def test_covariate_shift(self):
n_sample = 100
# Biased training
var_bias = .5**2
mean_bias = .7
x_train = SP.random.randn(n_sample)*SP.sqrt(var_bias) + mean_bias
y_train = self.complete_sample(x_train)
# Unbiased test set
var = .3**2
mean = 0
x_test = SP.random.randn(n_sample)*SP.sqrt(var) + mean
x_complete = SP.hstack((x_train, x_test))
kernel = utils.getQuadraticKernel(x_complete, d=1) +\
10 * SP.dot(x_complete.reshape(-1, 1), x_complete.reshape(1, -1))
kernel = utils.scale_K(kernel)
kernel_train = kernel[SP.ix_(SP.arange(x_train.size),
SP.arange(x_train.size))]
kernel_test = kernel[SP.ix_(SP.arange(x_train.size, x_complete.size),
SP.arange(x_train.size))]
mf = MF(n_estimators=100, kernel=kernel_train, min_depth=0,
subsampling=False)
mf.fit(x_train.reshape(-1, 1), y_train.reshape(-1, 1))
response_gp = mf.predict(x_test.reshape(-1, 1), kernel_test, depth=0)
self.assertTrue(((response_gp - self.polynom(x_test))**2).sum() < 2.4)
def test_covariate_shift(self):
n_sample = 100
# Biased training
var_bias = .5**2
mean_bias = .7
x_train = SP.random.randn(n_sample) * SP.sqrt(var_bias) + mean_bias
y_train = self.complete_sample(x_train)
# Unbiased test set
var = .3**2
mean = 0
x_test = SP.random.randn(n_sample) * SP.sqrt(var) + mean
x_complete = SP.hstack((x_train, x_test))
kernel = utils.getQuadraticKernel(x_complete, d=1) +\
10 * SP.dot(x_complete.reshape(-1, 1), x_complete.reshape(1, -1))
kernel = utils.scale_K(kernel)
kernel_train = kernel[SP.ix_(SP.arange(x_train.size),
SP.arange(x_train.size))]
kernel_test = kernel[SP.ix_(SP.arange(x_train.size, x_complete.size),
SP.arange(x_train.size))]
mf = MF(n_estimators=100,
kernel=kernel_train,
min_depth=0,
subsampling=False)
mf.fit(x_train.reshape(-1, 1), y_train.reshape(-1, 1))
response_gp = mf.predict(x_test.reshape(-1, 1), kernel_test, depth=0)
self.assertTrue(((response_gp - self.polynom(x_test))**2).sum() < 2.4)
def test_delta_updating(self):
n_sample = 100
# A 20 x 2 random integer matrix
X = SP.empty((n_sample, 2))
X[:, 0] = SP.arange(0, 1, 1.0 / n_sample)
X[:, 1] = SP.random.rand(n_sample)
sd_noise = .5
sd_conf = .5
noise = SP.random.randn(n_sample, 1) * sd_noise
# print 'true delta equals', (sd_noise**2)/(sd_conf**2)
# Here, the observed y is just a linear function of the first column
# in X and # a little independent gaussian noise
y_fixed = (X[:, 0:1] > .5) * 1.0
y_fn = y_fixed + noise
# Divide into training and test sample using 2/3 of data for training
training_sample = SP.zeros(n_sample, dtype='bool')
training_sample[SP.random.permutation(n_sample)
[:SP.int_(.66 * n_sample)]] = True
test_sample = ~training_sample
kernel = utils.getQuadraticKernel(X[:, 0], d=0.0025) +\
1e-3*SP.eye(n_sample)
# The confounded version of y_lin is computed as
y_conf = sd_conf * SP.random.multivariate_normal(
SP.zeros(n_sample), kernel, 1).reshape(-1, 1)
y_tot = y_fn + y_conf
# Selects rows and columns
kernel_train = kernel[SP.ix_(training_sample, training_sample)]
kernel_test = kernel[SP.ix_(test_sample, training_sample)]
lm_forest = MF(kernel=kernel_train,
update_delta=False,
max_depth=1,
verbose=0)
# Returns prediction for random effect
lm_forest.fit(X[training_sample], y_tot[training_sample])
response_lmf = lm_forest.predict(X[test_sample], k=kernel_test)
# print 'fitting forest (delta-update)'
# earn random forest, not accounting for the confounding
random_forest = MF(kernel=kernel_train,
update_delta=True,
max_depth=5,
verbose=0)
random_forest.fit(X[training_sample], y_tot[training_sample])
response_rf = random_forest.predict(X[test_sample], k=kernel_test)
def test_delta_updating(self):
n_sample = 100
# A 20 x 2 random integer matrix
X = SP.empty((n_sample, 2))
X[:, 0] = SP.arange(0, 1, 1.0/n_sample)
X[:, 1] = SP.random.rand(n_sample)
sd_noise = .5
sd_conf = .5
noise = SP.random.randn(n_sample, 1)*sd_noise
# print 'true delta equals', (sd_noise**2)/(sd_conf**2)
# Here, the observed y is just a linear function of the first column
# in X and # a little independent gaussian noise
y_fixed = (X[:, 0:1] > .5)*1.0
y_fn = y_fixed + noise
# Divide into training and test sample using 2/3 of data for training
training_sample = SP.zeros(n_sample, dtype='bool')
training_sample[
SP.random.permutation(n_sample)[:SP.int_(.66*n_sample)]] = True
test_sample = ~training_sample
kernel = utils.getQuadraticKernel(X[:, 0], d=0.0025) +\
1e-3*SP.eye(n_sample)
# The confounded version of y_lin is computed as
y_conf = sd_conf*SP.random.multivariate_normal(SP.zeros(n_sample),
kernel, 1).reshape(-1, 1)
y_tot = y_fn + y_conf
# Selects rows and columns
kernel_train = kernel[SP.ix_(training_sample, training_sample)]
kernel_test = kernel[SP.ix_(test_sample, training_sample)]
lm_forest = MF(kernel=kernel_train, update_delta=False, max_depth=1,
verbose=0)
# Returns prediction for random effect
lm_forest.fit(X[training_sample], y_tot[training_sample])
response_lmf = lm_forest.predict(X[test_sample], k=kernel_test)
# print 'fitting forest (delta-update)'
# earn random forest, not accounting for the confounding
random_forest = MF(kernel=kernel_train, update_delta=True, max_depth=5,
verbose=0)
random_forest.fit(X[training_sample], y_tot[training_sample])
response_rf = random_forest.predict(X[test_sample], k=kernel_test)
