def fit_network_hawkes_gibbs(S, K, C, dt, dt_max,
output_path,
standard_model=None):
# Check for existing Gibbs results
if os.path.exists(output_path + ".gibbs.pkl"):
with open(output_path + ".gibbs.pkl", 'r') as f:
print "Loading Gibbs results from ", (output_path + ".gibbs.pkl")
(samples, timestamps) = cPickle.load(f)
else:
print "Fitting the data with a network Hawkes model using Gibbs sampling"
# Make a new model for inference
# test_model = DiscreteTimeNetworkHawkesModelGammaMixture(C=C, K=K, dt=dt, dt_max=dt_max, B=B,
# alpha=1.0, beta=1.0/20.0)
test_basis = IdentityBasis(dt, dt_max, allow_instantaneous=True)
network_hypers = {'C': C, 'alpha': 1.0, 'beta': 1.0/10.0,
'tau1': 1.0, 'tau0': 10.0,
'allow_self_connections': False}
test_model = DiscreteTimeNetworkHawkesModelSpikeAndSlab(K=K, dt=dt, dt_max=dt_max,
basis=test_basis,
network_hypers=network_hypers)
test_model.add_data(S)
# Initialize with the standard model parameters
if standard_model is not None:
test_model.initialize_with_standard_model(standard_model)
plt.ion()
im = plot_network(test_model.weight_model.A, test_model.weight_model.W, vmax=0.5)
plt.pause(0.001)
# Gibbs sample
N_samples = 100
samples = []
lps = [test_model.log_probability()]
timestamps = []
for itr in xrange(N_samples):
if itr % 1 == 0:
print "Iteration ", itr, "\tLL: ", lps[-1]
im.set_data(test_model.weight_model.W_effective)
plt.pause(0.001)
# lps.append(test_model.log_probability())
lps.append(test_model.log_probability())
samples.append(test_model.resample_and_copy())
timestamps.append(time.clock())
# Save this sample
with open(output_path + ".gibbs.itr%04d.pkl" % itr, 'w') as f:
cPickle.dump(samples[-1], f, protocol=-1)
# Save the Gibbs samples
with open(output_path + ".gibbs.pkl", 'w') as f:
print "Saving Gibbs samples to ", (output_path + ".gibbs.pkl")
cPickle.dump((samples, timestamps), f, protocol=-1)
return samples, timestamps
def demo(K=3, T=1000, dt_max=20, p=0.25):
"""
:param K: Number of nodes
:param T: Number of time bins to simulate
:param dt_max: Number of future time bins an event can influence
:param p: Sparsity of network
:return:
"""
###########################################################
# Generate synthetic data
###########################################################
network_hypers = {"p": p, "allow_self_connections": False}
true_model = DiscreteTimeNetworkHawkesModelSpikeAndSlab(
K=K, dt_max=dt_max,
network_hypers=network_hypers)
assert true_model.check_stability()
# Sample from the true model
S,R = true_model.generate(T=T, keep=True, print_interval=50)
plt.ion()
true_figure, _ = true_model.plot(color="#377eb8", T_slice=(0,100))
###########################################################
# Create a test spike and slab model
###########################################################
test_model = DiscreteTimeNetworkHawkesModelSpikeAndSlab(
K=K, dt_max=dt_max,
network_hypers=network_hypers)
test_model.add_data(S)
# Initialize plots
test_figure, test_handles = test_model.plot(color="#e41a1c", T_slice=(0,100))
###########################################################
# Fit the test model with Gibbs sampling
###########################################################
N_samples = 100
samples = []
lps = []
for itr in range(N_samples):
print("Gibbs iteration ", itr)
test_model.resample_model()
lps.append(test_model.log_probability())
samples.append(test_model.copy_sample())
# Update plots
test_model.plot(handles=test_handles)
###########################################################
# Analyze the samples
###########################################################
analyze_samples(true_model, samples, lps)
def demo(K=3, T=1000, dt_max=20, p=0.25):
"""
:param K: Number of nodes
:param T: Number of time bins to simulate
:param dt_max: Number of future time bins an event can influence
:param p: Sparsity of network
:return:
"""
###########################################################
# Generate synthetic data
###########################################################
network_hypers = {"p": p, "allow_self_connections": False}
true_model = DiscreteTimeNetworkHawkesModelSpikeAndSlab(
K=K, dt_max=dt_max,
network_hypers=network_hypers)
assert true_model.check_stability()
# Sample from the true model
S,R = true_model.generate(T=T, keep=True, print_interval=50)
plt.ion()
true_figure, _ = true_model.plot(color="#377eb8", T_slice=(0,100))
###########################################################
# Create a test spike and slab model
###########################################################
test_model = DiscreteTimeNetworkHawkesModelSpikeAndSlab(
K=K, dt_max=dt_max,
network_hypers=network_hypers)
test_model.add_data(S)
# Initialize plots
test_figure, test_handles = test_model.plot(color="#e41a1c", T_slice=(0,100))
###########################################################
# Fit the test model with Gibbs sampling
###########################################################
N_samples = 100
samples = []
lps = []
for itr in xrange(N_samples):
print "Gibbs iteration ", itr
test_model.resample_model()
lps.append(test_model.log_probability())
samples.append(test_model.copy_sample())
# Update plots
test_model.plot(handles=test_handles)
###########################################################
# Analyze the samples
###########################################################
analyze_samples(true_model, samples, lps)
def fit_network_hawkes_gibbs_ss(S, K, C, B, dt, dt_max,
output_path, p,
standard_model=None):
samples_and_timestamps = load_partial_results(output_path, typ="gibbs_ss")
if samples_and_timestamps is not None:
samples, timestamps = samples_and_timestamps
else:
print "Fitting the data with a spike and slab network Hawkes model using Gibbs sampling"
# Make a new model for inference
network_hypers = {'C': C, 'alpha': 1.0, 'beta': 1.0/20.0, 'p': p,
'v': 5.0,'c': np.arange(C).repeat((K // C))}
test_model = DiscreteTimeNetworkHawkesModelSpikeAndSlab(K=K, dt=dt, dt_max=dt_max, B=B,
network_hypers=network_hypers)
test_model.add_data(S)
# Initialize with the standard model parameters
if standard_model is not None:
test_model.initialize_with_standard_model(standard_model)
# Gibbs sample
N_samples = 1000
samples = []
lps = []
timestamps = [time.clock()]
for itr in xrange(N_samples):
lps.append(test_model.log_probability())
samples.append(test_model.resample_and_copy())
timestamps.append(time.clock())
print test_model.network.v
if itr % 1 == 0:
print "Iteration ", itr, "\t LP: ", lps[-1]
# Save this sample
with open(output_path + ".gibbs_ss.itr%04d.pkl" % itr, 'w') as f:
cPickle.dump((samples[-1], timestamps[-1]-timestamps[0]), f, protocol=-1)
# Save the Gibbs timestamps
timestamps = np.array(timestamps)
with open(output_path + ".gibbs_ss.timestamps.pkl", 'w') as f:
print "Saving spike and slab Gibbs samples to ", (output_path + ".gibbs_ss.timestamps.pkl")
cPickle.dump(timestamps, f, protocol=-1)
# Save the Gibbs samples
with open(output_path + ".gibbs_ss.pkl", 'w') as f:
print "Saving Gibbs samples to ", (output_path + ".gibbs_ss.pkl")
cPickle.dump((samples, timestamps[1:] - timestamps[0]), f, protocol=-1)
return samples, timestamps
def demo(K=3, T=1000, dt_max=20, p=0.25):
"""
:param K: Number of nodes
:param T: Number of time bins to simulate
:param dt_max: Number of future time bins an event can influence
:param p: Sparsity of network
:return:
"""
###########################################################
# Generate synthetic data
###########################################################
network = ErdosRenyiFixedSparsity(K, p, v=1., allow_self_connections=False)
bkgd_hypers = {"alpha": 1.0, "beta": 20.0}
true_model = DiscreteTimeNetworkHawkesModelSpikeAndSlab(
K=K, dt_max=dt_max, bkgd_hypers=bkgd_hypers, network=network)
A_true = np.zeros((K, K))
A_true[0, 1] = A_true[0, 2] = 1
W_true = np.zeros((K, K))
W_true[0, 1] = W_true[0, 2] = 1.0
true_model.weight_model.A = A_true
true_model.weight_model.W = W_true
true_model.bias_model.lambda0[0] = 0.2
assert true_model.check_stability()
# Sample from the true model
S, R = true_model.generate(T=T, keep=True, print_interval=50)
plt.ion()
true_figure, _ = true_model.plot(color="#377eb8", T_slice=(0, 100))
# Save the true figure
true_figure.savefig("gifs/true.gif")
###########################################################
# Create a test spike and slab model
###########################################################
test_model = DiscreteTimeNetworkHawkesModelSpikeAndSlab(K=K,
dt_max=dt_max,
network=network)
test_model.add_data(S)
# Initialize plots
test_figure, test_handles = test_model.plot(color="#e41a1c",
T_slice=(0, 100))
test_figure.savefig("gifs/test0.gif")
###########################################################
# Fit the test model with Gibbs sampling
###########################################################
N_samples = 100
samples = []
lps = []
for itr in xrange(N_samples):
print "Gibbs iteration ", itr
test_model.resample_model()
lps.append(test_model.log_probability())
samples.append(test_model.copy_sample())
# Update plots
test_model.plot(handles=test_handles)
test_figure.savefig("gifs/test%d.gif" % (itr + 1))
def fit_spikeslab_network_hawkes_gibbs(S,
S_test,
dt,
dt_max,
output_path,
model_args={},
standard_model=None,
N_samples=100,
time_limit=8 * 60 * 60):
T, K = S.shape
# Check for existing Gibbs results
if os.path.exists(output_path):
with gzip.open(output_path, 'r') as f:
print("Loading Gibbs results from ", output_path)
results = pickle.load(f)
else:
print(
"Fitting the data with a network Hawkes model using Gibbs sampling"
)
test_model = DiscreteTimeNetworkHawkesModelSpikeAndSlab(K=K,
dt=dt,
dt_max=dt_max,
**model_args)
test_model.add_data(S)
# Initialize with the standard model parameters
if standard_model is not None:
test_model.initialize_with_standard_model(standard_model)
# TODO: Precompute F_test
F_test = test_model.basis.convolve_with_basis(S_test)
# Gibbs sample
samples = []
lps = [test_model.log_probability()]
hlls = [test_model.heldout_log_likelihood(S_test)]
times = [0]
for _ in progprint_xrange(N_samples, perline=10):
# Update the model
tic = time.time()
test_model.resample_model()
samples.append(copy.deepcopy(test_model.get_parameters()))
times.append(time.time() - tic)
# Compute log probability and heldout log likelihood
# lps.append(test_model.log_probability())
hlls.append(test_model.heldout_log_likelihood(S_test, F=F_test))
# # Save this sample
# with open(output_path + ".gibbs.itr%04d.pkl" % itr, 'w') as f:
# cPickle.dump(samples[-1], f, protocol=-1)
# Check if time limit has been exceeded
if np.sum(times) > time_limit:
break
# Get cumulative timestamps
timestamps = np.cumsum(times)
lps = np.array(lps)
hlls = np.array(hlls)
# Make results object
results = Results(samples, timestamps, lps, hlls)
# Save the Gibbs samples
with gzip.open(output_path, 'w') as f:
print("Saving Gibbs samples to ", output_path)
pickle.dump(results, f, protocol=-1)
return results
def demo(seed=None):
"""
Create a discrete time Hawkes model and generate from it.
:return:
"""
if seed is None:
seed = np.random.randint(2**32)
print("Setting seed to ", seed)
np.random.seed(seed)
###########################################################
# Load some example data.
# See data/synthetic/generate.py to create more.
###########################################################
data_path = os.path.join("data", "synthetic",
"synthetic_K20_C4_T10000.pkl.gz")
with gzip.open(data_path, 'r') as f:
S, true_model = pickle.load(f)
T = S.shape[0]
K = true_model.K
B = true_model.B
dt = true_model.dt
dt_max = true_model.dt_max
###########################################################
# Initialize with MAP estimation on a standard Hawkes model
###########################################################
init_with_map = True
if init_with_map:
init_len = T
print("Initializing with BFGS on first ", init_len, " time bins.")
init_model = DiscreteTimeStandardHawkesModel(K=K,
dt=dt,
dt_max=dt_max,
B=B,
alpha=1.0,
beta=1.0)
init_model.add_data(S[:init_len, :])
init_model.initialize_to_background_rate()
init_model.fit_with_bfgs()
else:
init_model = None
###########################################################
# Create a test spike and slab model
###########################################################
# Copy the network hypers.
# Give the test model p, but not c, v, or m
network_hypers = true_model.network_hypers.copy()
network_hypers['c'] = None
network_hypers['v'] = None
network_hypers['m'] = None
test_network = StochasticBlockModel(K=K, **network_hypers)
test_model = DiscreteTimeNetworkHawkesModelSpikeAndSlab(
K=K,
dt=dt,
dt_max=dt_max,
B=B,
basis_hypers=true_model.basis_hypers,
bkgd_hypers=true_model.bkgd_hypers,
impulse_hypers=true_model.impulse_hypers,
weight_hypers=true_model.weight_hypers,
network=test_network)
test_model.add_data(S)
# F_test = test_model.basis.convolve_with_basis(S_test)
# Initialize with the standard model parameters
if init_model is not None:
test_model.initialize_with_standard_model(init_model)
# Initialize plots
ln, im_net, im_clus = initialize_plots(true_model, test_model, S)
###########################################################
# Fit the test model with Gibbs sampling
###########################################################
N_samples = 50
samples = []
lps = []
# plls = []
for itr in range(N_samples):
lps.append(test_model.log_probability())
# plls.append(test_model.heldout_log_likelihood(S_test, F=F_test))
samples.append(test_model.copy_sample())
print("")
print("Gibbs iteration ", itr)
print("LP: ", lps[-1])
test_model.resample_model()
# Update plot
if itr % 1 == 0:
update_plots(itr, test_model, S, ln, im_clus, im_net)
###########################################################
# Analyze the samples
###########################################################
analyze_samples(true_model, init_model, samples, lps)
def execute_toy(self,mode="discrete",dt_max=3,N_samples=1000,network_priors={"p": 1.0, "allow_self_connections": False}):
#np.random.seed(0)
if mode == 'discrete':
test_model1 = DiscreteTimeNetworkHawkesModelSpikeAndSlab(K=self.K, dt_max=dt_max,
network_hypers=network_priors)
test_model1.add_data(self.data)
test_model1.initialize_with_standard_model(None)
elif mode == 'continuous':
test_model = ContinuousTimeNetworkHawkesModel(self.K, dt_max=dt_max,
network_hypers=network_hypers)
test_model.add_data(self.data,self.labels)
###########################################################
# Fit the test model with Gibbs sampling
###########################################################
samples = []
lps = []
#for itr in xrange(N_samples):
# test_model1.resample_model()
# lps.append(test_model1.log_probability())
# samples.append(test_model1.copy_sample())
test_model = DiscreteTimeStandardHawkesModel(K=self.K, dt_max=dt_max, allow_self_connections= False)
#test_model.initialize_with_gibbs_model(test_model1)
test_model.add_data(self.data)
test_model.fit_with_bfgs()
impulse = test_model1.impulse_model.impulses
responses = {}
#for i in range(3):
# responses[str(i)] = []
# for j in range(3):
# responses[str(i)].append({"key":"response: process "+str(i)+" to "+str(j),"values":[{"x":idx,"y":k} for idx,k in enumerate(impulse[:,i,j])]})
# with open('/Users/PauKung/hawkes_demo/webapp/static/data/response'+str(i)+'.json','w') as outfile:
# json.dump({"out":responses[str(i)]},outfile)
# calculate convolved basis
rr = test_model.basis.convolve_with_basis(np.ones((dt_max*2,self.K)))
impulse = np.sum(rr, axis=2)
impulse[dt_max:,:] = 0
for i in range(3):
responses[str(i)] = {"key":"response: process "+str(i),"values":[{"x":idx,"y":k} for idx,k in enumerate(impulse[:,i])]}
with open('/Users/PauKung/hawkes_demo/webapp/static/data/response'+str(i)+'.json','w') as outfile:
json.dump({"out":responses[str(i)]},outfile)
rates = test_model.compute_rate()#self.compute_rate(test_model,mode,dt_max)
inferred_rate = {}
S,F = test_model.data_list[0]
print F
for i in range(3):
inferred_rate[str(i)] = []
inferred_rate[str(i)].append({"key":"background",
"values":[[j,test_model.bias[i]] for j in range(self.T)]})
#"values":[[j,test_model1.bias_model.lambda0[i]] for j in range(self.T)]})
for i in range(3):
inferred_rate[str(i)].append({"key":"influence: process"+str(i),
"values":[[idx,j-test_model.bias[i]] for idx,j in enumerate(rates[:,i])]})
with open('/Users/PauKung/hawkes_demo/webapp/static/data/infer'+str(i)+'.json','w') as outfile:
json.dump({"out":inferred_rate[str(i)]},outfile)
# output response function diagram (K x K timeseries)
#plt.subplot(3,3,1)
#for i in range(3):
# for j in range(3):
# plt.subplot(3,3,3*i+(j+1))
# plt.plot(np.arange(4),impulse[:,i,j],color="#377eb8", lw=2)
#plt.savefig(fpath+"response_fun.png",transparent=True)
# output background bias diagram (K x 1 timeseries)
#plt.subplot(3,1,1)
#for i in range(3):
# plt.subplot(3,1,i+1)
# plt.plot(np.arange(4),[test_model.bias_model.lambda0[i] for j in range(4)],color="#333333",lw=2)
#plt.savefig(fpath+"bias.png",transparent=True)
# output inferred rate diagram (K x 1 timeseries)
#test_figure, test_handles = test_model.plot(color="#e41a1c", T_slice=(0,self.T))
#plt.savefig(fpath+"inferred_rate.png",transparent=True)
print test_model.W
return test_model.W, inferred_rate, responses
def fit_network_hawkes_gibbs(S, K, C, dt, dt_max, output_path, standard_model=None):
# Check for existing Gibbs results
if os.path.exists(output_path + ".gibbs.pkl"):
with open(output_path + ".gibbs.pkl", "r") as f:
print "Loading Gibbs results from ", (output_path + ".gibbs.pkl")
(samples, timestamps) = cPickle.load(f)
else:
print "Fitting the data with a network Hawkes model using Gibbs sampling"
# Make a new model for inference
# test_model = DiscreteTimeNetworkHawkesModelGammaMixture(C=C, K=K, dt=dt, dt_max=dt_max, B=B,
# alpha=1.0, beta=1.0/20.0)
test_basis = IdentityBasis(dt, dt_max, allow_instantaneous=True)
# Set the network prior such that E[W] ~= 0.01
# W ~ Gamma(kappa, v) for kappa = 1.25 => v ~ 125
# v ~ Gamma(alpha, beta) for alpha = 10, beta = 10 / 125
E_W = 0.01
kappa = 10.0
E_v = kappa / E_W
alpha = 10.0
beta = alpha / E_v
network_hypers = {
"C": 2,
"kappa": kappa,
"alpha": alpha,
"beta": beta,
"p": 0.8,
"allow_self_connections": False,
}
test_model = DiscreteTimeNetworkHawkesModelSpikeAndSlab(
K=K, dt=dt, dt_max=dt_max, basis=test_basis, network_hypers=network_hypers
)
test_model.add_data(S)
# Initialize with the standard model parameters
if standard_model is not None:
test_model.initialize_with_standard_model(standard_model)
plt.ion()
im = plot_network(test_model.weight_model.A, test_model.weight_model.W, vmax=0.5)
plt.pause(0.001)
# Gibbs sample
N_samples = 100
samples = []
lps = [test_model.log_probability()]
timestamps = []
for itr in xrange(N_samples):
if itr % 1 == 0:
print "Iteration ", itr, "\tLL: ", lps[-1]
im.set_data(test_model.weight_model.W_effective)
plt.pause(0.001)
# lps.append(test_model.log_probability())
lps.append(test_model.log_probability())
samples.append(test_model.resample_and_copy())
timestamps.append(time.clock())
# Save this sample
with open(output_path + ".gibbs.itr%04d.pkl" % itr, "w") as f:
cPickle.dump(samples[-1], f, protocol=-1)
# Save the Gibbs samples
with open(output_path + ".gibbs.pkl", "w") as f:
print "Saving Gibbs samples to ", (output_path + ".gibbs.pkl")
cPickle.dump((samples, timestamps), f, protocol=-1)
return samples, timestamps
def fit_spikeslab_network_hawkes_gibbs(S, S_test, dt, dt_max, output_path,
model_args={}, standard_model=None,
N_samples=100, time_limit=8*60*60):
T,K = S.shape
# Check for existing Gibbs results
if os.path.exists(output_path):
with gzip.open(output_path, 'r') as f:
print "Loading Gibbs results from ", output_path
results = cPickle.load(f)
else:
print "Fitting the data with a network Hawkes model using Gibbs sampling"
test_model = DiscreteTimeNetworkHawkesModelSpikeAndSlab(K=K, dt=dt, dt_max=dt_max, **model_args)
test_model.add_data(S)
# Initialize with the standard model parameters
if standard_model is not None:
test_model.initialize_with_standard_model(standard_model)
# TODO: Precompute F_test
F_test = test_model.basis.convolve_with_basis(S_test)
# Gibbs sample
samples = []
lps = [test_model.log_probability()]
hlls = [test_model.heldout_log_likelihood(S_test)]
times = [0]
for _ in progprint_xrange(N_samples, perline=10):
# Update the model
tic = time.time()
test_model.resample_model()
samples.append(copy.deepcopy(test_model.get_parameters()))
times.append(time.time() - tic)
# Compute log probability and heldout log likelihood
# lps.append(test_model.log_probability())
hlls.append(test_model.heldout_log_likelihood(S_test, F=F_test))
# # Save this sample
# with open(output_path + ".gibbs.itr%04d.pkl" % itr, 'w') as f:
# cPickle.dump(samples[-1], f, protocol=-1)
# Check if time limit has been exceeded
if np.sum(times) > time_limit:
break
# Get cumulative timestamps
timestamps = np.cumsum(times)
lps = np.array(lps)
hlls = np.array(hlls)
# Make results object
results = Results(samples, timestamps, lps, hlls)
# Save the Gibbs samples
with gzip.open(output_path, 'w') as f:
print "Saving Gibbs samples to ", output_path
cPickle.dump(results, f, protocol=-1)
return results
def demo(seed=None):
"""
Create a discrete time Hawkes model and generate from it.
:return:
"""
if seed is None:
seed = np.random.randint(2**32)
print "Setting seed to ", seed
np.random.seed(seed)
###########################################################
# Load some example data.
# See data/synthetic/generate.py to create more.
###########################################################
data_path = os.path.join("data", "synthetic", "synthetic_K20_C4_T10000.pkl.gz")
with gzip.open(data_path, 'r') as f:
S, true_model = cPickle.load(f)
T = S.shape[0]
K = true_model.K
B = true_model.B
dt = true_model.dt
dt_max = true_model.dt_max
###########################################################
# Initialize with MAP estimation on a standard Hawkes model
###########################################################
init_with_map = True
if init_with_map:
init_len = T
print "Initializing with BFGS on first ", init_len, " time bins."
init_model = DiscreteTimeStandardHawkesModel(K=K, dt=dt, dt_max=dt_max, B=B,
alpha=1.0, beta=1.0)
init_model.add_data(S[:init_len, :])
init_model.initialize_to_background_rate()
init_model.fit_with_bfgs()
else:
init_model = None
###########################################################
# Create a test spike and slab model
###########################################################
# Copy the network hypers.
# Give the test model p, but not c, v, or m
network_hypers = true_model.network_hypers.copy()
network_hypers['c'] = None
network_hypers['v'] = None
network_hypers['m'] = None
test_network = StochasticBlockModel(K=K, **network_hypers)
test_model = DiscreteTimeNetworkHawkesModelSpikeAndSlab(K=K, dt=dt, dt_max=dt_max, B=B,
basis_hypers=true_model.basis_hypers,
bkgd_hypers=true_model.bkgd_hypers,
impulse_hypers=true_model.impulse_hypers,
weight_hypers=true_model.weight_hypers,
network=test_network)
test_model.add_data(S)
# F_test = test_model.basis.convolve_with_basis(S_test)
# Initialize with the standard model parameters
if init_model is not None:
test_model.initialize_with_standard_model(init_model)
# Initialize plots
ln, im_net, im_clus = initialize_plots(true_model, test_model, S)
###########################################################
# Fit the test model with Gibbs sampling
###########################################################
N_samples = 50
samples = []
lps = []
# plls = []
for itr in xrange(N_samples):
lps.append(test_model.log_probability())
# plls.append(test_model.heldout_log_likelihood(S_test, F=F_test))
samples.append(test_model.copy_sample())
print ""
print "Gibbs iteration ", itr
print "LP: ", lps[-1]
test_model.resample_model()
# Update plot
if itr % 1 == 0:
update_plots(itr, test_model, S, ln, im_clus, im_net)
###########################################################
# Analyze the samples
###########################################################
analyze_samples(true_model, init_model, samples, lps)
def test_gibbs_sbm(seed=None):
"""
Create a discrete time Hawkes model and generate from it.
:return:
"""
if seed is None:
seed = np.random.randint(2**32)
print("Setting seed to ", seed)
np.random.seed(seed)
C = 2
K = 100
c = np.arange(C).repeat(np.ceil(K/float(C)))[:K]
T = 1000
dt = 1.0
B = 3
# Generate from a true model
true_p = np.random.rand(C,C) * 0.25
true_network = StochasticBlockModel(K, C, c=c, p=true_p, v=10.0)
true_model = \
DiscreteTimeNetworkHawkesModelSpikeAndSlab(
K=K, dt=dt, B=B, network=true_network)
S,R = true_model.generate(T)
# Plot the true network
plt.ion()
true_im = true_model.plot_adjacency_matrix()
plt.pause(0.001)
# Make a new model for inference
test_network = StochasticBlockModel(K, C, beta=1./K)
test_model = \
DiscreteTimeNetworkHawkesModelSpikeAndSlab(
K=K, dt=dt, B=B, network=test_network)
test_model.add_data(S)
# Gibbs sample
N_samples = 100
c_samples = []
lps = []
for itr in progprint_xrange(N_samples):
c_samples.append(test_network.c.copy())
lps.append(test_model.log_probability())
# Resample the network only
test_model.network.resample((true_model.weight_model.A,
true_model.weight_model.W))
c_samples = np.array(c_samples)
plt.ioff()
# Compute sample statistics for second half of samples
print("True c: ", true_model.network.c)
print("Test c: ", c_samples[-10:, :])
# Compute the adjusted mutual info score of the clusterings
amis = []
arss = []
for c in c_samples:
amis.append(adjusted_mutual_info_score(true_model.network.c, c))
arss.append(adjusted_rand_score(true_model.network.c, c))
plt.figure()
plt.plot(np.arange(N_samples), amis, '-r')
plt.plot(np.arange(N_samples), arss, '-b')
plt.xlabel("Iteration")
plt.ylabel("Clustering score")
plt.show()
def test_gibbs_sbm(seed=None):
"""
Create a discrete time Hawkes model and generate from it.
:return:
"""
if seed is None:
seed = np.random.randint(2**32)
print("Setting seed to ", seed)
np.random.seed(seed)
C = 2
K = 100
c = np.arange(C).repeat(np.ceil(K / float(C)))[:K]
T = 1000
dt = 1.0
B = 3
# Generate from a true model
true_p = np.random.rand(C, C) * 0.25
true_network = StochasticBlockModel(K, C, c=c, p=true_p, v=10.0)
true_model = \
DiscreteTimeNetworkHawkesModelSpikeAndSlab(
K=K, dt=dt, B=B, network=true_network)
S, R = true_model.generate(T)
# Plot the true network
plt.ion()
true_im = true_model.plot_adjacency_matrix()
plt.pause(0.001)
# Make a new model for inference
test_network = StochasticBlockModel(K, C, beta=1. / K)
test_model = \
DiscreteTimeNetworkHawkesModelSpikeAndSlab(
K=K, dt=dt, B=B, network=test_network)
test_model.add_data(S)
# Gibbs sample
N_samples = 100
c_samples = []
lps = []
for itr in progprint_xrange(N_samples):
c_samples.append(test_network.c.copy())
lps.append(test_model.log_probability())
# Resample the network only
test_model.network.resample(
(true_model.weight_model.A, true_model.weight_model.W))
c_samples = np.array(c_samples)
plt.ioff()
# Compute sample statistics for second half of samples
print("True c: ", true_model.network.c)
print("Test c: ", c_samples[-10:, :])
# Compute the adjusted mutual info score of the clusterings
amis = []
arss = []
for c in c_samples:
amis.append(adjusted_mutual_info_score(true_model.network.c, c))
arss.append(adjusted_rand_score(true_model.network.c, c))
plt.figure()
plt.plot(np.arange(N_samples), amis, '-r')
plt.plot(np.arange(N_samples), arss, '-b')
plt.xlabel("Iteration")
plt.ylabel("Clustering score")
plt.show()
def demo(K=3, T=1000, dt_max=20, p=0.25):
"""
:param K: Number of nodes
:param T: Number of time bins to simulate
:param dt_max: Number of future time bins an event can influence
:param p: Sparsity of network
:return:
"""
###########################################################
# Generate synthetic data
###########################################################
network = ErdosRenyiFixedSparsity(K, p, v=1., allow_self_connections=False)
bkgd_hypers = {"alpha": 1.0, "beta": 20.0}
true_model = DiscreteTimeNetworkHawkesModelSpikeAndSlab(
K=K, dt_max=dt_max, bkgd_hypers=bkgd_hypers, network=network)
A_true = np.zeros((K,K))
A_true[0,1] = A_true[0,2] = 1
W_true = np.zeros((K,K))
W_true[0,1] = W_true[0,2] = 1.0
true_model.weight_model.A = A_true
true_model.weight_model.W = W_true
true_model.bias_model.lambda0[0] = 0.2
assert true_model.check_stability()
# Sample from the true model
S,R = true_model.generate(T=T, keep=True, print_interval=50)
plt.ion()
true_figure, _ = true_model.plot(color="#377eb8", T_slice=(0,100))
# Save the true figure
true_figure.savefig("gifs/true.gif")
###########################################################
# Create a test spike and slab model
###########################################################
test_model = DiscreteTimeNetworkHawkesModelSpikeAndSlab(
K=K, dt_max=dt_max, network=network)
test_model.add_data(S)
# Initialize plots
test_figure, test_handles = test_model.plot(color="#e41a1c", T_slice=(0,100))
test_figure.savefig("gifs/test0.gif")
###########################################################
# Fit the test model with Gibbs sampling
###########################################################
N_samples = 100
samples = []
lps = []
for itr in xrange(N_samples):
print "Gibbs iteration ", itr
test_model.resample_model()
lps.append(test_model.log_probability())
samples.append(test_model.copy_sample())
# Update plots
test_model.plot(handles=test_handles)
test_figure.savefig("gifs/test%d.gif" % (itr+1))
def main(args):
try:
os.system('mkdir {0}'.format(args.savedir))
except:
pass
#Get teh country
country = args.datafile.split('/')[-1].split('_')[0]
#Load the data
df = loaders.load_country_data(args.datafile, index_col=False)
#Stitch the data together on a real number range
date_ordinals = pd.DataFrame(pd.date_range('2001-01-01',
'2005-12-31').values,
columns=['date'])
#Convert each group to the date range
print('generate the groups to the dates')
gnames = []
date_grouped = df.groupby(['gname', 'date']).agg({
'eventid': 'count'
}).reset_index()
for group, groupdf in date_grouped.groupby('gname'):
gnames.append(group)
#Set the new columns
rgdf = groupdf.rename(columns={'eventid': group})
#merge it
date_ordinals = date_ordinals.merge(rgdf.loc[:, ['date', group]],
how='left')
#Now we have a merged date_ordinals, so write it out
date_ordinals.to_csv('../../data/%s_multihawkes_data.csv' % country)
#read it back in
date_ordinals = pd.read_csv('../../data/%s_multihawkes_data.csv' % country,
index_col=0)
date_ordinals.fillna(0, inplace=True)
#Set the index on 'date' since we don't care about it
date_ordinals.set_index('date', inplace=True)
date_ordinals = date_ordinals.applymap(int)
#Parameter setting
K = len(date_ordinals.columns)
dt_max = len(date_ordinals)
p = 0.25
network_hypers = {"p": p, "allow_self_connections": True}
#set-up the model
hawkes_model = DiscreteTimeNetworkHawkesModelSpikeAndSlab(
K=K, dt_max=dt_max, network_hypers=network_hypers)
hawkes_model.add_data(np.array(date_ordinals.values.tolist()))
#Set-up the runs
srfpass = False
loopcount = 0
#set-up the model
hawkes_models = {}
for ichain in range(args.num_chains):
hawkes_models[ichain] = DiscreteTimeNetworkHawkesModelSpikeAndSlab(
K=K, dt_max=dt_max, network_hypers=network_hypers)
hawkes_models[ichain].add_data(np.array(date_ordinals.values.tolist()))
#hold variables
parameter_trace = {
ichain: {g: []
for g in gnames}
for ichain in range(args.num_chains)
}
trace_stats = {
ichain: {g: {
'mean': 0,
'std': 0
}
for g in gnames}
for ichain in range(args.num_chains)
}
while srfpass == False:
#resample all chains
for ichain in range(args.num_chains):
hawkes_models[ichain].resample_model()
#Record the parameters
for i, group in enumerate(gnames):
parameter_trace[ichain][group].append(hawkes_model.lambda0[i])
#Calculate the stats
trace_stats[ichain][group]['mean'] = np.mean(
parameter_trace[ichain][group][args.burn::args.thin])
trace_stats[ichain][group]['std'] = np.std(
parameter_trace[ichain][group][args.burn::args.thin])
#increment
print(loopcount)
loopcount += 1
#Start checking
if loopcount > 1000 and loopcount % args.thin == 0:
#Calculate out the parts
B = calcB(trace_stats, gnames, args.num_chains)
W = calcW(trace_stats, gnames, args.num_chains)
VarSig = calcVar(W, B, args.num_chains)
R = calcR(VarSig, W)
#SRF pass check
srf_pass_set = []
for param, srf_val in R.items():
if abs(srf_val - 1.0) < args.tol:
srf_pass_set.append(1)
if np.mean(srf_pass_set) == 1:
srfpass = True
#Write out the SRFs
with open('%s/%s_srf.csv' % (args.savedir, country), 'w') as wfile:
print('group,B,W,V,R', file=wfile)
for gname in B.keys():
print('%s,%f,%f,%f,%f' %
(gname, B[gname], W[gname], VarSig[gname], R[gname]),
file=wfile)
#Pull the data
dataset = {}
header = ['gname', 'A', 'B', 'W_effective', 'lambda0']
for i, group in enumerate(gnames):
dataset[group] = {
'B': float(hawkes_model.B),
'W': hawkes_model.W_effective[i].tolist(),
'lambda': float(hawkes_model.lambda0[i])
}
json.dump(dataset,
open('%s/%s_multihawkes.json' % (args.savedir, country), 'w'),
indent=4)
