seckcoder
diff --git a/‎sklearn/preprocessing.py
Copy file name to clipboardExpand all lines: sklearn/preprocessing.py
+5Lines changed: 5 additions & 0 deletions b/‎sklearn/preprocessing.py
Copy file name to clipboardExpand all lines: sklearn/preprocessing.py
+5Lines changed: 5 additions & 0 deletions
diff --git a/‎sklearn/tests/test_preprocessing.py
Copy file name to clipboardExpand all lines: sklearn/tests/test_preprocessing.py
+17-4Lines changed: 17 additions & 4 deletions b/‎sklearn/tests/test_preprocessing.py
Copy file name to clipboardExpand all lines: sklearn/tests/test_preprocessing.py
+17-4Lines changed: 17 additions & 4 deletions
@@ -535,6 +535,7 @@ def binarize(X, threshold=0.0, copy=True):
 
     threshold : float, optional (0.0 by default)
         The lower bound that triggers feature values to be replaced by 1.0.
+        The threshold cannot be less than 0 for operations on sparse matrices.
 
     copy : boolean, optional, default is True
         set to False to perform inplace binarization and avoid a copy
@@ -554,6 +555,9 @@ def binarize(X, threshold=0.0, copy=True):
 
     X = check_arrays(X, sparse_format=sparse_format, copy=copy)[0]
     if sp.issparse(X):
+        if threshold < 0:
+            raise ValueError('Cannot binarize a sparse matrix with threshold '
+                             '< 0')
         cond = X.data > threshold
         not_cond = np.logical_not(cond)
         X.data[cond] = 1
@@ -585,6 +589,7 @@ class Binarizer(BaseEstimator, TransformerMixin):
     ----------
     threshold : float, optional (0.0 by default)
         The lower bound that triggers feature values to be replaced by 1.0.
+        The threshold cannot be less than 0 for operations on sparse matrices.
 
     copy : boolean, optional, default is True
         set to False to perform inplace binarization and avoid a copy (if
 
@@ -421,9 +421,9 @@ def test_normalize_errors():
 
 
 def test_binarizer():
-    X_ = np.array([[1, 0, 5], [2, 3, 0]])
+    X_ = np.array([[1, 0, 5], [2, 3, -1]])
 
-    for init in (np.array, sp.csr_matrix, sp.csc_matrix):
+    for init in (np.array, list, sp.csr_matrix, sp.csc_matrix):
 
         X = init(X_.copy())
 
@@ -432,7 +432,7 @@ def test_binarizer():
         assert_equal(np.sum(X_bin == 0), 4)
         assert_equal(np.sum(X_bin == 1), 2)
         X_bin = binarizer.transform(X)
-        assert_equal(type(X), type(X_bin))
+        assert_equal(sp.issparse(X), sp.issparse(X_bin))
 
         binarizer = Binarizer(copy=True).fit(X)
         X_bin = toarray(binarizer.transform(X))
@@ -449,11 +449,24 @@ def test_binarizer():
 
         binarizer = Binarizer(copy=False)
         X_bin = binarizer.transform(X)
-        assert_true(X_bin is X)
+        if init is not list:
+            assert_true(X_bin is X)
         X_bin = toarray(X_bin)
         assert_equal(np.sum(X_bin == 0), 2)
         assert_equal(np.sum(X_bin == 1), 4)
 
+    binarizer = Binarizer(threshold=-0.5, copy=True)
+    for init in (np.array, list):
+        X = init(X_.copy())
+
+        X_bin = toarray(binarizer.transform(X))
+        assert_equal(np.sum(X_bin == 0), 1)
+        assert_equal(np.sum(X_bin == 1), 5)
+        X_bin = binarizer.transform(X)
+
+    # Cannot use threshold < 0 for sparse
+    assert_raises(ValueError, binarizer.transform, sp.csc_matrix(X))
+
 
 def test_label_binarizer():
     lb = LabelBinarizer()