I am getting this ValueError: total size of new array must be unchanged error. Can anyone resolve?

Question

I want to plot the data according to the classes given using Support Vector Machine. I am stuck in this code.

Error is shown at -> Z = Z.reshape(XX.shape)

Please note the code is imported from sklearn-svm . When I try to change the datasets given to the application the above error is shown.

    import numpy as np
    import matplotlib.pyplot as plt
    from sklearn import svm,datasets

    iris = datasets.load_iris()
    X = iris.data[:, :2]  # we only take the first two features. We could
                             # avoid this ugly slicing by using a two-dim dataset
    Y = iris.target
    Y = np.array(Y)
    # figure number
    fignum = 1

    # fit the model
    for kernel in ('linear', 'poly', 'rbf'):
        clf = svm.SVC(kernel=kernel, gamma=2)
        clf.fit(X, Y)

        # plot the line, the points, and the nearest vectors to the plane
        plt.figure(fignum, figsize=(4, 3))
        plt.clf()

        plt.scatter(clf.support_vectors_[:, 0], clf.support_vectors_[:, 1], s=80,
                    facecolors='none', zorder=10)
        plt.scatter(X[:, 0], X[:, 1], c=Y, zorder=10, cmap=plt.cm.Paired)

        plt.axis('tight')
        x_min = 0
        x_max = 10
        y_min = 0
        y_max = 10

        XX, YY = np.mgrid[x_min:x_max:200j, y_min:y_max:200j]
        Z = clf.decision_function(np.c_[XX.ravel(), YY.ravel()])
        # Put the result into a color plot
        Z = Z.reshape(XX.shape)
        #print Z
        plt.figure(fignum, figsize=(4, 3))
        plt.pcolormesh(XX, YY, Z > 0, cmap=plt.cm.Paired)
        plt.contour(XX, YY, Z, colors=['k', 'k', 'k'], linestyles=['--', '-', '--'],levels=[-.5, 0, .5])
        plt.xlim(x_min, x_max)
        plt.ylim(y_min, y_max)

        plt.xticks(())
        plt.yticks(())
        fignum = fignum + 1
    plt.show()

Answer 1

XX and YY both have the shape (200, 200) , but your Z has shape (40000, 3) . So XX and YY both contain 40000 values, while Z has 120000 values and can therefore not simply be reshaped to the shape of XX or YY as you would lose values. The call to decision_function() does not return a matrix of shape (N_samples, 1) as you seem to expect. Instead, according to scikit documentation , it returns (N_samples, n_class * (n_class-1) / 2) . You can replace the call with predict() to get the (probably) desired result, ie

Z = clf.predict(np.c_[XX.ravel(), YY.ravel()])