for j in range(repeat):
# generate data
X = np.random.randn(n_samples, n_features)
# add some outliers
outliers_index = np.random.permutation(n_samples)[:n_outliers]
outliers_offset = 10. * \
(np.random.randint(2, size=(n_outliers, n_features)) - 0.5)
X[outliers_index] += outliers_offset
inliers_mask = np.ones(n_samples).astype(bool)
inliers_mask[outliers_index] = False
# fit a Minimum Covariance Determinant (MCD) robust estimator to data
S = MinCovDet().fit(X)
# compare raw robust estimates with the true location and covariance
err_loc_mcd[i, j] = np.sum(S.location_**2)
err_cov_mcd[i, j] = S.error_norm(np.eye(n_features))
# compare estimators learnt from the full data set with true parameters
err_loc_emp_full[i, j] = np.sum(X.mean(0)**2)
err_cov_emp_full[i, j] = EmpiricalCovariance().fit(X).error_norm(
np.eye(n_features))
# compare with an empirical covariance learnt from a pure data set
# (i.e. "perfect" MCD)
pure_X = X[inliers_mask]
pure_location = pure_X.mean(0)
pure_emp_cov = EmpiricalCovariance().fit(pure_X)
err_loc_emp_pure[i, j] = np.sum(pure_location**2)
err_cov_emp_pure[i, j] = pure_emp_cov.error_norm(np.eye(n_features))
# Display results
font_prop = matplotlib.font_manager.FontProperties(size=11)
pl.subplot(2, 1, 1)
for j in range(repeat):
# generate data
X = np.random.randn(n_samples, n_features)
# add some outliers
outliers_index = np.random.permutation(n_samples)[:n_outliers]
outliers_offset = 10. * \
(np.random.randint(2, size=(n_outliers, n_features)) - 0.5)
X[outliers_index] += outliers_offset
inliers_mask = np.ones(n_samples).astype(bool)
inliers_mask[outliers_index] = False
# fit a Minimum Covariance Determinant (MCD) robust estimator to data
S = MinCovDet().fit(X)
# compare raw robust estimates with the true location and covariance
err_loc_mcd[i, j] = np.sum(S.location_ ** 2)
err_cov_mcd[i, j] = S.error_norm(np.eye(n_features))
# compare estimators learnt from the full data set with true parameters
err_loc_emp_full[i, j] = np.sum(X.mean(0) ** 2)
err_cov_emp_full[i, j] = EmpiricalCovariance().fit(X).error_norm(
np.eye(n_features))
# compare with an empirical covariance learnt from a pure data set
# (i.e. "perfect" MCD)
pure_X = X[inliers_mask]
pure_location = pure_X.mean(0)
pure_emp_cov = EmpiricalCovariance().fit(pure_X)
err_loc_emp_pure[i, j] = np.sum(pure_location ** 2)
err_cov_emp_pure[i, j] = pure_emp_cov.error_norm(np.eye(n_features))
# Display results
font_prop = matplotlib.font_manager.FontProperties(size=11)
pl.subplot(2, 1, 1)
