def apply_kmeans(do_pca, x_train, y_train, x_test, y_test, kmeans_max_iter, kmeans_max_k):
print('kmeans\n')
train_sses_vs_iter = []
train_sses_vs_k = []
train_purities_vs_k = []
##################################
# YOUR CODE GOES HERE #
##################################
max_repeat = 7
for repeat in range(1, max_repeat):
if repeat == 1:
for k in range(1, kmeans_max_k):
kmeans = KMeans(k, kmeans_max_iter)
sse_vs_iter = kmeans.fit(x_train)
train_sses_vs_iter.append(sse_vs_iter)
train_purities_vs_k.append(kmeans.get_purity(x_train, y_train))
train_sses_vs_k.append(min(sse_vs_iter))
elif repeat == max_repeat-1:
for k in range(1, kmeans_max_k):
kmeans = KMeans(k, kmeans_max_iter)
sse_vs_iter = kmeans.fit(x_train)
train_sses_vs_iter[k-1] += sse_vs_iter[k-1]
train_sses_vs_iter[k-1] = train_sses_vs_iter[k-1]/repeat
train_purities_vs_k[k-1] += kmeans.get_purity(x_train, y_train)
train_purities_vs_k[k-1] = train_purities_vs_k[k-1] / repeat
print("Purity: ", train_purities_vs_k[k-1])
train_sses_vs_k[k-1] += min(sse_vs_iter)
train_sses_vs_k[k-1] = train_sses_vs_k[k-1]/repeat
else:
for k in range(1, kmeans_max_k):
kmeans = KMeans(k, kmeans_max_iter)
sse_vs_iter = kmeans.fit(x_train)
train_sses_vs_iter[k-1] += sse_vs_iter[k-1]
train_purities_vs_k[k-1] += kmeans.get_purity(x_train, y_train)
train_sses_vs_k[k-1] += min(sse_vs_iter)
plot_y_vs_x_list(train_sses_vs_iter, x_label='iter', y_label='sse',
save_path='plot_sse_vs_k_subplots_%d'%do_pca)
plot_y_vs_x(train_sses_vs_k, x_label='k', y_label='sse',
save_path='plot_sse_vs_k_%d'%do_pca)
plot_y_vs_x(train_purities_vs_k, x_label='k', y_label='purities',
save_path='plot_purity_vs_k_%d'%do_pca)
def apply_kmeans(do_pca, x_train, y_train, kmeans_max_iter, kmeans_max_k):
print('kmeans\n')
train_sses_vs_iter = []
train_sses_vs_k = []
train_purities_vs_k = []
##################################
# YOUR CODE GOES HERE #
##################################
# iterations for 5 different runs of k-means.
for k in range(0, 5):
kmeans = KMeans(6, kmeans_max_iter)
sse_vs_iter = kmeans.fit(x_train)
train_sses_vs_iter.append(sse_vs_iter)
train_purities_vs_k.append(kmeans.get_purity(x_train, y_train))
train_sses_vs_k.append(min(sse_vs_iter))
if k == 0:
avg_list = [0] * len(sse_vs_iter)
avg_list = [
avg_list[i] + sse_vs_iter[i] for i in range(len(sse_vs_iter))
]
plot_y_vs_x_list(train_sses_vs_iter,
x_label='iter',
y_label='sse',
save_path='plot_sse_vs_k_subplots_%d' % do_pca)
plot_y_vs_x(avg_list,
x_label='iterations',
y_label='sse',
save_path='plot_sse_vs_iter_%d' % do_pca)
def apply_kmeans(do_pca, x_train, y_train, kmeans_max_iter, kmeans_max_k):
print('kmeans\n')
train_sses_vs_iter = []
train_sses_vs_k = []
train_purities_vs_k = []
##################################
# YOUR CODE GOES HERE #
##################################
start = time.time()
for k in range(1, kmeans_max_k):
print("On step k =", k, "of", kmeans_max_k,
"\telapsed time: %.2f" % (time.time() - start), "s")
kmeans = KMeans(k, kmeans_max_iter)
sse_vs_iter = kmeans.fit(x_train)
train_sses_vs_iter.append(sse_vs_iter)
train_purities_vs_k.append(kmeans.get_purity(x_train, y_train))
train_sses_vs_k.append(min(sse_vs_iter))
plot_y_vs_x_list(train_sses_vs_iter,
x_label='iter',
y_label='sse',
save_path='plot_sse_vs_k_subplots_%d' % do_pca)
plot_y_vs_x(train_sses_vs_k,
x_label='k',
y_label='sse',
save_path='plot_sse_vs_k_%d' % do_pca)
plot_y_vs_x(train_purities_vs_k,
x_label='k',
y_label='purities',
save_path='plot_purity_vs_k_%d' % do_pca)
def apply_kmeans(do_pca, x_train, y_train, x_test, y_test, kmeans_max_iter,
kmeans_max_k):
print('kmeans\n')
train_sses_vs_iter = []
train_sses_vs_k = []
train_purities_vs_k = []
##################################
# YOUR CODE GOES HERE #
##################################
for k in range(1, kmeans_max_k):
kmeans = KMeans(k, kmeans_max_iter)
sse_vs_iter = kmeans.fit(x_train)
train_sses_vs_iter.append(sse_vs_iter)
train_purities_vs_k.append(kmeans.get_purity(x_train, y_train))
train_sses_vs_k.append(min(sse_vs_iter))
plot_y_vs_x_list(train_sses_vs_iter,
x_label='iter',
y_label='sse',
save_path='plot_sse_vs_k_subplots_%d' % do_pca)
plot_y_vs_x(train_sses_vs_k,
x_label='k',
y_label='sse',
save_path='plot_sse_vs_k_%d' % do_pca)
plot_y_vs_x(train_purities_vs_k,
x_label='k',
y_label='purities',
save_path='plot_purity_vs_k_%d' % do_pca)
def apply_kmeans3(do_pca, x_train, y_train, kmeans_max_iter, kmeans_max_k):
print('kmeans\n')
train_sses_vs_iter = []
train_sses_vs_k = []
train_purities_vs_k = []
##################################
# YOUR CODE GOES HERE #
##################################
result = []
for k in range(1, 11):
print('k:', k)
for times in range(0, 5):
kmeans = KMeans(k, kmeans_max_iter)
sse_vs_iter = kmeans.fit(x_train)
train_sses_vs_iter.append(sse_vs_iter)
train_purities_vs_k.append(kmeans.get_purity(x_train, y_train))
train_sses_vs_k.append(min(sse_vs_iter))
print(train_purities_vs_k)
avg = sum(train_purities_vs_k) / len(train_purities_vs_k)
result.append(avg)
train_purities_vs_k = []
print(result)
print('max purity', max(result))
plot_y_vs_x(result,
x_label='k',
y_label='purities',
save_path='plot_purity_vs_k_%d' % do_pca)
def apply_kmeans1(do_pca, x_train, y_train, kmeans_max_iter, kmeans_max_k):
print('kmeans\n')
train_sses_vs_iter = []
train_sses_vs_k = []
train_purities_vs_k = []
##################################
# YOUR CODE GOES HERE #
##################################
for run in range(0, 5):
kmeans = KMeans(6, kmeans_max_iter)
sse_vs_iter = kmeans.fit(x_train)
train_sses_vs_iter.append(sse_vs_iter)
train_purities_vs_k.append(kmeans.get_purity(x_train, y_train))
train_sses_vs_k.append(min(sse_vs_iter))
result = []
for col in range(len(train_sses_vs_iter[0])):
sum = 0
for row in range(0, 5):
sum += train_sses_vs_iter[row][col]
sum = sum / 5
result.append(sum)
result = [result]
print(result)
plot_y_vs_x_list(result,
x_label='iter',
y_label='sse',
save_path='plot_sse_vs_k_subplots_%d' % do_pca)
def apply_kmeans(do_pca, x_train, y_train, kmeans_max_iter, kmeans_max_k):
print('kmeans\n')
train_sses_vs_iter = []
train_sses_vs_k = []
train_purities_vs_k = []
##################################
# YOUR CODE GOES HERE #
##################################
for k in range(1, kmeans_max_k):
sses = None
avg_purity = 0.
# do five tests to reduce effect of random start
for i in range(5):
kmeans = KMeans(k, kmeans_max_iter)
sse = kmeans.fit(x_train)
if (sses == None):
sses = sse
else:
for j in range(len(sse)):
sses[j] = (sses[j] + sse[j])
avg_purity += kmeans.get_purity(x_train, y_train)
avg_purity = avg_purity / 5.
for j in range(len(sses)):
sses[j] = sses[j] / 5.0
# avg_sses = np.sum(np.array(sses), 0) / 5
train_sses_vs_iter.append(sses)
train_purities_vs_k.append(avg_purity)
train_sses_vs_k.append(min(sses))
plot_y_vs_x_list(train_sses_vs_iter,
x_label='iter',
y_label='sse',
save_path='plot_sse_vs_k_subplots_%d' % do_pca)
plot_y_vs_x(train_sses_vs_k,
x_label='k',
y_label='sse',
save_path='plot_sse_vs_k_%d' % do_pca)
plot_y_vs_x(train_purities_vs_k,
x_label='k',
y_label='purities',
save_path='plot_purity_vs_k_%d' % do_pca)
def apply_kmeans_3(do_pca, x_train, y_train, kmeans_max_iter, kmeans_max_k):
train_sses_vs_iter = []
train_sses_vs_k = []
train_purities_vs_k = []
averg_list = []
for k in range(1, 11):
for it in range(0, 5):
kmeans = KMeans(k, kmeans_max_iter)
sse_vs_iter = kmeans.fit(x_train)
train_sses_vs_iter.append(sse_vs_iter)
train_purities_vs_k.append(kmeans.get_purity(x_train, y_train))
train_sses_vs_k.append(min(sse_vs_iter))
averg_list.append(
(sum(train_purities_vs_k) / len(train_purities_vs_k)))
#plot the average purity
plot_y_vs_x(averg_list,
x_label='k',
y_label='purities',
save_path='plot_purity_vs_k_%d' % do_pca)
def apply_kmeans_2(do_pca, x_train, y_train, kmeans_max_iter, kmeans_max_k):
print('kmeans\n')
train_sses_vs_iter = []
train_sses_vs_k = []
train_purities_vs_k = []
avg_me = []
for k in range(1, 11):
for it in range(0, 5):
kmeans = KMeans(k, kmeans_max_iter)
sse_vs_iter = kmeans.fit(x_train)
train_sses_vs_iter.append(sse_vs_iter)
train_purities_vs_k.append(kmeans.get_purity(x_train, y_train))
train_sses_vs_k.append(min(sse_vs_iter))
avg_me.append((sum(train_sses_vs_k) / len(train_sses_vs_k)))
plot_y_vs_x(avg_me,
x_label='k',
y_label='sse',
save_path='plot_sse_vs_k_%d' % do_pca)
def apply_kmeans_avg(x_train, y_train, kmeans_max_iter, k, iterations=5):
train_sses_vs_iter = None
sse = 0
purity = 0
print("")
for step in range(iterations):
print("On step ", step + 1, "of", iterations, "for k =", k)
kmeans = KMeans(k, kmeans_max_iter)
sse_vs_iter_loop = np.array(kmeans.fit(x_train))
# initialize the train sse array
if train_sses_vs_iter is None:
train_sses_vs_iter = np.zeros(len(sse_vs_iter_loop))
train_sses_vs_iter += sse_vs_iter_loop
purity += kmeans.get_purity(x_train, y_train)
sse += sse_vs_iter_loop.min()
return (train_sses_vs_iter /
iterations).tolist(), sse / iterations, purity / iterations
def apply_kmeans(do_pca, x_train, y_train, kmeans_max_iter, kmeans_max_k):
train_sses_vs_iter = []
train_sses_vs_k = []
train_purities_vs_k = []
##################################
# YOUR CODE GOES HERE #
##################################
sses_sum = 0
purities_sum = 0
for k in range(1, kmeans_max_k):
# for k in range(1, 6):
for i in range(5):
kmeans = KMeans(k, kmeans_max_iter)
sse_vs_iter = kmeans.fit(x_train)
sses_sum += min(sse_vs_iter)
purities_sum += kmeans.get_purity(x_train, y_train)
print(k)
sses_sum /= 5
purities_sum /= 5
train_sses_vs_k.append(sses_sum)
train_purities_vs_k.append(purities_sum)
print(train_sses_vs_k)
print(train_purities_vs_k)
plot_y_vs_x_list(train_sses_vs_iter,
x_label='iter',
y_label='sse',
save_path='plot_sse_vs_k_subplots_%d' % do_pca)
plot_y_vs_x(train_sses_vs_k,
x_label='k',
y_label='sse',
save_path='plot_sse_vs_k_%d' % do_pca)
plot_y_vs_x(train_purities_vs_k,
x_label='k',
y_label='purities',
save_path='plot_purity_vs_k_%d' % do_pca)
