def test_kernel_regression_rbf4(self):
rega = KernelRidgeRegression(random_seed=28378)
filename = os.path.join(pyvision.__path__[0], 'data', 'synthetic',
'synth1_quad.txt')
reg_file = open(filename, 'r')
labels = []
vectors = []
truth = []
for line in reg_file:
datapoint = line.split()
labels.append(float(datapoint[1]))
vectors.append([float(datapoint[0])])
truth.append(float(datapoint[2]))
for i in range(100):
rega.addTraining(labels[i], vectors[i])
rega.train(verbose=False)
#print rega.w
mse = 0.0
ase = 0.0
total = 0
table = Table()
for i in range(100, len(labels)):
p = rega.predict(vectors[i])
e = p - labels[i]
mse += e * e
a = p - truth[i]
ase += a * a
table.setElement(i, 'x', vectors[i][0])
table.setElement(i, 'measure', labels[i])
table.setElement(i, 'truth', truth[i])
table.setElement(i, 'pred', p)
table.setElement(i, 'e', e)
table.setElement(i, 'a', a)
mse = mse / (len(labels) - 100)
ase = ase / (len(labels) - 100)
#print "Regression Error:",mse
#print table
#table.save("../../rbf4.csv")
self.assertAlmostEqual(mse, 0.063883259792847411, places=7)
self.assertAlmostEqual(ase, 0.028811752673991175, places=7)
def test_kernel_regression_rbf2(self):
rega = KernelRidgeRegression(lams=0.1, kernels=RBF())
filename = os.path.join(pyvision.__path__[0], 'data', 'synthetic',
'synth1_mix.txt')
reg_file = open(filename, 'r')
labels = []
vectors = []
truth = []
for line in reg_file:
datapoint = line.split()
labels.append(float(datapoint[1]))
vectors.append([float(datapoint[0])])
truth.append(float(datapoint[2]))
for i in range(100):
rega.addTraining(labels[i], vectors[i])
rega.train()
#print rega.w
mse = 0.0
ase = 0.0
total = 0
table = Table()
for i in range(100, len(labels)):
p = rega.predict(vectors[i])
e = p - labels[i]
mse += e * e
a = p - truth[i]
ase += a * a
table.setElement(i, 'x', vectors[i][0])
table.setElement(i, 'measure', labels[i])
table.setElement(i, 'truth', truth[i])
table.setElement(i, 'pred', p)
table.setElement(i, 'e', e)
table.setElement(i, 'a', a)
mse = mse / (len(labels) - 100)
ase = ase / (len(labels) - 100)
#print "Regression Error:",mse
#print table
#table.save("../../rbf2.csv")
self.assertAlmostEqual(mse, 0.563513669235162, places=7)
self.assertAlmostEqual(ase, 0.51596869146460422, places=7)
def test_regression_linear(self):
# synthetic linear regression
rega = RidgeRegression()
filename = os.path.join(pyvision.__path__[0], 'data', 'synthetic',
'regression.dat')
reg_file = open(filename, 'r')
labels = []
vectors = []
for line in reg_file:
datapoint = line.split()
labels.append(float(datapoint[0]))
vectors.append([
float(datapoint[3]),
float(datapoint[4]),
float(datapoint[5])
])
for i in range(50):
rega.addTraining(labels[i], vectors[i])
rega.train()
mse = 0.0
total = 0
table = Table()
for i in range(50, len(labels)):
p = rega.predict(vectors[i])
e = p - labels[i]
table.setElement(i, 'truth', labels[i])
table.setElement(i, 'pred', p)
table.setElement(i, 'Residual', e)
#print labels[i],p,e
mse += e * e
#print table
#table.save('../../tmp.csv')
mse = mse / (len(labels) - 50)
self.assertAlmostEqual(mse, 0.24301122718491874, places=4)
def train_SVR_Linear(self,
labels,
vectors,
verbose,
C_range,
callback=None):
'''Private use only'''
# combine the labels and vectors into one set.
data = []
for i in range(len(labels)):
data.append([labels[i], vectors[i]])
#shuffle the data
rng = random.Random()
if self.random_seed != None:
rng.seed(self.random_seed)
rng.shuffle(data)
# partition into validation and training
if type(
self.validation_size
) == float and self.validation_size > 0.0 and self.validation_size < 1.0:
training_cutoff = int(len(data) * (1.0 - self.validation_size))
elif type(self.validation_size
) == int and self.validation_size < len(labels):
training_cutoff = len(labels) - self.validation_size
else:
raise NotImplementedError(
"Cannot determine validation set from %s" %
self.validation_size)
if verbose: print "Training Cutoff:", len(labels), training_cutoff
training_data = data[:training_cutoff]
validation_data = data[training_cutoff:]
tmp_labels = []
tmp_vectors = []
for each in training_data:
tmp_labels.append(each[0])
tmp_vectors.append(each[1])
prob = svm.svm_problem(tmp_labels, tmp_vectors)
training_info = []
training_svm = []
training_table = Table()
self.training_table = training_table
i = 0
for C in C_range:
param = svm.svm_parameter(svm_type=self.svm_type,
kernel_type=svm.LINEAR,
C=C,
p=self.epsilon,
nu=self.nu)
test_svm = svm.svm_model(prob, param)
mse = 0.0
total = len(validation_data)
for label, vector in validation_data:
pred = test_svm.predict(vector)
error = label - pred
mse += error * error
mse = mse / total
training_svm.append(test_svm)
training_info.append([C, mse])
training_table.setElement(i, 'C', C)
training_table.setElement(i, 'mse', mse)
i += 1
if callback != None:
callback(int(100 * float(i) / len(C_range)))
if verbose: print
if verbose: print "------------------------------"
if verbose: print " Tuning Information:"
if verbose: print " C error"
if verbose: print "------------------------------"
best = training_info[0]
best_svm = training_svm[0]
for i in range(len(training_info)):
each = training_info[i]
if verbose: print " %8.3e %0.8f" % (each[0], each[1])
if best[-1] > each[-1]:
best = each
best_svm = training_svm[i]
if verbose: print "------------------------------"
if verbose: print
if verbose: print "------------------------------"
if verbose: print " Best Tuning:"
if verbose: print " C error"
if verbose: print "------------------------------"
if verbose: print " %8.3e %0.8f" % (best[0], best[1])
if verbose: print "------------------------------"
if verbose: print
self.training_info = training_info
self.C = best[0]
self.error = best[1]
self.svm = best_svm
