ENH less copying in validation for neighbors

Author: larsmans

sklearn/neighbors/base.py

@@ -173,10 +173,7 @@ def _fit(self, X):
             self._fit_method = 'kd_tree'
             return self
 
-        X = safe_asarray(X)
-
-        if X.ndim != 2:
-            raise ValueError("data type not understood")
+        X = atleast2d_or_csr(X, copy=False)
 
         n_samples = X.shape[0]
         if n_samples == 0:
@@ -189,7 +186,7 @@ def _fit(self, X):
             if self.effective_metric_ not in VALID_METRICS_SPARSE['brute']:
                 raise ValueError("metric '%s' not valid for sparse input"
                                  % self.effective_metric_)
-            self._fit_X = X.tocsr()
+            self._fit_X = X.copy()
             self._tree = None
             self._fit_method = 'brute'
             return self

sklearn/utils/tests/test_validation.py

@@ -70,6 +70,25 @@ def test_as_float_array():
         assert_false(np.isnan(M).any())
 
 
+def test_atleast2d_or_sparse():
+    for typ in [sp.csr_matrix, sp.dok_matrix, sp.lil_matrix, sp.coo_matrix]:
+        X = typ(np.arange(9, dtype=float).reshape(3, 3))
+
+        Y = atleast2d_or_csr(X, copy=True)
+        assert_true(isinstance(Y, sp.csr_matrix))
+        Y.data[:] = 1
+        assert_array_equal(X.toarray().ravel(), np.arange(9))
+
+        Y = atleast2d_or_csc(X, copy=False)
+        Y.data[:] = 4
+        assert_true(np.all(X.data == 4)
+                    if isinstance(X, sp.csc_matrix)
+                    else np.all(X.toarray().ravel() == np.arange(9)))
+
+        Y = atleast2d_or_csr(X, dtype=np.float32)
+        assert_true(Y.dtype == np.float32)
+
+
 def test_check_arrays_exceptions():
     """Check that invalid arguments raise appropriate exceptions"""
     assert_raises(ValueError, check_arrays, [0], [0, 1])

sklearn/utils/validation.py

@@ -117,9 +117,11 @@ def array2d(X, dtype=None, order=None, copy=False, force_all_finite=True):
 
 
 def _atleast2d_or_sparse(X, dtype, order, copy, sparse_class, convmethod,
-                         force_all_finite):
+                         check_same_type, force_all_finite):
     if sparse.issparse(X):
-        if dtype is None or X.dtype == dtype:
+        if check_same_type(X) and X.dtype == dtype:
+            X = getattr(X, convmethod)(copy=copy)
+        elif dtype is None or X.dtype == dtype:
             X = getattr(X, convmethod)()
         else:
             X = sparse_class(X, dtype=dtype)
@@ -139,7 +141,8 @@ def atleast2d_or_csc(X, dtype=None, order=None, copy=False,
     Also, converts np.matrix to np.ndarray.
     """
     return _atleast2d_or_sparse(X, dtype, order, copy, sparse.csc_matrix,
-                                "tocsc", force_all_finite)
+                                "tocsc", sparse.isspmatrix_csc,
+                                force_all_finite)
 
 
 def atleast2d_or_csr(X, dtype=None, order=None, copy=False,
@@ -149,7 +152,8 @@ def atleast2d_or_csr(X, dtype=None, order=None, copy=False,
     Also, converts np.matrix to np.ndarray.
     """
     return _atleast2d_or_sparse(X, dtype, order, copy, sparse.csr_matrix,
-                                "tocsr", force_all_finite)
+                                "tocsr", sparse.isspmatrix_csr,
+                                force_all_finite)
 
 
 def _num_samples(x):