def sample_trajectory_loglin(dataframe,
n_particles,
n_samples,
pseudo_obs=1.0,
alpha=0.5,
beta=0.5,
radius=None,
reset_cache=True,
**args):
p = dataframe.shape[1]
if radius is None:
radius = p
n_levels = np.array(dataframe.columns.get_level_values(1), dtype=int)
levels = np.array([range(l) for l in n_levels])
sd = seqdist.LogLinearJTPosterior()
sd.init_model(dataframe.get_values(), pseudo_obs, levels, {})
return sample_trajectory(n_particles,
alpha,
beta,
radius,
n_samples,
sd,
reset_cache=reset_cache)
def sample_trajectories_loglin_parallel(dataframe,
n_samples,
randomize=[1000],
pseudo_obs=[1.0],
reps=1,
output_directory=".",
**args):
n_levels = np.array(dataframe.columns.get_level_values(1), dtype=int)
levels = np.array([range(l) for l in n_levels])
queue = multiprocessing.Queue()
processes = []
rets = []
for _ in range(reps):
for r in randomize:
for T in n_samples:
sd = seqdist.LogLinearJTPosterior()
sd.init_model(dataframe.get_values(), pseudo_obs, levels)
print("Starting: " + str((T, r, str(sd), True)))
proc = Process(target=trajectory_to_queue,
args=(T, r, sd, queue, True))
proc.start()
processes.append(proc)
time.sleep(2)
for _ in processes:
ret = queue.get() # will block
rets.append(ret)
for p in processes:
p.join()
return rets
def sample_trajectory_loglin(dataframe, n_samples, pseudo_obs=1.0, randomize=1000, cache={}, **args):
n_levels = np.array(dataframe.columns.get_level_values(1), dtype=int)
levels = np.array([range(l) for l in n_levels])
sd = seqdist.LogLinearJTPosterior()
sd.init_model(dataframe.get_values(), pseudo_obs, levels, cache_complete_set_prob=cache)
return sample_trajectory(n_samples, randomize, sd)
def sample_trajectories_loglin_parallel(dataframe,
n_particles,
n_samples,
pseudo_observations=[1.0],
alphas=[0.5],
betas=[0.5],
radii=[None],
reset_cache=True,
reps=1,
output_directory=".",
**args):
p = dataframe.shape[1]
if radii == [None]:
radii = [p]
n_levels = np.array(dataframe.columns.get_level_values(1), dtype=int)
levels = np.array([range(l) for l in n_levels])
queue = multiprocessing.Queue()
processes = []
rets = []
cache = {}
for _ in range(reps):
for N in n_particles:
for T in n_samples:
for rad in radii:
for alpha in alphas:
for beta in betas:
for pseudo_obs in pseudo_observations:
sd = seqdist.LogLinearJTPosterior()
sd.init_model(dataframe.get_values(),
pseudo_obs,
levels,
cache_complete_set_prob=cache)
print("Starting: " +
str((N, T, alpha, beta, rad, str(sd),
reset_cache, output_directory,
True)))
proc = Process(target=trajectory_to_queue,
args=(N, T, alpha, beta, rad,
sd, queue, reset_cache,
True))
proc.start()
processes.append(proc)
time.sleep(2)
for _ in processes:
ret = queue.get() # will block
rets.append(ret)
for p in processes:
p.join()
return rets
def from_json(self, mcmc_json):
graphs = [json_graph.node_link_graph(js_graph)
for js_graph in mcmc_json["trajectory"]]
self.set_trajectory(graphs)
self.set_time(mcmc_json["run_time"])
self.optional = mcmc_json["optional"]
self.sampling_method = mcmc_json["sampling_method"]
if mcmc_json["model"]["name"] == "ggm_jt_post":
self.seqdist = sd.GGMJTPosterior()
elif mcmc_json["model"]["name"] == "loglin_jt_post":
self.seqdist = sd.LogLinearJTPosterior()
self.seqdist.init_model_from_json(mcmc_json["model"])
def sample_trajectories_loglin_to_file(dataframe, n_samples, randomize=[1000], pseudo_obs=[1.0],
reps=1, output_directory=".", **args):
n_levels = np.array(dataframe.columns.get_level_values(1), dtype=int)
levels = np.array([range(l) for l in n_levels])
graph_trajectories = []
for _ in range(reps):
for r in randomize:
for T in n_samples:
sd = seqdist.LogLinearJTPosterior()
sd.init_model(dataframe.get_values(), pseudo_obs, levels)
graph_trajectory = trajectory_to_file(T, r, sd, dir=output_directory)
graph_trajectories.append(graph_trajectory)
return graph_trajectories
def sample_trajectories_loglin_to_file(dataframe,
n_particles,
n_samples,
pseudo_observations=[1.0],
alphas=[0.5],
betas=[0.5],
radii=[None],
reset_cache=True,
reps=1,
output_directory=".",
output_filename="trajectory.json",
**args):
p = dataframe.shape[1]
if radii == [None]:
radii = [p]
n_levels = np.array(dataframe.columns.get_level_values(1), dtype=int)
levels = np.array([range(l) for l in n_levels])
graph_trajectories = []
cache = {}
for _ in range(reps):
for N in n_particles:
for T in n_samples:
for rad in radii:
for alpha in alphas:
for beta in betas:
for pseudo_obs in pseudo_observations:
sd = seqdist.LogLinearJTPosterior()
sd.init_model(dataframe.get_values(),
pseudo_obs,
levels,
cache_complete_set_prob=cache)
graph_trajectory = trajectory_to_file(
N,
T,
alpha,
beta,
rad,
sd,
reset_cache=reset_cache,
output_filename=output_filename,
dir=output_directory)
graph_trajectories.append(graph_trajectory)
return graph_trajectories