def run_synth_test():
""" Run a test with synthetic data and MCMC inference
"""
options, popn, data, popn_true, x_true = initialize_test_harness()
# Sample random initial state
x0 = popn.sample()
ll0 = popn.compute_log_p(x0)
print "LL0: %f" % ll0
# Perform inference
x_inf = coord_descent(popn, data, x0=x0, maxiter=1,
use_hessian=False,
use_rop=False)
ll_inf = popn.compute_log_p(x_inf)
print "LL_inf: %f" % ll_inf
# Save results
results_file = os.path.join(options.resultsDir, 'results.pkl')
print "Saving results to %s" % results_file
with open(results_file, 'w') as f:
cPickle.dump(x_inf, f, protocol=-1)
# Plot results
plot_results(popn, x_inf, popn_true, x_true, resdir=options.resultsDir)
def run_synth_test():
""" Run a test with synthetic data and MCMC inference
"""
options, popn, data, popn_true, x_true = initialize_test_harness()
results_file = os.path.join(options.resultsDir, 'results.pkl')
N_samples = 100
if os.path.exists(results_file):
print "Results found. Loading from file."
with open(results_file) as f:
x_smpls = cPickle.load(f)
N_samples = len(x_smpls)
# TODO: Check that the results are from the same model?
else:
print "Results not found. Running MCMC inference."
# If x0 specified, load x0 from file
x0 = None
if options.x0_file is not None:
with open(options.x0_file, 'r') as f:
print "Initializing with state from: %s" % options.x0_file
mle_x0 = cPickle.load(f)
# HACK: We're assuming x0 came from a standard GLM
mle_model = make_model('standard_glm', N=data['N'])
mle_popn = Population(mle_model)
mle_popn.set_data(data)
x0 = popn.sample()
x0 = convert_model(mle_popn, mle_model, mle_x0, popn,
popn.model, x0)
# Prepare for online plotting
plt.ion()
plotters = initialize_plotting(popn_true, x_true, popn)
plt.show()
cbk = lambda x: plot_sample_callback(x, plotters)
# Perform inference
raw_input('Press any key to begin inference...\n')
x_smpls = gibbs_sample(popn,
data,
x0=x0,
N_samples=N_samples,
init_from_mle=False,
callback=cbk)
# Save results
print "Saving results to %s" % results_file
with open(results_file, 'w') as f:
cPickle.dump(x_smpls, f, protocol=-1)
# Plot average of last 20% of samples
smpl_frac = 0.2
plot_results(popn,
x_smpls[-1 * int(smpl_frac * N_samples):],
popn_true=popn_true,
x_true=x_true,
resdir=options.resultsDir)
def run_synth_test():
""" Run a test with synthetic data and MCMC inference
"""
options, popn, data, popn_true, x_true = initialize_test_harness()
results_file = os.path.join(options.resultsDir, 'results.pkl')
N_samples = 100
if os.path.exists(results_file):
print "Results found. Loading from file."
with open(results_file) as f:
x_smpls = cPickle.load(f)
N_samples = len(x_smpls)
# TODO: Check that the results are from the same model?
else:
print "Results not found. Running MCMC inference."
# If x0 specified, load x0 from file
x0 = None
if options.x0_file is not None:
with open(options.x0_file, 'r') as f:
print "Initializing with state from: %s" % options.x0_file
mle_x0 = cPickle.load(f)
# HACK: We're assuming x0 came from a standard GLM
mle_model = make_model('standard_glm', N=data['N'])
mle_popn = Population(mle_model)
mle_popn.set_data(data)
x0 = popn.sample()
x0 = convert_model(mle_popn, mle_model, mle_x0, popn, popn.model, x0)
# Prepare for online plotting
plt.ion()
plotters = initialize_plotting(popn_true, x_true, popn)
plt.show()
cbk = lambda x: plot_sample_callback(x, plotters)
# Perform inference
raw_input('Press any key to begin inference...\n')
x_smpls = gibbs_sample(popn, data, x0=x0, N_samples=N_samples,
init_from_mle=False,
callback=cbk)
# Save results
print "Saving results to %s" % results_file
with open(results_file, 'w') as f:
cPickle.dump(x_smpls, f, protocol=-1)
# Plot average of last 20% of samples
smpl_frac = 0.2
plot_results(popn,
x_smpls[-1*int(smpl_frac*N_samples):],
popn_true=popn_true,
x_true=x_true,
resdir=options.resultsDir)
def run_synth_test():
""" Run a test with synthetic data and MCMC inference
"""
# Make a population with N neurons
N = 2
population, data, x_true = initialize_test_harness(N)
# Sample random initial state
x0 = population.sample()
ll0 = population.compute_log_p(x0)
print "LL0: %f" % ll0
# Perform inference
x_inf = gibbs_sample(population, data, x0=x0, N_samples=1000)
ll_inf = population.compute_log_p(x_inf)
print "LL_inf: %f" % ll_inf
# Save results
# Plot results
plot_results(population, x_true, x_inf)
def run_synth_test():
""" Run a test with synthetic data and MCMC inference
"""
options, popn, data, popn_true, x_true = initialize_test_harness()
# Sample random initial state
x0 = popn.sample()
ll0 = popn.compute_log_p(x0)
print "LL0: %f" % ll0
# Perform inference
x_inf = coord_descent(popn, x0=x0, maxiter=1)
ll_inf = popn.compute_log_p(x_inf)
print "LL_inf: %f" % ll_inf
# Save results
results_file = os.path.join(options.resultsDir, 'results.pkl')
print "Saving results to %s" % results_file
with open(results_file, 'w') as f:
cPickle.dump(x_inf, f, protocol=-1)
# Plot results
plot_results(popn, x_inf, popn_true, x_true, resdir=options.resultsDir)
def run_synth_test():
""" Run a test with synthetic data and MCMC inference
"""
options, popn, data, popn_true, x_true = initialize_test_harness()
# If x0 specified, load x0 from file
x0 = None
if options.x0_file is not None:
with open(options.x0_file, 'r') as f:
print "Initializing with state from: %s" % options.x0_file
mle_x0 = cPickle.load(f)
# HACK: We're assuming x0 came from a standard GLM
mle_model = make_model('standard_glm', N=data['N'])
mle_popn = Population(mle_model)
mle_popn.set_data(data)
x0 = popn.sample()
x0 = convert_model(mle_popn, mle_model, mle_x0, popn, popn.model, x0)
# Perform inference
N_samples = 1000
x_smpls = gibbs_sample(popn, data, x0=x0, N_samples=N_samples)
# Save results
results_file = os.path.join(options.resultsDir, 'results.pkl')
print "Saving results to %s" % results_file
with open(results_file, 'w') as f:
cPickle.dump(x_smpls, f, protocol=-1)
# Plot average of last 20% of samples
smpl_frac = 0.2
plot_results(popn,
x_smpls[-1*int(smpl_frac*N_samples):],
popn_true=popn_true,
x_true=x_true,
resdir=options.resultsDir)
def run_synth_test():
""" Run a test with synthetic data and MAP inference with cross validation
"""
options, popn, data, popn_true, x_true = initialize_test_harness()
# Get the list of models for cross validation
base_model = make_model(options.model, N=data['N'])
models = get_xv_models(base_model)
# TODO Segment data into training and cross validation sets
train_frac = 0.75
T_split = data['T'] * train_frac
train_data = segment_data(data, (0,T_split))
xv_data = segment_data(data, (T_split,data['T']))
# Sample random initial state
x0 = popn.sample()
# Track the best model and parameters
best_ind = -1
best_xv_ll = -np.Inf
best_x = x0
best_model = None
# Fit each model using the optimum of the previous models
train_lls = np.zeros(len(models))
xv_lls = np.zeros(len(models))
total_lls = np.zeros(len(models))
for (i,model) in enumerate(models):
print "Training model %d" % i
x0 = copy.deepcopy(best_x)
popn.set_hyperparameters(model)
popn.set_data(train_data)
ll0 = popn.compute_log_p(x0)
print "Training LL0: %f" % ll0
# Perform inference
x_inf = coord_descent(popn, data, x0=x0, maxiter=1,
use_hessian=False,
use_rop=False)
ll_train = popn.compute_log_p(x_inf)
print "Training LL_inf: %f" % ll_train
train_lls[i] = ll_train
# Compute log lkhd on xv data
popn.set_data(xv_data)
ll_xv = popn.compute_ll(x_inf)
print "Cross Validation LL: %f" % ll_xv
xv_lls[i] = ll_xv
# Compute log lkhd on total dataset
popn.set_data(data)
ll_total = popn.compute_ll(x_inf)
print "Tota LL: %f" % ll_total
total_lls[i] = ll_total
# Update best model
if ll_xv > best_xv_ll:
best_ind = i
best_xv_ll = ll_xv
best_x = copy.deepcopy(x_inf)
best_model = copy.deepcopy(model)
# Create a population with the best model
popn.set_hyperparameters(best_model)
popn.set_data(data)
# Fit the best model on the full training data
best_x = coord_descent(popn, data, x0=x0, maxiter=1,
use_hessian=False,
use_rop=False)
# Print results summary
for i in np.arange(len(models)):
print "Model %d:\tTrain LL: %.1f\tXV LL: %.1f\tTotal LL: %.1f" % (i, train_lls[i], xv_lls[i], total_lls[i])
print "Best model: %d" % best_ind
print "Best Total LL: %f" % popn.compute_ll(best_x)
print "True LL: %f" % popn_true.compute_ll(x_true)
# Save results
results_file = os.path.join(options.resultsDir, 'results.pkl')
print "Saving results to %s" % results_file
with open(results_file, 'w') as f:
cPickle.dump(best_x, f)
# Plot results
plot_results(popn, best_x, popn_true, x_true, resdir=options.resultsDir)
def run_synth_test():
""" Run a test with synthetic data and MAP inference with cross validation
"""
options, popn, data, popn_true, x_true = initialize_test_harness()
# Get the list of models for cross validation
base_model = make_model(options.model, N=data['N'], dt=0.001)
models = get_xv_models(base_model)
# TODO Segment data into training and cross validation sets
train_frac = 0.75
T_split = data['T'] * train_frac
train_data = segment_data(data, (0, T_split))
xv_data = segment_data(data, (T_split, data['T']))
# Preprocess the data sequences
train_data = popn.preprocess_data(train_data)
xv_data = popn.preprocess_data(xv_data)
# Sample random initial state
x0 = popn.sample()
# Track the best model and parameters
best_ind = -1
best_xv_ll = -np.Inf
best_x = x0
best_model = None
# Fit each model using the optimum of the previous models
train_lls = np.zeros(len(models))
xv_lls = np.zeros(len(models))
total_lls = np.zeros(len(models))
for (i, model) in enumerate(models):
print "Training model %d" % i
x0 = copy.deepcopy(best_x)
popn.set_hyperparameters(model)
popn.set_data(train_data)
ll0 = popn.compute_log_p(x0)
print "Training LL0: %f" % ll0
# Perform inference
x_inf = coord_descent(popn, x0=x0, maxiter=1)
ll_train = popn.compute_log_p(x_inf)
print "Training LP_inf: %f" % ll_train
train_lls[i] = ll_train
# Compute log lkhd on xv data
popn.set_data(xv_data)
ll_xv = popn.compute_ll(x_inf)
print "Cross Validation LL: %f" % ll_xv
xv_lls[i] = ll_xv
# Compute log lkhd on total dataset
popn.set_data(data)
ll_total = popn.compute_ll(x_inf)
print "Total LL: %f" % ll_total
total_lls[i] = ll_total
# Update best model
if ll_xv > best_xv_ll:
best_ind = i
best_xv_ll = ll_xv
best_x = copy.deepcopy(x_inf)
best_model = copy.deepcopy(model)
# Create a population with the best model
popn.set_hyperparameters(best_model)
popn.set_data(data)
# Fit the best model on the full training data
best_x = coord_descent(popn,
data,
x0=x0,
maxiter=1,
use_hessian=False,
use_rop=False)
# Print results summary
for i in np.arange(len(models)):
print "Model %d:\tTrain LL: %.1f\tXV LL: %.1f\tTotal LL: %.1f" % (
i, train_lls[i], xv_lls[i], total_lls[i])
print "Best model: %d" % best_ind
print "Best Total LL: %f" % popn.compute_ll(best_x)
print "True LL: %f" % popn_true.compute_ll(x_true)
# Save results
results_file = os.path.join(options.resultsDir, 'results.pkl')
print "Saving results to %s" % results_file
with open(results_file, 'w') as f:
cPickle.dump(best_x, f)
# Plot results
plot_results(popn, best_x, popn_true, x_true, resdir=options.resultsDir)
def fit_latent_network_to_mle():
""" Run a test with synthetic data and MCMC inference
"""
options, popn, data, popn_true, x_true = initialize_test_harness()
import pdb; pdb.set_trace()
# Load MLE parameters from command line
mle_x = None
if options.x0_file is not None:
with open(options.x0_file, 'r') as f:
print "Initializing with state from: %s" % options.x0_file
mle_x = cPickle.load(f)
mle_model = make_model('standard_glm', N=data['N'])
mle_popn = Population(mle_model)
mle_popn.set_data(data)
# Create a location sampler
print "Initializing latent location sampler"
loc_sampler = LatentLocationUpdate()
loc_sampler.preprocess(popn)
# Convert the mle results into a weighted adjacency matrix
x_aw = popn.sample(None)
x_aw = convert_model(mle_popn, mle_model, mle_x, popn, popn.model, x_aw)
# Get rid of unnecessary keys
del x_aw['glms']
# Fit the latent distance network to a thresholded adjacency matrix
ws = np.sort(np.abs(x_aw['net']['weights']['W']))
wperm = np.argsort(np.abs(x_aw['net']['weights']['W']))
nthrsh = 20
threshs = np.arange(ws.size, step=ws.size/nthrsh)
res = []
N = popn.N
for th in threshs:
print "Fitting network for threshold: %.3f" % th
A = np.zeros_like(ws, dtype=np.int8)
A[wperm[th:]] = 1
A = A.reshape((N,N))
# A = (np.abs(x_aw['net']['weights']['W']) >= th).astype(np.int8).reshape((N,N))
# Make sure the diag is still all 1s
A[np.diag_indices(N)] = 1
x = copy.deepcopy(x_aw)
x['net']['graph']['A'] = A
smpls = fit_latent_network_given_A(x, loc_sampler)
# Index the results by the overall sparsity of A
key = (np.sum(A)-N) / (np.float(np.size(A))-N)
res.append((key, smpls))
# Save results
results_file = os.path.join(options.resultsDir, 'fit_latent_network_results.pkl')
print "Saving results to %s" % results_file
with open(results_file, 'w') as f:
cPickle.dump(res, f)
