1
$\begingroup$

I am getting the following error when running a Gaussian Mixture Model:

ValueError: Fitting the mixture model failed because some components have ill-defined empirical covariance (for instance caused by singleton or collapsed samples). Try to decrease the number of components, or increase reg_covar.

The matrix that I am using has a relatively large shape so it will be hard to display on this page, however, here is an overview

[[  6.10086000e+05   1.58787000e+05   0.00000000e+00 ...,   8.00000000e+00
    0.00000000e+00   0.00000000e+00]
 [  2.36273000e+05   1.48953000e+05   0.00000000e+00 ...,   5.00000000e+00
    0.00000000e+00   0.00000000e+00]
 [  1.70486000e+05   1.53083000e+05   0.00000000e+00 ...,   3.50000000e+01
    0.00000000e+00   0.00000000e+00]
 ..., 
 [  0.00000000e+00   0.00000000e+00   0.00000000e+00 ...,   0.00000000e+00
    0.00000000e+00   0.00000000e+00]
 [  0.00000000e+00   0.00000000e+00   0.00000000e+00 ...,   2.00000000e+01
    0.00000000e+00   0.00000000e+00]
 [  0.00000000e+00   0.00000000e+00   0.00000000e+00 ...,   2.00000000e+00
    0.00000000e+00   1.00000000e+00]]

This is the code snippet for running the GMM:

def perform_gaussian_mixture():
    colors = ["navy", "cyan", "darkorange", "orchid", "lime"]

    def make_ellipses(gmm, ax):
        for n, color in enumerate(colors):
            if gmm.covariance_type == 'full':
                covariances = gmm.covariances_[n][:2, :2]
            elif gmm.covariance_type == 'tied':
                covariances = gmm.covariances_[:2, :2]
            elif gmm.covariance_type == 'diag':
                covariances = np.diag(gmm.covariances_[n][:2])
            elif gmm.covariance_type == 'spherical':
                covariances = np.eye(gmm.means_.shape[1]) * gmm.covariances_[n]
            v, w = np.linalg.eigh(covariances)
            u = w[0] / np.linalg.norm(w[0])
            angle = np.arctan2(u[1], u[0])
            angle = 180 * angle / np.pi  # convert to degrees
            v = 2. * np.sqrt(2.) * np.sqrt(v)
            ell = mpl.patches.Ellipse(gmm.means_[n, :2], v[0], v[1],
                                      180 + angle, color=color)
            ell.set_clip_box(ax.bbox)
            ell.set_alpha(0.5)
            ax.add_artist(ell)

    data = matricize()

    x_train, x_test, y_train, y_test = train_test_split(data["data"], data["target"], test_size=0.25, random_state=42)

    n_classes = len(np.unique(data["target"]))

    # Try GMMs using different types of covariances.
    estimators = dict((cov_type, mixture.GaussianMixture(n_components=n_classes,
                                                         covariance_type=cov_type, max_iter=20, random_state=0))
                      for cov_type in ["full"])

    n_estimators = len(estimators)

    plt.figure(figsize=(3 * n_estimators // 2, 6))
    plt.subplots_adjust(bottom=.01, top=0.95, hspace=.15, wspace=.05,
                        left=.01, right=.99)

    for index, (name, estimator) in enumerate(estimators.items()):

        # Since we have class labels for the training data, we can
        # initialize the GMM parameters in a supervised manner.
        estimator.means_init = np.array([x_train[np.where(y_train == i)].mean(axis=0)
                                         for i in range(n_classes)])

        # Train the other parameters using the EM algorithm.
        estimator.fit(x_train)

        h = plt.subplot(2, n_estimators // 2, index + 1)
        make_ellipses(estimator, h)

        for n, color in enumerate(colors):
            d = data["data"][np.where(data["target"] == n)]
            plt.scatter(d[:, 0], d[:, 1], s=0.8, color=color,
                        label=data["target_names"][n])
        # Plot the test data with crosses
        for n, color in enumerate(colors):
            d = x_test[np.where(y_test == n)]
            plt.scatter(d[:, 0], d[:, 1], marker='x', color=color)

        y_train_pred = estimator.predict(x_train)
        train_accuracy = np.mean(y_train_pred.ravel() == y_train.ravel()) * 100
        plt.text(0.05, 0.9, 'Train accuracy: %.1f' % train_accuracy,
                 transform=h.transAxes)

        y_test_pred = estimator.predict(x_test)
        test_accuracy = np.mean(y_test_pred.ravel() == y_test.ravel()) * 100
        plt.text(0.05, 0.8, 'Test accuracy: %.1f' % test_accuracy,
                 transform=h.transAxes)

        plt.xticks(())
        plt.yticks(())
        plt.title(name)

    plt.legend(scatterpoints=1, loc='lower right', prop=dict(size=12))
    plt.show()

Please let me know if more information is required.

$\endgroup$

1 Answer 1

0
$\begingroup$

In mixture.GaussianMixture(...) add an argument 'reg_covar=1e-5' or larger values if it still gives an error.

It should work fine then.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.