def test_toy_data_rand(self):
y_conf = self.data['y_conf'].value
kernel = self.data['kernel'].value
X = self.data['X'].value
# This is a non-random cross validation
(training, test) = utils.crossValidationScheme(2, y_conf.size)
lm_forest = MF(kernel=kernel[SP.ix_(training, training)],
sampsize=.5, verbose=0, n_estimators=100)
lm_forest.fit(X[training], y_conf[training])
response_tot = lm_forest.predict(X[test],
kernel[SP.ix_(test, training)])
random_forest = MF(kernel='iid')
random_forest.fit(X[training], y_conf[training])
response_iid = random_forest.predict(X[test])
response_fixed = lm_forest.predict(X[test])
feature_scores_lmf = lm_forest.log_importance
feature_scores_rf = random_forest.log_importance
# All consistency checks
err = (feature_scores_lmf-self.data['feature_scores_lmf'].value).sum()
self.assertTrue(SP.absolute(err) < 10)
err = (feature_scores_rf-self.data['feature_scores_rf'].value).sum()
self.assertTrue(SP.absolute(err) < 10)
err = SP.absolute(self.data['response_tot'] - response_tot).sum()
self.assertTrue(SP.absolute(err) < 2)
err = SP.absolute(self.data['response_fixed'] - response_fixed).sum()
self.assertTrue(SP.absolute(err) < 4)
err = SP.absolute(self.data['response_iid'] - response_iid).sum()
self.assertTrue(SP.absolute(err) < 8)
def test_toy_data_rand(self):
y_conf = self.data['y_conf'].value
kernel = self.data['kernel'].value
X = self.data['X'].value
# This is a non-random cross validation
(training, test) = utils.crossValidationScheme(2, y_conf.size)
lm_forest = MF(kernel=kernel[SP.ix_(training, training)],
sampsize=.5,
verbose=0,
n_estimators=100)
lm_forest.fit(X[training], y_conf[training])
response_tot = lm_forest.predict(X[test],
kernel[SP.ix_(test, training)])
random_forest = MF(kernel='iid')
random_forest.fit(X[training], y_conf[training])
response_iid = random_forest.predict(X[test])
response_fixed = lm_forest.predict(X[test])
feature_scores_lmf = lm_forest.log_importance
feature_scores_rf = random_forest.log_importance
# All consistency checks
err = (feature_scores_lmf -
self.data['feature_scores_lmf'].value).sum()
self.assertTrue(SP.absolute(err) < 10)
err = (feature_scores_rf - self.data['feature_scores_rf'].value).sum()
self.assertTrue(SP.absolute(err) < 10)
err = SP.absolute(self.data['response_tot'] - response_tot).sum()
self.assertTrue(SP.absolute(err) < 2)
err = SP.absolute(self.data['response_fixed'] - response_fixed).sum()
self.assertTrue(SP.absolute(err) < 4)
err = SP.absolute(self.data['response_iid'] - response_iid).sum()
self.assertTrue(SP.absolute(err) < 8)
def setUp(self, n=100, m=1):
self.dir_name = os.path.dirname(os.path.realpath(__file__))
self.data = h5py.File(os.path.join(self.dir_name,
'test_data/lmm_forest_toy_data.h5'),
'r')
SP.random.seed(1)
self.x, self.y = utils.lin_data_cont_predictors(n=n,m=m)
self.n, self.m = self.x.shape
[self.train, self.test] = utils.crossValidationScheme(2,self.n)
self.n_estimators = 100
def setUp(self, n=100, m=1):
self.dir_name = os.path.dirname(os.path.realpath(__file__))
self.data = h5py.File(
os.path.join(self.dir_name, 'test_data/lmm_forest_toy_data.h5'),
'r')
SP.random.seed(1)
self.x, self.y = utils.lin_data_cont_predictors(n=n, m=m)
self.n, self.m = self.x.shape
[self.train, self.test] = utils.crossValidationScheme(2, self.n)
self.n_estimators = 100