plt.xlabel("Pairwise squared distances in original space")
plt.ylabel("Pairwise squared distances in projected space")
plt.title("Pairwise distances distribution for n_components=%d" %
n_components)
cb = plt.colorbar()
cb.set_label('Sample pairs counts')
rates = projected_dists / dists
print("Mean distances rate: %0.2f (%0.2f)"
% (np.mean(rates), np.std(rates)))
plt.savefig('Figs/02b_rp_pwdist_{}_{}'.format(data_name, n_components))
plt.figure()
plt.hist(rates, bins=50, range=(0., 2.), edgecolor='k', **density_param)
plt.xlabel("Squared distances rate: projected / original")
plt.ylabel("Distribution of samples pairs")
plt.title("Histogram of pairwise distance rates for n_components=%d" %
n_components)
plt.savefig('Figs/02b_rp_histogram_{}_{}'.format(data_name, n_components))
plt.clf()
# TODO: compute the expected value of eps and add them to the previous plot
# as vertical lines / region
np.random.seed(0)
digits = load_digits()
X, y = digits.data, digits.target
johnson_lindenstrauss(digits.data, 'digits')
X, y, data = getCreditCardData('./Data/ccdefault.xls', subset=0.2)
johnson_lindenstrauss(data, 'credit')
ax.set_title(
'Dimensionality Reduced Data for NN (using {})'.format(reducer_name))
# For each number of components, find the best classifier results
results = pd.DataFrame(search.cv_results_)
results.to_csv(
path_or_buf='Figs/05_{}_cluster_nn.csv'.format(reducer_name))
best_clfs = results.groupby(components_col).apply(
lambda g: g.nlargest(1, 'mean_test_score'))
best_clfs.plot(x=components_col,
y='mean_test_score',
yerr='std_test_score',
legend=False,
ax=ax)
ax.set_ylabel('Classification accuracy (val)')
ax.set_xlabel('n_components')
plt.tight_layout()
plt.savefig('Figs/05_{}_cluster_nn'.format(reducer_name))
np.random.seed(0)
X, y, data = getCreditCardData('./Data/ccdefault.xls')
reducer = KMeans(random_state=0)
cluster_nn(X, y, reducer, 'kmeans')
reducer = custGMM(GaussianMixture(reg_covar=1.0, random_state=0))
cluster_nn(X, y, reducer, 'gaussian_mix')
plt.plot(range(1, n + 1), test_mean_acc1, 'r')
plt.fill_between(range(1, n + 1),
test_mean_acc1 - 1 * test_std_acc1,
test_mean_acc1 + 1 * test_std_acc1,
alpha=0.10)
plt.plot(range(1, n + 1), train_mean_acc1, 'm')
plt.fill_between(range(1, n + 1),
train_mean_acc1 - 1 * train_std_acc1,
train_mean_acc1 + 1 * train_std_acc1,
alpha=0.10)
plt.legend(('Test Accuracy - {}'.format(data_name),
'Training Accuracy - {}'.format(data_name)))
plt.ylabel('Accuracy')
plt.xlabel('Decision Tree Depth')
plt.tight_layout()
plt.savefig('Figs/DT-depth-{}'.format(data_name))
plt.clf()
if __name__ == "__main__":
np.random.seed(0)
test_size = 0.2
X_train1, X_test1, y_train1, y_test1 = getCreditCardData(
path='./Data/ccdefault.xls', test_size=test_size)
X_train2, X_test2, y_train2, y_test2 = getWineData(
path='./Data/winequality-white.csv', test_size=test_size)
DT(X_train1, X_test1, y_train1, y_test1, 'Credit Card Default', 0.8, 0.9)
DT(X_train2, X_test2, y_train2, y_test2, 'Wine', 0.4, 1.01)