def launch_mcd_on_dataset(n_samples, n_features, n_outliers, tol_loc, tol_cov,
tol_support):
rand_gen = np.random.RandomState(0)
data = rand_gen.randn(n_samples, n_features)
# add some outliers
outliers_index = rand_gen.permutation(n_samples)[:n_outliers]
outliers_offset = 10. * \
(rand_gen.randint(2, size=(n_outliers, n_features)) - 0.5)
data[outliers_index] += outliers_offset
inliers_mask = np.ones(n_samples).astype(bool)
inliers_mask[outliers_index] = False
pure_data = data[inliers_mask]
# compute MCD by fitting an object
mcd_fit = MinCovDet(random_state=rand_gen).fit(data)
T = mcd_fit.location_
S = mcd_fit.covariance_
H = mcd_fit.support_
# compare with the estimates learnt from the inliers
error_location = np.mean((pure_data.mean(0) - T)**2)
assert (error_location < tol_loc)
error_cov = np.mean((empirical_covariance(pure_data) - S)**2)
assert (error_cov < tol_cov)
assert (np.sum(H) >= tol_support)
assert_array_almost_equal(mcd_fit.mahalanobis(data), mcd_fit.dist_)
# Show contours of the distance functions
xx, yy = np.meshgrid(np.linspace(plt.xlim()[0],
plt.xlim()[1], 100),
np.linspace(plt.ylim()[0],
plt.ylim()[1], 100))
zz = np.c_[xx.ravel(), yy.ravel()]
mahal_emp_cov = emp_cov.mahalanobis(zz)
mahal_emp_cov = mahal_emp_cov.reshape(xx.shape)
emp_cov_contour = subfig1.contour(xx,
yy,
np.sqrt(mahal_emp_cov),
cmap=plt.cm.PuBu_r,
linestyles='dashed')
mahal_robust_cov = robust_cov.mahalanobis(zz)
mahal_robust_cov = mahal_robust_cov.reshape(xx.shape)
robust_contour = subfig1.contour(xx,
yy,
np.sqrt(mahal_robust_cov),
cmap=plt.cm.YlOrBr_r,
linestyles='dotted')
subfig1.legend([
emp_cov_contour.collections[1], robust_contour.collections[1], inlier_plot,
outlier_plot
], ['MLE dist', 'robust dist', 'inliers', 'outliers'],
loc="upper right",
borderaxespad=0)
plt.xticks(())
plt.yticks(())