def testRegression():
y = data.loadSVMLightTarget("../feature_set/synthetic.reg")
# we are using pseudo index instead of the real feature set to use the
# precomputed kernel.
x = range(y.shape[0])
dataset = zip(x, y)
random.shuffle(dataset)
# this precomputed kernel reads the index value and returns the covariance
# matrix
kernel = kernel_factory.precomputed("../feature_set/synthetic.kernel")
for train, test in data.kFolds(dataset):
x_train, y_train = zip(*train)
x_train = np.atleast_2d(np.array(x_train)).T
y_train = np.atleast_2d(np.array(y_train)).T
reg = regress.GPRegressor(kernel)
reg.fit(x_train, y_train)
print "fitted"
# test
x_test, y_test = zip(*test)
x_test = np.atleast_2d(np.array(x_test)).T
y_test = np.atleast_2d(np.array(y_test)).T
y_predict = reg.predict(x_test)
print x_test.T
print y_predict.T
break
def kernelAnalysis():
y = data.loadSVMLightTarget("../feature_set/text.sreg")
Cov = np.loadtxt("../feature_set/text.kernel")
array = []
for i in range(y.shape[0]):
Cov[0][i]
def regressAgeWithGP():
y = data.loadSVMLightTarget("../feature_set/text.sreg")
# we are using pseudo index instead of the real feature set to use the
# precomputed kernel.
x = range(y.shape[0])
dataset = zip(x, y)
random.shuffle(dataset)
# this precomputed kernel reads the index value and returns the covariance
# matrix
for tau in [1e-3, 1e-2, 1e-1, 1, 1e1, 1e2, 1e3]:
kernel = kernel_factory.precomputed("../feature_set/text.kernel", tau)
rms_errors = []
diviations = []
for train, test in data.kFolds(dataset):
x_train, y_train = zip(*train)
x_train = np.atleast_2d(np.array(x_train)).T
y_train = np.atleast_2d(np.array(y_train)).T
reg = regress.GPRegressor(kernel)
reg.fit(x_train, y_train)
# test
x_test, y_test = zip(*test)
x_test = np.atleast_2d(np.array(x_test)).T
y_test = np.atleast_2d(np.array(y_test)).T
y_predict = reg.predict(x_test)
rms_e = sqrt(np.mean((y_predict - y_test) ** 2))
div_e = np.mean(np.absolute(y_predict - y_test))
rms_errors.append(rms_e)
diviations.append(div_e)
print "tau:", tau
print "rms error:", np.mean(np.array(rms_e))
print "diviation:", np.mean(np.array(div_e))