[1])
else:
diff --git a/sklearn/discriminant_analysis.py b/sklearn/discriminant_analysis.py
index c48feaa066d5dc67f5e4bf88ca81d3c28c2bb844..e442f278f31063ca908d88aedcb9af36b03a1383 100644
--- a/sklearn/discriminant_analysis.py
+++ b/sklearn/discriminant_analysis.py
@@ -419,7 +419,7 @@ class LinearDiscriminantAnalysis(BaseEstimator, LinearClassifierMixin,
"the estimator initialisation or set_params method.",
DeprecationWarning)
self.tol = tol
- X, y = check_X_y(X, y, ensure_min_samples=2)
+ X, y = check_X_y(X, y, ensure_min_samples=2, estimator=self)
self.classes_ = unique_labels(y)
if self.priors is None: # estimate priors from sample
diff --git a/sklearn/linear_model/omp.py b/sklearn/linear_model/omp.py
index 589939ed7858f90b5b95008636af7f00d090552c..3b87b9cf6c41057c2938ea6c9b6495604ea75e6b 100644
--- a/sklearn/linear_model/omp.py
+++ b/sklearn/linear_model/omp.py
@@ -832,7 +832,8 @@ class OrthogonalMatchingPursuitCV(LinearModel, RegressorMixin):
self : object
returns an instance of self.
"""
- X, y = check_X_y(X, y, y_numeric=True, ensure_min_features=2)
+ X, y = check_X_y(X, y, y_numeric=True, ensure_min_features=2,
+ estimator=self)
X = as_float_array(X, copy=False, force_all_finite=False)
cv = check_cv(self.cv, X, y, classifier=False)
max_iter = (min(max(int(0.1 * X.shape[1]), 5), X.shape[1])
diff --git a/sklearn/linear_model/randomized_l1.py b/sklearn/linear_model/randomized_l1.py
index 652f0375215cc46e4a930c810a1bfd2cf94ca8ab..aa02d0c5a643783e429cb771c3b4075b88ebf837 100644
--- a/sklearn/linear_model/randomized_l1.py
+++ b/sklearn/linear_model/randomized_l1.py
@@ -89,7 +89,7 @@ class BaseRandomizedLinearModel(six.with_metaclass(ABCMeta, BaseEstimator,
Returns an instance of self.
"""
X, y = check_X_y(X, y, ['csr', 'csc'], y_numeric=True,
- ensure_min_samples=2)
+ ensure_min_samples=2, estimator=self)
X = as_float_array(X, copy=False)
n_samples, n_features = X.shape
diff --git a/sklearn/manifold/spectral_embedding_.py b/sklearn/manifold/spectral_embedding_.py
index c67064b5bb288d0f4677f2b246a579d2640187aa..26825d8deb9337d3b035515bc50721a38be8fa17 100644
--- a/sklearn/manifold/spectral_embedding_.py
+++ b/sklearn/manifold/spectral_embedding_.py
@@ -452,7 +452,7 @@ class SpectralEmbedding(BaseEstimator):
Returns the instance itself.
"""
- X = check_array(X, ensure_min_samples=2)
+ X = check_array(X, ensure_min_samples=2, estimator=self)
random_state = check_random_state(self.random_state)
if isinstance(self.affinity, six.string_types):
diff --git a/sklearn/mixture/gmm.py b/sklearn/mixture/gmm.py
index 42c9aadb93403c0566523449b98e2adfc1740c2e..de11daf147106873fcd377d55bca5e9cc4658b80 100644
--- a/sklearn/mixture/gmm.py
+++ b/sklearn/mixture/gmm.py
@@ -462,7 +462,8 @@ class GMM(BaseEstimator):
"""
# initialization step
- X = check_array(X, dtype=np.float64, ensure_min_samples=2)
+ X = check_array(X, dtype=np.float64, ensure_min_samples=2,
+ estimator=self)
if X.shape[0] < self.n_components:
raise ValueError(
'GMM estimation with %s components, but got only %s samples' %
diff --git a/sklearn/utils/validation.py b/sklearn/utils/validation.py
index 4481ef914d1011b25b5fb7b477f42354a68ef1e2..d3ac1a18630c396b9cd97118be7f22708e72da33 100644
--- a/sklearn/utils/validation.py
+++ b/sklearn/utils/validation.py
@@ -357,6 +357,15 @@ def check_array(array, accept_sparse=None, dtype="numeric", order=None,
# list of accepted types.
dtype = dtype[0]
+ if estimator is not None:
+ if isinstance(estimator, six.string_types):
+ estimator_name = estimator
+ else:
+ estimator_name = estimator.__class__.__name__
+ else:
+ estimator_name = "Estimator"
+ context = " by %s" % estimator_name if estimator is not None else ""
+
if sp.issparse(array):
array = _ensure_sparse_format(array, accept_sparse, dtype, copy,
force_all_finite)
@@ -379,8 +388,8 @@ def check_array(array, accept_sparse=None, dtype="numeric", order=None,
if dtype_numeric and array.dtype.kind == "O":
array = array.astype(np.float64)
if not allow_nd and array.ndim >= 3:
- raise ValueError("Found array with dim %d. Expected <= 2" %
- array.ndim)
+ raise ValueError("Found array with dim %d. %s expected <= 2."
+ % (array.ndim, estimator_name))
if force_all_finite:
_assert_all_finite(array)
@@ -389,23 +398,21 @@ def check_array(array, accept_sparse=None, dtype="numeric", order=None,
n_samples = _num_samples(array)
if n_samples < ensure_min_samples:
raise ValueError("Found array with %d sample(s) (shape=%s) while a"
- " minimum of %d is required."
- % (n_samples, shape_repr, ensure_min_samples))
+ " minimum of %d is required%s."
+ % (n_samples, shape_repr, ensure_min_samples,
+ context))
if ensure_min_features > 0 and array.ndim == 2:
n_features = array.shape[1]
if n_features < ensure_min_features:
raise ValueError("Found array with %d feature(s) (shape=%s) while"
- " a minimum of %d is required."
- % (n_features, shape_repr, ensure_min_features))
+ " a minimum of %d is required%s."
+ % (n_features, shape_repr, ensure_min_features,
+ context))
if warn_on_dtype and dtype_orig is not None and array.dtype != dtype_orig:
- msg = ("Data with input dtype %s was converted to %s"
- % (dtype_orig, array.dtype))
- if estimator is not None:
- if not isinstance(estimator, six.string_types):
- estimator = estimator.__class__.__name__
- msg += " by %s" % estimator
+ msg = ("Data with input dtype %s was converted to %s%s."
+ % (dtype_orig, array.dtype, context))
warnings.warn(msg, DataConversionWarning)
return array