def run_experiment(index, dataset_name, name, constraint_getter, master_tree, X, y, out_dir, n_iters=1000, add_constraint=200, add_score=200,
add_likelihood=200, should_continue=False):
N, D = X.shape
df = Inverse(c=1)
if dataset_name == 'iris':
lm = GaussianLikelihoodModel(sigma=np.eye(D) / 9.0, sigma0=np.eye(D) / 2.0, mu0=X.mean(axis=0)).compile()
elif dataset_name == 'zoo':
lm = GaussianLikelihoodModel(sigma=np.diag(np.diag(np.cov(X.T))) / 4.0, sigma0=np.eye(D) / 2.0, mu0=X.mean(axis=0)).compile()
else:
lm = GaussianLikelihoodModel(sigma=np.diag(np.diag(np.cov(X.T))) / 2.0, sigma0=np.eye(D) / 2.0, mu0=X.mean(axis=0)).compile()
if should_continue:
with open(out_dir / name / 'scores-%u.pkl' % index, 'r') as fp:
scores = pickle.load(fp)
with open(out_dir / name / 'costs-%u.pkl' % index, 'r') as fp:
costs = pickle.load(fp)
with open(out_dir / name / 'final-tree-%u.pkl' % index, 'r') as fp:
tree = DirichletDiffusionTree(df=df, likelihood_model=lm)
tree.set_state(pickle.load(fp))
sampler = MetropolisHastingsSampler(tree, X)
else:
scores = []
costs = []
tree = DirichletDiffusionTree(df=df, likelihood_model=lm)
sampler = MetropolisHastingsSampler(tree, X)
sampler.initialize_assignments()
if dataset_name == 'zoo':
sampler.tree = sampler.tree.induced_subtree(master_tree.points())
current_run = []
for i in tqdm(xrange(n_iters + 1)):
sampler.sample()
current_run.append(sampler.tree)
if i % add_score == 0:
scores.append(dist(master_tree, sampler.tree))
if i % add_likelihood == 0:
costs.append(sampler.tree.marg_log_likelihood())
if i != 0 and i % add_constraint == 0:
if constraint_getter is not None:
constraint = constraint_getter.get_constraint(current_run)
if constraint is not None:
sampler.add_constraint(constraint)
current_run = []
# plot_tree(sampler.tree, y)
(out_dir / name).mkdir_p()
with open(out_dir / name / 'scores-%u.pkl' % index, 'w') as fp:
pickle.dump(scores, fp)
print len(costs)
with open(out_dir / name / 'costs-%u.pkl' % index, 'w') as fp:
pickle.dump(costs, fp)
# with open(out_dir / name / 'trees-%u.pkl' % index, 'r') as fp:
# previous_trees = pickle.load(fp)
# with open(out_dir / name / 'trees-%u.pkl' % index, 'w') as fp:
# pickle.dump(previous_trees + [t.get_state() for t in trees], fp)
with open(out_dir / name / 'final-tree-%u.pkl' % index, 'w') as fp:
pickle.dump(sampler.tree.get_state(), fp)
return costs, scores, sampler
if tree.verify_constraint((a, b, c)):
return (a, b, c)
if tree.verify_constraint((a, c, b)):
return (a, c, b)
if tree.verify_constraint((b, c, a)):
return (b, c, a)
if __name__ == "__main__":
with open('scripts/zoo.tree', 'rb') as fp:
master_tree = pickle.load(fp)
points = master_tree.root.points()
tree1 = DirichletDiffusionTree(df=df, likelihood_model=lm)
sampler1 = MetropolisHastingsSampler(tree1, X)
sampler1.initialize_assignments()
sampler1.tree = sampler1.tree.induced_subtree(points)
tree2 = DirichletDiffusionTree(df=df, likelihood_model=lm)
sampler2 = MetropolisHastingsSampler(tree2, X)
sampler2.initialize_assignments()
sampler2.tree = sampler2.tree.induced_subtree(points)
all_constraints = list(master_tree.generate_constraints())
np.random.seed(0)
np.random.shuffle(all_constraints)
test_constraints = all_constraints[:10000]
satisfied = [set(), set()]
iterate(sampler1, 100)
def run_experiment(index,
dataset_name,
name,
constraint_getter,
master_tree,
X,
y,
out_dir,
n_iters=1000,
add_constraint=200,
add_score=200,
add_likelihood=200,
should_continue=False):
N, D = X.shape
df = Inverse(c=1)
if dataset_name == 'iris':
lm = GaussianLikelihoodModel(sigma=np.eye(D) / 9.0,
sigma0=np.eye(D) / 2.0,
mu0=X.mean(axis=0)).compile()
elif dataset_name == 'zoo':
lm = GaussianLikelihoodModel(sigma=np.diag(np.diag(np.cov(X.T))) / 4.0,
sigma0=np.eye(D) / 2.0,
mu0=X.mean(axis=0)).compile()
else:
lm = GaussianLikelihoodModel(sigma=np.diag(np.diag(np.cov(X.T))) / 2.0,
sigma0=np.eye(D) / 2.0,
mu0=X.mean(axis=0)).compile()
if should_continue:
with open(out_dir / name / 'scores-%u.pkl' % index, 'r') as fp:
scores = pickle.load(fp)
with open(out_dir / name / 'costs-%u.pkl' % index, 'r') as fp:
costs = pickle.load(fp)
with open(out_dir / name / 'final-tree-%u.pkl' % index, 'r') as fp:
tree = DirichletDiffusionTree(df=df, likelihood_model=lm)
tree.set_state(pickle.load(fp))
sampler = MetropolisHastingsSampler(tree, X)
else:
scores = []
costs = []
tree = DirichletDiffusionTree(df=df, likelihood_model=lm)
sampler = MetropolisHastingsSampler(tree, X)
sampler.initialize_assignments()
if dataset_name == 'zoo':
sampler.tree = sampler.tree.induced_subtree(master_tree.points())
current_run = []
for i in tqdm(xrange(n_iters + 1)):
sampler.sample()
current_run.append(sampler.tree)
if i % add_score == 0:
scores.append(dist(master_tree, sampler.tree))
if i % add_likelihood == 0:
costs.append(sampler.tree.marg_log_likelihood())
if i != 0 and i % add_constraint == 0:
if constraint_getter is not None:
constraint = constraint_getter.get_constraint(current_run)
if constraint is not None:
sampler.add_constraint(constraint)
current_run = []
# plot_tree(sampler.tree, y)
(out_dir / name).mkdir_p()
with open(out_dir / name / 'scores-%u.pkl' % index, 'w') as fp:
pickle.dump(scores, fp)
print len(costs)
with open(out_dir / name / 'costs-%u.pkl' % index, 'w') as fp:
pickle.dump(costs, fp)
# with open(out_dir / name / 'trees-%u.pkl' % index, 'r') as fp:
# previous_trees = pickle.load(fp)
# with open(out_dir / name / 'trees-%u.pkl' % index, 'w') as fp:
# pickle.dump(previous_trees + [t.get_state() for t in trees], fp)
with open(out_dir / name / 'final-tree-%u.pkl' % index, 'w') as fp:
pickle.dump(sampler.tree.get_state(), fp)
return costs, scores, sampler
return (a, b, c)
if tree.verify_constraint((a, c, b)):
return (a, c, b)
if tree.verify_constraint((b, c, a)):
return (b, c, a)
if __name__ == "__main__":
with open('scripts/zoo.tree', 'rb') as fp:
master_tree = pickle.load(fp)
points = master_tree.root.points()
tree1 = DirichletDiffusionTree(df=df, likelihood_model=lm)
sampler1 = MetropolisHastingsSampler(tree1, X)
sampler1.initialize_assignments()
sampler1.tree = sampler1.tree.induced_subtree(points)
tree2 = DirichletDiffusionTree(df=df, likelihood_model=lm)
sampler2 = MetropolisHastingsSampler(tree2, X)
sampler2.initialize_assignments()
sampler2.tree = sampler2.tree.induced_subtree(points)
all_constraints = list(master_tree.generate_constraints())
np.random.seed(0)
np.random.shuffle(all_constraints)
test_constraints = all_constraints[:10000]
satisfied = [set(), set()]
iterate(sampler1, 100)
