def compute_bootstrap(self):
print "Computing bootstrap..."
self.dataset['bootstrap_nitems_pval'] = np.nan*np.empty(self.dataset['n_items_size'])
self.dataset['bootstrap_nitems'] = np.empty(self.dataset['n_items_size'], dtype=np.object)
self.dataset['bootstrap_subject_nitems'] = np.empty((self.dataset['subject_size'], self.dataset['n_items_size']), dtype=np.object)
self.dataset['bootstrap_subject_nitems_pval'] = np.nan*np.empty((self.dataset['subject_size'], self.dataset['n_items_size']))
for n_items_i, n_items in enumerate(np.unique(self.dataset['n_items'])):
if n_items > 1:
for subject_i, subject in enumerate(np.unique(self.dataset['subject'])):
print "Nitems %d, subject %d" % (n_items, subject)
# Bootstrap per subject and nitems
ids_filtered = (self.dataset['subject']==subject).flatten() & (self.dataset['n_items'] == n_items).flatten()
# Compute bootstrap if required
bootstrap = em_circularmixture_allitems_uniquekappa.bootstrap_nontarget_stat(self.dataset['response'][ids_filtered, 0], self.dataset['item_angle'][ids_filtered, 0], self.dataset['item_angle'][ids_filtered, 1:n_items], nb_bootstrap_samples=nb_bootstrap_samples)
self.dataset['bootstrap_subject_nitems'][subject_i, n_items_i] = bootstrap
self.dataset['bootstrap_subject_nitems_pval'][subject_i, n_items_i] = bootstrap['p_value']
print self.dataset['bootstrap_subject_nitems_pval'][:, n_items_i]
print "Nitems %d, all subjects" % (n_items)
# Data collapsed accross subjects
ids_filtered = (self.dataset['n_items'] == n_items).flatten()
bootstrap = em_circularmixture_allitems_uniquekappa.bootstrap_nontarget_stat(self.dataset['response'][ids_filtered, 0], self.dataset['item_angle'][ids_filtered, 0], self.dataset['item_angle'][ids_filtered, 1:n_items], nb_bootstrap_samples=nb_bootstrap_samples)
self.dataset['bootstrap_nitems'][n_items_i] = bootstrap
self.dataset['bootstrap_nitems_pval'][n_items_i] = bootstrap['p_value']
print self.dataset['bootstrap_nitems_pval']
def launcher_do_nontarget_bootstrap(args):
'''
Compute a bootstrap estimate, using outputs from the model run earlier
'''
print "Doing a piece of work for launcher_do_nontarget_bootstrap"
try:
# Convert Argparse.Namespace to dict
all_parameters = vars(args)
except TypeError:
# Assume it's already done
assert type(args) is dict, "args is neither Namespace nor dict, WHY?"
all_parameters = args
print all_parameters
# Create DataIO
# (complete label with current variable state)
dataio = DataIO.DataIO(output_folder=all_parameters['output_directory'], label=all_parameters['label'].format(**all_parameters))
save_every = 1
run_counter = 0
# Load the data
if all_parameters['subaction'] == 'mixed':
# Mixed runs
model_outputs = utils.load_npy( os.path.join(os.getenv("WORKDIR_DROP", None), 'Experiments', 'bootstrap_nontargets', 'global_plots_errors_distribution-plots_errors_distribution-d977e237-cfce-473b-a292-00695e725259.npy'))
else:
# Conjunctive runs
model_outputs = utils.load_npy( os.path.join(os.getenv("WORKDIR_DROP", None), 'Experiments', 'bootstrap_nontargets', 'global_plots_errors_distribution-plots_errors_distribution-cc1a49b0-f5f0-4e82-9f0f-5a16a2bfd4e8.npy'))
data_responses_all = model_outputs['result_responses_all'][..., 0]
data_target_all = model_outputs['result_target_all'][..., 0]
data_nontargets_all = model_outputs['result_nontargets_all'][..., 0]
T_space = model_outputs['T_space']
sigmax_space = model_outputs['sigmax_space']
K = data_nontargets_all.shape[-1]
# Result arrays
result_bootstrap_samples_allitems = np.nan*np.ones((sigmax_space.size, T_space.size, all_parameters['num_repetitions']))
result_bootstrap_samples = np.nan*np.ones((sigmax_space.size, T_space.size, all_parameters['num_repetitions']))
result_bootstrap_samples_allitems_uniquekappa_sumnontarget = np.nan*np.ones((sigmax_space.size, T_space.size, all_parameters['num_repetitions']))
result_bootstrap_samples_allitems_uniquekappa_allnontarget = np.nan*np.ones((sigmax_space.size, T_space.size, K*all_parameters['num_repetitions']))
search_progress = progress.Progress(sigmax_space.size*(T_space.size-1))
for sigmax_i, sigmax in enumerate(sigmax_space):
for T_i, T in enumerate(T_space[1:]):
T_i += 1
print "%.2f%%, %s left - %s" % (search_progress.percentage(), search_progress.time_remaining_str(), search_progress.eta_str())
print "Bootstrap for T=%d, sigmax=%.2f, %d bootstrap samples" % (T, sigmax, all_parameters['num_repetitions'])
# Update parameter
### WORK WORK WORK work? ###
# Get some bootstrap samples
bootstrap_allitems_nontargets_allitems_uniquekappa = em_circularmixture_allitems_uniquekappa.bootstrap_nontarget_stat(
data_responses_all[sigmax_i, T_i],
data_target_all[sigmax_i, T_i],
data_nontargets_all[sigmax_i, T_i, :, :T_i],
nb_bootstrap_samples=all_parameters['num_repetitions'],
resample_targets=False)
# bootstrap_allitems_nontargets_allitems = em_circularmixture_allitems.bootstrap_nontarget_stat(
# data_responses_all[sigmax_i, T_i],
# data_target_all[sigmax_i, T_i],
# data_nontargets_all[sigmax_i, T_i, :, :T_i],
# nb_bootstrap_samples=all_parameters['num_repetitions'],
# resample_targets=False)
bootstrap_allitems_nontargets = em_circularmixture.bootstrap_nontarget_stat(
data_responses_all[sigmax_i, T_i],
data_target_all[sigmax_i, T_i],
data_nontargets_all[sigmax_i, T_i, :, :T_i],
nb_bootstrap_samples=all_parameters['num_repetitions'],
resample_targets=False)
# Collect and store responses
# result_bootstrap_samples_allitems[sigmax_i, T_i] = bootstrap_allitems_nontargets_allitems['nontarget_bootstrap_samples']
result_bootstrap_samples[sigmax_i, T_i] = bootstrap_allitems_nontargets['nontarget_bootstrap_samples']
result_bootstrap_samples_allitems_uniquekappa_sumnontarget[sigmax_i, T_i] = bootstrap_allitems_nontargets_allitems_uniquekappa['nontarget_bootstrap_samples']
result_bootstrap_samples_allitems_uniquekappa_allnontarget[sigmax_i, T_i, :all_parameters['num_repetitions']*T_i] = bootstrap_allitems_nontargets_allitems_uniquekappa['allnontarget_bootstrap_samples']
print result_bootstrap_samples_allitems[sigmax_i, T_i]
print result_bootstrap_samples[sigmax_i, T_i]
print result_bootstrap_samples_allitems_uniquekappa_sumnontarget[sigmax_i, T_i]
print result_bootstrap_samples_allitems_uniquekappa_allnontarget[sigmax_i, T_i]
### /Work ###
search_progress.increment()
if run_counter % save_every == 0 or search_progress.done():
dataio.save_variables_default(locals())
run_counter += 1
# Finished
dataio.save_variables_default(locals())
print "All finished"
return locals()
def launcher_do_bootstrap_experimental(args):
'''
Compute a bootstrap estimate, using outputs from the experimental data
'''
print "Doing a piece of work for launcher_do_bootstrap_experimental"
try:
# Convert Argparse.Namespace to dict
all_parameters = vars(args)
except TypeError:
# Assume it's already done
assert type(args) is dict, "args is neither Namespace nor dict, WHY?"
all_parameters = args
print all_parameters
# Create DataIO
# (complete label with current variable state)
dataio = DataIO.DataIO(output_folder=all_parameters['output_directory'], label=all_parameters['label'].format(**all_parameters))
save_every = 1
run_counter = 0
# Load the data
if all_parameters['subaction'] == 'bays09' or all_parameters['subaction'] == '':
# Bays2009 dataset
dataset = load_experimental_data.load_data_bays09(fit_mixture_model=True)
# Result arrays
result_bootstrap_nitems_samples = np.nan*np.empty((dataset['n_items_size'], all_parameters['num_repetitions']))
result_bootstrap_subject_nitems_samples = np.nan*np.empty((dataset['subject_size'], dataset['n_items_size'], all_parameters['num_repetitions']))
search_progress = progress.Progress(dataset['subject_size']*(dataset['n_items_size']-1))
for n_items_i, n_items in enumerate(np.unique(dataset['n_items'])):
if n_items > 1:
print "Nitems %d, all subjects" % (n_items)
# Data collapsed accross subjects
ids_filtered = (dataset['n_items'] == n_items).flatten()
bootstrap = em_circularmixture_allitems_uniquekappa.bootstrap_nontarget_stat(
dataset['response'][ids_filtered, 0],
dataset['item_angle'][ids_filtered, 0],
dataset['item_angle'][ids_filtered, 1:n_items],
nb_bootstrap_samples=all_parameters['num_repetitions'],
resample_targets=False
)
result_bootstrap_nitems_samples[n_items_i] = bootstrap['nontarget_bootstrap_samples']
print result_bootstrap_nitems_samples
for subject_i, subject in enumerate(np.unique(dataset['subject'])):
print "Nitems %d, subject %d" % (n_items, subject)
# Bootstrap per subject and nitems
ids_filtered = (dataset['subject']==subject).flatten() & (dataset['n_items'] == n_items).flatten()
# Compute bootstrap if required
bootstrap = em_circularmixture_allitems_uniquekappa.bootstrap_nontarget_stat(
dataset['response'][ids_filtered, 0],
dataset['item_angle'][ids_filtered, 0],
dataset['item_angle'][ids_filtered, 1:n_items],
nb_bootstrap_samples=all_parameters['num_repetitions'],
resample_targets=False)
result_bootstrap_subject_nitems_samples[subject_i, n_items_i] = bootstrap['nontarget_bootstrap_samples']
print result_bootstrap_subject_nitems_samples[:, n_items_i]
search_progress.increment()
if run_counter % save_every == 0 or search_progress.done():
dataio.save_variables_default(locals())
run_counter += 1
# Finished
dataio.save_variables_default(locals())
print "All finished"
return locals()
def launcher_do_nontarget_bootstrap_misbindingruns(args):
'''
Compute a bootstrap estimate, using outputs from a Misbinding generator run.
'''
print "Doing a piece of work for launcher_do_nontarget_bootstrap"
try:
# Convert Argparse.Namespace to dict
all_parameters = vars(args)
except TypeError:
# Assume it's already done
assert type(args) is dict, "args is neither Namespace nor dict, WHY?"
all_parameters = args
print all_parameters
# Create DataIO
# (complete label with current variable state)
dataio = DataIO.DataIO(output_folder=all_parameters['output_directory'], label=all_parameters['label'].format(**all_parameters))
save_every = 1
run_counter = 0
# Load the data
if all_parameters['subaction'] == 'mixed' or all_parameters['subaction'] == '':
# Mixed runs
model_outputs = utils.load_npy( os.path.join(os.getenv("WORKDIR_DROP", None), 'Experiments', 'bootstrap_nontargets', 'SAVE_global_plots_misbinding_logposterior-plots_misbinding_logposterior-36eb41e9-6370-453e-995e-3876d5105388.npy'))
data_responses_all = model_outputs['result_all_thetas']
data_target = model_outputs['target_angle']
data_nontargets = model_outputs['nontarget_angles']
ratio_space = model_outputs['ratio_space']
# Result arrays
result_bootstrap_samples_allitems = np.nan*np.ones((ratio_space.size, all_parameters['num_repetitions']))
result_bootstrap_samples = np.nan*np.ones((ratio_space.size, all_parameters['num_repetitions']))
result_bootstrap_samples_allitems_uniquekappa_sumnontarget = np.nan*np.ones((ratio_space.size, all_parameters['num_repetitions']))
result_bootstrap_samples_allitems_uniquekappa_allnontarget = np.nan*np.ones((ratio_space.size, all_parameters['num_repetitions']))
search_progress = progress.Progress(ratio_space.size)
for ratio_conj_i, ratio_conj in enumerate(ratio_space):
print "%.2f%%, %s left - %s" % (search_progress.percentage(), search_progress.time_remaining_str(), search_progress.eta_str())
print "Bootstrap for ratio=%.2f, %d bootstrap samples" % (ratio_conj, all_parameters['num_repetitions'])
### WORK WORK WORK work? ###
# Get some bootstrap samples
bootstrap_allitems_nontargets_allitems_uniquekappa = em_circularmixture_allitems_uniquekappa.bootstrap_nontarget_stat(
data_responses_all[ratio_conj_i],
data_target,
data_nontargets,
nb_bootstrap_samples=all_parameters['num_repetitions'],
resample_targets=False)
bootstrap_allitems_nontargets = em_circularmixture.bootstrap_nontarget_stat(
data_responses_all[ratio_conj_i],
data_target,
data_nontargets,
nb_bootstrap_samples=all_parameters['num_repetitions'],
resample_targets=False)
# Collect and store responses
result_bootstrap_samples[ratio_conj_i] = bootstrap_allitems_nontargets['nontarget_bootstrap_samples']
result_bootstrap_samples_allitems_uniquekappa_sumnontarget[ratio_conj_i] = bootstrap_allitems_nontargets_allitems_uniquekappa['nontarget_bootstrap_samples']
result_bootstrap_samples_allitems_uniquekappa_allnontarget[ratio_conj_i] = bootstrap_allitems_nontargets_allitems_uniquekappa['allnontarget_bootstrap_samples']
print result_bootstrap_samples_allitems[ratio_conj_i]
print result_bootstrap_samples[ratio_conj_i]
print result_bootstrap_samples_allitems_uniquekappa_sumnontarget[ratio_conj_i]
print result_bootstrap_samples_allitems_uniquekappa_allnontarget[ratio_conj_i]
### /Work ###
search_progress.increment()
if run_counter % save_every == 0 or search_progress.done():
dataio.save_variables_default(locals())
run_counter += 1
# Finished
dataio.save_variables_default(locals())
print "All finished"
return locals()
def plots_boostrap(data_pbs, generator_module=None):
'''
Reload bootstrap samples, plot its histogram, fit empirical CDF and save it for quicker later use.
'''
#### SETUP
#
savefigs = True
savedata = True
load_fit_bootstrap = True
plots_hist_cdf = True
estimate_bootstrap = True
should_fit_bootstrap = True
# caching_bootstrap_filename = None
caching_bootstrap_filename = os.path.join(generator_module.pbs_submission_infos['simul_out_dir'], 'outputs', 'cache_bootstrap.pickle')
plt.rcParams['font.size'] = 16
#
#### /SETUP
print "Order parameters: ", generator_module.dict_parameters_range.keys()
result_bootstrap_samples_allitems_uniquekappa_sumnontarget = np.squeeze(data_pbs.dict_arrays['result_bootstrap_samples_allitems_uniquekappa_sumnontarget']['results'])
result_bootstrap_samples = np.squeeze(data_pbs.dict_arrays['result_bootstrap_samples']['results'])
result_bootstrap_samples_allitems_uniquekappa_allnontarget = np.squeeze(data_pbs.dict_arrays['result_bootstrap_samples_allitems_uniquekappa_allnontarget']['results'])
sigmax_space = data_pbs.loaded_data['datasets_list'][0]['sigmax_space']
T_space = data_pbs.loaded_data['datasets_list'][0]['T_space']
print result_bootstrap_samples_allitems_uniquekappa_sumnontarget.shape
print result_bootstrap_samples.shape
print result_bootstrap_samples_allitems_uniquekappa_allnontarget.shape
dataio = DataIO(output_folder=generator_module.pbs_submission_infos['simul_out_dir'] + '/outputs/', label='global_' + dataset_infos['save_output_filename'])
if load_fit_bootstrap:
if caching_bootstrap_filename is not None:
if os.path.exists(caching_bootstrap_filename):
# Got file, open it and try to use its contents
try:
with open(caching_bootstrap_filename, 'r') as file_in:
# Load and assign values
cached_data = pickle.load(file_in)
bootstrap_ecdf_bays_sigmax_T = cached_data['bootstrap_ecdf_bays_sigmax_T']
bootstrap_ecdf_allitems_sum_sigmax_T = cached_data['bootstrap_ecdf_allitems_sum_sigmax_T']
bootstrap_ecdf_allitems_all_sigmax_T = cached_data['bootstrap_ecdf_allitems_all_sigmax_T']
should_fit_bootstrap = False
except IOError:
print "Error while loading ", caching_bootstrap_filename, "falling back to computing the EM fits"
if should_fit_bootstrap:
bootstrap_ecdf_bays_sigmax_T = dict()
bootstrap_ecdf_allitems_sum_sigmax_T = dict()
bootstrap_ecdf_allitems_all_sigmax_T = dict()
# Fit bootstrap
for sigmax_i, sigmax in enumerate(sigmax_space):
for T_i, T in enumerate(T_space):
if T>1:
# One bootstrap CDF per condition
bootstrap_ecdf_bays = stmodsdist.empirical_distribution.ECDF(utils.dropnan(result_bootstrap_samples[sigmax_i, T_i]))
bootstrap_ecdf_allitems_sum = stmodsdist.empirical_distribution.ECDF(utils.dropnan(result_bootstrap_samples_allitems_uniquekappa_sumnontarget[sigmax_i, T_i]))
bootstrap_ecdf_allitems_all = stmodsdist.empirical_distribution.ECDF(utils.dropnan(result_bootstrap_samples_allitems_uniquekappa_allnontarget[sigmax_i, T_i]))
# Store in a dict(sigmax) -> dict(T) -> ECDF object
bootstrap_ecdf_bays_sigmax_T.setdefault(sigmax_i, dict())[T_i] = dict(ecdf=bootstrap_ecdf_bays, T=T, sigmax=sigmax)
bootstrap_ecdf_allitems_sum_sigmax_T.setdefault(sigmax_i, dict())[T_i] = dict(ecdf=bootstrap_ecdf_allitems_sum, T=T, sigmax=sigmax)
bootstrap_ecdf_allitems_all_sigmax_T.setdefault(sigmax_i, dict())[T_i] = dict(ecdf=bootstrap_ecdf_allitems_all, T=T, sigmax=sigmax)
# Save everything to a file, for faster later plotting
if caching_bootstrap_filename is not None:
try:
with open(caching_bootstrap_filename, 'w') as filecache_out:
data_bootstrap = dict(bootstrap_ecdf_allitems_sum_sigmax_T=bootstrap_ecdf_allitems_sum_sigmax_T, bootstrap_ecdf_allitems_all_sigmax_T=bootstrap_ecdf_allitems_all_sigmax_T, bootstrap_ecdf_bays_sigmax_T=bootstrap_ecdf_bays_sigmax_T)
pickle.dump(data_bootstrap, filecache_out, protocol=2)
except IOError:
print "Error writing out to caching file ", caching_bootstrap_filename
if plots_hist_cdf:
## Plots now
for sigmax_i, sigmax in enumerate(sigmax_space):
for T_i, T in enumerate(T_space):
if T > 1:
# Histogram of samples
_, axes = plt.subplots(ncols=3, figsize=(18, 6))
axes[0].hist(utils.dropnan(result_bootstrap_samples[sigmax_i, T_i]), bins=100, normed='density')
axes[0].set_xlim([0.0, 1.0])
axes[1].hist(utils.dropnan(result_bootstrap_samples_allitems_uniquekappa_sumnontarget[sigmax_i, T_i]), bins=100, normed='density')
axes[1].set_xlim([0.0, 1.0])
axes[2].hist(utils.dropnan(result_bootstrap_samples_allitems_uniquekappa_allnontarget[sigmax_i, T_i]), bins=100, normed='density')
axes[2].set_xlim([0.0, 1.0])
if savefigs:
dataio.save_current_figure('hist_bootstrap_sigmax%.2f_T%d_{label}_{unique_id}.pdf' % (sigmax, T))
# ECDF now
_, axes = plt.subplots(ncols=3, sharey=True, figsize=(18, 6))
axes[0].plot(bootstrap_ecdf_bays_sigmax_T[sigmax_i][T_i]['ecdf'].x, bootstrap_ecdf_bays_sigmax_T[sigmax_i][T_i]['ecdf'].y, linewidth=2)
axes[0].set_xlim([0.0, 1.0])
axes[1].plot(bootstrap_ecdf_allitems_sum_sigmax_T[sigmax_i][T_i]['ecdf'].x, bootstrap_ecdf_allitems_sum_sigmax_T[sigmax_i][T_i]['ecdf'].y, linewidth=2)
axes[1].set_xlim([0.0, 1.0])
axes[2].plot(bootstrap_ecdf_allitems_all_sigmax_T[sigmax_i][T_i]['ecdf'].x, bootstrap_ecdf_allitems_all_sigmax_T[sigmax_i][T_i]['ecdf'].y, linewidth=2)
axes[2].set_xlim([0.0, 1.0])
if savefigs:
dataio.save_current_figure('ecdf_bootstrap_sigmax%.2f_T%d_{label}_{unique_id}.pdf' % (sigmax, T))
if estimate_bootstrap:
## Should be in reloader_error_distribution_mixed_121113 instead
model_outputs = utils.load_npy( os.path.join(os.getenv("WORKDIR_DROP", None), 'Experiments', 'bootstrap_nontargets', 'global_plots_errors_distribution-plots_errors_distribution-d977e237-cfce-473b-a292-00695e725259.npy'))
data_responses_all = model_outputs['result_responses_all'][..., 0]
data_target_all = model_outputs['result_target_all'][..., 0]
data_nontargets_all = model_outputs['result_nontargets_all'][..., 0]
# Compute bootstrap p-value
result_pvalue_bootstrap_sum = np.empty((sigmax_space.size, T_space.size-1))*np.nan
result_pvalue_bootstrap_all = np.empty((sigmax_space.size, T_space.size-1, T_space.size-1))*np.nan
for sigmax_i, sigmax in enumerate(sigmax_space):
for T in T_space[1:]:
bootstrap_allitems_nontargets_allitems_uniquekappa = em_circularmixture_allitems_uniquekappa.bootstrap_nontarget_stat(data_responses_all[sigmax_i, (T-1)], data_target_all[sigmax_i, (T-1)], data_nontargets_all[sigmax_i, (T-1), :, :(T-1)], sumnontargets_bootstrap_ecdf=bootstrap_ecdf_allitems_sum_sigmax_T[sigmax_i][T-1]['ecdf'], allnontargets_bootstrap_ecdf=bootstrap_ecdf_allitems_all_sigmax_T[sigmax_i][T-1]['ecdf'])
result_pvalue_bootstrap_sum[sigmax_i, T-2] = bootstrap_allitems_nontargets_allitems_uniquekappa['p_value']
result_pvalue_bootstrap_all[sigmax_i, T-2, :(T-1)] = bootstrap_allitems_nontargets_allitems_uniquekappa['allnontarget_p_value']
print sigmax, T, result_pvalue_bootstrap_sum[sigmax_i, T-2], result_pvalue_bootstrap_all[sigmax_i, T-2, :(T-1)], np.sum(result_pvalue_bootstrap_all[sigmax_i, T-2, :(T-1)] < 0.05)
all_args = data_pbs.loaded_data['args_list']
variables_to_save = ['nb_repetitions']
if savedata:
dataio.save_variables_default(locals(), variables_to_save)
dataio.make_link_output_to_dropbox(dropbox_current_experiment_folder='bootstrap_nontargets')
plt.show()
return locals()
def plots_boostrap(data_pbs, generator_module=None):
'''
Reload bootstrap samples, plot its histogram, fit empirical CDF and save it for quicker later use.
'''
#### SETUP
#
savefigs = True
savedata = True
load_fit_bootstrap = True
plots_hist_cdf = True
estimate_bootstrap = True
should_fit_bootstrap = True
# caching_bootstrap_filename = None
caching_bootstrap_filename = os.path.join(generator_module.pbs_submission_infos['simul_out_dir'], 'outputs', 'cache_bootstrap_bays09.pickle')
plt.rcParams['font.size'] = 16
#
#### /SETUP
print "Order parameters: ", generator_module.dict_parameters_range.keys()
result_bootstrap_nitems_samples = np.squeeze(data_pbs.dict_arrays['result_bootstrap_nitems_samples']['results'])
result_bootstrap_subject_nitems_samples = np.squeeze(data_pbs.dict_arrays['result_bootstrap_subject_nitems_samples']['results'])
dataio = DataIO(output_folder=generator_module.pbs_submission_infos['simul_out_dir'] + '/outputs/', label='global_' + dataset_infos['save_output_filename'])
dataset = load_experimental_data.load_data_bays09(fit_mixture_model=True)
if load_fit_bootstrap:
if caching_bootstrap_filename is not None:
if os.path.exists(caching_bootstrap_filename):
# Got file, open it and try to use its contents
try:
with open(caching_bootstrap_filename, 'r') as file_in:
# Load and assign values
cached_data = pickle.load(file_in)
bootstrap_nitems_samples = cached_data['bootstrap_nitems_samples']
bootstrap_subject_nitems_samples = cached_data['bootstrap_subject_nitems_samples']
should_fit_bootstrap = False
except IOError:
print "Error while loading ", caching_bootstrap_filename, "falling back to computing the EM fits"
if should_fit_bootstrap:
bootstrap_nitems_samples = dict()
bootstrap_subject_nitems_samples = dict()
# Fit ECDF
for n_items_i, n_items in enumerate(np.unique(dataset['n_items'])):
if n_items > 1:
print "Nitems %d, all subjects" % (n_items)
current_ecdf_allitems = stmodsdist.empirical_distribution.ECDF(utils.dropnan(result_bootstrap_nitems_samples[n_items_i]))
# Store in a dict(n_items_i) -> {ECDF object, n_items}
bootstrap_nitems_samples[n_items_i] = dict(ecdf=current_ecdf_allitems, n_items=n_items)
for subject_i, subject in enumerate(np.unique(dataset['subject'])):
print "Nitems %d, subject %d" % (n_items, subject)
current_ecdf_subj_items = stmodsdist.empirical_distribution.ECDF(utils.dropnan(result_bootstrap_subject_nitems_samples[subject_i, n_items_i]))
if n_items_i not in bootstrap_subject_nitems_samples:
bootstrap_subject_nitems_samples[n_items_i] = dict()
bootstrap_subject_nitems_samples[n_items_i][subject_i] = dict(ecdf=current_ecdf_subj_items, n_items=n_items, subject=subject)
# Save everything to a file, for faster later plotting
if caching_bootstrap_filename is not None:
try:
with open(caching_bootstrap_filename, 'w') as filecache_out:
data_bootstrap = dict(bootstrap_nitems_samples=bootstrap_nitems_samples, bootstrap_subject_nitems_samples=bootstrap_subject_nitems_samples)
pickle.dump(data_bootstrap, filecache_out, protocol=2)
except IOError:
print "Error writing out to caching file ", caching_bootstrap_filename
if plots_hist_cdf:
## Plots now
for n_items_i, n_items in enumerate(np.unique(dataset['n_items'])):
if n_items > 1:
for subject_i, subject in enumerate(np.unique(dataset['subject'])):
# Histogram of samples, for subject/nitems
_, axes = plt.subplots(ncols=2, figsize=(12, 6))
axes[0].hist(utils.dropnan(result_bootstrap_subject_nitems_samples[subject_i, n_items_i]), bins=100, normed='density')
axes[0].set_xlim([0.0, 1.0])
# ECDF now
axes[1].plot(bootstrap_subject_nitems_samples[n_items_i][subject_i]['ecdf'].x, bootstrap_subject_nitems_samples[n_items_i][subject_i]['ecdf'].y, linewidth=2)
axes[1].set_xlim([0.0, 1.0])
if savefigs:
dataio.save_current_figure('histecdf_bootstrap_nitems%d_subject%d_{label}_{unique_id}.pdf' % (n_items, subject))
# Same for collapsed data accross subjects
# Histogram of samples, for subject/nitems
_, axes = plt.subplots(ncols=2, figsize=(12, 6))
axes[0].hist(utils.dropnan(result_bootstrap_nitems_samples[n_items_i]), bins=100, normed='density')
axes[0].set_xlim([0.0, 1.0])
# ECDF now
axes[1].plot(bootstrap_nitems_samples[n_items_i]['ecdf'].x, bootstrap_nitems_samples[n_items_i]['ecdf'].y, linewidth=2)
axes[1].set_xlim([0.0, 1.0])
if savefigs:
dataio.save_current_figure('histecdf_bootstrap_nitems%d_{label}_{unique_id}.pdf' % (n_items))
if estimate_bootstrap:
# Compute bootstrap p-value
result_pvalue_bootstrap_nitems = np.empty(dataset['n_items_size'])*np.nan
result_pvalue_bootstrap_subject_nitems_samples = np.empty((dataset['n_items_size'], dataset['subject_size']))*np.nan
for n_items_i, n_items in enumerate(np.unique(dataset['n_items'])):
if n_items > 1:
print "Nitems %d, all subjects" % (n_items)
# Data collapsed accross subjects
ids_filtered = (dataset['n_items'] == n_items).flatten()
bootstrap = em_circularmixture_allitems_uniquekappa.bootstrap_nontarget_stat(
dataset['response'][ids_filtered, 0],
dataset['item_angle'][ids_filtered, 0],
dataset['item_angle'][ids_filtered, 1:n_items],
sumnontargets_bootstrap_ecdf=bootstrap_nitems_samples[n_items_i]['ecdf']
)
result_pvalue_bootstrap_nitems[n_items_i] = bootstrap['p_value']
print "p_val:", result_pvalue_bootstrap_nitems
for subject_i, subject in enumerate(np.unique(dataset['subject'])):
print "Nitems %d, subject %d" % (n_items, subject)
# Bootstrap per subject and nitems
ids_filtered = (dataset['subject']==subject).flatten() & (dataset['n_items'] == n_items).flatten()
# Get pvalue
bootstrap = em_circularmixture_allitems_uniquekappa.bootstrap_nontarget_stat(
dataset['response'][ids_filtered, 0],
dataset['item_angle'][ids_filtered, 0],
dataset['item_angle'][ids_filtered, 1:n_items],
sumnontargets_bootstrap_ecdf=bootstrap_subject_nitems_samples[n_items_i][subject_i]['ecdf'])
result_pvalue_bootstrap_subject_nitems_samples[n_items_i, subject_i] = bootstrap['p_value']
print "p_val:", result_pvalue_bootstrap_subject_nitems_samples[n_items_i, subject_i]
signif_level = 0.05
result_signif_nitems = result_pvalue_bootstrap_nitems < signif_level
result_num_signif_subject_nitems = np.sum(result_pvalue_bootstrap_subject_nitems_samples < signif_level, axis=1)
print "Summary:"
print "Collapsed subjects:",result_signif_nitems
print "Per subjects (%d total): %s" % (dataset['subject_size'], result_num_signif_subject_nitems)
all_args = data_pbs.loaded_data['args_list']
variables_to_save = ['nb_repetitions', 'signif_level']
if savedata:
dataio.save_variables_default(locals(), variables_to_save)
dataio.make_link_output_to_dropbox(dropbox_current_experiment_folder='bootstrap_nontargets')
plt.show()
return locals()
def plots_errors_distribution(data_pbs, generator_module=None):
'''
Reload responses
Plot errors distributions.
'''
#### SETUP
#
savefigs = True
savedata = True
plot_persigmax = True
do_best_nontarget = False
load_test_bootstrap = True
caching_bootstrap_filename = os.path.join(generator_module.pbs_submission_infos['simul_out_dir'], 'outputs', 'cache_bootstrap_errordistrib_mixed_sigmaxT.pickle')
colormap = None # or 'cubehelix'
plt.rcParams['font.size'] = 16
angle_space = np.linspace(-np.pi, np.pi, 51)
#
#### /SETUP
print "Order parameters: ", generator_module.dict_parameters_range.keys()
result_responses_all = data_pbs.dict_arrays['result_responses']['results']
result_target_all = data_pbs.dict_arrays['result_target']['results']
result_nontargets_all = data_pbs.dict_arrays['result_nontargets']['results']
result_em_fits_all = data_pbs.dict_arrays['result_em_fits']['results']
T_space = data_pbs.loaded_data['parameters_uniques']['T']
sigmax_space = data_pbs.loaded_data['parameters_uniques']['sigmax']
nb_repetitions = result_responses_all.shape[-1]
N = result_responses_all.shape[-2]
result_pval_vtest_nontargets = np.empty((sigmax_space.size, T_space.size))*np.nan
result_pvalue_bootstrap_sum = np.empty((sigmax_space.size, T_space.size-1))*np.nan
result_pvalue_bootstrap_all = np.empty((sigmax_space.size, T_space.size-1, T_space.size-1))*np.nan
print sigmax_space
print T_space
print result_responses_all.shape, result_target_all.shape, result_nontargets_all.shape, result_em_fits_all.shape
dataio = DataIO.DataIO(output_folder=generator_module.pbs_submission_infos['simul_out_dir'] + '/outputs/', label='global_' + dataset_infos['save_output_filename'])
if load_test_bootstrap:
if caching_bootstrap_filename is not None:
if os.path.exists(caching_bootstrap_filename):
# Got file, open it and try to use its contents
try:
with open(caching_bootstrap_filename, 'r') as file_in:
# Load and assign values
cached_data = pickle.load(file_in)
bootstrap_ecdf_bays_sigmax_T = cached_data['bootstrap_ecdf_bays_sigmax_T']
bootstrap_ecdf_allitems_sum_sigmax_T = cached_data['bootstrap_ecdf_allitems_sum_sigmax_T']
bootstrap_ecdf_allitems_all_sigmax_T = cached_data['bootstrap_ecdf_allitems_all_sigmax_T']
except IOError:
print "Error while loading ", caching_bootstrap_filename, "falling back to computing the EM fits"
load_test_bootstrap = False
if load_test_bootstrap:
# Now compute the pvalue for each sigmax/T
# only use 1000 samples
data_responses_all = result_responses_all[..., 0]
data_target_all = result_target_all[..., 0]
data_nontargets_all = result_nontargets_all[..., 0]
# Compute bootstrap p-value
for sigmax_i, sigmax in enumerate(sigmax_space):
for T in T_space[1:]:
bootstrap_allitems_nontargets_allitems_uniquekappa = em_circularmixture_allitems_uniquekappa.bootstrap_nontarget_stat(data_responses_all[sigmax_i, (T-1)], data_target_all[sigmax_i, (T-1)], data_nontargets_all[sigmax_i, (T-1), :, :(T-1)], sumnontargets_bootstrap_ecdf=bootstrap_ecdf_allitems_sum_sigmax_T[sigmax_i][T-1]['ecdf'], allnontargets_bootstrap_ecdf=bootstrap_ecdf_allitems_all_sigmax_T[sigmax_i][T-1]['ecdf'])
result_pvalue_bootstrap_sum[sigmax_i, T-2] = bootstrap_allitems_nontargets_allitems_uniquekappa['p_value']
result_pvalue_bootstrap_all[sigmax_i, T-2, :(T-1)] = bootstrap_allitems_nontargets_allitems_uniquekappa['allnontarget_p_value']
print sigmax, T, result_pvalue_bootstrap_sum[sigmax_i, T-2], result_pvalue_bootstrap_all[sigmax_i, T-2, :(T-1)], np.sum(result_pvalue_bootstrap_all[sigmax_i, T-2, :(T-1)] < 0.05)
if plot_persigmax:
T_space_filtered = np.array([1, 2, 4, 6])
for sigmax_i, sigmax in enumerate(sigmax_space):
print "sigmax: ", sigmax
# Compute the error between the response and the target
errors_targets = utils.wrap_angles(result_responses_all[sigmax_i] - result_target_all[sigmax_i])
errors_nontargets = np.nan*np.empty(result_nontargets_all[sigmax_i].shape)
if do_best_nontarget:
errors_best_nontarget = np.empty(errors_targets.shape)
for T_i in xrange(1, T_space.size):
for repet_i in xrange(nb_repetitions):
# Could do a nicer indexing but f**k it
# Compute the error between the responses and nontargets.
errors_nontargets[T_i, :, :, repet_i] = utils.wrap_angles((result_responses_all[sigmax_i, T_i, :, repet_i, np.newaxis] - result_nontargets_all[sigmax_i, T_i, :, :, repet_i]))
# Errors between the response the best nontarget.
if do_best_nontarget:
errors_best_nontarget[T_i, :, repet_i] = errors_nontargets[T_i, np.arange(errors_nontargets.shape[1]), np.nanargmin(np.abs(errors_nontargets[T_i, ..., repet_i]), axis=1), repet_i]
f1, axes1 = plt.subplots(ncols=T_space_filtered.size, figsize=(T_space_filtered.size*6, 6), sharey=True)
f2, axes2 = plt.subplots(ncols=T_space_filtered.size-1, figsize=((T_space_filtered.size-1)*6, 6), sharey=True)
for T_i, T in enumerate(T_space_filtered):
print "T: ", T
# Now, per T items, show the distribution of errors and of errors to non target
# Error to target
# hist_errors_targets = np.zeros((angle_space.size, nb_repetitions))
# for repet_i in xrange(nb_repetitions):
# hist_errors_targets[:, repet_i], _, _ = utils_math.histogram_binspace(errors_targets[T_i, :, repet_i], bins=angle_space)
# f, ax = plt.subplots()
# ax.bar(angle_space, np.mean(hist_errors_targets, axis=-1), width=2.*np.pi/(angle_space.size-1), align='center')
# ax.set_xlim([angle_space[0] - np.pi/(angle_space.size-1), angle_space[-1] + np.pi/(angle_space.size-1)])
# utils.plot_mean_std_area(angle_space, np.mean(hist_errors_targets, axis=-1), np.std(hist_errors_targets, axis=-1))
# utils.hist_samples_density_estimation(errors_targets[T_i].reshape(nb_repetitions*N), bins=angle_space, title='Errors between response and target, N=%d' % (T))
utils.hist_angular_data(utils.dropnan(errors_targets[T_i]), bins=angle_space, norm='density', ax_handle=axes1[T_i], pretty_xticks=True)
axes1[T_i].set_ylim([0., 2.0])
if T > 1:
# Error to nontarget
# ax_handle = utils.hist_samples_density_estimation(errors_nontargets[T_i, :, :T_i].reshape(nb_repetitions*N*T_i), bins=angle_space, title='Errors between response and non targets, N=%d' % (T))
utils.hist_angular_data(utils.dropnan(errors_nontargets[T_i, :, :T_i]), bins=angle_space, title='N=%d' % (T), norm='density', ax_handle=axes2[T_i-1], pretty_xticks=True)
axes2[T_i-1].set_title('')
result_pval_vtest_nontargets[sigmax_i, T_i] = utils.V_test(utils.dropnan(errors_nontargets[T_i, :, :T_i]))['pvalue']
print result_pval_vtest_nontargets[sigmax_i, T_i]
# axes2[T_i-1].text(0.03, 0.96, "Vtest pval: %.2f" % (result_pval_vtest_nontargets[sigmax_i, T_i]), transform=axes2[T_i - 1].transAxes, horizontalalignment='left', fontsize=12)
axes2[T_i-1].text(0.03, 0.94, "$p=%.1f$" % (result_pvalue_bootstrap_sum[sigmax_i, T_i]), transform=axes2[T_i - 1].transAxes, horizontalalignment='left', fontsize=18)
axes2[T_i-1].set_ylim([0., 0.30])
# Error to best non target
if do_best_nontarget:
utils.hist_samples_density_estimation(errors_best_nontarget[T_i].reshape(nb_repetitions*N), bins=angle_space, title='N=%d' % (T))
if savefigs:
dataio.save_current_figure('error_bestnontarget_hist_sigmax%.2f_T%d_{label}_{unique_id}.pdf' % (sigmax, T))
if savefigs:
plt.figure(f1.number)
plt.tight_layout()
dataio.save_current_figure('error_target_hist_sigmax%.2f_Tall_{label}_{unique_id}.pdf' % (sigmax))
plt.figure(f2.number)
plt.tight_layout()
dataio.save_current_figure('error_nontargets_hist_sigmax%.2f_Tall_{label}_{unique_id}.pdf' % (sigmax))
all_args = data_pbs.loaded_data['args_list']
if savedata:
dataio.save_variables_default(locals())
dataio.make_link_output_to_dropbox(dropbox_current_experiment_folder='error_distribution')
plt.show()
return locals()
def plots_misbinding_logposterior(data_pbs, generator_module=None):
'''
Reload 3D volume runs from PBS and plot them
'''
#### SETUP
#
savedata = False
savefigs = True
plot_logpost = False
plot_error = False
plot_mixtmodel = True
plot_hist_responses_fisherinfo = True
compute_plot_bootstrap = False
compute_fisher_info_perratioconj = True
# mixturemodel_to_use = 'original'
mixturemodel_to_use = 'allitems'
# mixturemodel_to_use = 'allitems_kappafi'
caching_fisherinfo_filename = os.path.join(generator_module.pbs_submission_infos['simul_out_dir'], 'cache_fisherinfo.pickle')
#
#### /SETUP
print "Order parameters: ", generator_module.dict_parameters_range.keys()
result_all_log_posterior = np.squeeze(data_pbs.dict_arrays['result_all_log_posterior']['results'])
result_all_thetas = np.squeeze(data_pbs.dict_arrays['result_all_thetas']['results'])
ratio_space = data_pbs.loaded_data['parameters_uniques']['ratio_conj']
print ratio_space
print result_all_log_posterior.shape
N = result_all_thetas.shape[-1]
result_prob_wrong = np.zeros((ratio_space.size, N))
result_em_fits = np.empty((ratio_space.size, 6))*np.nan
all_args = data_pbs.loaded_data['args_list']
fixed_means = [-np.pi*0.6, np.pi*0.6]
all_angles = np.linspace(-np.pi, np.pi, result_all_log_posterior.shape[-1])
dataio = DataIO(output_folder=generator_module.pbs_submission_infos['simul_out_dir'] + '/outputs/', label='global_' + dataset_infos['save_output_filename'])
plt.rcParams['font.size'] = 18
if plot_hist_responses_fisherinfo:
# From cache
if caching_fisherinfo_filename is not None:
if os.path.exists(caching_fisherinfo_filename):
# Got file, open it and try to use its contents
try:
with open(caching_fisherinfo_filename, 'r') as file_in:
# Load and assign values
cached_data = pickle.load(file_in)
result_fisherinfo_ratio = cached_data['result_fisherinfo_ratio']
compute_fisher_info_perratioconj = False
except IOError:
print "Error while loading ", caching_fisherinfo_filename, "falling back to computing the Fisher Info"
if compute_fisher_info_perratioconj:
# We did not save the Fisher info, but need it if we want to fit the mixture model with fixed kappa. So recompute them using the args_dicts
result_fisherinfo_ratio = np.empty(ratio_space.shape)
# Invert the all_args_i -> ratio_conj direction
parameters_indirections = data_pbs.loaded_data['parameters_dataset_index']
for ratio_conj_i, ratio_conj in enumerate(ratio_space):
# Get index of first dataset with the current ratio_conj (no need for the others, I think)
arg_index = parameters_indirections[(ratio_conj,)][0]
# Now using this dataset, reconstruct a RandomFactorialNetwork and compute the fisher info
curr_args = all_args[arg_index]
curr_args['stimuli_generation'] = lambda T: np.linspace(-np.pi*0.6, np.pi*0.6, T)
(random_network, data_gen, stat_meas, sampler) = launchers.init_everything(curr_args)
# Theo Fisher info
result_fisherinfo_ratio[ratio_conj_i] = sampler.estimate_fisher_info_theocov()
del curr_args['stimuli_generation']
# Save everything to a file, for faster later plotting
if caching_fisherinfo_filename is not None:
try:
with open(caching_fisherinfo_filename, 'w') as filecache_out:
data_cache = dict(result_fisherinfo_ratio=result_fisherinfo_ratio)
pickle.dump(data_cache, filecache_out, protocol=2)
except IOError:
print "Error writing out to caching file ", caching_fisherinfo_filename
# Now plots. Do histograms of responses (around -pi/6 and pi/6), add Von Mises derived from Theo FI on top, and vertical lines for the correct target/nontarget angles.
for ratio_conj_i, ratio_conj in enumerate(ratio_space):
# Histogram
ax = utils.hist_angular_data(result_all_thetas[ratio_conj_i], bins=100, title='ratio %.2f, fi %.0f' % (ratio_conj, result_fisherinfo_ratio[ratio_conj_i]))
bar_heights, _, _ = utils.histogram_binspace(result_all_thetas[ratio_conj_i], bins=100, norm='density')
# Add Fisher info prediction on top
x = np.linspace(-np.pi, np.pi, 1000)
if result_fisherinfo_ratio[ratio_conj_i] < 700:
# Von Mises PDF
utils.plot_vonmises_pdf(x, utils.stddev_to_kappa(1./result_fisherinfo_ratio[ratio_conj_i]**0.5), mu=fixed_means[-1], ax_handle=ax, linewidth=3, color='r', scale=np.max(bar_heights), fmt='-')
else:
# Switch to Gaussian instead
utils.plot_normal_pdf(x, mu=fixed_means[-1], std=1./result_fisherinfo_ratio[ratio_conj_i]**0.5, ax_handle=ax, linewidth=3, color='r', scale=np.max(bar_heights), fmt='-')
# ax.set_xticks([])
# ax.set_yticks([])
# Add vertical line to correct target/nontarget
ax.axvline(x=fixed_means[0], color='g', linewidth=2)
ax.axvline(x=fixed_means[1], color='r', linewidth=2)
ax.get_figure().canvas.draw()
if savefigs:
# plt.tight_layout()
dataio.save_current_figure('results_misbinding_histresponses_vonmisespdf_ratioconj%.2f{label}_{unique_id}.pdf' % (ratio_conj))
if plot_logpost:
for ratio_conj_i, ratio_conj in enumerate(ratio_space):
# ax = utils.plot_mean_std_area(all_angles, nanmean(result_all_log_posterior[ratio_conj_i], axis=0), nanstd(result_all_log_posterior[ratio_conj_i], axis=0))
# ax.set_xlim((-np.pi, np.pi))
# ax.set_xticks((-np.pi, -np.pi / 2, 0, np.pi / 2., np.pi))
# ax.set_xticklabels((r'$-\pi$', r'$-\frac{\pi}{2}$', r'$0$', r'$\frac{\pi}{2}$', r'$\pi$'))
# ax.set_yticks(())
# ax.get_figure().canvas.draw()
# if savefigs:
# dataio.save_current_figure('results_misbinding_logpost_ratioconj%.2f_{label}_global_{unique_id}.pdf' % ratio_conj)
# Compute the probability of answering wrongly (from fitting mixture distrib onto posterior)
for n in xrange(result_all_log_posterior.shape[1]):
result_prob_wrong[ratio_conj_i, n], _, _ = utils.fit_gaussian_mixture_fixedmeans(all_angles, np.exp(result_all_log_posterior[ratio_conj_i, n]), fixed_means=fixed_means, normalise=True, return_fitted_data=False, should_plot=False)
# ax = utils.plot_mean_std_area(ratio_space, nanmean(result_prob_wrong, axis=-1), nanstd(result_prob_wrong, axis=-1))
plt.figure()
plt.plot(ratio_space, utils.nanmean(result_prob_wrong, axis=-1))
# ax.get_figure().canvas.draw()
if savefigs:
dataio.save_current_figure('results_misbinding_probwrongpost_allratioconj_{label}_global_{unique_id}.pdf')
if plot_error:
## Compute Standard deviation/precision from samples and plot it as a function of ratio_conj
stats = utils.compute_mean_std_circular_data(utils.wrap_angles(result_all_thetas - fixed_means[1]).T)
f = plt.figure()
plt.plot(ratio_space, stats['std'])
plt.ylabel('Standard deviation [rad]')
if savefigs:
dataio.save_current_figure('results_misbinding_stddev_allratioconj_{label}_global_{unique_id}.pdf')
f = plt.figure()
plt.plot(ratio_space, utils.compute_angle_precision_from_std(stats['std'], square_precision=False), linewidth=2)
plt.ylabel('Precision [$1/rad$]')
plt.xlabel('Proportion of conjunctive units')
plt.grid()
if savefigs:
dataio.save_current_figure('results_misbinding_precision_allratioconj_{label}_global_{unique_id}.pdf')
## Compute the probability of misbinding
# 1) Just count samples < 0 / samples tot
# 2) Fit a mixture model, average over mixture probabilities
prob_smaller0 = np.sum(result_all_thetas <= 1, axis=1)/float(result_all_thetas.shape[1])
em_centers = np.zeros((ratio_space.size, 2))
em_covs = np.zeros((ratio_space.size, 2))
em_pk = np.zeros((ratio_space.size, 2))
em_ll = np.zeros(ratio_space.size)
for ratio_conj_i, ratio_conj in enumerate(ratio_space):
cen_lst, cov_lst, em_pk[ratio_conj_i], em_ll[ratio_conj_i] = pygmm.em(result_all_thetas[ratio_conj_i, np.newaxis].T, K = 2, max_iter = 400, init_kw={'cluster_init':'fixed', 'fixed_means': fixed_means})
em_centers[ratio_conj_i] = np.array(cen_lst).flatten()
em_covs[ratio_conj_i] = np.array(cov_lst).flatten()
# print em_centers
# print em_covs
# print em_pk
f = plt.figure()
plt.plot(ratio_space, prob_smaller0)
plt.ylabel('Misbound proportion')
if savefigs:
dataio.save_current_figure('results_misbinding_countsmaller0_allratioconj_{label}_global_{unique_id}.pdf')
f = plt.figure()
plt.plot(ratio_space, np.max(em_pk, axis=-1), 'g', linewidth=2)
plt.ylabel('Mixture proportion, correct')
plt.xlabel('Proportion of conjunctive units')
plt.grid()
if savefigs:
dataio.save_current_figure('results_misbinding_emmixture_allratioconj_{label}_global_{unique_id}.pdf')
# Put everything on one figure
f = plt.figure(figsize=(10, 6))
norm_for_plot = lambda x: (x - np.min(x))/np.max((x - np.min(x)))
plt.plot(ratio_space, norm_for_plot(stats['std']), ratio_space, norm_for_plot(utils.compute_angle_precision_from_std(stats['std'], square_precision=False)), ratio_space, norm_for_plot(prob_smaller0), ratio_space, norm_for_plot(em_pk[:, 1]), ratio_space, norm_for_plot(em_pk[:, 0]))
plt.legend(('Std dev', 'Precision', 'Prob smaller 1', 'Mixture proportion correct', 'Mixture proportion misbinding'))
# plt.plot(ratio_space, norm_for_plot(compute_angle_precision_from_std(stats['std'], square_precision=False)), ratio_space, norm_for_plot(em_pk[:, 1]), linewidth=2)
# plt.legend(('Precision', 'Mixture proportion correct'), loc='best')
plt.grid()
if savefigs:
dataio.save_current_figure('results_misbinding_allmetrics_allratioconj_{label}_global_{unique_id}.pdf')
if plot_mixtmodel:
# Fit Paul's model
target_angle = np.ones(N)*fixed_means[1]
nontarget_angles = np.ones((N, 1))*fixed_means[0]
for ratio_conj_i, ratio_conj in enumerate(ratio_space):
print "Ratio: ", ratio_conj
responses = result_all_thetas[ratio_conj_i]
if mixturemodel_to_use == 'allitems_kappafi':
curr_params_fit = em_circularmixture_allitems_kappafi.fit(responses, target_angle, nontarget_angles, kappa=result_fisherinfo_ratio[ratio_conj_i])
elif mixturemodel_to_use == 'allitems':
curr_params_fit = em_circularmixture_allitems_uniquekappa.fit(responses, target_angle, nontarget_angles)
else:
curr_params_fit = em_circularmixture.fit(responses, target_angle, nontarget_angles)
result_em_fits[ratio_conj_i] = [curr_params_fit['kappa'], curr_params_fit['mixt_target']] + utils.arrnum_to_list(curr_params_fit['mixt_nontargets']) + [curr_params_fit[key] for key in ('mixt_random', 'train_LL', 'bic')]
print curr_params_fit
if False:
f, ax = plt.subplots()
ax2 = ax.twinx()
# left axis, kappa
ax = utils.plot_mean_std_area(ratio_space, result_em_fits[:, 0], 0*result_em_fits[:, 0], xlabel='Proportion of conjunctive units', ylabel="Inverse variance $[rad^{-2}]$", ax_handle=ax, linewidth=3, fmt='o-', markersize=8, label='Fitted kappa', color='k')
# Right axis, mixture probabilities
utils.plot_mean_std_area(ratio_space, result_em_fits[:, 1], 0*result_em_fits[:, 1], xlabel='Proportion of conjunctive units', ylabel="Mixture probabilities", ax_handle=ax2, linewidth=3, fmt='o-', markersize=8, label='Target')
utils.plot_mean_std_area(ratio_space, result_em_fits[:, 2], 0*result_em_fits[:, 2], xlabel='Proportion of conjunctive units', ylabel="Mixture probabilities", ax_handle=ax2, linewidth=3, fmt='o-', markersize=8, label='Nontarget')
utils.plot_mean_std_area(ratio_space, result_em_fits[:, 3], 0*result_em_fits[:, 3], xlabel='Proportion of conjunctive units', ylabel="Mixture probabilities", ax_handle=ax2, linewidth=3, fmt='o-', markersize=8, label='Random')
lines, labels = ax.get_legend_handles_labels()
lines2, labels2 = ax2.get_legend_handles_labels()
ax.legend(lines + lines2, labels + labels2, fontsize=12, loc='right')
# ax.set_xlim([0.9, 5.1])
# ax.set_xticks(range(1, 6))
# ax.set_xticklabels(range(1, 6))
plt.grid()
f.canvas.draw()
if True:
# Mixture probabilities
ax = utils.plot_mean_std_area(ratio_space, result_em_fits[:, 1], 0*result_em_fits[:, 1], xlabel='Proportion of conjunctive units', ylabel="Mixture probabilities", linewidth=3, fmt='-', markersize=8, label='Target')
utils.plot_mean_std_area(ratio_space, result_em_fits[:, 2], 0*result_em_fits[:, 2], xlabel='Proportion of conjunctive units', ylabel="Mixture probabilities", ax_handle=ax, linewidth=3, fmt='-', markersize=8, label='Nontarget')
utils.plot_mean_std_area(ratio_space, result_em_fits[:, 3], 0*result_em_fits[:, 3], xlabel='Proportion of conjunctive units', ylabel="Mixture probabilities", ax_handle=ax, linewidth=3, fmt='-', markersize=8, label='Random')
ax.legend(loc='right')
# ax.set_xlim([0.9, 5.1])
# ax.set_xticks(range(1, 6))
# ax.set_xticklabels(range(1, 6))
plt.grid()
if savefigs:
dataio.save_current_figure('results_misbinding_emmixture_allratioconj_{label}_global_{unique_id}.pdf')
if True:
# Kappa
# ax = utils.plot_mean_std_area(ratio_space, result_em_fits[:, 0], 0*result_em_fits[:, 0], xlabel='Proportion of conjunctive units', ylabel="$\kappa [rad^{-2}]$", linewidth=3, fmt='-', markersize=8, label='Kappa')
ax = utils.plot_mean_std_area(ratio_space, utils.kappa_to_stddev(result_em_fits[:, 0]), 0*result_em_fits[:, 2], xlabel='Proportion of conjunctive units', ylabel="Standard deviation [rad]", linewidth=3, fmt='-', markersize=8, label='Mixture model $\kappa$')
# Add Fisher Info theo
ax = utils.plot_mean_std_area(ratio_space, utils.kappa_to_stddev(result_fisherinfo_ratio), 0*result_em_fits[:, 2], xlabel='Proportion of conjunctive units', ylabel="Standard deviation [rad]", linewidth=3, fmt='-', markersize=8, label='Fisher Information', ax_handle=ax)
ax.legend(loc='best')
# ax.set_xlim([0.9, 5.1])
# ax.set_xticks(range(1, 6))
# ax.set_xticklabels(range(1, 6))
plt.grid()
if savefigs:
dataio.save_current_figure('results_misbinding_kappa_allratioconj_{label}_global_{unique_id}.pdf')
if compute_plot_bootstrap:
## Compute the bootstrap pvalue for each ratio
# use the bootstrap CDF from mixed runs, not the exact current ones, not sure if good idea.
bootstrap_to_load = 1
if bootstrap_to_load == 1:
cache_bootstrap_fn = os.path.join(generator_module.pbs_submission_infos['simul_out_dir'], 'outputs', 'cache_bootstrap_mixed_from_bootstrapnontargets.pickle')
bootstrap_ecdf_sum_label = 'bootstrap_ecdf_allitems_sum_sigmax_T'
bootstrap_ecdf_all_label = 'bootstrap_ecdf_allitems_all_sigmax_T'
elif bootstrap_to_load == 2:
cache_bootstrap_fn = os.path.join(generator_module.pbs_submission_infos['simul_out_dir'], 'outputs', 'cache_bootstrap_misbinding_mixed.pickle')
bootstrap_ecdf_sum_label = 'bootstrap_ecdf_allitems_sum_ratioconj'
bootstrap_ecdf_all_label = 'bootstrap_ecdf_allitems_all_ratioconj'
try:
with open(cache_bootstrap_fn, 'r') as file_in:
# Load and assign values
cached_data = pickle.load(file_in)
assert bootstrap_ecdf_sum_label in cached_data
assert bootstrap_ecdf_all_label in cached_data
should_fit_bootstrap = False
except IOError:
print "Error while loading ", cache_bootstrap_fn
# Select the ECDF to use
if bootstrap_to_load == 1:
sigmax_i = 3 # corresponds to sigmax = 2, input here.
T_i = 1 # two possible targets here.
bootstrap_ecdf_sum_used = cached_data[bootstrap_ecdf_sum_label][sigmax_i][T_i]['ecdf']
bootstrap_ecdf_all_used = cached_data[bootstrap_ecdf_all_label][sigmax_i][T_i]['ecdf']
elif bootstrap_to_load == 2:
ratio_conj_i = 4
bootstrap_ecdf_sum_used = cached_data[bootstrap_ecdf_sum_label][ratio_conj_i]['ecdf']
bootstrap_ecdf_all_used = cached_data[bootstrap_ecdf_all_label][ratio_conj_i]['ecdf']
result_pvalue_bootstrap_sum = np.empty(ratio_space.size)*np.nan
result_pvalue_bootstrap_all = np.empty((ratio_space.size, nontarget_angles.shape[-1]))*np.nan
for ratio_conj_i, ratio_conj in enumerate(ratio_space):
print "Ratio: ", ratio_conj
responses = result_all_thetas[ratio_conj_i]
bootstrap_allitems_nontargets_allitems_uniquekappa = em_circularmixture_allitems_uniquekappa.bootstrap_nontarget_stat(responses, target_angle, nontarget_angles,
sumnontargets_bootstrap_ecdf=bootstrap_ecdf_sum_used,
allnontargets_bootstrap_ecdf=bootstrap_ecdf_all_used)
result_pvalue_bootstrap_sum[ratio_conj_i] = bootstrap_allitems_nontargets_allitems_uniquekappa['p_value']
result_pvalue_bootstrap_all[ratio_conj_i] = bootstrap_allitems_nontargets_allitems_uniquekappa['allnontarget_p_value']
## Plots
# f, ax = plt.subplots()
# ax.plot(ratio_space, result_pvalue_bootstrap_all, linewidth=2)
# if savefigs:
# dataio.save_current_figure("pvalue_bootstrap_all_ratioconj_{label}_{unique_id}.pdf")
f, ax = plt.subplots()
ax.plot(ratio_space, result_pvalue_bootstrap_sum, linewidth=2)
plt.grid()
if savefigs:
dataio.save_current_figure("pvalue_bootstrap_sum_ratioconj_{label}_{unique_id}.pdf")
# plt.figure()
# plt.plot(ratio_MMlower, results_filtered_smoothed/np.max(results_filtered_smoothed, axis=0), linewidth=2)
# plt.plot(ratio_MMlower[np.argmax(results_filtered_smoothed, axis=0)], np.ones(results_filtered_smoothed.shape[-1]), 'ro', markersize=10)
# plt.grid()
# plt.ylim((0., 1.1))
# plt.subplots_adjust(right=0.8)
# plt.legend(['%d item' % i + 's'*(i>1) for i in xrange(1, T+1)], loc='center right', bbox_to_anchor=(1.3, 0.5))
# plt.xticks(np.linspace(0, 1.0, 5))
variables_to_save = ['target_angle', 'nontarget_angles']
if savedata:
dataio.save_variables_default(locals(), variables_to_save)
dataio.make_link_output_to_dropbox(dropbox_current_experiment_folder='misbindings')
plt.show()
return locals()
