def main():
fnm = 'prob5.data'
patterns = md.read_data(fnm).T
patterns = km.augment_patterns(patterns)
k = 4 # Number of clusters. Figure out where to put this
current_centers = km.init_cluster_centers(patterns, k)
iteration_count = 0
errors = np.matrix((1, k))
while True:
cluster_assignments = km.cluster_patterns(
patterns, current_centers)
patterns[0,] = cluster_assignments
km.plot_patterns_and_centers(patterns, current_centers)
new_means = km.calculate_new_means(patterns, k)
mean_diff = current_centers[1:,1:] - new_means[1:,1:]
errors = (mean_diff.T * mean_diff).diagonal()
iteration_count += 1
if (errors > .1).any():
current_centers = new_means
else:
break
print(current_centers[0,:])
print(errors)
print('Converged in', iteration_count,'iterations.')
def main():
fnm = 'prob3.data'
data = md.read_data(fnm)
D1 = data[0:8,].T
D2 = data[8:,].T
u1 = np.matrix((np.mean(D1[0,:]), np.mean(D1[1,:]))).T
u2 = np.matrix((np.mean(D2[0,:]), np.mean(D2[1,:]))).T
sigma1 = np.asmatrix(np.cov(D1, bias=1))
sigma2 = np.asmatrix(np.cov(D1, bias=1))
g1 = discrim_func(u1, sigma1)
g2 = discrim_func(u2, sigma2)
steps = 100
x = np.linspace(-2,2,steps)
y = np.linspace(-6,6,steps)
X,Y = np.meshgrid(x,y)
z = [g1(X[r,c], Y[r,c]) - g2(X[r,c], Y[r,c])
for r in range(0,steps) for c in range(0,steps)]
Z = np.array(z)
px = X.ravel()
py = Y.ravel()
pz = Z.ravel()
gridsize = 50
plot = plt.subplot(111)
plt.hexbin(px,py,C=pz, gridsize=gridsize, cmap=cm.jet, bins=None)
cb = plt.colorbar()
cb.set_label('g1 minus g2')
return plot
def main():
p1a_fnm = 'prob1a.data'
p1b_fnm = 'prob1b.data'
# Separate omega 1 and 2
p1a_data = md.read_data(p1a_fnm)
(tc, w) = bp.separate(p1a_data)
print("Separated omega 1 and omega 2 in", tc, "iterations")
bp.plot_solution(w, p1a_data, "Problem 1a",
dict(mincat="Omega 1", maxcat="Omega 2"))
# Separate omega 2 and 3
p1b_data = md.read_data(p1b_fnm)
(tc, w) = bp.separate(p1b_data)
print("Separated omega 2 and omega 3 in", tc, "iterations")
bp.plot_solution(w, p1b_data, "Problem 1b",
dict(mincat="Omega 2", maxcat="Omega 3"))
def main():
p1a_fnm = 'prob1a.data'
p1b_fnm = 'prob1b.data'
# Separate omega 1 and 2
p1a_data = md.read_data(p1a_fnm)
(tc, w) = bp.separate(p1a_data)
print("Separated omega 1 and omega 2 in", tc, "iterations")
bp.plot_solution(w, p1a_data, "Problem 1a",
dict(mincat="Omega 1", maxcat="Omega 2"))
# Separate omega 2 and 3
p1b_data = md.read_data(p1b_fnm)
(tc, w) = bp.separate(p1b_data)
print("Separated omega 2 and omega 3 in", tc, "iterations")
bp.plot_solution(w, p1b_data, "Problem 1b",
dict(mincat="Omega 2", maxcat="Omega 3"))
def make_data():
datax, datay = read_data('data.xlsx')
#[]变为（[]） 将序列型对象转化为数组
datax = np.array(datax)
datay = np.array(datay)
random_index = random.sample(list(range(datax.shape[0])), datax.shape[0])
#shape[0]数组行数，生成指定列表 从0到行数的列表，list将元组转化为列表
train_size = int(datax.shape[0] * 0.6)#转化为整型
train_index = random_index[:train_size] #索引范围
test_index = list(set(random_index).difference(set(train_index)))
train_feature = datax[train_index]
train_label = datay[train_index]
test_feature = datax[test_index]
test_label = datay[test_index]
return train_feature, train_label, test_feature, test_label
def main():
fnm = 'p4.data'
# Read the data into a one-dimensional array
data = np.array(md.read_data(fnm)).squeeze()
h = 1 # Window size
# Create plots for the zero-one window function
phi = pw.zero_one(h)
print("Zero-one window function...")
plot_data(phi, data, "Zero-One Window", "images/zero-one.eps")
# Create plots for the Gauss window function
phi = pw.gauss(h)
print("Gauss window function...")
plot_data(phi, data, "Gauss Window", "images/gauss.eps")
def main():
training_data = md.circle_data(40)
training_data = md.convert_data(training_data)
# Make a test data set
test_data = md.read_data('homework1_data.csv')
test_data = md.convert_data(test_data)
alpha = 0.5
theta = .0001
iter_limit = 50000
mynet = nn.NeuralNet((2, 2, 1), sf.bipolar, sf.bipolar_prime, alpha)
n = training_data.shape[0]
total_count = 0
k = -1
plot_data = np.matrix("0 0")
fh = open('nn_quad.csv', 'w')
while True:
total_count += 1
k = (k + 1) % n
#k = np.random.randint(0, n)
pattern = np.asarray(training_data[k, 1:]).squeeze()
teacher = [training_data[k, 0]]
error = mynet.train(pattern, teacher, theta)
if (total_count % 10) == 0:
plot_data = np.vstack((plot_data, np.matrix((total_count, error))))
msg = ','.join([str(total_count), str(error)])
fh.write(msg)
fh.write('\n')
if (total_count > iter_limit) or (error < theta):
print("Stopped at iter count ", total_count,
"with a final error of ", error)
break
mynet.dt.tofile('bub_quad.txt')
fh.close()
plt.plot(plot_data[0:, 0], plot_data[0:, 1])
plt.show()
counter = check_net(test_data, mynet.fwd)
print('Assigned', counter, 'patterns of', test_data.shape[0], 'correctly.')
def main():
training_data = md.circle_data(40)
training_data = md.convert_data(training_data)
# Make a test data set
test_data = md.read_data('homework1_data.csv')
test_data = md.convert_data(test_data)
alpha = 0.5
theta = .0001
iter_limit = 50000
mynet = nn.NeuralNet((2,2,1), sf.bipolar, sf.bipolar_prime, alpha)
n = training_data.shape[0]
total_count = 0
k = -1
plot_data = np.matrix("0 0")
fh = open('nn_quad.csv', 'w')
while True:
total_count += 1
k = (k+1) % n
#k = np.random.randint(0, n)
pattern = np.asarray(training_data[k,1:]).squeeze()
teacher = [training_data[k,0]]
error = mynet.train(pattern, teacher, theta)
if (total_count % 10) == 0:
plot_data = np.vstack((plot_data, np.matrix((total_count, error))))
msg = ','.join([str(total_count), str(error)])
fh.write(msg)
fh.write('\n')
if (total_count > iter_limit) or (error < theta):
print("Stopped at iter count ",
total_count, "with a final error of ", error)
break
mynet.dt.tofile('bub_quad.txt')
fh.close()
plt.plot(plot_data[0:,0], plot_data[0:,1])
plt.show()
counter = check_net(test_data, mynet.fwd)
print('Assigned', counter, 'patterns of', test_data.shape[0],'correctly.')
def main():
fnm = 'prob5.data'
patterns = md.read_data(fnm).T
patterns = km.augment_patterns(patterns)
k = 4 # Number of clusters. Figure out where to put this
current_centers = km.init_cluster_centers(patterns, k)
iteration_count = 0
errors = np.matrix((1, k))
while True:
cluster_assignments = km.cluster_patterns(patterns, current_centers)
patterns[0, ] = cluster_assignments
km.plot_patterns_and_centers(patterns, current_centers)
new_means = km.calculate_new_means(patterns, k)
mean_diff = current_centers[1:, 1:] - new_means[1:, 1:]
errors = (mean_diff.T * mean_diff).diagonal()
iteration_count += 1
if (errors > .1).any():
current_centers = new_means
else:
break
print(current_centers[0, :])
print(errors)
print('Converged in', iteration_count, 'iterations.')