Update supervised.rst (#356)

The verbose (and almost all other parameters) need to be passed to the constructor and not the .fit() function. This was not refelcted in the example snipplets for LMNN in the docs.

Author: DaminK

doc/supervised.rst

@@ -164,8 +164,8 @@ indicates :math:`\mathbf{x}_{i}, \mathbf{x}_{j}` belong to different classes,
     X = iris_data['data']
     Y = iris_data['target']
 
-    lmnn = LMNN(n_neighbors=5, learn_rate=1e-6)
-    lmnn.fit(X, Y, verbose=False)
+    lmnn = LMNN(n_neighbors=5, learn_rate=1e-6, verbose=False)
+    lmnn.fit(X, Y)
 
 .. rubric:: References