def compare_cluster_runtime(data, n_clusters, n_components):
t0 = time()
features = data[0]
KMeans(n_clusters=n_clusters).fit_transform(features)
t1 = time() - t0
t0 = time()
mixture.GMM(n_components=n_clusters).fit(features)
t2 = time() - t0
reduced_higgs_data, t3 = pca_eval.transform(data, n_components=n_components)
reduced_higgs_data, t4 = rand_projections.transform(data, n_components=n_components)
reduced_higgs_data, t5 = ica_eval.transform(data, n_components=n_components)
reduced_higgs_data, t6 = trunk_svd.transform(data, n_components=n_components)
t0 = time()
KMeans(n_clusters=n_clusters).fit_transform(reduced_higgs_data)
t7 = time() - t0
t0 = time()
mixture.GMM(n_components=n_clusters).fit(reduced_higgs_data)
t8 = time() - t0
ser = pd.Series([t1, t2, t3, t4, t5, t6, t7, t8], index=['original Kmeans clustering',
'original GMM clustering',
'PCA', 'RCA', 'ICA', 'LSA',
'reduced Kmeans clustering',
'reduced GMM clustering'])
ser.name = 'time'
return ser
def run_higg_dimensionality_reduction(higgs_data, n_components):
pca_trns, pca_elapsed = pca_eval.transform(higgs_data, n_components=n_components)
rand_proj_trns, rand_proj_elapsed = rand_projections.transform(higgs_data, n_components=n_components)
ica_trns, ica_elapsed = ica_eval.transform(higgs_data, n_components=n_components)
lsa_trns, lsa_elapsed = trunk_svd.transform(higgs_data, n_components=n_components)
transformation_time = pd.Series([pca_elapsed, rand_proj_elapsed, ica_elapsed, lsa_elapsed],
index=['PCA', 'RCA', 'ICA', 'LSA'],
name='transformation_time')
return {'PCA': pca_trns, 'RCA': rand_proj_trns, 'ICA': ica_trns, 'LSA': lsa_trns}, transformation_time
def run_higg_dimensionality_reduction(higgs_data, n_components):
pca_trns, pca_elapsed = pca_eval.transform(higgs_data,
n_components=n_components)
rand_proj_trns, rand_proj_elapsed = rand_projections.transform(
higgs_data, n_components=n_components)
ica_trns, ica_elapsed = ica_eval.transform(higgs_data,
n_components=n_components)
lsa_trns, lsa_elapsed = trunk_svd.transform(higgs_data,
n_components=n_components)
transformation_time = pd.Series(
[pca_elapsed, rand_proj_elapsed, ica_elapsed, lsa_elapsed],
index=['PCA', 'RCA', 'ICA', 'LSA'],
name='transformation_time')
return {
'PCA': pca_trns,
'RCA': rand_proj_trns,
'ICA': ica_trns,
'LSA': lsa_trns
}, transformation_time