def run_dr_clustering():
deposit_data = load_cleanse_data()
income_data = loadData()
pcakMeans(deposit_data, 7, 'deposit', 'manhattan')
# running PCA/kmeans for income Data
pcakMeans(income_data, 4, 'income', 'euclidean')
# running PCA/em for Deposit Data
pcaem(deposit_data, 7, 'deposit', 'manhattan')
# running PCA/em for Deposit Data
pcaem(income_data, 4, 'income', 'euclidean')
# ICA for deposit clustering
icakMeans(deposit_data, 35, 'deposit', 'manhattan')
icaem(deposit_data, 35, 'deposit', 'manhattan')
# ICA for income clustering
icakMeans(income_data, 12, 'income', 'euclidean')
icaem(income_data, 12, 'income', 'euclidean')
rpkMeans(deposit_data, 30, 'deposit', 'manhattan')
rpem(deposit_data, 30, 'deposit', 'manhattan')
# ICA for income clustering
rpkMeans(income_data, 8, 'income', 'euclidean')
rpem(income_data, 8, 'income', 'euclidean')
uvfskMeans(deposit_data, 30, 'deposit', 'manhattan')
uvfsem(deposit_data, 30, 'deposit', 'manhattan')
uvfskMeans(income_data, 10, 'income', 'euclidean')
uvfsem(income_data, 10, 'income', 'euclidean')
def performIncomePCA():
data = loadData()
pca.perform_pca(data['features'], 'income')
pca.validate_pca_nn(data, [4, 6, 8, 10, 12,14], 'income')
def performIncomeuvfs():
data = loadData()
uvfs.validate_uvfs_nn(data, [4, 6, 8, 10, 12, 14],'income')
def performIncomeRandomProjection():
data = loadData()
randomprojection.validate_rp_nn(data, [4, 6, 8, 10, 12, 14],'income')
def performIncomeICA():
data = loadData()
ica.perform_ica(data['features'], 'income', [4, 6, 8, 10, 12, 14])
ica.validate_ica_nn(data, [4, 6, 8, 10, 12, 14], 'income')
def income_em():
data = loadData()
print(data)
estimate_em_k(data, 'income', 'plots/em/', 'euclidean')
validate_em_k(data, 'plots/em/', 'income')
def income_clustering():
data = loadData()
estimate_k(data, 'income', 'plots/kmeans/', 'euclidean')
validate_k(data, 'plots/kmeans/', 'income')