def test_runner_multiprocessing_convergence():
domains = [4]
defn = model_definition(domains, [((0, 0), bb)])
prng = rng()
relations, posterior = data_with_posterior(defn, prng)
views = map(numpy_dataview, relations)
latents = [model.initialize(defn, views, prng)
for _ in xrange(mp.cpu_count())]
kc = [('assign', range(len(domains)))]
runners = [runner.runner(defn, views, latent, kc) for latent in latents]
r = parallel.runner(runners)
r.run(r=prng, niters=10000) # burnin
product_assignments = tuple(map(list, map(permutation_iter, domains)))
idmap = {C: i for i, C in enumerate(it.product(*product_assignments))}
def sample_iter():
r.run(r=prng, niters=10)
for latent in r.get_latents():
key = tuple(tuple(permutation_canonical(latent.assignments(i)))
for i in xrange(len(domains)))
yield idmap[key]
ref = [None]
def sample_fn():
if ref[0] is None:
ref[0] = sample_iter()
try:
return next(ref[0])
except StopIteration:
ref[0] = None
return sample_fn()
assert_discrete_dist_approx(sample_fn, posterior, ntries=100, kl_places=2)
def _test_runner_simple(defn, kc_fn):
views = map(numpy_dataview, toy_dataset(defn))
kc = kc_fn(defn)
prng = rng()
latent = model.initialize(defn, views, prng)
r = runner.runner(defn, views, latent, kc)
r.run(prng, 10)
def _test_runner_simple(defn, kc_fn):
views = map(numpy_dataview, toy_dataset(defn))
kc = kc_fn(defn)
prng = rng()
latent = model.initialize(defn, views, prng)
r = runner.runner(defn, views, latent, kc)
r.run(prng, 10)
def test_runner_multiprocessing():
defn = model_definition([10, 10], [((0, 0), bb), ((0, 1), nich)])
views = map(numpy_dataview, toy_dataset(defn))
kc = runner.default_kernel_config(defn)
prng = rng()
latents = [model.initialize(defn, views, prng)
for _ in xrange(mp.cpu_count())]
runners = [runner.runner(defn, views, latent, kc) for latent in latents]
r = parallel.runner(runners)
# check it is restartable
r.run(r=prng, niters=10)
r.run(r=prng, niters=10)
def test_runner_multiprocessing():
defn = model_definition([10, 10], [((0, 0), bb), ((0, 1), nich)])
views = map(numpy_dataview, toy_dataset(defn))
kc = runner.default_kernel_config(defn)
prng = rng()
latents = [
model.initialize(defn, views, prng) for _ in xrange(mp.cpu_count())
]
runners = [runner.runner(defn, views, latent, kc) for latent in latents]
r = parallel.runner(runners)
# check it is restartable
r.run(r=prng, niters=10)
r.run(r=prng, niters=10)
def test_runner_default_kernel_config_convergence():
domains = [4]
defn = model_definition(domains, [((0, 0), bb)])
prng = rng()
relations, posterior = data_with_posterior(defn, prng)
views = map(numpy_dataview, relations)
latent = model.initialize(defn, views, prng)
r = runner.runner(defn, views, latent, [('assign', range(len(domains)))])
r.run(r=prng, niters=1000) # burnin
product_assignments = tuple(map(list, map(permutation_iter, domains)))
idmap = {C: i for i, C in enumerate(it.product(*product_assignments))}
def sample_fn():
r.run(r=prng, niters=10)
new_latent = r.get_latent()
key = tuple(tuple(permutation_canonical(new_latent.assignments(i)))
for i in xrange(len(domains)))
return idmap[key]
assert_discrete_dist_approx(sample_fn, posterior, ntries=100)
def test_runner_default_kernel_config_convergence():
domains = [4]
defn = model_definition(domains, [((0, 0), bb)])
prng = rng()
relations, posterior = data_with_posterior(defn, prng)
views = map(numpy_dataview, relations)
latent = model.initialize(defn, views, prng)
r = runner.runner(defn, views, latent, [('assign', range(len(domains)))])
r.run(r=prng, niters=1000) # burnin
product_assignments = tuple(map(list, map(permutation_iter, domains)))
idmap = {C: i for i, C in enumerate(it.product(*product_assignments))}
def sample_fn():
r.run(r=prng, niters=10)
new_latent = r.get_latent()
key = tuple(
tuple(permutation_canonical(new_latent.assignments(i)))
for i in xrange(len(domains)))
return idmap[key]
assert_discrete_dist_approx(sample_fn, posterior, ntries=100)
def test_runner_multiprocessing_convergence():
domains = [4]
defn = model_definition(domains, [((0, 0), bb)])
prng = rng()
relations, posterior = data_with_posterior(defn, prng)
views = map(numpy_dataview, relations)
latents = [
model.initialize(defn, views, prng) for _ in xrange(mp.cpu_count())
]
kc = [('assign', range(len(domains)))]
runners = [runner.runner(defn, views, latent, kc) for latent in latents]
r = parallel.runner(runners)
r.run(r=prng, niters=10000) # burnin
product_assignments = tuple(map(list, map(permutation_iter, domains)))
idmap = {C: i for i, C in enumerate(it.product(*product_assignments))}
def sample_iter():
r.run(r=prng, niters=10)
for latent in r.get_latents():
key = tuple(
tuple(permutation_canonical(latent.assignments(i)))
for i in xrange(len(domains)))
yield idmap[key]
ref = [None]
def sample_fn():
if ref[0] is None:
ref[0] = sample_iter()
try:
return next(ref[0])
except StopIteration:
ref[0] = None
return sample_fn()
assert_discrete_dist_approx(sample_fn, posterior, ntries=100, kl_places=2)
# 5. run the runners
# In[5]:
from microscopes.common.rng import rng
from microscopes.common.relation.dataview import numpy_dataview
from microscopes.models import bb as beta_bernoulli
from microscopes.irm.definition import model_definition
from microscopes.irm import model, runner, query
from microscopes.kernels import parallel
from microscopes.common.query import groups, zmatrix_heuristic_block_ordering, zmatrix_reorder
defn = model_definition([N], [((0, 0), beta_bernoulli)])
views = [numpy_dataview(communications_relation)]
prng = rng()
nchains = 1
latents = [model.initialize(defn, views, r=prng, cluster_hps=[{'alpha':1}]) for _ in xrange(nchains)]
kc = runner.default_assign_kernel_config(defn)
print kc
r = runner.runner(defn, views, latents[0], kc)
# ##From here, we can finally run each chain of the sampler 1000 times
# In[ ]:
start = time.time()
print start
r.run(r=prng, niters=1)
print "inference took {} seconds".format(time.time() - start)
defn = model_definition([N], [((0, 0), beta_bernoulli)])
views = [numpy_dataview(communications_relation)]
prng = rng()
# ##Next, let's initialize the model and define the runners.
#
# ##These runners are our MCMC chains. We'll use `cpu_count` to define our number of chains.
# In[ ]:
nchains = cpu_count()
latents = [model.initialize(defn, views, r=prng, cluster_hps=[{'alpha':1e-3}]) for _ in xrange(nchains)]
kc = runner.default_assign_kernel_config(defn)
runners = [runner.runner(defn, views, latent, kc) for latent in latents]
r = parallel.runner(runners)
# ##From here, we can finally run each chain of the sampler 1000 times
# In[ ]:
start = time.time()
r.run(r=prng, niters=1000)
print "inference took {} seconds".format(time.time() - start)
# ##Now that we have learned our model let's get our cluster assignments
# In[ ]:
def infinite_relational_model(corr_matrix, lag_matrix, threshold, sampled_coords, window_size):
import numpy as np
import math
import json
import time
import itertools as it
from multiprocessing import cpu_count
from microscopes.common.rng import rng
from microscopes.common.relation.dataview import numpy_dataview
from microscopes.models import bb as beta_bernoulli
from microscopes.irm.definition import model_definition
from microscopes.irm import model, runner, query
from microscopes.kernels import parallel
from microscopes.common.query import groups, zmatrix_heuristic_block_ordering, zmatrix_reorder
cluster_matrix = []
graph = []
# calculate graph
for row in corr_matrix:
graph_row = []
for corr in row:
if corr < threshold:
graph_row.append(False)
else:
graph_row.append(True)
graph.append(graph_row)
graph = np.array(graph, dtype=np.bool)
graph_size = len(graph)
# conduct Infinite Relational Model
defn = model_definition([graph_size], [((0, 0), beta_bernoulli)])
views = [numpy_dataview(graph)]
prng = rng()
nchains = cpu_count()
latents = [model.initialize(defn, views, r=prng, cluster_hps=[{'alpha':1e-3}]) for _ in xrange(nchains)]
kc = runner.default_assign_kernel_config(defn)
runners = [runner.runner(defn, views, latent, kc) for latent in latents]
r = parallel.runner(runners)
start = time.time()
# r.run(r=prng, niters=1000)
# r.run(r=prng, niters=100)
r.run(r=prng, niters=20)
print ("inference took", time.time() - start, "seconds")
infers = r.get_latents()
clusters = groups(infers[0].assignments(0), sort=True)
ordering = list(it.chain.from_iterable(clusters))
z = graph.copy()
z = z[ordering]
z = z[:,ordering]
corr_matrix = corr_matrix[ordering]
corr_matrix = corr_matrix[:,ordering]
lag_matrix = lag_matrix[ordering]
lag_matrix = lag_matrix[:,ordering]
cluster_sampled_coords = np.array(sampled_coords)
cluster_sampled_coords = cluster_sampled_coords[ordering]
response_msg = {
'corrMatrix': corr_matrix.tolist(),
'lagMatrix': lag_matrix.tolist(),
'clusterMatrix': z.tolist(),
'clusterSampledCoords': cluster_sampled_coords.tolist(),
'nClusterList': [len(cluster) for cluster in clusters],
'ordering': ordering,
}
f = open("./expdata/clustermatrix-" + str(window_size) + ".json", "w")
json.dump(response_msg, f)
f.close()
return response_msg
prng = rng()
# ##Next, let's initialize the model and define the runners.
#
# ##These runners are our MCMC chains. We'll use `cpu_count` to define our number of chains.
# In[ ]:
nchains = cpu_count()
latents = [
model.initialize(defn, views, r=prng, cluster_hps=[{
'alpha': 1e-3
}]) for _ in xrange(nchains)
]
kc = runner.default_assign_kernel_config(defn)
runners = [runner.runner(defn, views, latent, kc) for latent in latents]
r = parallel.runner(runners)
# ##From here, we can finally run each chain of the sampler 1000 times
# In[ ]:
start = time.time()
r.run(r=prng, niters=1000)
print "inference took {} seconds".format(time.time() - start)
# ##Now that we have learned our model let's get our cluster assignments
# In[ ]:
infers = r.get_latents()
from microscopes.common.rng import rng
from microscopes.common.relation.dataview import numpy_dataview
from microscopes.models import bb as beta_bernoulli
from microscopes.irm.definition import model_definition
from microscopes.irm import model, runner, query
from microscopes.kernels import parallel
from microscopes.common.query import groups, zmatrix_heuristic_block_ordering, zmatrix_reorder
defn = model_definition([N], [((0, 0), beta_bernoulli)])
views = [numpy_dataview(communications_relation)]
prng = rng()
nchains = 1
latents = [
model.initialize(defn, views, r=prng, cluster_hps=[{
'alpha': 1
}]) for _ in xrange(nchains)
]
kc = runner.default_assign_kernel_config(defn)
print kc
r = runner.runner(defn, views, latents[0], kc)
# ##From here, we can finally run each chain of the sampler 1000 times
# In[ ]:
start = time.time()
print start
r.run(r=prng, niters=1)
print "inference took {} seconds".format(time.time() - start)
