def test_mixed_interventions(self):
gdag = cd.GaussDAG([0, 1, 2], arcs={(0, 1): 2, (0, 2): 3, (1, 2): 5})
factor = .1
gdag_iv = cd.GaussDAG([0, 1, 2], arcs={(0, 1): 2, (0, 2): 3*factor, (1, 2): 5*factor}, means=[1, 0, 0], variances=[.5, 1, 1])
iv = {0: GaussIntervention(1, .5), 2: ScalingIntervention(factor=factor)}
samples = gdag.sample_interventional(iv, 100000)
print(np.cov(samples, rowvar=False))
print(gdag_iv.covariance)
print(np.mean(samples, axis=0))
def test_scaling_intervention(self):
gdag = cd.GaussDAG([0, 1, 2], arcs={(0, 1): 2, (0, 2): 3, (1, 2): 5})
factor = .1
gdag_iv = cd.GaussDAG([0, 1, 2], arcs={(0, 1): 2, (0, 2): 3*factor, (1, 2): 5*factor})
iv = {2: ScalingIntervention(factor=factor)}
samples = gdag.sample_interventional(iv, 100000)
print(np.cov(samples, rowvar=False))
print(gdag_iv.covariance)
# === TEST WHEN INTERVENED NODE HAS NO PARENTS
gdag = cd.GaussDAG([0, 1, 2], arcs={(0, 1): 2, (0, 2): 3, (1, 2): 5})
factor = .1
iv = {0: ScalingIntervention(factor=factor)}
samples = gdag.sample_interventional(iv, 100000)
print(np.cov(samples, rowvar=False))
print(gdag.covariance)
# === TEST WITH STD FACTOR, INTERVENED NODE HAS PARENTS
gdag = cd.GaussDAG([0, 1, 2], arcs={(0, 1): 2, (0, 2): 3, (1, 2): 5})
factor = .1
std_factor = .2
gdag_iv = cd.GaussDAG([0, 1, 2], arcs={(0, 1): 2, (0, 2): 3 * factor, (1, 2): 5 * factor}, variances=[1, 1, std_factor**2])
iv = {2: ScalingIntervention(factor, std_factor)}
samples = gdag.sample_interventional(iv, 100000)
print(np.cov(samples, rowvar=False))
print(gdag_iv.covariance)
# === TEST WITH STD FACTOR, INTERVENED NODE HAS NO PARENTS
gdag = cd.GaussDAG([0, 1, 2], arcs={(0, 1): 2, (0, 2): 3, (1, 2): 5})
factor = .1
std_factor = .2
gdag_iv = cd.GaussDAG([0, 1, 2], arcs={(0, 1): 2, (0, 2): 3, (1, 2): 5}, variances=[std_factor ** 2, 1, 1])
iv = {0: ScalingIntervention(factor, std_factor)}
samples = gdag.sample_interventional(iv, 100000)
print(np.cov(samples, rowvar=False))
print(gdag_iv.covariance)
# === TEST WITH STD FACTOR, CHANGE IN MEAN, INTERVENED NODE HAS NO PARENTS
gdag = cd.GaussDAG([0, 1, 2], arcs={(0, 1): 2, (0, 2): 3, (1, 2): 5})
factor = .1
std_factor = .2
gdag_iv = cd.GaussDAG([0, 1, 2], arcs={(0, 1): 2, (0, 2): 3, (1, 2): 5}, variances=[std_factor ** 2, 1, 1])
iv = {0: ScalingIntervention(factor, std_factor, mean=2.13)}
samples = gdag.sample_interventional(iv, 100000)
print(np.cov(samples, rowvar=False))
print(gdag_iv.covariance)
print(np.mean(samples[:, 0]))
def test_hsic_invariance_cond_set_false_negatives(self):
false_negatives = 0
alpha = .05
num_tests = 100
nsamples = 200
for i in range(num_tests):
d = cd.GaussDAG(nodes=[0, 1, 2], arcs={(0, 1), (0, 2), (1, 2)})
samples = d.sample(nsamples)
iv_samples = d.sample_interventional_soft(
{1: ScalingIntervention(0)}, nsamples=nsamples)
test_results = cd.utils.ci_tests.hsic_invariance_test(samples,
iv_samples,
0,
cond_set=[1],
alpha=alpha)
if not test_results[
'reject']: # should be rejecting the hypothesis of invariance
false_negatives += 1
print("Number of false negatives:", false_negatives)
def save_dags(self, folder):
os.makedirs(folder, exist_ok=True)
yaml.dump(asdict(self), open(os.path.join(folder, 'config.yaml'), 'w'))
if self.graph_type == 'erdos':
dags = cd.rand.directed_erdos(self.n_nodes, self.edge_prob, size=self.n_dags)
if self.n_dags == 1:
dags = [dags]
elif self.graph_type == 'erdos-bounded':
dags = []
while len(dags) < self.n_dags:
dag = cd.rand.directed_erdos(self.n_nodes, self.edge_prob)
cpdag = dag.cpdag()
mec_size = len(cpdag.all_dags())
if mec_size < MAX_MEC_SIZE:
dags.append(dag)
elif self.graph_type == 'components':
dags = [get_component_dag(self.n_nodes, self.edge_prob) for _ in range(self.n_dags)]
elif self.graph_type == 'unoriented_by_one':
dags = []
while len(dags) < self.n_dags:
dag = cd.rand.directed_erdos(self.n_nodes, self.edge_prob)
cpdag = dag.cpdag()
if len(cpdag.all_dags()) < MAX_MEC_SIZE:
print(cpdag.undirected_neighbors[0])
dags.append(dag)
else:
dags = [graph_utils.generate_DAG(self.n_nodes, type_=self.graph_type) for _ in range(self.n_dags)]
dag_arcs = [{(i, j): np.random.uniform() for i, j in dag.arcs} for dag in dags] # A-ICP paper: Generate random weights
gdags = [cd.GaussDAG(nodes=list(range(self.n_nodes)), arcs=arcs) for arcs in dag_arcs]
print('=== Saving DAGs ===')
for i, gdag in enumerate(gdags):
os.makedirs(os.path.join(DATA_FOLDER, folder, 'dags', 'dag%d' % i), exist_ok=True)
np.savetxt(os.path.join(DATA_FOLDER, folder, 'dags', 'dag%d' % i, 'adjacency.txt'), gdag.to_amat())
# A-ICP paper: Sample means/variances uniformly at random from (0,1)
means = np.random.uniform(size=len(gdag.nodes))
variances = np.random.uniform(size=len(gdag.nodes))
np.savetxt(os.path.join(DATA_FOLDER, folder, 'dags', 'dag%d' % i, 'means.txt'), means)
np.savetxt(os.path.join(DATA_FOLDER, folder, 'dags', 'dag%d' % i, 'variances.txt'), variances)
print('=== Saved ===')
return gdags
import causaldag as cd
import time
import numpy as np
g = cd.GaussDAG([0, 1, 2], arcs={(0, 1), (0, 2)})
cov = g.covariance
nsamples = 2500
trials = 10
iv = {1: cd.GaussIntervention(0, 1)}
# === TIME INVARIANCE TEST NO CONDITIONING SET
start = time.time()
for _ in range(trials):
samples = g.sample(nsamples)
cd.utils.ci_tests.hsic_test_vector(samples[:, 0], samples[:, 1])
print(time.time() - start)
# === TIME INVARIANCE TEST WITH CONDITIONING SET
# start = time.time()
# for _ in range(trials):
# samples = g.sample(nsamples)
# cd.utils.ci_tests.hsic_invariance_test(samples[:, 0], samples[:, 1], 0)
# print(time.time() - start)
import causaldag as cd
import matplotlib.pyplot as plt
import os
import random
import numpy as np
from numpy.ma import masked_array
random.seed(181)
np.random.seed(181)
nsamples = 10
g = cd.GaussDAG(nodes=[0, 1, 2], arcs={(0, 1): 1, (0, 2): 1}, variances=[1, .2, .2])
obs_samples = g.sample(nsamples)
iv1_samples = g.sample_interventional({1: cd.GaussIntervention(0, 1)}, nsamples=nsamples)
iv01_samples = g.sample_interventional({1: cd.GaussIntervention(0, 1), 0: cd.GaussIntervention(1, .1)}, nsamples=nsamples)
cmap = 'bwr'
plt.clf()
os.makedirs('figures/example_data/', exist_ok=True)
plt.imshow(obs_samples, cmap=cmap)
plt.xticks([])
plt.yticks([])
plt.tight_layout()
plt.savefig('figures/example_data/obs.png', transparent=True, bbox_inches='tight')
plt.clf()
plt.imshow(iv1_samples, cmap=cmap)
plt.xticks([])
plt.yticks([])
# find probs
probs = np.zeros(k)
for fval, w in zip(fvals, weights):
probs[fval] += w
# = find entropy
mask = probs != 0
plogps = np.zeros(len(probs))
plogps[mask] = np.log2(probs[mask]) * probs[mask]
return -plogps.sum()
return get_k_entropy
np.random.seed(100)
g = cd.rand.directed_erdos(10, .5)
g = cd.GaussDAG(nodes=list(range(10)), arcs=g.arcs)
mec = [
cd.DAG(arcs=arcs) for arcs in cd.DAG(arcs=g.arcs).cpdag().all_dags()
]
strat = create_info_gain_strategy_dag_collection(
mec, [get_mec_functional_k(mec)], [get_k_entropy_fxn(len(mec))],
verbose=True)
samples = g.sample(1000)
precision_matrix = samples.T @ samples / 1000
sel_interventions = strat(
IterationData(current_data={-1: g.sample(1000)},
max_interventions=1,
n_samples=500,
batch_num=0,
n_batches=1,
import causaldag as cd
from causaldag import GaussIntervention
from causaldag.inference.structural import igsp, unknown_target_igsp
from causaldag.utils.ci_tests import gauss_ci_test, hsic_invariance_test
import numpy as np
import random
import os
from config import PROJECT_FOLDER
from R_algs.wrappers import run_gies
np.random.seed(1729)
random.seed(1729)
ntrials = 10
nnodes = 5
d = cd.DAG(arcs={(i, i + 1) for i in range(nnodes - 1)})
g = cd.GaussDAG(nodes=list(range(nnodes)), arcs=d.arcs)
cpdag = d.cpdag()
print(d.interventional_cpdag({nnodes - 1}, cpdag=cpdag).arcs)
print(d.interventional_cpdag({0, nnodes - 1}, cpdag=cpdag).arcs)
shds_igsp = []
shds_utigsp = []
shds_gies = []
dags_igsp = []
dags_utigsp = []
dags_gies = []
for i in range(ntrials):
nsamples = 500
intervention = GaussIntervention(1, .01)
samples = g.sample(nsamples)
iv_samples = g.sample_interventional_perfect(
def plot_roc(target, true_adj_mat, adj_mats):
avg_inc_mat = np.zeros(true_adj_mat.shape)
for adj_mat in adj_mats:
avg_inc_mat += graph_utils.adj2inc(adj_mat)
true_inc_mat = graph_utils.adj2inc(true_adj_mat)
roc_curve(true_inc_mat[:, target], avg_inc_mat[:, target])
if __name__ == '__main__':
adj_true = np.loadtxt('./data/dataset_5000/graph_2/adjacency.csv')
g = cd.from_amat(adj_true)
dict_weights = {}
for arc in g.arcs:
dict_weights[arc] = adj_true[arc[0], arc[1]]
gdag = cd.GaussDAG(nodes=list(range(50)), arcs=dict_weights)
all_data = [gdag.sample(250)]
interventions = [-1] * 250
all_iv = np.random.randint(0, 50, 10)
for iv in all_iv:
interventions += [iv] * 25
g_iv = cd.GaussIntervention(mean=2, variance=1)
all_data.append(gdag.sample_interventional({iv: g_iv}, 25))
all_data = np.vstack(all_data)
interventions = np.array(interventions)
interventions[interventions != -1] = interventions[interventions != -1] + 1
np.savetxt('./random_data', all_data)
np.savetxt('./random_interventions', interventions)
interventions[interventions != -1] = interventions[interventions != -1] - 1
graph_utils.run_gies_boot(200, './random_data', './random_interventions')
if __name__ == '__main__':
import causaldag as cd
from tqdm import tqdm
import random
np.random.seed(1818)
random.seed(11)
nsamples = 10000
ntrials = 10
perms = [
np.random.permutation(list(range(nsamples))) for _ in range(ntrials)
]
samples_list = [np.random.normal(size=nsamples) for _ in range(ntrials)]
d = cd.GaussDAG(nodes=[0, 1], arcs=set())
samples = d.sample(1000)
TEST_TIME = False
if TEST_TIME:
samples_list = [d.sample(nsamples) for _ in range(ntrials)]
for samples in tqdm(samples_list):
fadcor_test_vector(samples[:, 0], samples[:, 1])
TEST_PARTIAL_SUM = False
if TEST_PARTIAL_SUM:
x = samples[:, 0]
y = samples[:, 1]
c = np.random.normal(size=len(x))
res1 = partial_sum2d(x, y, c)
res2 = _partial_sum_simple(x, y, c)
