def B1(pca=False):
'''
Plot WC_SSD and SC over K.
'''
K = [2, 4, 6, 8, 16, 32]
fnames = [
'digits-embedding.csv', 'digits-embedding-2467.csv',
'digits-embedding-67.csv'
]
wc_ssd_val = zeros((len(fnames), len(K)))
sc_val = zeros((len(fnames), len(K)))
for i, fname in enumerate(fnames):
X = genfromtxt(fname, delimiter=',')[:, 2:]
for j, k in enumerate(K):
kmeans = KMeans(n_clusters=k)
kmeans.fit(X)
wc_ssd_val[i, j], sc_val[i, j], _ = kmeans.get_evals()
# Plot WC_SSD
figure()
for i, fname in enumerate(fnames):
plot(K, wc_ssd_val[i], label=fname)
legend()
title('WC_SSD v.s. K')
figure()
for i, fname in enumerate(fnames):
plot(K, sc_val[i], label=fname)
legend()
title('SC v.s. K')
show()
def B4(pca=False):
'''
Evaluate using NMI and visualize in 2D.
'''
fnames = [
'digits-embedding.csv', 'digits-embedding-2467.csv',
'digits-embedding-67.csv'
]
nmi = zeros(len(fnames))
for i, k, fname in zip([0, 1, 2], [8, 4, 2], fnames):
raw = genfromtxt(fname, delimiter=',')
X = raw[:, 2:]
y = get_normalized_labels(raw[:, 1])
kmeans = KMeans(n_clusters=k)
ind = kmeans.fit(X, y)
_, _, nmi[i] = kmeans.get_evals()
figure()
perm = permutation(X.shape[0])[:1000]
X = X[perm]
ind = ind[perm]
colors = rand(k, 3)[ind, :]
scatter(X[:, 0], X[:, 1], c=colors, alpha=0.9, s=30)
print(fnames)
print("NMI =", nmi)
show()
def Bonus4():
'''
Repeat B1, B2, B4 with PCA embedding.
'''
K = [2, 4, 6, 8, 16, 32]
fnames = [
'digits-pca-embedding.csv', 'digits-pca-embedding-2467.csv',
'digits-pca-embedding-67.csv'
]
wc_ssd_val = zeros((len(fnames), len(K), 10))
sc_val = zeros((len(fnames), len(K), 10))
nmi_val = zeros((len(fnames), len(K), 10))
for i, fname in enumerate(fnames):
raw = genfromtxt(fname, delimiter=',')
X = raw[:, 2:]
y = get_normalized_labels(raw[:, 1])
for j, k in enumerate(K):
for m in range(10):
kmeans = KMeans(n_clusters=k)
ind = kmeans.fit(X, y)
wc_ssd_val[i, j,
m], sc_val[i, j,
m], nmi_val[i, j,
m] = kmeans.get_evals()
figure()
perm = permutation(X.shape[0])[:1000]
X = X[perm]
ind = ind[perm]
colors = rand(k, 3)[ind, :]
scatter(X[:, 0], X[:, 1], c=colors, alpha=0.9, s=30)
save('Bonus_wc_ssd_val.npy', wc_ssd_val)
save('Bonus_sc_val.npy', sc_val)
save('Bonus_nmi_val.npy', nmi_val)
wc_ssd_val = load('Bonus_wc_ssd_val.npy')
sc_val = load('Bonus_sc_val.npy')
# nmi_val = load('Bonus_nmi_val.npy')
ssd_means = mean(wc_ssd_val, axis=2)
sc_means = mean(sc_val, axis=2)
ssd_std = std(wc_ssd_val, axis=2)
sc_std = std(sc_val, axis=2)
# Plot WC_SSD
figure()
for i, fname in enumerate(fnames):
errorbar(K, ssd_means[i], ssd_std[i], capsize=4, label=fname)
legend()
title('WC_SSD v.s. K')
figure()
for i, fname in enumerate(fnames):
errorbar(K, sc_means[i], sc_std[i], capsize=4, label=fname)
legend()
title('SC v.s. K')
print(fnames)
print("NMI =", mean(nmi_val, axis=2))
show()
def B3():
'''
Repeat 10 times for each K.
'''
K = [2, 4, 6, 8, 16, 32]
fnames = [
'digits-embedding.csv', 'digits-embedding-2467.csv',
'digits-embedding-67.csv'
]
wc_ssd_val = zeros((len(fnames), len(K), 10))
sc_val = zeros((len(fnames), len(K), 10))
for i, fname in enumerate(fnames):
X = genfromtxt(fname, delimiter=',')[:, 2:]
for j, k in enumerate(K):
for m in range(10):
kmeans = KMeans(n_clusters=k)
kmeans.fit(X)
wc_ssd_val[i, j, m], sc_val[i, j, m], _ = kmeans.get_evals()
save('B3_wc_ssd_val.npy', wc_ssd_val), save('B3_sc_val.npy', sc_val)
wc_ssd_val = load('B3_wc_ssd_val.npy')
sc_val = load('B3_sc_val.npy')
ssd_means = mean(wc_ssd_val, axis=2)
sc_means = mean(sc_val, axis=2)
ssd_std = std(wc_ssd_val, axis=2)
sc_std = std(sc_val, axis=2)
# Plot WC_SSD
figure()
for i, fname in enumerate(fnames):
errorbar(K, ssd_means[i], ssd_std[i], capsize=4, label=fname)
legend()
title('WC_SSD v.s. K')
figure()
for i, fname in enumerate(fnames):
errorbar(K, sc_means[i], sc_std[i], capsize=4, label=fname)
legend()
title('SC v.s. K')
show()
