def get_rbig_cvmodel(n_layers=50,
bins="auto",
bounds=0.1,
alpha=1e-10,
random_state=123,
init=None,
**kwargs):
if init is not None:
# Choose the Histogram estimator that converts the data X to uniform U(0,1)
univariate_estimator = HistogramUnivariateDensity(bounds=bounds,
bins=bins,
alpha=alpha)
# Marginally uses histogram estimator
marginal_uniformization = IndependentDensity(
univariate_estimators=univariate_estimator)
# Creates "Destructor" D_theta_1
init = IndependentDestructor(marginal_uniformization)
deep_rbig_model = get_deep_rbig_model(
n_layers=n_layers,
bins=bins,
bounds=bounds,
alpha=alpha,
random_state=random_state,
)
# Initialize Deep RBIG CV Model
deep_rbig_cvmodel = DeepDestructorCV(init_destructor=clone(init),
canonical_destructor=deep_rbig_model,
**kwargs)
return deep_rbig_cvmodel
def test_histogram_univariate_destructor():
destructor = IndependentDestructor(independent_density=IndependentDensity(
# Note only one univariate estimator
univariate_estimators=[
HistogramUnivariateDensity(bins=4, alpha=10, bounds=[0, 1])
]))
assert check_destructor(destructor)
def test_histogram_multivariate_density():
density = IndependentDensity(
univariate_estimators=HistogramUnivariateDensity(
bins=10, alpha=10, bounds=[0, 1]
)
)
assert check_density(density)
def test_tree_destructor_with_node_destructor():
node_tree_destructor = IndependentDestructor(
independent_density=IndependentDensity(
univariate_estimators=HistogramUnivariateDensity(
bins=10, alpha=100, bounds=[0, 1])))
for node_destructor in [IdentityDestructor(), node_tree_destructor]:
destructor = TreeDestructor(tree_density=TreeDensity(
tree_estimator=RandomTreeEstimator(max_leaf_nodes=3,
random_state=0),
node_destructor=node_destructor,
uniform_weight=0.9,
))
assert check_destructor(destructor)
def _get_model(data_name, model_name, model_kwargs):
if 'is_test' not in model_kwargs:
model_kwargs['is_test'] = False
# Init destructor is shared with all models
init_destructor = CompositeDestructor(
destructors=[
_get_inverse_logit_destructor(data_name),
IndependentDestructor(independent_density=IndependentDensity(
univariate_estimators=HistogramUnivariateDensity(
bins=256, bounds=[0, 1], alpha=1)))
],
random_state=0,
)
# Setup canonical destructor for various models
if model_name == 'deep-copula':
deep_stop_tol = 0.001
canonical_destructor = _get_copula_destructor()
else:
deep_stop_tol = 0.0001
n_jobs = model_kwargs['n_jobs']
# Get pair estimators (i.e. pairs of pixels in a spiral pattern)
pair_estimators = _get_pair_estimators(data_name, n_uniq_dir=8)
# Setup the local/pair destructor
pair_canonical_destructor = _get_pair_canonical_destructor(model_name)
# Setup a list of canonical destructors that destroy in each pixel direction
canonical_destructor = [
FeatureGroupsDestructor(
groups_estimator=pair_estimator,
group_canonical_destructor=clone(pair_canonical_destructor),
n_jobs=n_jobs) for pair_estimator in pair_estimators
]
# Shared DeepDestructorCV
return DeepDestructorCV(
init_destructor=init_destructor,
canonical_destructor=canonical_destructor,
stop_tol=deep_stop_tol,
# Either n_extend or max_canonical_destructors must be None
n_extend=1,
cv=model_kwargs['cv'],
refit=model_kwargs['refit'],
silent=False,
log_prefix='',
random_state=0,
# Set maximum number of layers (None for infinite)
max_canonical_destructors=None if not model_kwargs['is_test'] else 1,
)
def _get_copula_destructor(hist_kwargs=None):
if hist_kwargs is None:
hist_kwargs = dict(bins=40, bounds=[0, 1], alpha=100)
return CompositeDestructor(
destructors=[
IndependentDestructor(independent_density=IndependentDensity(
univariate_estimators=HistogramUnivariateDensity(
**hist_kwargs))),
IndependentInverseCdf(),
BestLinearReconstructionDestructor(
linear_estimator=PCA(),
destructor=IndependentDestructor(),
)
],
random_state=0,
)
def get_rbig_model(bins="auto", bounds=0.1, alpha=1e-10):
# ================================ #
# Step I - Marginal Uniformization
# ================================ #
# Choose the Histogram estimator that converts the data X to uniform U(0,1)
univariate_estimator = HistogramUnivariateDensity(bounds=bounds,
bins=bins,
alpha=alpha)
# Marginally uses histogram estimator
marginal_uniformization = IndependentDensity(
univariate_estimators=univariate_estimator)
# Creates "Destructor" D_theta_1
uniform_density = IndependentDestructor(marginal_uniformization)
# ================================== #
# Step II - Marginal Gaussianization
# ================================== #
# Choose destructor D_theta_2 that converts data
marginal_gaussianization = IndependentInverseCdf()
# =================== #
# Step III - Rotation
# =================== #
# Choose a linear projection to rotate the features (PCA) "D_theta_3"
rotation = LinearProjector(linear_estimator=PCA())
# ==================== #
# Composite Destructor
# ==================== #
# Composite Destructor
rbig_model = CompositeDestructor([
clone(uniform_density), # Marginal Uniformization
clone(marginal_gaussianization), # Marginal Gaussianization
clone(rotation), # Rotation (PCA)
])
return rbig_model
def test_inverse_canonical_destructor():
rng = check_random_state(0)
fitted_canonical_destructor = IdentityDestructor().fit(rng.rand(10, 2))
destructor = get_inverse_canonical_destructor(fitted_canonical_destructor)
assert check_destructor(destructor)
# Alpha must be high to pass the identity test
fitted_canonical_destructor = get_inverse_canonical_destructor(
TreeDestructor(TreeDensity(uniform_weight=0.99)).fit(rng.rand(10, 2))
)
destructor = get_inverse_canonical_destructor(fitted_canonical_destructor)
assert check_destructor(destructor)
# Alpha must be high to pass the identity test
fitted_canonical_destructor = IndependentDestructor(
independent_density=IndependentDensity(
univariate_estimators=HistogramUnivariateDensity(bins=10, alpha=1000, bounds=[0, 1])
)
).fit(rng.rand(10, 2))
destructor = get_inverse_canonical_destructor(fitted_canonical_destructor)
assert check_destructor(destructor)
def _get_toy_destructors_and_names():
# BASELINE SHALLOW DESTRUCTORS
gaussian_full = CompositeDestructor(
destructors=[
LinearProjector(
linear_estimator=PCA(),
orthogonal=False,
),
IndependentDestructor(),
],
)
mixture_20 = AutoregressiveDestructor(
density_estimator=GaussianMixtureDensity(
covariance_type='spherical',
n_components=20,
)
)
random_tree = CompositeDestructor(
destructors=[
IndependentDestructor(),
TreeDestructor(
tree_density=TreeDensity(
tree_estimator=RandomTreeEstimator(min_samples_leaf=20, max_leaf_nodes=50),
node_destructor=IndependentDestructor(
independent_density=IndependentDensity(
univariate_estimators=HistogramUnivariateDensity(
bins=10, alpha=10, bounds=[0, 1]
)
)
)
)
)
]
)
density_tree = CompositeDestructor(
destructors=[
IndependentDestructor(),
TreeDestructor(
tree_density=TreeDensity(
tree_estimator=MlpackDensityTreeEstimator(min_samples_leaf=10),
uniform_weight=0.001,
)
)
]
)
baseline_destructors = [gaussian_full, mixture_20, random_tree, density_tree]
baseline_names = ['Gaussian', 'Mixture', 'SingleRandTree', 'SingleDensityTree']
# LINEAR DESTRUCTORS
alpha_histogram = [10] # [1, 10, 100]
random_linear_projector = LinearProjector(
linear_estimator=RandomOrthogonalEstimator(), orthogonal=True
)
canonical_histogram_destructors = [
IndependentDestructor(
independent_density=IndependentDensity(
univariate_estimators=HistogramUnivariateDensity(bins=20, bounds=[0, 1], alpha=a)
)
)
for a in alpha_histogram
]
linear_destructors = [
DeepDestructorCV(
init_destructor=IndependentDestructor(),
canonical_destructor=CompositeDestructor(destructors=[
IndependentInverseCdf(), # Project to inf real space
random_linear_projector, # Random linear projector
IndependentDestructor(), # Project to canonical space
destructor, # Histogram destructor in canonical space
]),
n_extend=20, # Need to extend since random projections
)
for destructor in canonical_histogram_destructors
]
linear_names = ['RandLin (%g)' % a for a in alpha_histogram]
# MIXTURE DESTRUCTORS
fixed_weight = [0.5] # [0.1, 0.5, 0.9]
mixture_destructors = [
CompositeDestructor(destructors=[
IndependentInverseCdf(),
AutoregressiveDestructor(
density_estimator=FirstFixedGaussianMixtureDensity(
covariance_type='spherical',
n_components=20,
fixed_weight=w,
)
)
])
for w in fixed_weight
]
# Make deep destructors
mixture_destructors = [
DeepDestructorCV(
init_destructor=IndependentDestructor(),
canonical_destructor=destructor,
n_extend=5,
)
for destructor in mixture_destructors
]
mixture_names = ['GausMix (%.2g)' % w for w in fixed_weight]
# TREE DESTRUCTORS
# Random trees
histogram_alpha = [10] # [1, 10, 100]
tree_destructors = [
TreeDestructor(
tree_density=TreeDensity(
tree_estimator=RandomTreeEstimator(
max_leaf_nodes=4
),
node_destructor=IndependentDestructor(
independent_density=IndependentDensity(
univariate_estimators=HistogramUnivariateDensity(
alpha=a, bins=10, bounds=[0, 1]
)
)
),
)
)
for a in histogram_alpha
]
tree_names = ['RandTree (%g)' % a for a in histogram_alpha]
# Density trees using mlpack
tree_uniform_weight = [0.5] # [0.1, 0.5, 0.9]
tree_destructors.extend([
TreeDestructor(
tree_density=TreeDensity(
tree_estimator=MlpackDensityTreeEstimator(min_samples_leaf=10),
uniform_weight=w,
)
)
for w in tree_uniform_weight
])
tree_names.extend(['DensityTree (%.2g)' % w for w in tree_uniform_weight])
# Add random rotation to tree destructors
tree_destructors = [
CompositeDestructor(destructors=[
IndependentInverseCdf(),
LinearProjector(linear_estimator=RandomOrthogonalEstimator()),
IndependentDestructor(),
destructor,
])
for destructor in tree_destructors
]
# Make deep destructors
tree_destructors = [
DeepDestructorCV(
init_destructor=IndependentDestructor(),
canonical_destructor=destructor,
# Density trees don't need to extend as much as random trees
n_extend=50 if 'Rand' in name else 5,
)
for destructor, name in zip(tree_destructors, tree_names)
]
# Collect all destructors and set CV parameter
destructors = baseline_destructors + linear_destructors + mixture_destructors + tree_destructors
destructor_names = baseline_names + linear_names + mixture_names + tree_names
for d in destructors:
if 'cv' in d.get_params():
d.set_params(cv=cv)
# **** Change from notebook to make faster ****
if 'max_canonical_destructors' in d.get_params():
d.set_params(max_canonical_destructors=1)
return destructors, destructor_names
def test_histogram_univariate_density():
density = HistogramUnivariateDensity(
bins=10, alpha=10, bounds=[0, 1]
)
assert check_density(density)