def run_log_regression():
nb_in_sample = 100
nb_out_of_sample = 100000
nb_runs = 100
nb_epochs = 0
nb_Eout = 0
lr = 0.01
eps = 0.01
for i in range(nb_runs):
# generate random function
l = randomline()
f = target_random_function(l)
# generate in sample data and out of sample data
data_in_sample = data(nb_in_sample)
data_out_of_sample = data(nb_out_of_sample)
# create training set structure [[w0,w1,...],target_value]
t_set_in = build_training_set_fmultipleparams(data_in_sample,f)
t_set_out = build_training_set_fmultipleparams(data_out_of_sample,f)
# run logistic regression in sample
epochs,w = log_regression_sgd(t_set_in,eps,lr)
# compute the out of sample error given the previously compute weights.
e_out = log_regression_compute_Eout(t_set_out,w)
print "Run: %s - epochs: %s"%(i, epochs)
print "Eout: %s"%(e_out)
nb_Eout += e_out
nb_epochs += epochs
print 'Number of runs:%s'%(nb_runs)
print "Avg epochs: %s"%(nb_epochs / nb_runs*1.0)
print "Avg Eout: %s"%(nb_Eout / nb_runs*1.0)
def run_log_regression():
nb_in_sample = 100
nb_out_of_sample = 100000
nb_runs = 100
nb_epochs = 0
nb_Eout = 0
lr = 0.01
eps = 0.01
for i in range(nb_runs):
# generate random function
l = randomline()
f = target_random_function(l)
# generate in sample data and out of sample data
data_in_sample = data(nb_in_sample)
data_out_of_sample = data(nb_out_of_sample)
# create training set structure [[w0,w1,...],target_value]
t_set_in = build_training_set_fmultipleparams(data_in_sample, f)
t_set_out = build_training_set_fmultipleparams(data_out_of_sample, f)
# run logistic regression in sample
epochs, w = log_regression_sgd(t_set_in, eps, lr)
# compute the out of sample error given the previously compute weights.
e_out = log_regression_compute_Eout(t_set_out, w)
print "Run: %s - epochs: %s" % (i, epochs)
print "Eout: %s" % (e_out)
nb_Eout += e_out
nb_epochs += epochs
print 'Number of runs:%s' % (nb_runs)
print "Avg epochs: %s" % (nb_epochs / nb_runs * 1.0)
print "Avg Eout: %s" % (nb_Eout / nb_runs * 1.0)
def run_linear_regression(N_samples, N_points):
'''runs on N_samples and with N_points a linear regression
computes Ein by average of the samples as well as Eout
'''
print 'running Linear Regression on %s samples' % str(N_samples)
print 'Each sample has %s data points' % str(N_points)
Ein_avg = []
Eout_avg = []
for i in range(N_samples):
d = data(N_points)
l = randomline()
f = target_function(l)
t_set = build_training_set(d, f)
wlin, X, y = linear_regression(N_points, t_set)
Ein = compute_Ein(wlin, X, y)
Ein_avg.append(Ein)
Eout = compute_Eout(wlin, f, N_points)
Eout_avg.append(Eout)
print_avg('Ein', Ein_avg)
print_avg('Eout', Eout_avg)
def run_linear_regression(N_samples,N_points):
'''runs on N_samples and with N_points a linear regression
computes Ein by average of the samples as well as Eout
'''
print 'running Linear Regression on %s samples' %str(N_samples)
print 'Each sample has %s data points' %str(N_points)
Ein_avg = []
Eout_avg = []
for i in range(N_samples):
d = data(N_points)
l = randomline()
f = target_function(l)
t_set = build_training_set(d,f)
wlin,X,y = linear_regression(N_points,t_set)
Ein = compute_Ein(wlin,X,y)
Ein_avg.append(Ein)
Eout = compute_Eout(wlin,f,N_points)
Eout_avg.append(Eout)
print_avg('Ein',Ein_avg)
print_avg('Eout',Eout_avg)
def get_current_pos():
savefile = open('current_pos.txt', 'w')
data = inst.query('SOURce:SCENario:LOG?')
savefile.write(data)
savefile.close()
pos = (tools.data('current_pos.txt'))
return pos
#print(get_current_pos())
#print(inst.query('SOURce:SCENario:LOG?'))
#done = tools.data('spectracom_data.txt')
#print(done)
def generate_t_set(N, f=None):
'''
Generate a training set of N = 1000 points on X = [1; 1] * [1; 1] with uniform
probability of picking each x that belongs X . Generate simulated noise by
fipping the sign of a random 10% subset of the generated training set
'''
d = data(N)
if f is None:
f = lambda x: sign(x[0]**2 + x[1]**2 - 0.6)
t_set = build_training_set_fmultipleparams(d, f)
t_set = t_set_errorNoise(t_set, N / 10)
return t_set, f
def generate_t_set(N,f=None):
'''
Generate a training set of N = 1000 points on X = [1; 1] * [1; 1] with uniform
probability of picking each x that belongs X . Generate simulated noise by
fipping the sign of a random 10% subset of the generated training set
'''
d = data(N)
if f is None:
f = lambda x: sign(x[0]**2 + x[1]**2 -0.6)
t_set = build_training_set_fmultipleparams(d,f)
t_set = t_set_errorNoise(t_set,N/10)
return t_set,f
def compute_Eout(wlin, f, N_points):
'number of out-of-sample points misclassifed / total number of out-of-sample points'
d = data(N_points)
t_set = build_training_set(d, f)
X_matrix = input_data_matrix(t_set)
y_vector = target_vector(t_set)
g_vector = dot(X_matrix, wlin)
for i in range(len(g_vector)):
g_vector[i] = sign(g_vector[i])
vEout = g_vector - y_vector
nEout = 0
for i in range(len(vEout)):
if vEout[i] != 0:
nEout = nEout + 1
Eout = nEout / (len(vEout) * 1.0)
return Eout
def compute_Eout(wlin,f,N_points):
'number of out-of-sample points misclassifed / total number of out-of-sample points'
d = data(N_points)
t_set = build_training_set(d,f)
X_matrix = input_data_matrix(t_set)
y_vector = target_vector(t_set)
g_vector = dot(X_matrix,wlin)
for i in range(len(g_vector)):
g_vector[i] = sign(g_vector[i])
vEout = g_vector - y_vector
nEout = 0
for i in range(len(vEout)):
if vEout[i]!=0:
nEout = nEout + 1
Eout = nEout/(len(vEout)*1.0)
return Eout
def run_lr_and_pla(N_samples, N_points):
'''runs on N_samples and with N_points a linear regresion
then from the weight vector runs PLA algorithm
compute the average number of iterations of PLA with this w vector
'''
print 'running Linear Regression on %s samples' %N_samples
print 'Each samples has %s data points' %N_points
iteration_avg = []
for i in range(N_samples):
d = data(N_points)
l = randomline()
f = target_function(l)
t_set = build_training_set(d,f)
wlin,X,y = linear_regression(N_points,t_set)
w_pla,iteration = PLA(N_points,wlin,f,t_set)
iteration_avg.append(iteration)
print_avg('Number of iterations',iteration_avg)
def run_lr_and_pla(N_samples, N_points):
'''runs on N_samples and with N_points a linear regresion
then from the weight vector runs PLA algorithm
compute the average number of iterations of PLA with this w vector
'''
print 'running Linear Regression on %s samples' % N_samples
print 'Each samples has %s data points' % N_points
iteration_avg = []
for i in range(N_samples):
d = data(N_points)
l = randomline()
f = target_function(l)
t_set = build_training_set(d, f)
wlin, X, y = linear_regression(N_points, t_set)
w_pla, iteration = PLA(N_points, wlin, f, t_set)
iteration_avg.append(iteration)
print_avg('Number of iterations', iteration_avg)
def run_PLA(N_samples, N_points):
samples = [] # vector of 1 clasified, 0 misclassified
iterations = [] #vector of iterations needed for each PLA
b_misclassified = False
diff = [] #vector of difference average between f and g
for i in range(N_samples):
# run PLA in sample
d = data(N_points)
l = randomline()
f = target_function(l)
t_set = build_training_set(d, f)
w = [0, 0, 0] #Start the PLA with the weight vector w being all zeros
w, iteration = PLA(N_points, w, f, t_set)
iterations.append(iteration)
# check if points are classified or not
for i in range(len(t_set)):
point = t_set[i][0]
s = h(w, point)
yn = t_set[i][1]
if yn != s:
samples.append(0)
b_misclassified = True
break
# check difference between f and g
diff.append(evaluate_diff_f_g(f, w))
if not b_misclassified: samples.append(1)
b_misclassified = False
print 'number of samples misclassified: %s ' % samples.count(0)
print 'number of classified samples: %s ' % samples.count(1)
print 'number of iteration avg: %s ' % (str(
sum(iterations) / len(iterations) * 1.0))
print 'average of difference in function g: %s' % (sum(diff) /
(len(diff) * 1.0))
def run_PLA(N_samples,N_points):
samples = []# vector of 1 clasified, 0 misclassified
iterations = []#vector of iterations needed for each PLA
b_misclassified = False
diff = []#vector of difference average between f and g
for i in range(N_samples):
# run PLA in sample
d = data(N_points)
l = randomline()
f = target_function(l)
t_set = build_training_set(d,f)
w = [0,0,0]
w,iteration = PLA(N_points,w,f,t_set)
iterations.append(iteration)
# check if points are classified or not
for i in range(len(t_set)):
point = t_set[i][0]
s = h(w,point)
yn = t_set[i][1]
if yn != s:
samples.append(0)
b_misclassified = True
break
# check difference between f and g
diff.append(evaluate_diff_f_g(f,w))
if not b_misclassified: samples.append(1)
b_misclassified = False
print 'number of samples misclassified: %s ' % samples.count(0)
print 'number of classified samples: %s ' % samples.count(1)
print 'number of iteration avg: %s ' % (str(sum(iterations)/len(iterations)*1.0))
print 'average of difference in function g: %s' % ( sum(diff)/(len(diff)*1.0) )
__author__ = 'tobie'
import tools, math
from matplotlib import pyplot as plt
# Open files we need
spec =open('spectracom_data.txt', 'r')
ublox = open('ublox_data.txt', 'r')
# take back information we need ie [time, Lat, Long, Alt]
speclist = tools.data('spectracom_data.txt')
ubloxlist = tools.data('ublox_data.txt')
print(speclist)
print(ubloxlist)
def synchronisation(speclist, ubloxlist):
# to compare information sent and received, they must be synchronized
new_spec =[]
new_ublox = []
for i in range(len(speclist)):
for j in range(len(ubloxlist)):
if speclist[i][0][0:6] == ubloxlist[j][0][0:6]:
new_spec.append(speclist[i])
new_ublox.append(ubloxlist[j])
return (new_spec, new_ublox)
new_spec = synchronisation(speclist, ubloxlist)[0]
new_ublox = synchronisation(speclist, ubloxlist)[1]
print(new_spec)
print(new_ublox)
def player(id):
return data(models.Player.query.filter(models.Player.id == id).one())
def match(id):
m = models.Match.query.filter(models.Match.id == id).one()
if request.method == 'GET':
return data(m)
if request.method == 'PUT':
return modify_resource(m)
def tournament(id):
return data(models.Tournament.query.filter(models.Tournament.id == id).one())
def run_pla_vs_svm(nbruns=1, N=10):
solvers.options['show_progress'] = False
d = []
l = 0
f = 0
t_set = []
y = []
svm_vs_pla = []
for i in range(nbruns):
onBothSides = False
while (not onBothSides):
d = data(N)
l = randomline()
f = target_function(l)
t_set = build_training_set(d, f)
y = target_vector(t_set)
if (1 in y) and (-1 in y):
onBothSides = True
else:
onBothSides = False
w = [0, 0, 0]
w_pla, iteration = PLA(N, w, f, t_set)
plaEout = evaluate_diff_f_g(f, w_pla)
X_matrix = input_data_matrix(t_set)
dimension = len(X_matrix[0])
#identity matrix of size dim X dim matrix x,I,J,typecode double
P = spmatrix(1, range(dimension), range(dimension), tc='d')
#vector of zeros of size dim, typecode double
q = matrix([0] * (dimension), tc='d')
mat = []
for t in t_set:
y = t[1]
temp = [x * -1.0 * y for x in t[0]]
mat.append(temp)
G = matrix(mat, tc='d')
G = G.trans()
# vectors of -1 of size t_set
h = matrix([-1] * len(t_set), tc='d')
#http://abel.ee.ucla.edu/cvxopt/examples/tutorial/qp.html
qp_sln = solvers.qp(P, q, G, h)
wsvm = list(qp_sln['x'])
# number of support vectors you can get at each run
count_sv = 0
for t in t_set:
wsvm = array(wsvm)
x = array(t[0])
y = t[1]
res = fabs(y * dot(wsvm, x) - 1)
if res < 0.001:
count_sv = count_sv + 1
#print count_sv
# Eout of svm
svmEout = computeEout_svm(f, wsvm)
#print 'svmEout: %s'%svmEout
if (svmEout < plaEout):
svm_vs_pla.append([True, count_sv])
else:
svm_vs_pla.append([False, count_sv])
print "svm win pla %f" % (len(filter(lambda a: a[0] is True, svm_vs_pla)) *
1.0 / N)
percent_svm_won = len([r[0] for r in svm_vs_pla if r[0] is True
]) * 1.0 / len(svm_vs_pla)
print "question 9: svm beat pla %f percent of the time" % (
percent_svm_won * 100)
avg_sv = sum([a[1] for a in svm_vs_pla]) * 1.0 / len(svm_vs_pla)
print "avg sv:", avg_sv
def run_pla_vs_svm(nbruns = 1, N = 10):
solvers.options['show_progress'] = False
d = []
l = 0
f = 0
t_set = []
y = []
svm_vs_pla = []
for i in range(nbruns):
onBothSides = False
while(not onBothSides):
d = data(N)
l = randomline()
f = target_function(l)
t_set = build_training_set(d,f)
y = target_vector(t_set)
if (1 in y) and (-1 in y):
onBothSides = True
else:
onBothSides = False
w = [0,0,0]
w_pla,iteration = PLA(N,w,f,t_set)
plaEout = evaluate_diff_f_g(f,w_pla)
X_matrix = input_data_matrix(t_set)
dimension = len(X_matrix[0])
#identity matrix of size dim X dim matrix x,I,J,typecode double
P = spmatrix(1, range(dimension), range(dimension), tc='d')
#vector of zeros of size dim, typecode double
q = matrix([0]*(dimension), tc='d')
mat = []
for t in t_set:
y = t[1]
temp = [x * -1.0*y for x in t[0]]
mat.append(temp)
G = matrix(mat, tc='d')
G = G.trans()
# vectors of -1 of size t_set
h = matrix([-1]*len(t_set), tc='d')
#http://abel.ee.ucla.edu/cvxopt/examples/tutorial/qp.html
qp_sln = solvers.qp(P, q, G, h)
wsvm = list(qp_sln['x'])
# number of support vectors you can get at each run
count_sv = 0
for t in t_set:
wsvm = array(wsvm)
x = array(t[0])
y = t[1]
res = fabs(y*dot(wsvm,x)-1)
if res < 0.001:
count_sv = count_sv + 1
#print count_sv
# Eout of svm
svmEout = computeEout_svm(f,wsvm)
#print 'svmEout: %s'%svmEout
if(svmEout < plaEout):
svm_vs_pla.append([True,count_sv])
else:
svm_vs_pla.append([False,count_sv])
print "svm win pla %f" % (len(filter(lambda a: a[0] is True, svm_vs_pla))*1.0/N)
percent_svm_won = len([r[0] for r in svm_vs_pla if r[0] is True])*1.0/len(svm_vs_pla)
print "question 9: svm beat pla %f percent of the time" % (percent_svm_won*100)
avg_sv = sum([a[1] for a in svm_vs_pla])*1.0/len(svm_vs_pla)
print "avg sv:", avg_sv
