diff --git a/skimage/graph/_ncut.py b/skimage/graph/_ncut.py
index 46ffb528..2735bbd2 100644
--- a/skimage/graph/_ncut.py
+++ b/skimage/graph/_ncut.py
@@ -19,10 +19,10 @@ def DW_matrices(graph):
     Returns
     -------
     D : csc_matrix
-        The diagonal matrix of the graph. `D[i, i]` is the sum of weights of
+        The diagonal matrix of the graph. ``D[i, i]`` is the sum of weights of
         all edges incident on `i`. All other enteries are `0`.
     W : csc_matrix
-        The weight matrix of the graph. `W[i, j]` is the weight of the edge
+        The weight matrix of the graph. ``W[i, j]`` is the weight of the edge
         joining `i` to `j`.
     """
     # sparse.eighsh is most efficient with CSC-formatted input
@@ -62,7 +62,7 @@ def ncut_cost(cut, D, W):
     # D has elements only along the diagonal, one per node, so we can directly
     # index the data attribute with cut.
     assoc_a = D.data[cut].sum()
-    assoc_b = D.data[np.logical_not(cut)].sum()
+    assoc_b = D.data[~cut].sum()
 
     return (cut_cost / assoc_a) + (cut_cost / assoc_b)
 
diff --git a/skimage/graph/_ncut_cy.pyx b/skimage/graph/_ncut_cy.pyx
index 0f859edf..0888be72 100644
--- a/skimage/graph/_ncut_cy.pyx
+++ b/skimage/graph/_ncut_cy.pyx
@@ -6,7 +6,7 @@ cimport numpy as cnp
 import numpy as np
 
 
-def argmin2(cnp.float64_t[:] array):
+def argmin2(cnp.double_t[:] array):
     """Return the index of the 2nd smallest value in an array.
 
     Parameters
diff --git a/skimage/graph/graph_cut.py b/skimage/graph/graph_cut.py
index e44f8a5c..b86f6c48 100644
--- a/skimage/graph/graph_cut.py
+++ b/skimage/graph/graph_cut.py
@@ -89,11 +89,11 @@ def cut_normalized(labels, rag, thresh=0.001, num_cuts=10):
     Returns
     -------
     out : ndarray
-        The new labelled array.
+        The new labeled array.
 
     Examples
     --------
-    >>> from skimage import data, graph, segmentation, color, io
+    >>> from skimage import data, graph, segmentation
     >>> img = data.lena()
     >>> labels = segmentation.slic(img, compactness=30, n_segments=400)
     >>> rag = graph.rag_mean_color(img, labels, mode='similarity')
@@ -103,7 +103,7 @@ def cut_normalized(labels, rag, thresh=0.001, num_cuts=10):
     ----------
     .. [1] Shi, J.; Malik, J., "Normalized cuts and image segmentation",
            Pattern Analysis and Machine Intelligence,
-           IEEE Transactions on , vol.22, no.8, pp.888,905, Aug 2000
+           IEEE Transactions on , vol.22, no.8, pp.888,905, August 2000
 
     """
     map_array = np.arange(labels.max() + 1)
@@ -138,7 +138,7 @@ def partition_by_cut(cut, rag):
 
 
 def get_min_ncut(ev, d, w, num_cuts):
-    """Threshold an eigen vector evenly, to determine minimum ncut.
+    """Threshold an eigenvector evenly, to determine minimum ncut.
 
     Parameters
     ----------
@@ -174,7 +174,7 @@ def get_min_ncut(ev, d, w, num_cuts):
 def _ncut_relabel(rag, thresh, num_cuts, map_array):
     """Perform Normalized Graph cut on the Region Adjacency Graph.
 
-    Recursively partition the graph into 2, untill further subdividing
+    Recursively partition the graph into 2, until further subdivision
     yields a cut greather than `thresh` or such a cut cannot be computed.
     For such a subgraph, indices to labels of all its nodes map to a single
     unique value.
@@ -212,7 +212,7 @@ def _ncut_relabel(rag, thresh, num_cuts, map_array):
         stop = True
 
     if not stop:
-        # Pick second smalles eigen vector.
+        # Pick second smalles eigenvector.
         # Refer Shi & Malik 2001, Section 3.2.3, Page 893
         vals, vectors = np.real(vals), np.real(vectors)
         index2 = _ncut_cy.argmin2(vals)
diff --git a/skimage/graph/rag.py b/skimage/graph/rag.py
index 209ee602..f33936c2 100644
--- a/skimage/graph/rag.py
+++ b/skimage/graph/rag.py
@@ -146,17 +146,17 @@ def rag_mean_color(image, labels, connectivity=2, mode='dissimilarity',
         The strategy to assign edge weights.
 
             'similarity' : The weight between two adjacent regions is the
-            :math:`|c_1 - c_2|`, where :math:`c1` and :math:`c2` are the mean
+            :math:`|c_1 - c_2|`, where :math:`c_1` and :math:`c_2` are the mean
             colors of the two regions. It represents how different two regions
             are.
 
             'dissimilarity' : The weight between two adjacent is
             :math:`e^{-d^2/sigma}` where :math:`d=|c_1 - c_2|`, where
-            :math:`c1` and :math:`c2` are the mean colors of the two regions.
+            :math:`c_1` and :math:`c_2` are the mean colors of the two regions.
             It represents how similar two regions are.
     sigma : float, optional
-        Used for computation when `mode='dissimilarity'`. It governs how close
-        to each other two colors should be, for their corresponding edge
+        Used for computation when `mode` is "dissimilarity". It governs how
+        close to each other two colors should be, for their corresponding edge
         weight to be significant. A very large value of `sigma` could make
         any two colors behave as though they were similar.
 
diff --git a/skimage/graph/tests/test_rag.py b/skimage/graph/tests/test_rag.py
index 81889d6f..1e643fc4 100644
--- a/skimage/graph/tests/test_rag.py
+++ b/skimage/graph/tests/test_rag.py
@@ -95,4 +95,4 @@ def test_cut_normalized():
 def test_rag_error():
     img = np.zeros((10, 10, 3), dtype='uint8')
     labels = np.zeros((10, 10), dtype='uint8')
-    testing.assert_raises(ValueError, graph.rag_mean_color,img, labels, 2, 'non existant mode')
+    testing.assert_raises(ValueError, graph.rag_mean_color, img, labels, 2, 'non existant mode')