Added MDS to manifold comparison methods

examples/manifold/plot_compare_methods.py

@@ -21,6 +21,7 @@
 from matplotlib.ticker import NullFormatter
 
 from sklearn import manifold, datasets
+from sklearn.metrics import euclidean_distances
 
 # Next line to silence pyflakes. This import is needed.
 Axes3D
@@ -36,11 +37,11 @@
 
 try:
     # compatibility matplotlib < 1.0
-    ax = fig.add_subplot(231, projection='3d')
+    ax = fig.add_subplot(241, projection='3d')
     ax.scatter(X[:, 0], X[:, 1], X[:, 2], c=color, cmap=pl.cm.Spectral)
     ax.view_init(4, -72)
 except:
-    ax = fig.add_subplot(231, projection='3d')
+    ax = fig.add_subplot(241, projection='3d')
     pl.scatter(X[:, 0], X[:, 2], c=color, cmap=pl.cm.Spectral)
 
 methods = ['standard', 'ltsa', 'hessian', 'modified']
@@ -54,7 +55,7 @@
     t1 = time()
     print "%s: %.2g sec" % (methods[i], t1 - t0)
 
-    ax = fig.add_subplot(232 + i)
+    ax = fig.add_subplot(242 + i)
     pl.scatter(Y[:, 0], Y[:, 1], c=color, cmap=pl.cm.Spectral)
     pl.title("%s (%.2g sec)" % (labels[i], t1 - t0))
     ax.xaxis.set_major_formatter(NullFormatter())
@@ -65,11 +66,24 @@
 Y = manifold.Isomap(n_neighbors, n_components).fit_transform(X)
 t1 = time()
 print "Isomap: %.2g sec" % (t1 - t0)
-ax = fig.add_subplot(236)
+ax = fig.add_subplot(246)
 pl.scatter(Y[:, 0], Y[:, 1], c=color, cmap=pl.cm.Spectral)
 pl.title("Isomap (%.2g sec)" % (t1 - t0))
 ax.xaxis.set_major_formatter(NullFormatter())
 ax.yaxis.set_major_formatter(NullFormatter())
 pl.axis('tight')
 
+
+t0 = time()
+Y = manifold.MDS(n_components).fit_transform(euclidean_distances(X))
+t1 = time()
+print "MDS: %.2g sec" % (t1 - t0)
+ax = fig.add_subplot(247)
+pl.scatter(Y[:, 0], Y[:, 1], c=color, cmap=pl.cm.Spectral)
+pl.title("MDS (%.2g sec)" % (t1 - t0))
+ax.xaxis.set_major_formatter(NullFormatter())
+ax.yaxis.set_major_formatter(NullFormatter())
+pl.axis('tight')
+
+
 pl.show()

examples/manifold/plot_lle_digits.py

@@ -19,6 +19,7 @@
 from matplotlib import offsetbox
 from sklearn.utils.fixes import qr_economic
 from sklearn import manifold, datasets, decomposition, lda
+from sklearn.metrics import euclidean_distances
 
 digits = datasets.load_digits(n_class=6)
 X = digits.data
@@ -35,9 +36,9 @@ def plot_embedding(X, title=None):
 
     pl.figure()
     ax = pl.subplot(111)
-    for i in range(digits.data.shape[0]):
+    for i in range(X.shape[0]):
         pl.text(X[i, 0], X[i, 1], str(digits.target[i]),
-                color=pl.cm.Set1(digits.target[i] / 10.),
+                color=pl.cm.Set1(y[i] / 10.),
                 fontdict={'weight': 'bold', 'size': 9})
 
     if hasattr(offsetbox, 'AnnotationBbox'):
@@ -167,4 +168,15 @@ def plot_embedding(X, title=None):
     "Local Tangent Space Alignment of the digits (time %.2fs)" %
     (time() - t0))
 
+#----------------------------------------------------------------------
+# MDS  embedding of the digits dataset
+print "Computing MDS embedding"
+clf = manifold.MDS(n_components=2, n_init=2)
+t0 = time()
+X_mds = clf.fit_transform(euclidean_distances(X))
+print "Done. Stress: %f" % clf.stress_
+plot_embedding(X_mds,
+    "MDS embedding of the digits (time %.2fs)" %
+    (time() - t0))
+
 pl.show()