def get_model(num_exm, num_train, lens, feats, anomaly_prob=0.15):
print('Generating {0} sequences, {1} for training, each with {2} anomaly probability.'.format(num_exm, num_train, anomaly_prob))
mean = 0.0
cnt = 0
X = []
Y = []
label = []
for i in range(num_exm):
(exm, lbl, marker) = ToyData.get_2state_gaussian_seq(lens,dims=feats,anom_prob=anomaly_prob)
#if i<4:
# (exm,lbl) = ToyData.get_2state_gaussian_seq(LENS,dims=2,means1=[1,-3],means2=[3,7],vars1=[1,1],vars2=[1,1])
mean += co.matrix(1.0, (1, lens))*exm.trans()
cnt += lens
X.append(exm)
Y.append(lbl)
label.append(marker)
mean = mean / float(cnt)
for i in range(num_exm):
#if (i<10):
# pos = int(np.single(co.uniform(1))*float(LENS)*0.8 + 4.0)
# print pos
# trainX[i][1,pos] = 100.0
for d in range(feats):
X[i][d,:] = X[i][d,:]-mean[d]
return (SOHMM(X[0:num_train],Y[0:num_train]), SOHMM(X[num_train:],Y[num_train:]), SOHMM(X,Y), label)
def get_model(num_exm,
num_train,
lens,
block_len,
blocks=1,
anomaly_prob=0.15):
print(
'Generating {0} sequences, {1} for training, each with {2} anomaly probability.'
.format(num_exm, num_train, anomaly_prob))
cnt = 0
X = []
Y = []
label = []
lblcnt = co.matrix(0.0, (1, lens))
for i in range(num_exm):
(exm, lbl,
marker) = ToyData.get_2state_anom_seq(lens,
block_len,
anom_prob=anomaly_prob,
num_blocks=blocks)
cnt += lens
X.append(exm)
Y.append(lbl)
label.append(marker)
# some lbl statistics
if i < num_train:
lblcnt += lbl
X = normalize_sequence_data(X)
return (SOHMM(X[0:num_train],
Y[0:num_train]), SOHMM(X[num_train:],
Y[num_train:]), SOHMM(X, Y), label)
def get_model(num_exm, num_train, lens, feats, anomaly_prob=0.15):
print(
'Generating {0} sequences, {1} for training, each with {2} anomaly probability.'
.format(num_exm, num_train, anomaly_prob))
mean = 0.0
cnt = 0
X = []
Y = []
label = []
for i in range(num_exm):
(exm, lbl,
marker) = ToyData.get_2state_gaussian_seq(lens,
dims=feats,
anom_prob=anomaly_prob)
#if i<4:
# (exm,lbl) = ToyData.get_2state_gaussian_seq(LENS,dims=2,means1=[1,-3],means2=[3,7],vars1=[1,1],vars2=[1,1])
mean += co.matrix(1.0, (1, lens)) * exm.trans()
cnt += lens
X.append(exm)
Y.append(lbl)
label.append(marker)
mean = mean / float(cnt)
for i in range(num_exm):
#if (i<10):
# pos = int(np.single(co.uniform(1))*float(LENS)*0.8 + 4.0)
# print pos
# trainX[i][1,pos] = 100.0
for d in range(feats):
X[i][d, :] = X[i][d, :] - mean[d]
return (SOHMM(X[0:num_train],
Y[0:num_train]), SOHMM(X[num_train:],
Y[num_train:]), SOHMM(X, Y), label)
def get_model(num_exm, num_train, lens, block_len, blocks=1, anomaly_prob=0.15):
print('Generating {0} sequences, {1} for training, each with {2} anomaly probability.'.format(num_exm, num_train, anomaly_prob))
cnt = 0
X = []
Y = []
label = []
for i in range(num_exm):
(exm, lbl, marker) = ToyData.get_2state_anom_seq(lens, block_len, anom_prob=anomaly_prob, num_blocks=blocks)
cnt += lens
X.append(exm)
Y.append(lbl)
label.append(marker)
X = remove_mean(X,1)
return (SOHMM(X[0:num_train],Y[0:num_train]), SOHMM(X[num_train:],Y[num_train:]), SOHMM(X,Y), label)
def plot_icml_toy_seqs():
from toydata import ToyData
lens = 600
blocks = [1, 2, 5, 10, 20, 40, 60, 100]
data = []
lbl = []
for i in blocks:
(exm, label, marker) = ToyData.get_2state_anom_seq(lens,
120,
anom_prob=1.0,
num_blocks=i)
data.append(exm)
lbl.append(label)
plt.figure(1)
style = ['-', '--', '-', '.-', '--', '-', '-', '-', '-', '--']
marker = ['D', 'o', '^', 'D', 's', '^', 'D', 's', 's', 'o']
colors = ['r', 'b', 'm', 'm', 'm', 'c', 'c', 'c', 'g', 'g']
alphas = [1., 0.9, .8, .6, .4, .8, .6, .4, 1., .6]
widths = [2, 4, 1, 4, 8, 1, 4, 8, 1, 8]
ys = []
for i in [0, -1]:
ys.append(i * 10)
plt.plot(range(lens), np.array(data[i]).T + ys[-1], \
color='r', linewidth=2, alpha=0.6, marker='')
plt.plot(range(lens), np.array(lbl[i]).T + ys[-1], \
color='k', linewidth=2, alpha=0.8, marker='')
#plt.yscale('log')
plt.xticks([0, 300, 600], ['0', '300', '600'], fontsize=16)
plt.yticks(ys, ['0%', '100%'], fontsize=16)
plt.ylabel('Percentage of disorganization', fontsize=18)
plt.xlabel('Sequence position', fontsize=18)
plt.legend(['Noisy observations', 'True state sequence'],
fontsize=18,
fancybox=True,
framealpha=0.7)
plt.show()
import cvxopt as co
import numpy as np
import pylab as pl
import matplotlib.pyplot as plt
from ssvm import SSVM
from so_multiclass import SOMultiClass
from toydata import ToyData
if __name__ == '__main__':
NUM_CLASSES = 4
# generate raw training data
Dtrain1 = ToyData.get_gaussian(1000,
dims=2,
means=[4.0, 2.0],
vars=[1.0, 0.3])
Dtrain2 = ToyData.get_gaussian(100,
dims=2,
means=[-2.0, 1.0],
vars=[0.3, 1.3])
Dtrain3 = ToyData.get_gaussian(100,
dims=2,
means=[3.0, -1.0],
vars=[0.3, 0.3])
Dtrain4 = ToyData.get_gaussian(50,
dims=2,
means=[6.0, -3.0],
vars=[0.2, 0.1])
Dtrain = co.matrix([[Dtrain1], [Dtrain2], [Dtrain3], [Dtrain4]])
import pylab as pl import matplotlib.pyplot as plt from ssvm import SSVM from latentsvdd import LatentSVDD from structured_ocsvm import StructuredOCSVM from structured_pca import StructuredPCA from so_multiclass import SOMultiClass from toydata import ToyData if __name__ == '__main__': NUM_CLASSES = 6 # generate raw training data Dtrain1 = ToyData.get_gaussian(100,dims=2,means=[1.0,1.0],vars=[1.0,0.3]) Dtrain2 = ToyData.get_gaussian(10,dims=2,means=[-2.0,1.0],vars=[0.3,1.3]) Dtrain3 = ToyData.get_gaussian(10,dims=2,means=[3.0,-3.0],vars=[0.3,0.3]) Dtrain4 = ToyData.get_gaussian(5,dims=2,means=[6.0,-3.0],vars=[0.2,0.1]) Dtrain = co.matrix([[Dtrain1], [Dtrain2], [Dtrain3], [Dtrain4]]) Dtrain = co.matrix([[Dtrain.trans()],[co.matrix(1.0,(125,1))]]).trans() Dy = co.matrix([co.matrix([0]*100), co.matrix([1]*10), co.matrix([2]*10), co.matrix([3]*5)]) # generate structured object sobj = SOMultiClass(Dtrain, y=Dy , classes=NUM_CLASSES) # unsupervised methods lsvdd = LatentSVDD(sobj,1.0/(125.0*1.0)) spca = StructuredPCA(sobj) socsvm = StructuredOCSVM(sobj,1.0/(125.0*1.0))
