def _run_alg(excluded):
sample_dict_exclude = {
k: v
for k, v in sample_dict.items() if k != frozenset({excluded})
}
iv_estimated_folder = os.path.join(ESTIMATED_FOLDER,
'exclude_%s' % excluded)
filename = os.path.join(
iv_estimated_folder,
'igsp_effective_%s_alpha=%.2e,alpha_i=%.2e.txt' %
(ci_test, alpha, alpha_invariance))
if not os.path.exists(filename):
if ci_test == 'gauss_ci':
est_dag = igsp(sample_dict_exclude,
suffstat,
nnodes,
gauss_ci_test,
hsic_invariance_test,
alpha=alpha,
nruns=10,
alpha_invariance=alpha_invariance)
elif ci_test == 'hsic':
est_dag = igsp(sample_dict_exclude,
sample_dict_exclude[frozenset()],
nnodes,
hsic_test,
hsic_invariance_test,
alpha=alpha,
nruns=10,
alpha_invariance=alpha_invariance)
else:
raise ValueError
np.savetxt(filename, est_dag.to_amat())
def run_igsp():
for i in range(100):
igsp(samples,
suffstat,
nnodes,
gauss_ci_test,
hsic_invariance_test,
nruns=10)
def _run_alg(excluded):
# === REMOVE EXCLUDED FROM SAMPLES
setting_list_exclude = [
setting for setting in setting_list
if excluded not in setting['known_interventions']
]
sample_dict_exclude = dict()
for setting in setting_list_exclude:
iv_nodes = frozenset(setting['known_interventions'])
samples = setting['samples']
if iv_nodes not in sample_dict_exclude:
sample_dict_exclude[iv_nodes] = samples
else:
sample_dict_exclude[iv_nodes] = np.concatenate(
(sample_dict_exclude[iv_nodes], samples), axis=0)
# === CREATE FILENAME
iv_estimated_folder = os.path.join(ESTIMATED_FOLDER,
'exclude_%s' % excluded)
filename = os.path.join(
iv_estimated_folder, 'igsp_%s_alpha=%.2e,alpha_i=%.2e.txt' %
(ci_test, alpha, alpha_invariance))
if not os.path.exists(filename):
if ci_test == 'gauss_ci':
os.system('touch gauss_ci_igsp_%d.tst' % excluded)
est_dag = igsp(sample_dict_exclude,
suffstat,
nnodes,
gauss_ci_test,
hsic_invariance_test,
alpha=alpha,
nruns=10,
alpha_invariance=alpha_invariance)
else:
os.system('touch hsic_igsp_%d.tst' % excluded)
est_dag = igsp(sample_dict_exclude,
sample_dict_exclude[frozenset()],
nnodes,
hsic_test,
hsic_invariance_test,
alpha=alpha,
nruns=10,
alpha_invariance=alpha_invariance)
np.savetxt(filename, est_dag.to_amat())
from causaldag.inference.structural import igsp
from causaldag.utils.ci_tests import gauss_ci_test, hsic_invariance_test
import causaldag as cd
import numpy as np
import random
np.random.seed(40)
random.seed(9879132)
nnodes = 10
nsamples = 100
dag = cd.rand.directed_erdos(nnodes, 1.5 / (nnodes - 1), 1)
gdag = cd.rand.rand_weights(dag)
obs_samples = gdag.sample(nsamples)
sample_dict = {}
sample_dict[frozenset()] = obs_samples
for i in range(10):
sample_dict[frozenset({i})] = gdag.sample_interventional_perfect(
{i: cd.GaussIntervention(1, .1)}, nsamples)
suffstat = dict(C=np.corrcoef(obs_samples, rowvar=False), n=nsamples)
est_dag = igsp(sample_dict,
suffstat,
nnodes,
gauss_ci_test,
hsic_invariance_test,
1e-5,
1e-5,
nruns=5,
verbose=True)
sample_dict = {frozenset(): samples, frozenset({nnodes - 1}): iv_samples}
suffstat = dict(C=np.corrcoef(samples, rowvar=False), n=nsamples)
# === SAVE SAMPLES
sample_folder = os.path.join(PROJECT_FOLDER, 'tmp')
iv_sample_folder = os.path.join(sample_folder, 'interventional')
os.makedirs(iv_sample_folder, exist_ok=True)
np.savetxt(os.path.join(sample_folder, 'observational.txt'), samples)
iv_str = 'known_ivs=%s;unknown_ivs=%s.txt' % (nnodes - 1, 0)
np.savetxt(os.path.join(iv_sample_folder, iv_str), iv_samples)
# === RUN ALGORITHMS
dag_igsp = igsp(sample_dict,
suffstat,
nnodes,
gauss_ci_test,
hsic_invariance_test,
nruns=10,
alpha_invariance=1e-5)
dag_utigsp = unknown_target_igsp(sample_dict,
suffstat,
nnodes,
gauss_ci_test,
hsic_invariance_test,
nruns=10,
alpha_invariance=1e-2)
amat_gies = run_gies(sample_folder, lambda_=50)
dag_gies = cd.DAG.from_amat(amat_gies)
dags_igsp.append(dag_igsp)
dags_utigsp.append(dag_utigsp)
setting_list = [{
'known_interventions': iv_nodes,
'samples': samples
} for iv_nodes, samples in sample_dict.items() if iv_nodes != frozenset()]
nnodes = obs_samples.shape[1]
np.random.seed(1729)
random.seed(1729)
# starting_permutations = [random.sample(list(range(nnodes)), nnodes) for i in range(10)]
starting_permutations = [true_dag.topological_sort()]
# === RUN IGSP
igsp_dag = igsp(sample_dict,
suffstat,
nnodes,
gauss_ci_test,
hsic_invariance_test,
alpha=1e-5,
alpha_invariance=1e-5,
depth=6,
verbose=True,
starting_permutations=starting_permutations)
np.random.seed(1729)
random.seed(1729)
# === RUN UTIGSP
utigsp_dag = unknown_target_igsp(obs_samples,
setting_list,
suffstat,
nnodes,
gauss_ci_test,
hsic_invariance_test,
alpha=1e-5,