def run(model, model_updater, params_true, time=100):
timer = Timer()
trace = [_get_trace_row(model, model_updater, params_true, 0.0)]
while timer.elapsed < time:
timer.start()
model_updater.update(model)
timer.stop()
trace.append(
_get_trace_row(model, model_updater, params_true, timer.elapsed))
df = pd.DataFrame(trace)
model.params = params_true
df["log_p_true"] = model.log_p
df["rel_log_p"] = (df["log_p"] - df["log_p_true"]) / df["log_p_true"].abs()
df = df[[
"time", "num_features", "log_p", "log_p_true", "rel_log_p",
"b_cubed_f", "b_cubed_p", "b_cubed_r", "max_particles"
]]
return df
def run(data_true, model, model_updater, params_true, time=100):
timer = Timer()
trace = [_get_trace_row(data_true, model, params_true, 0.0)]
while timer.elapsed < time:
timer.start()
model_updater.update(model)
timer.stop()
trace.append(_get_trace_row(data_true, model, params_true, timer.elapsed))
df = pd.DataFrame(trace)
model.params = params_true
df['log_p_true'] = model.log_p
df['rel_log_p'] = (df['log_p'] - df['log_p_true']) / df['log_p_true'].abs()
df = df[['time', 'num_features', 'log_p', 'log_p_true', 'rel_log_p', 'b_cubed_f', 'b_cubed_p', 'b_cubed_r', 'error']]
return df
def run(data_true, model, model_updater, params_true, time=100):
trace = [_get_trace_row(data_true, model, params_true, 0.0)]
# Run annealing if required
timer = Timer()
while model_updater.feat_alloc_updater.annealing_schedule(model_updater.feat_alloc_updater.iter) < 1.0:
timer.start()
model_updater.update(model)
timer.stop()
trace.append(_get_trace_row(data_true, model, params_true, timer.elapsed, annealed=True))
annealing_time = timer.elapsed
# Main run
timer = Timer()
while timer.elapsed < time:
timer.start()
model_updater.update(model)
timer.stop()
trace.append(_get_trace_row(data_true, model, params_true, timer.elapsed, annealed=False))
df = pd.DataFrame(trace)
model.params = params_true
df["annealing_time"] = annealing_time
df["log_p_true"] = model.log_p
df["rel_log_p"] = (df["log_p"] - df["log_p_true"]) / df["log_p_true"].abs()
df = df[[
"annealed",
"time",
"annealing_time",
"num_features",
"log_p",
"log_p_true",
"rel_log_p",
"b_cubed_f",
"b_cubed_p",
"b_cubed_r",
"rmse"
]]
return df
def run(model, model_updater, time=100):
timer = Timer()
trace = [_get_trace_row(model, 0.0)]
while timer.elapsed < time:
timer.start()
model_updater.update(model)
timer.stop()
trace.append(_get_trace_row(model, timer.elapsed))
df = pd.DataFrame(trace)
df = df[["time", "num_features", "num_features_used", "log_p"]]
return df
def run(data_true, model, model_updater, trace_writer, time=100):
timer = Timer()
trace = [_get_trace_row(data_true, model, 0.0)]
while True:
timer.start()
model_updater.update(model)
timer.stop()
trace_writer.write_row(model, timer.elapsed)
trace.append(_get_trace_row(data_true, model, timer.elapsed))
if timer.elapsed >= time:
break
df = pd.DataFrame(trace)
df = df[["time", "num_features", "num_features_used", "log_p", "rmse"]]
return df
def main(args):
if args.ibp:
print(
'Warning: IBP sampling for the PyClone model is not properly supported.'
)
set_seed(args.data_seed)
params = pgfa.models.pyclone.binomial.simulate_params(args.num_dims,
args.num_data_points,
K=args.num_features,
alpha=args.alpha)
data = pgfa.models.pyclone.binomial.simulate_data(params)
model_updater = get_model_updater(annealing_power=args.annealing_power,
feat_alloc_updater_type=args.sampler,
ibp=args.ibp,
mixture_prob=args.mixture_prob,
num_particles=args.num_particles,
test_path=args.test_path)
set_seed(args.param_seed)
if args.ibp:
model_K = None
else:
model_K = args.num_features
model = pgfa.models.pyclone.binomial.get_model(data, K=model_K)
set_seed(args.run_seed)
old_params = model.params.copy()
model.params = params.copy()
log_p_true = model.log_p
model.params = old_params.copy()
print('Arguments')
print('-' * 100)
for key, value in sorted(vars(args).items()):
print('{0}: {1}'.format(key, value))
print('@' * 100)
print('True feature counts (sorted): {}'.format(
sorted(np.sum(params.Z, axis=0))))
print('True log density: {}'.format(log_p_true))
print('@' * 100)
timer = Timer()
i = 0
last_print_time = -np.float('inf')
while timer.elapsed < args.time:
if (timer.elapsed - last_print_time) > args.print_freq:
last_print_time = timer.elapsed
print('Iteration: {}'.format(i))
print('Log density: {}'.format(model.log_p))
print('Relative log density: {}'.format(
(model.log_p - log_p_true) / abs(log_p_true)))
if args.ibp:
print('Num features: {}'.format(model.params.K))
print('B-Cube scores: {}'.format(
get_b_cubed_score(params.Z, model.params.Z)))
print('Feature counts (sorted): {}'.format(
sorted(np.sum(model.params.Z, axis=0))))
print('#' * 100)
timer.start()
model_updater.update(model)
timer.stop()
i += 1
def main(args):
set_seed(args.data_seed)
params = pgfa.models.linear_gaussian.simulate_params(
alpha=args.alpha,
tau_v=args.tau_v,
tau_x=args.tau_x,
D=args.num_dims,
K=args.num_features,
N=args.num_data_points)
data, data_true = pgfa.models.linear_gaussian.simulate_data(
params, prop_missing=args.prop_missing)
# Make sure we do not have rows/columns of data that are all missing
for d in range(params.D):
assert not np.all(np.isnan(data[:, d]))
for n in range(params.N):
assert not np.all(np.isnan(data[n]))
model_updater = get_model_updater(annealing_power=args.annealing_power,
feat_alloc_updater_type=args.sampler,
ibp=args.ibp,
mixture_prob=args.mixture_prob,
num_particles=args.num_particles,
test_path=args.test_path)
set_seed(args.param_seed)
if args.ibp:
model_K = None
else:
model_K = args.num_features
model = pgfa.models.linear_gaussian.get_model(data, K=model_K)
set_seed(args.run_seed)
old_params = model.params.copy()
model.params = params.copy()
log_p_true = model.log_p
model.params = old_params.copy()
print('Arguments')
print('-' * 100)
for key, value in sorted(vars(args).items()):
print('{0}: {1}'.format(key, value))
print('@' * 100)
print('True feature counts (sorted): {}'.format(
sorted(np.sum(params.Z, axis=0))))
print('True log density: {}'.format(log_p_true))
print('@' * 100)
timer = Timer()
i = 0
last_print_time = -np.float('inf')
while timer.elapsed < args.time:
if (timer.elapsed - last_print_time) > args.print_freq:
last_print_time = timer.elapsed
print('Iteration: {}'.format(i))
print('Log density: {}'.format(model.log_p))
print('Relative log density: {}'.format(
(model.log_p - log_p_true) / abs(log_p_true)))
if args.prop_missing > 0:
print('L2 error: {}'.format(
compute_l2_error(data, data_true, model.params)))
if args.ibp:
print('Num features: {}'.format(model.params.K))
print('B-Cube scores: {}'.format(
get_b_cubed_score(params.Z, model.params.Z)))
print('Feature counts (sorted): {}'.format(
sorted(np.sum(model.params.Z, axis=0))))
print('#' * 100)
timer.start()
model_updater.update(model)
timer.stop()
i += 1
def main(args):
set_seed(args.data_seed)
params = pgfa.models.lfrm.simulate_params(
args.num_data_points, K=args.num_features, alpha=args.alpha, tau=args.tau
)
data, data_true = pgfa.models.lfrm.simulate_data(
params, prop_missing=args.prop_missing, symmetric=args.symmetric
)
model_updater = get_model_updater(
annealing_power=args.annealing_power,
feat_alloc_updater_type=args.sampler,
ibp=args.ibp,
mixture_prob=args.mixture_prob,
num_particles=args.num_particles,
test_path=args.test_path
)
set_seed(args.param_seed)
if args.ibp:
model_K = None
else:
model_K = args.num_features
model = pgfa.models.lfrm.get_model(data, K=model_K, symmetric=args.symmetric)
old_params = model.params.copy()
model.params = params.copy()
log_p_true = model.log_p
model.params = old_params.copy()
print('Arguments')
print('-' * 100)
for key, value in sorted(vars(args).items()):
print('{0}: {1}'.format(key, value))
print('@' * 100)
print('True feature counts (sorted): {}'.format(sorted(np.sum(params.Z, axis=0))))
print('True log density: {}'.format(log_p_true))
print('@' * 100)
timer = Timer()
i = 0
last_print_time = -np.float('inf')
while timer.elapsed < args.time:
if (timer.elapsed - last_print_time) > args.print_freq:
last_print_time = timer.elapsed
print('Iteration: {}'.format(i))
print('Log density: {}'.format(model.log_p))
print('Relative log density: {}'.format((model.log_p - log_p_true) / abs(log_p_true)))
print('Error: {}'.format(np.sum(np.abs(model.predict(method='max') - data_true))))
if args.ibp:
print('Num features: {}'.format(model.params.K))
print('B-Cube scores: {}'.format(get_b_cubed_score(params.Z, model.params.Z)))
print('Feature counts (sorted): {}'.format(sorted(np.sum(model.params.Z, axis=0))))
print('#' * 100)
timer.start()
model_updater.update(model)
timer.stop()
i += 1