def dr(X, y, savedir, ds):
# First do pca
pca_pipe = A3.pca(X, y)
pca = pca_pipe.named_steps['pca']
plt.savefig('{}/{}-pca.png'.format(savedir, ds))
np.savetxt('{}/{}-pca-ev.csv'.format(savedir, ds), pca.explained_variance_)
np.savetxt('{}/{}-pca-ev-ratio.csv'.format(savedir, ds),
pca.explained_variance_ratio_)
plt.close('all')
plt.plot(np.cumsum(pca.explained_variance_ratio_))
plt.xlabel('n_components')
plt.ylabel('explained variance (%)')
plt.savefig('{}/{}-pca-ev.png'.format(savedir, ds))
plt.close('all')
reconstruction_error = A3.recon_error(pca, X)
logging.info('PCA reconstruction error: {}'.format(reconstruction_error))
# second ICA
ica = None
max_kurtosis = -np.inf
ica_range = range(10, X.shape[1], 10)
kurt_per_comp = []
for i in ica_range:
ica_pipe = A3.ica(X, y, i)
# This should be selected by kurtosis
kurt = A3.avg_kurtosis(ica_pipe.transform(X))
kurt_per_comp.append(kurt)
logging.info('ICA {} average kurtosis: {}'.format(i, kurt))
if kurt > max_kurtosis:
ica = ica_pipe.named_steps['fastica']
max_kurtosis = kurt
logging.info('ICA max kurtosis {} with {} components'.format(
max_kurtosis, ica.components_.shape[0]))
plt.plot(ica_range, kurt_per_comp)
plt.xlabel('n_components')
plt.ylabel('mean kurtosis')
plt.savefig('{}/{}-ica-kurtosis.png'.format(savedir, ds))
# RP
logging.info('Starting randomized projection...')
rp_errors = []
rp = None
best_rp_err = np.inf
reconstruction_errors = []
for rp_run in range(10):
logging.info('RP iteration {}'.format(rp_run))
best_run = np.inf
run_errors = []
for i in range(10, X.shape[1], 10):
rp_pipe = A3.random_projection(X, y, i)
err = A3.recon_error(
rp_pipe.named_steps['gaussianrandomprojection'], X)
run_errors.append(err)
logging.info('RP {} components reconstruction error: {}'.format(
i, err))
if err < best_rp_err:
rp = rp_pipe.named_steps['gaussianrandomprojection']
best_rp_err = err
if err < best_run:
best_run = err
reconstruction_errors.append(run_errors)
rp_errors.append(best_run)
pd.DataFrame(reconstruction_errors,
columns=range(10, X.shape[1], 10)).to_csv(
'{}/{}-rp-reconstruction.csv'.format(savedir, ds))
# Manually set random projection
if ds == 'musk':
rp.set_params(n_components=50)
elif ds == 'shoppers':
rp.set_params(n_components=30)
plt.figure()
plt.plot(range(10), rp_errors)
plt.xlabel('iteration')
plt.ylabel('reconstruction error')
plt.savefig('{}/{}-rp-reconstruction.png'.format(savedir, ds))
plt.close('all')
logging.info('RP best n_components: {}'.format(rp.n_components_))
# TODO: fourth dimension reduction
rf_pipe = A3.rfselect(X, y)
rf = rf_pipe.named_steps['randomforest']
return [pca, ica, rp, rf]