def demo():
import matplotlib.pyplot as plt
from kmeans import kmeans_cluster
np.random.seed(1111)
dim, k = 2, 2
# generate data
num = 50
mean1 = np.zeros(dim)
mean2 = np.ones(dim) * 2
cov1 = np.eye(dim)
cov2 = np.eye(dim) * 0.5
x1 = np.random.multivariate_normal(mean1, cov1, [
num,
])
x2 = np.random.multivariate_normal(mean2, cov2, [
num,
])
x = np.concatenate([x1, x2], 0)
plt.scatter(x1[:, 0], x1[:, 1], c='r')
plt.scatter(x2[:, 0], x2[:, 1], c='g')
# init GMM with kmeans
gs = []
centers, assignment = kmeans_cluster(x, k)
weight = []
for i in range(k):
# mean
mean = centers[i]
# covariate
cov = np.eye(dim) * 1e-6
count = 0.
for j in range(num * 2):
if i == assignment[j]:
cov += np.outer(mean - x[j], mean - x[j])
count += 1
cov /= count
weight.append(count / len(x))
gs.append(Gauss(dim, mean, cov))
gmm = GMM(gs, weight)
centers = np.stack([gmm[i].mean for i in range(gmm.k)])
plt.scatter(centers[:, 0], centers[:, 1], c='b', s=50, marker='v')
train_gmm(gmm, x, threshold=1e-4)
centers = np.stack([gmm[i].mean for i in range(gmm.k)])
plt.scatter(centers[:, 0], centers[:, 1], c='y', s=500, marker='^')
test[1][0] = 1.5
test[1][1] = 2.0
test[2][0] = 3.0
test[2][1] = 4.0
test[3][0] = 5.0
test[3][1] = 7.0
test[4][0] = 3.5
test[4][1] = 5.0
test[5][0] = 4.5
test[5][1] = 5.0
test[6][0] = 3.5
test[6][1] = 4.5
#kmeans.lloyd_iteration(test, cluster)
total = 0.0
for i in range(1000):
(C, a, obj) = kmeans.kmeans_cluster(X, 9, 'kmeans++', 1)
total = total + obj
print "ans:"
print total / 1000
result = np.zeros(30)
result[:] = sys.float_info.max
#for i in range(10):
# (C, a, obj) = kmeans.kmeans_cluster(X, i + 1, 'fixed', 10)
# TODO: Test update_assignments function, defined in kmeans.py
# TODO: Test update_centers function, defined in kmeans.py
# TODO: Test lloyd_iteration function, defined in kmeans.py
#result[i + 1] = obj
#idx = np.argmin(result)
mean = np.mean(train_set, axis=0)
s = np.var(train_set, axis=0)**0.5
# Normalize with mean # and standard deviation
for i in range(train_set.shape[0]):
train_set[i] = (train_set[i] - mean) / s
print(train_set)
print(np.mean(train_set, axis=0), np.var(train_set, axis=0), sep='\n')
train_set_PCA = PCA(train_set, threshold)
if len(train_set_PCA) == 0:
print("Threshold is too small. Please input a bigger threshold.\n")
sys.exit(1)
# plot_3D(train_set_PCA, label_set)
sil_coef, cluster_label = kmeans.kmeans_cluster(k, train_set_PCA)
# print(sil_coef)
sil_coef_mean = np.mean(sil_coef)
# Calculate Rand Index
a, d = 0, 0
n = len(label_set)
for i in range(n):
for j in range(i + 1, n):
if (label_set[i] == label_set[j]) and (cluster_label[i]
== cluster_label[j]):
a += 1
elif (label_set[i] != label_set[j]) and (cluster_label[i] !=
cluster_label[j]):
d += 1
pair_cnt = n * (n - 1) // 2
print("kernelval is {}".format(kernel_val.shape))
print("dim, hidden is {},{}".format(dim, hiddens))
assert kernel_val.shape == (dim, hiddens), \
'kernel shape error at {}'.format(layer_name)
except:
use_pretrained_param = False
print(
'2.Shape of the pretrained parameter of {} does not match, '
'use randomly initialized parameter'.format(layer_name))
if use_pretrained_param:
#tk
min_seed = 0
min_seed_val = float(9999999)
for i in xrange(10000):
kmeans1 = kmeans_cluster(kernel_val, nCluster=9800, max_iter=1000)
kmeans2 = XXhash(cWeights=kernel_val, nCluster=9800, seed=i)
#print("shape is {} and {}".format(kmeans1.weight().shape, kmeans2.weight().shape))
temp = sum(map(sum, abs(kmeans1.weight() - kmeans2.weight())))
print("temp is {} for {}".format(temp, i))
if temp < min_seed_val:
min_seed = i
min_seed_val = temp
print("SEED IS THIS!!!!!!{}", min_seed)
kmeans = XXhash(cWeights=kernel_val, nCluster=9800, seed=min_seed)
#kmeans = XXhash(cWeights=kernel_val, nCluster=9800, blocked=True, blocked_param=64)
print("Kmeans label is", kmeans.label())
print("Kmeans cluster_centers is", kmeans.centro())
print("Kmeans weight is", kmeans.weight())
import os
import csv
import numpy as np
import kmeans
data_dir = os.path.join('', 'data')
X = np.genfromtxt(os.path.join(data_dir, 'kmeans_test_data.csv'),
delimiter=',')
a = kmeans.update_assignments(X, C)
C = kmeans.update_centers(X, C, a)
(C, a) = kmeans.lloyd_iteration(X, C)
obj = kmeans.kmeans_obj(X, C, a)
(best_C, best_a, best_obj) = kmeans.kmeans_cluster(X, 5, "random", 2)
# TODO: Run experiments outlined in HW6 PDF
# For question 9 and 10
# from sklearn.decomposition import PCA
mnist_X = np.genfromtxt(os.path.join(data_dir, 'mnist_data.csv'),
delimiter=',')
# X[4][1] = 5.0 # X[5][0] = 4.5 # X[5][1] = 5.0 # X[6][0] = 3.5 # X[6][1] = 4.5 # x = [] # y = [] # for item in X: # x.append(item[0]) # y.append(item[1]) # plt.scatter(x,y) # plt.show() # obj = 0 # for i in range(0,1000): # (best_C, best_a, best_obj) = kmeans.kmeans_cluster(X,9,'kmeans++',1) # obj += best_obj # # print best_obj # print obj / 1000 X = np.genfromtxt(os.path.join(data_dir, 'mnist_data.csv'), delimiter=',') print X.shape[0],X.shape[1] print X[0,0] # x_reduced = PCA(n_components=5).fit_transform(X) print x_reduced.shape[0],x_reduced.shape[1] (best_C, best_a, best_obj) = kmeans.kmeans_cluster(x_reduced, 3, 'fixed', 1) print best_obj print best_C print best_a
if use_pretrained_param:
try:
#kernel_val = np.transpose(kernel_val, (1,0))
print("kernelval is {}".format(kernel_val.shape))
print("dim, hidden is {},{}".format(dim, hiddens))
assert kernel_val.shape == (dim, hiddens), \
'kernel shape error at {}'.format(layer_name)
except:
use_pretrained_param = False
print(
'2.Shape of the pretrained parameter of {} does not match, '
'use randomly initialized parameter'.format(layer_name))
if use_pretrained_param:
#tk
kmeans = kmeans_cluster(kernel_val, max_iter=1000)
#kmeans = kmeans_hash_cluster(kernel_val)
print("Kmeans label is", kmeans.label())
print("Kmeans cluster_centers is", kmeans.centro())
print("Kmeans weight is", kmeans.weight())
kernel_init = tf.constant(kmeans.weight(), dtype=tf.float32)
bias_init = tf.constant(bias_val, dtype=tf.float32)
elif xavier:
kernel_init = tf.contrib.layers.xavier_initializer()
bias_init = tf.constant_initializer(0.0)
else:
kernel_init = tf.truncated_normal_initializer(stddev=stddev,
dtype=tf.float32)
bias_init = tf.constant_initializer(0.0)