def reconstruct_colours_exp1(self, datasets=('Data/ad.mat', 'Data/gb.mat', 'Data/kf.mat', 'Data/md.mat', 'Data/sf.mat', 'Data/sw.mat', 'Data/wd.mat', 'Data/zb.mat')):
'''
The colour is missing from the simultaneous experiment dataset
Reconstruct it.
'''
all_colours = []
all_preangles = []
all_targets = []
for dataset_fn in datasets:
dataset_fn = os.path.join(self.datadir, dataset_fn)
print dataset_fn
curr_data = sio.loadmat(dataset_fn, mat_dtype=True)
all_colours.append(curr_data['item_colour'])
all_preangles.append(utils.wrap_angles(curr_data['probe_pre_angle'], bound=np.pi))
all_targets.append(utils.wrap_angles(np.deg2rad(curr_data['item_angle'][:, 0]), bound=np.pi))
print "Data loaded"
all_colours = np.array(all_colours)
all_targets = np.array(all_targets)
all_preangles = np.array(all_preangles)
# Ordering in original data
order_subjects = [0, 2, 4, 6, 1, 3, 5, 7]
all_colours = all_colours[order_subjects]
all_targets = all_targets[order_subjects]
all_preangles = all_preangles[order_subjects]
# Convert colour ids into angles.
# Assume uniform coverage over circle...
nb_colours = np.unique(all_colours[0][:, 0]).size
# Make it so 0 is np.nan, and then 1...8 are possible colour angles
colours_possible = np.r_[np.nan, np.linspace(-np.pi, np.pi, nb_colours, endpoint=False)]
size_colour_arr = np.sum([col.shape[0] for col in all_colours])
item_colour = np.empty((size_colour_arr, all_colours[0].shape[1]))
start_i = 0
for i in xrange(all_colours.size):
# Get the indices. 0 will be np.nan, 1 .. nb_colours will work directly.
colours_indices = np.ma.masked_invalid(all_colours[i]).filled(fill_value = 0.0).astype(int)
# Get the colours!
# Indexing is annoying, as we have different shapes for different subjects
item_colour[start_i:start_i+colours_indices.shape[0]] = colours_possible[colours_indices]
start_i += colours_indices.shape[0]
item_preangle_arr = np.empty((0, all_preangles[0].shape[1]))
for arr in all_preangles:
item_preangle_arr = np.r_[item_preangle_arr, arr]
self.dataset['item_colour'] = item_colour
self.dataset['item_preangle'] = item_preangle_arr
self.dataset['all_targets'] = all_targets
def convert_wrap(self, keys_to_convert = ['item_angle', 'probe_angle', 'response', 'error', 'err'], multiply_factor=2., max_angle=np.pi):
'''
Takes a dataset and a list of keys. Each data associated with these keys will be converted to radian,
and wrapped in a [-max_angle, max_angle] interval
'''
for key in keys_to_convert:
if key in self.dataset:
self.dataset[key] = utils.wrap_angles(np.deg2rad(multiply_factor*self.dataset[key]), bound = max_angle)
def compute_all_errors(self):
'''
Will compute the error between the response and all possible items
'''
# Get the difference between angles
# Should also wrap it around
self.dataset['errors_all'] = utils.wrap_angles(self.dataset['item_angle'] - self.dataset['response'], bound=np.pi)
def validate_state(self, state: np.ndarray):
"""
Validate value of state by wrapping angle theta.
Arguments:
state: current state value
"""
state[1] = wrap_angles(state[1])
def test_bootstrap_nontargets():
'''
Check how the bootstrapped test for misbinding errors behaves
'''
# Negative example
N = 300
nb_nontargets = 1
kappa = 5.0
target = np.zeros(N)
nontargets = utils.wrap_angles(np.linspace(0.0, 2*np.pi, nb_nontargets + 1, endpoint=False)[1:])*np.ones((N, nb_nontargets))
responses = spst.vonmises.rvs(kappa, size=(N))
responses[np.random.randint(N, size=N/3)] = utils.sample_angle(N/3)
# em_fit = fit(responses, target, nontargets)
bootstrap_results = bootstrap_nontarget_stat(responses, target, nontargets, nb_bootstrap_samples=100)
print bootstrap_results
assert bootstrap_results['p_value'] > 0.05, "No misbinding here, should not reject H0"
# Positive example
N = 1000
N_nontarget = N/5
N_rnd = N/10
angles_nontargets = np.array([-np.pi/3-1., 0.5+np.pi/2.])
K = angles_nontargets.size
target = np.zeros(N)
nontargets = np.ones((N, K))*angles_nontargets
kappa = np.array([10.0])
# Sample from Von Mises
responses = spst.vonmises.rvs(kappa, size=(N))
# Randomly displace some points to their nontarget location (should still be VonMises(kappa))
for k in xrange(K):
curr_rand_indices = np.random.randint(N, size=N_nontarget/K)
responses[curr_rand_indices] = spst.vonmises.rvs(kappa, size=(N))
responses[curr_rand_indices] += angles_nontargets[k]
# Forces some points to be random
responses[np.random.randint(N, size=N_rnd)] = utils.sample_angle(N_rnd)
bootstrap_results = bootstrap_nontarget_stat(responses, target, nontargets, nb_bootstrap_samples=100)
assert np.any(bootstrap_results['p_value'] < 0.10), "Clear misbinding, should have rejected H0"
def test_bootstrap_nontargets():
'''
Check how the bootstrapped test for misbinding errors behaves
'''
N = 300
nb_nontargets = 1
kappa = 5.0
target = np.zeros(N)
nontargets = utils.wrap_angles(np.linspace(0.0, 2*np.pi, nb_nontargets + 1, endpoint=False)[1:])*np.ones((N, nb_nontargets))
responses = spst.vonmises.rvs(kappa, size=(N))
responses[np.random.randint(N, size=N/3)] = utils.sample_angle(N/3)
# em_fit = fit(responses, target, nontargets)
bootstrap_results = bootstrap_nontarget_stat(responses, target, nontargets)
print bootstrap_results
assert bootstrap_results['p_value'] > 0.05, "No misbinding here, should not reject H0"
def preprocess(self, parameters):
'''
This is the dataset where both colour and orientation can be recalled.
- There are two groups of subjects, either with 6 or 3 items shown (no intermediates...). Stored in 'n_items'
- Subjects recalled either colour or orientation, per blocks. Stored in 'cond'
- Subject report their confidence, which is cool.
Things to change:
- 'item_location' really contains 'item_angle'...
- item_location and probe_location should be wrapped back into -pi:pi.
- Should compute the errors.
'''
# Make some aliases
self.dataset['item_angle'] = self.dataset['item_location']
self.dataset['probe_angle'] = self.dataset['probe_location']
self.dataset['n_items'] = self.dataset['n_items'].astype(int)
self.dataset['cond'] = self.dataset['cond'].astype(int)
self.dataset['subject'] = self.dataset['subject'].astype(int)
self.dataset['probe'] = np.zeros(self.dataset['probe_angle'].shape[0], dtype=int)
self.dataset['n_items_space'] = np.unique(self.dataset['n_items'])
self.dataset['n_items_size'] = self.dataset['n_items_space'].size
self.dataset['subject_space'] = np.unique(self.dataset['subject'])
self.dataset['subject_size'] = self.dataset['subject_space'].size
# Get shortcuts for colour and orientation trials
self.dataset['colour_trials'] = (self.dataset['cond'] == 1).flatten()
self.dataset['angle_trials'] = (self.dataset['cond'] == 2).flatten()
self.dataset['3_items_trials'] = (self.dataset['n_items'] == 3).flatten()
self.dataset['6_items_trials'] = (self.dataset['n_items'] == 6).flatten()
# Wrap everything around
multiply_factor = 2.
self.dataset['item_angle'] = utils.wrap_angles(multiply_factor*self.dataset['item_angle'], np.pi)
self.dataset['probe_angle'] = utils.wrap_angles(multiply_factor*self.dataset['probe_angle'], np.pi)
self.dataset['item_colour'] = utils.wrap_angles(multiply_factor*self.dataset['item_colour'], np.pi)
self.dataset['probe_colour'] = utils.wrap_angles(multiply_factor*self.dataset['probe_colour'], np.pi)
# Remove wrong trials
reject_ids = (self.dataset['reject'] == 1.0).flatten()
for key in self.dataset:
if type(self.dataset[key]) == np.ndarray and self.dataset[key].shape[0] == reject_ids.size and key in ('probe_colour', 'probe_angle', 'item_angle', 'item_colour'):
self.dataset[key][reject_ids] = np.nan
# Compute the errors
self.dataset['errors_angle_all'] = utils.wrap_angles(self.dataset['item_angle'] - self.dataset['probe_angle'], np.pi)
self.dataset['errors_colour_all'] = utils.wrap_angles(self.dataset['item_colour'] - self.dataset['probe_colour'], np.pi)
self.dataset['error_angle'] = self.dataset['errors_angle_all'][:, 0]
self.dataset['error_colour'] = self.dataset['errors_colour_all'][:, 0]
self.dataset['error'] = np.where(~np.isnan(self.dataset['error_angle']), self.dataset['error_angle'], self.dataset['error_colour'])
self.dataset['errors_nitems'] = np.empty(self.dataset['n_items_size'], dtype=np.object)
self.dataset['errors_all_nitems'] = np.empty(self.dataset['n_items_size'], dtype=np.object)
for n_items_i, n_items in enumerate(np.unique(self.dataset['n_items'])):
ids_filtered = self.dataset['angle_trials'] & (self.dataset['n_items'] == n_items).flatten()
self.dataset['errors_nitems'][n_items_i] = self.dataset['error_angle'][ids_filtered]
self.dataset['errors_all_nitems'][n_items_i
] = self.dataset['errors_angle_all'][ids_filtered]
### Split the data up
self.generate_data_to_fit()
### Fit the mixture model
if parameters['fit_mixture_model']:
self.fit_mixture_model_cached(caching_save_filename=parameters.get('mixture_model_cache', None), saved_keys=['em_fits', 'em_fits_angle_nitems_subjects', 'em_fits_angle_nitems', 'em_fits_colour_nitems_subjects', 'em_fits_colour_nitems', 'em_fits_angle_nitems_arrays', 'em_fits_colour_nitems_arrays'])
# Try with Pandas for some advanced plotting
dataset_filtered = dict((k, self.dataset[k].flatten()) for k in ('n_items', 'trial', 'subject', 'reject', 'rating', 'probe_colour', 'probe_angle', 'cond', 'error', 'error_angle', 'error_colour', 'response', 'target'))
if parameters['fit_mixture_model']:
dataset_filtered.update(self.dataset['em_fits'])
self.dataset['panda'] = pd.DataFrame(dataset_filtered)
""" import numpy as np import matplotlib.pyplot as plt import utils import statsmodels.nonparametric.kde as stmokde # Sample from wrapped gaussian num_samples = 1000 std_target = 1.5 samples = np.random.normal(0.0, std_target, size=num_samples) samples_w = utils.wrap_angles(samples) x = np.linspace(-np.pi, np.pi, 10000) # KDE samples_kde = stmokde.KDEUnivariate(samples) samples_kde.fit() samples_w_kde = stmokde.KDEUnivariate(samples_w) samples_w_kde.fit() # Von Mises samples_vonmises = utils.fit_vonmises_samples(samples, num_points=300, return_fitted_data=True, should_plot=False) samples_w_vonmises = utils.fit_vonmises_samples(samples_w, num_points=300, return_fitted_data=True, should_plot=False) plt.figure() plt.hist(samples, bins=100, normed=True)
def plots_histograms_errors_triangle(self, size=12):
'''
Histograms of errors, for all n_items/trecall conditions.
'''
# Do the plots
f, axes = plt.subplots(
ncols=self.fit_exp.T_space.size,
nrows=2*self.fit_exp.T_space.size,
figsize=(size, 2*size))
angle_space = np.linspace(-np.pi, np.pi, 51)
for n_items_i, n_items in enumerate(self.fit_exp.T_space):
for trecall_i, trecall in enumerate(self.fit_exp.T_space):
if trecall <= n_items:
print "\n=== N items: {}, trecall: {}".format(
n_items, trecall)
# Sample
self.fit_exp.setup_experimental_stimuli(n_items, trecall)
if 'samples' in self.fit_exp.get_names_stored_responses():
self.fit_exp.restore_responses('samples')
else:
self.fit_exp.sampler.force_sampling_round()
self.fit_exp.store_responses('samples')
responses, targets, nontargets = (
self.fit_exp.sampler.collect_responses())
# Targets
errors_targets = utils.wrap_angles(targets - responses)
utils.hist_angular_data(
errors_targets,
bins=angle_space,
# title='N=%d, trecall=%d' % (n_items, trecall),
norm='density',
ax_handle=axes[2*n_items_i, trecall_i],
pretty_xticks=False)
axes[2*n_items_i, trecall_i].set_ylim([0., 1.4])
axes[2*n_items_i, trecall_i].xaxis.set_major_locator(
plt.NullLocator())
axes[2*n_items_i, trecall_i].yaxis.set_major_locator(
plt.NullLocator())
# Nontargets
if n_items > 1:
errors_nontargets = utils.wrap_angles((
responses[:, np.newaxis] - nontargets).flatten())
utils.hist_angular_data(
errors_nontargets,
bins=angle_space,
# title='Nontarget %s N=%d' % (dataset['name'], n_items),
norm='density',
ax_handle=axes[2*n_items_i + 1, trecall_i],
pretty_xticks=False)
axes[2*n_items_i + 1, trecall_i].set_ylim([0., 0.3])
axes[2*n_items_i + 1, trecall_i].xaxis.set_major_locator(plt.NullLocator())
axes[2*n_items_i + 1, trecall_i].yaxis.set_major_locator(plt.NullLocator())
else:
axes[2*n_items_i, trecall_i].axis('off')
axes[2*n_items_i + 1, trecall_i].axis('off')
return axes
def plots_memory_curves(data_pbs, generator_module=None):
"""
Reload and plot memory curve of a Mixed code.
Can use Marginal Fisher Information and fitted Mixture Model as well
"""
#### SETUP
#
savefigs = True
savedata = True
do_error_distrib_fits = True
plot_pcolor_fit_precision_to_fisherinfo = True
plot_selected_memory_curves = False
plot_best_memory_curves = False
plot_best_error_distrib = True
colormap = None # or 'cubehelix'
plt.rcParams["font.size"] = 16
#
#### /SETUP
print "Order parameters: ", generator_module.dict_parameters_range.keys()
result_all_precisions_mean = utils.nanmean(data_pbs.dict_arrays["result_all_precisions"]["results"], axis=-1)
result_all_precisions_std = utils.nanstd(data_pbs.dict_arrays["result_all_precisions"]["results"], axis=-1)
result_em_fits_mean = utils.nanmean(data_pbs.dict_arrays["result_em_fits"]["results"], axis=-1)
result_em_fits_std = utils.nanstd(data_pbs.dict_arrays["result_em_fits"]["results"], axis=-1)
result_marginal_inv_fi_mean = utils.nanmean(data_pbs.dict_arrays["result_marginal_inv_fi"]["results"], axis=-1)
result_marginal_inv_fi_std = utils.nanstd(data_pbs.dict_arrays["result_marginal_inv_fi"]["results"], axis=-1)
result_marginal_fi_mean = utils.nanmean(1.0 / data_pbs.dict_arrays["result_marginal_inv_fi"]["results"], axis=-1)
result_marginal_fi_std = utils.nanstd(1.0 / data_pbs.dict_arrays["result_marginal_inv_fi"]["results"], axis=-1)
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"]
M_space = data_pbs.loaded_data["parameters_uniques"]["M"].astype(int)
sigmax_space = data_pbs.loaded_data["parameters_uniques"]["sigmax"]
T_space = data_pbs.loaded_data["datasets_list"][0]["T_space"]
nb_repetitions = result_responses_all.shape[-1]
print M_space
print sigmax_space
print T_space
print result_all_precisions_mean.shape, result_em_fits_mean.shape, result_marginal_inv_fi_mean.shape
dataio = DataIO.DataIO(
output_folder=generator_module.pbs_submission_infos["simul_out_dir"] + "/outputs/",
label="global_" + dataset_infos["save_output_filename"],
)
## Load Experimental data
experim_datadir = os.environ.get("WORKDIR_DROP", os.path.split(load_experimental_data.__file__)[0])
data_simult = load_experimental_data.load_data_simult(
data_dir=os.path.normpath(os.path.join(experim_datadir, "../../experimental_data/")), fit_mixture_model=True
)
gorgo11_experimental_precision = data_simult["precision_nitems_theo"]
gorgo11_experimental_kappa = np.array([data["kappa"] for _, data in data_simult["em_fits_nitems"]["mean"].items()])
gorgo11_experimental_emfits_mean = np.array(
[
[data[key] for _, data in data_simult["em_fits_nitems"]["mean"].items()]
for key in ["kappa", "mixt_target", "mixt_nontargets", "mixt_random"]
]
)
gorgo11_experimental_emfits_std = np.array(
[
[data[key] for _, data in data_simult["em_fits_nitems"]["std"].items()]
for key in ["kappa", "mixt_target", "mixt_nontargets", "mixt_random"]
]
)
gorgo11_experimental_emfits_sem = gorgo11_experimental_emfits_std / np.sqrt(np.unique(data_simult["subject"]).size)
experim_datadir = os.environ.get("WORKDIR_DROP", os.path.split(load_experimental_data.__file__)[0])
data_bays2009 = load_experimental_data.load_data_bays09(
data_dir=os.path.normpath(os.path.join(experim_datadir, "../../experimental_data/")), fit_mixture_model=True
)
bays09_experimental_mixtures_mean = data_bays2009["em_fits_nitems_arrays"]["mean"]
bays09_experimental_mixtures_std = data_bays2009["em_fits_nitems_arrays"]["std"]
# add interpolated points for 3 and 5 items
emfit_mean_intpfct = spint.interp1d(np.unique(data_bays2009["n_items"]), bays09_experimental_mixtures_mean)
bays09_experimental_mixtures_mean_compatible = emfit_mean_intpfct(np.arange(1, 7))
emfit_std_intpfct = spint.interp1d(np.unique(data_bays2009["n_items"]), bays09_experimental_mixtures_std)
bays09_experimental_mixtures_std_compatible = emfit_std_intpfct(np.arange(1, 7))
T_space_bays09 = np.arange(1, 6)
# Boost non-targets
# bays09_experimental_mixtures_mean_compatible[1] *= 1.5
# bays09_experimental_mixtures_mean_compatible[2] /= 1.5
# bays09_experimental_mixtures_mean_compatible /= np.sum(bays09_experimental_mixtures_mean_compatible, axis=0)
# Compute some landscapes of fit!
# dist_diff_precision_margfi = np.sum(np.abs(result_all_precisions_mean*2. - result_marginal_fi_mean[..., 0])**2., axis=-1)
# dist_ratio_precision_margfi = np.sum(np.abs((result_all_precisions_mean*2.)/result_marginal_fi_mean[..., 0] - 1.0)**2., axis=-1)
# dist_diff_emkappa_margfi = np.sum(np.abs(result_em_fits_mean[..., 0]*2. - result_marginal_fi_mean[..., 0])**2., axis=-1)
# dist_ratio_emkappa_margfi = np.sum(np.abs((result_em_fits_mean[..., 0]*2.)/result_marginal_fi_mean[..., 0] - 1.0)**2., axis=-1)
dist_diff_precision_experim = np.sum(
np.abs(result_all_precisions_mean[..., : gorgo11_experimental_kappa.size] - gorgo11_experimental_precision)
** 2.0,
axis=-1,
)
dist_diff_emkappa_experim = np.sum(
np.abs(result_em_fits_mean[..., 0, : gorgo11_experimental_kappa.size] - gorgo11_experimental_kappa) ** 2.0,
axis=-1,
)
dist_diff_em_mixtures_bays09 = np.sum(
np.sum((result_em_fits_mean[..., 1:4] - bays09_experimental_mixtures_mean_compatible[1:].T) ** 2.0, axis=-1),
axis=-1,
)
dist_diff_modelfits_experfits_bays09 = np.sum(
np.sum((result_em_fits_mean[..., :4] - bays09_experimental_mixtures_mean_compatible.T) ** 2.0, axis=-1), axis=-1
)
if do_error_distrib_fits:
print "computing error distribution histograms fits"
# Now try to fit histograms of errors to target/nontargets
bays09_hist_target_mean = data_bays2009["hist_cnts_target_nitems_stats"]["mean"]
bays09_hist_target_std = data_bays2009["hist_cnts_target_nitems_stats"]["std"]
bays09_hist_nontarget_mean = data_bays2009["hist_cnts_nontarget_nitems_stats"]["mean"]
bays09_hist_nontarget_std = data_bays2009["hist_cnts_nontarget_nitems_stats"]["std"]
T_space_bays09_filt = np.unique(data_bays2009["n_items"])
angle_space = np.linspace(-np.pi, np.pi, bays09_hist_target_mean.shape[-1] + 1)
bins_center = angle_space[:-1] + np.diff(angle_space)[0] / 2
errors_targets = utils.wrap_angles(result_responses_all - result_target_all)
hist_targets_all = np.empty(
(M_space.size, sigmax_space.size, T_space_bays09_filt.size, angle_space.size - 1, nb_repetitions)
)
errors_nontargets = np.nan * np.empty(result_nontargets_all.shape)
hist_nontargets_all = np.empty(
(M_space.size, sigmax_space.size, T_space_bays09_filt.size, angle_space.size - 1, nb_repetitions)
)
for M_i, M in enumerate(M_space):
for sigmax_i, sigmax in enumerate(sigmax_space):
for T_bays_i, T_bays in enumerate(T_space_bays09_filt):
for repet_i in xrange(nb_repetitions):
# Could do a nicer indexing but f**k it
# Histogram errors to targets
hist_targets_all[M_i, sigmax_i, T_bays_i, :, repet_i], x, bins = utils.histogram_binspace(
utils.dropnan(errors_targets[M_i, sigmax_i, T_bays - 1, ..., repet_i]),
bins=angle_space,
norm="density",
)
# Compute the error between the responses and nontargets.
errors_nontargets[M_i, sigmax_i, T_bays - 1, :, :, repet_i] = utils.wrap_angles(
(
result_responses_all[M_i, sigmax_i, T_bays - 1, :, repet_i, np.newaxis]
- result_nontargets_all[M_i, sigmax_i, T_bays - 1, :, :, repet_i]
)
)
# Histogram it
hist_nontargets_all[M_i, sigmax_i, T_bays_i, :, repet_i], x, bins = utils.histogram_binspace(
utils.dropnan(errors_nontargets[M_i, sigmax_i, T_bays - 1, ..., repet_i]),
bins=angle_space,
norm="density",
)
hist_targets_mean = utils.nanmean(hist_targets_all, axis=-1).filled(np.nan)
hist_targets_std = utils.nanstd(hist_targets_all, axis=-1).filled(np.nan)
hist_nontargets_mean = utils.nanmean(hist_nontargets_all, axis=-1).filled(np.nan)
hist_nontargets_std = utils.nanstd(hist_nontargets_all, axis=-1).filled(np.nan)
# Compute distances to experimental histograms
dist_diff_hist_target_bays09 = np.nansum(
np.nansum((hist_targets_mean - bays09_hist_target_mean) ** 2.0, axis=-1), axis=-1
)
dist_diff_hist_nontargets_bays09 = np.nansum(
np.nansum((hist_nontargets_mean - bays09_hist_nontarget_mean) ** 2.0, axis=-1), axis=-1
)
dist_diff_hist_nontargets_5_6items_bays09 = np.nansum(
np.nansum((hist_nontargets_mean[:, :, -2:] - bays09_hist_nontarget_mean[-2:]) ** 2.0, axis=-1), axis=-1
)
if plot_pcolor_fit_precision_to_fisherinfo:
# Check fit between precision and Experiments
utils.pcolor_2d_data(
dist_diff_precision_experim,
log_scale=True,
x=M_space,
y=sigmax_space,
xlabel="M",
ylabel="sigmax",
xlabel_format="%d",
)
if savefigs:
dataio.save_current_figure("match_precision_exper_log_pcolor_{label}_{unique_id}.pdf")
utils.pcolor_2d_data(
dist_diff_emkappa_experim, x=M_space, y=sigmax_space, xlabel="M", ylabel="sigmax", xlabel_format="%d"
)
if savefigs:
dataio.save_current_figure("match_emkappa_model_exper_pcolor_{label}_{unique_id}.pdf")
utils.pcolor_2d_data(
dist_diff_em_mixtures_bays09,
x=M_space,
y=sigmax_space,
xlabel="M",
ylabel="sigmax",
log_scale=True,
xlabel_format="%d",
)
if savefigs:
dataio.save_current_figure("match_emmixtures_experbays09_log_pcolor_{label}_{unique_id}.pdf")
utils.pcolor_2d_data(
dist_diff_modelfits_experfits_bays09,
log_scale=True,
x=M_space,
y=sigmax_space,
xlabel="M",
ylabel="sigmax",
xlabel_format="%d",
)
if savefigs:
dataio.save_current_figure("match_diff_emfits_experbays09_pcolor_{label}_{unique_id}.pdf")
if do_error_distrib_fits:
utils.pcolor_2d_data(
dist_diff_hist_target_bays09,
x=M_space,
y=sigmax_space,
xlabel="M",
ylabel="sigmax",
log_scale=True,
xlabel_format="%d",
)
if savefigs:
dataio.save_current_figure("match_hist_targets_experbays09_log_pcolor_{label}_{unique_id}.pdf")
utils.pcolor_2d_data(
dist_diff_hist_nontargets_bays09,
x=M_space,
y=sigmax_space,
xlabel="M",
ylabel="sigmax",
log_scale=True,
xlabel_format="%d",
)
if savefigs:
dataio.save_current_figure("match_hist_nontargets_experbays09_log_pcolor_{label}_{unique_id}.pdf")
utils.pcolor_2d_data(
dist_diff_hist_nontargets_5_6items_bays09,
x=M_space,
y=sigmax_space,
xlabel="M",
ylabel="sigmax",
log_scale=True,
xlabel_format="%d",
)
if savefigs:
dataio.save_current_figure(
"match_hist_nontargets_6items_experbays09_log_pcolor_{label}_{unique_id}.pdf"
)
# Macro plot
def mem_plot_precision(sigmax_i, M_i, mem_exp_prec):
ax = utils.plot_mean_std_area(
T_space[: mem_exp_prec.size],
mem_exp_prec,
np.zeros(mem_exp_prec.size),
linewidth=3,
fmt="o-",
markersize=8,
label="Experimental data",
)
ax = utils.plot_mean_std_area(
T_space[: mem_exp_prec.size],
result_all_precisions_mean[M_i, sigmax_i, : mem_exp_prec.size],
result_all_precisions_std[M_i, sigmax_i, : mem_exp_prec.size],
ax_handle=ax,
linewidth=3,
fmt="o-",
markersize=8,
label="Precision of samples",
)
# ax = utils.plot_mean_std_area(T_space, 0.5*result_marginal_fi_mean[..., 0][M_i, sigmax_i], 0.5*result_marginal_fi_std[..., 0][M_i, sigmax_i], ax_handle=ax, linewidth=3, fmt='o-', markersize=8, label='Marginal Fisher Information')
# ax = utils.plot_mean_std_area(T_space, result_em_fits_mean[..., 0][M_i, sigmax_i], result_em_fits_std[..., 0][M_i, sigmax_i], ax_handle=ax, xlabel='Number of items', ylabel="Inverse variance $[rad^{-2}]$", linewidth=3, fmt='o-', markersize=8, label='Fitted kappa')
ax.set_title("M %d, sigmax %.2f" % (M_space[M_i], sigmax_space[sigmax_i]))
ax.legend()
ax.set_xlim([0.9, mem_exp_prec.size + 0.1])
ax.set_xticks(range(1, mem_exp_prec.size + 1))
ax.set_xticklabels(range(1, mem_exp_prec.size + 1))
if savefigs:
dataio.save_current_figure(
"memorycurves_precision_M%dsigmax%.2f_{label}_{unique_id}.pdf" % (M_space[M_i], sigmax_space[sigmax_i])
)
def mem_plot_kappa(sigmax_i, M_i, exp_kappa_mean, exp_kappa_std=None):
ax = utils.plot_mean_std_area(
T_space[: exp_kappa_mean.size],
exp_kappa_mean,
exp_kappa_std,
linewidth=3,
fmt="o-",
markersize=8,
label="Experimental data",
)
ax = utils.plot_mean_std_area(
T_space[: exp_kappa_mean.size],
result_em_fits_mean[..., : exp_kappa_mean.size, 0][M_i, sigmax_i],
result_em_fits_std[..., : exp_kappa_mean.size, 0][M_i, sigmax_i],
xlabel="Number of items",
ylabel="Memory error $[rad^{-2}]$",
linewidth=3,
fmt="o-",
markersize=8,
label="Fitted kappa",
ax_handle=ax,
)
# ax = utils.plot_mean_std_area(T_space, 0.5*result_marginal_fi_mean[..., 0][M_i, sigmax_i], 0.5*result_marginal_fi_std[..., 0][M_i, sigmax_i], ax_handle=ax, linewidth=3, fmt='o-', markersize=8, label='Marginal Fisher Information')
ax.set_title("M %d, sigmax %.2f" % (M_space[M_i], sigmax_space[sigmax_i]))
ax.legend()
ax.set_xlim([0.9, exp_kappa_mean.size + 0.1])
ax.set_xticks(range(1, exp_kappa_mean.size + 1))
ax.set_xticklabels(range(1, exp_kappa_mean.size + 1))
ax.get_figure().canvas.draw()
if savefigs:
dataio.save_current_figure(
"memorycurves_kappa_M%dsigmax%.2f_{label}_{unique_id}.pdf" % (M_space[M_i], sigmax_space[sigmax_i])
)
def em_plot(sigmax_i, M_i):
f, ax = plt.subplots()
ax2 = ax.twinx()
# left axis, kappa
ax = utils.plot_mean_std_area(
T_space,
result_em_fits_mean[..., 0][M_i, sigmax_i],
result_em_fits_std[..., 0][M_i, sigmax_i],
xlabel="Number of items",
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(
T_space,
result_em_fits_mean[..., 1][M_i, sigmax_i],
result_em_fits_std[..., 1][M_i, sigmax_i],
xlabel="Number of items",
ylabel="Mixture probabilities",
ax_handle=ax2,
linewidth=3,
fmt="o-",
markersize=8,
label="Target",
)
utils.plot_mean_std_area(
T_space,
result_em_fits_mean[..., 2][M_i, sigmax_i],
result_em_fits_std[..., 2][M_i, sigmax_i],
xlabel="Number of items",
ylabel="Mixture probabilities",
ax_handle=ax2,
linewidth=3,
fmt="o-",
markersize=8,
label="Nontarget",
)
utils.plot_mean_std_area(
T_space,
result_em_fits_mean[..., 3][M_i, sigmax_i],
result_em_fits_std[..., 3][M_i, sigmax_i],
xlabel="Number of items",
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)
ax.set_title("M %d, sigmax %.2f" % (M_space[M_i], sigmax_space[sigmax_i]))
ax.set_xlim([0.9, T_space.size])
ax.set_xticks(range(1, T_space.size + 1))
ax.set_xticklabels(range(1, T_space.size + 1))
f.canvas.draw()
if savefigs:
dataio.save_current_figure(
"memorycurves_emfits_M%dsigmax%.2f_{label}_{unique_id}.pdf" % (M_space[M_i], sigmax_space[sigmax_i])
)
def em_plot_paper(sigmax_i, M_i):
f, ax = plt.subplots()
# Right axis, mixture probabilities
utils.plot_mean_std_area(
T_space_bays09,
result_em_fits_mean[..., 1][M_i, sigmax_i][: T_space_bays09.size],
result_em_fits_std[..., 1][M_i, sigmax_i][: T_space_bays09.size],
xlabel="Number of items",
ylabel="Mixture probabilities",
ax_handle=ax,
linewidth=3,
fmt="o-",
markersize=5,
label="Target",
)
utils.plot_mean_std_area(
T_space_bays09,
result_em_fits_mean[..., 2][M_i, sigmax_i][: T_space_bays09.size],
result_em_fits_std[..., 2][M_i, sigmax_i][: T_space_bays09.size],
xlabel="Number of items",
ylabel="Mixture probabilities",
ax_handle=ax,
linewidth=3,
fmt="o-",
markersize=5,
label="Nontarget",
)
utils.plot_mean_std_area(
T_space_bays09,
result_em_fits_mean[..., 3][M_i, sigmax_i][: T_space_bays09.size],
result_em_fits_std[..., 3][M_i, sigmax_i][: T_space_bays09.size],
xlabel="Number of items",
ylabel="Mixture probabilities",
ax_handle=ax,
linewidth=3,
fmt="o-",
markersize=5,
label="Random",
)
ax.legend(prop={"size": 15})
ax.set_title("M %d, sigmax %.2f" % (M_space[M_i], sigmax_space[sigmax_i]))
ax.set_xlim([1.0, T_space_bays09.size])
ax.set_ylim([0.0, 1.1])
ax.set_xticks(range(1, T_space_bays09.size + 1))
ax.set_xticklabels(range(1, T_space_bays09.size + 1))
f.canvas.draw()
if savefigs:
dataio.save_current_figure(
"memorycurves_emfits_paper_M%dsigmax%.2f_{label}_{unique_id}.pdf"
% (M_space[M_i], sigmax_space[sigmax_i])
)
def hist_errors_targets_nontargets(hists_toplot_mean, hists_toplot_std, title="", M=0, sigmax=0, yaxis_lim="auto"):
f1, axes1 = plt.subplots(
ncols=hists_toplot_mean.shape[-2], figsize=(hists_toplot_mean.shape[-2] * 6, 6), sharey=True
)
for T_bays_i, T_bays in enumerate(T_space_bays09_filt):
if not np.all(np.isnan(hists_toplot_mean[T_bays_i])):
axes1[T_bays_i].bar(
bins_center,
hists_toplot_mean[T_bays_i],
width=2.0 * np.pi / (angle_space.size - 1),
align="center",
yerr=hists_toplot_std[T_bays_i],
)
axes1[T_bays_i].set_title("N=%d" % T_bays)
# axes1[T_{}]
axes1[T_bays_i].set_xlim(
[bins_center[0] - np.pi / (angle_space.size - 1), bins_center[-1] + np.pi / (angle_space.size - 1)]
)
if yaxis_lim == "target":
axes1[T_bays_i].set_ylim([0.0, 2.0])
elif yaxis_lim == "nontarget":
axes1[T_bays_i].set_ylim([0.0, 0.3])
else:
axes1[T_bays_i].set_ylim([0.0, np.nanmax(hists_toplot_mean + hists_toplot_std) * 1.1])
axes1[T_bays_i].set_xticks((-np.pi, -np.pi / 2, 0, np.pi / 2.0, np.pi))
axes1[T_bays_i].set_xticklabels(
(r"$-\pi$", r"$-\frac{\pi}{2}$", r"$0$", r"$\frac{\pi}{2}$", r"$\pi$"), fontsize=16
)
f1.canvas.draw()
if savefigs:
dataio.save_current_figure(
"memorycurves_hist_%s_paper_M%dsigmax%.2f_{label}_{unique_id}.pdf" % (title, M, sigmax)
)
#################################
if plot_selected_memory_curves:
selected_values = [[0.84, 0.23], [0.84, 0.19]]
for current_values in selected_values:
# Find the indices
M_i = np.argmin(np.abs(current_values[0] - M_space))
sigmax_i = np.argmin(np.abs(current_values[1] - sigmax_space))
mem_plot_precision(sigmax_i, M_i)
mem_plot_kappa(sigmax_i, M_i)
if plot_best_memory_curves:
# Best precision fit
best_axis2_i_all = np.argmin(dist_diff_precision_experim, axis=1)
for axis1_i, best_axis2_i in enumerate(best_axis2_i_all):
mem_plot_precision(best_axis2_i, axis1_i, gorgo11_experimental_precision)
# Best kappa fit
best_axis2_i_all = np.argmin(dist_diff_emkappa_experim, axis=1)
for axis1_i, best_axis2_i in enumerate(best_axis2_i_all):
mem_plot_kappa(
best_axis2_i, axis1_i, gorgo11_experimental_emfits_mean[0], gorgo11_experimental_emfits_std[0]
)
# em_plot(best_axis2_i, axis1_i)
# Best em parameters fit to Bays09
best_axis2_i_all = np.argmin(dist_diff_modelfits_experfits_bays09, axis=1)
# best_axis2_i_all = np.argmin(dist_diff_em_mixtures_bays09, axis=1)
for axis1_i, best_axis2_i in enumerate(best_axis2_i_all):
mem_plot_kappa(
best_axis2_i,
axis1_i,
bays09_experimental_mixtures_mean_compatible[0, : T_space_bays09.size],
bays09_experimental_mixtures_std_compatible[0, : T_space_bays09.size],
)
# em_plot(best_axis2_i, axis1_i)
em_plot_paper(best_axis2_i, axis1_i)
if plot_best_error_distrib and do_error_distrib_fits:
# Best target histograms
best_axis2_i_all = np.argmin(dist_diff_hist_target_bays09, axis=1)
for axis1_i, best_axis2_i in enumerate(best_axis2_i_all):
hist_errors_targets_nontargets(
hist_targets_mean[axis1_i, best_axis2_i],
hist_targets_std[axis1_i, best_axis2_i],
"target",
M=M_space[axis1_i],
sigmax=sigmax_space[best_axis2_i],
yaxis_lim="target",
)
# Best nontarget histograms
best_axis2_i_all = np.argmin(dist_diff_hist_nontargets_bays09, axis=1)
for axis1_i, best_axis2_i in enumerate(best_axis2_i_all):
hist_errors_targets_nontargets(
hist_nontargets_mean[axis1_i, best_axis2_i],
hist_nontargets_std[axis1_i, best_axis2_i],
"nontarget",
M=M_space[axis1_i],
sigmax=sigmax_space[best_axis2_i],
yaxis_lim="nontarget",
)
all_args = data_pbs.loaded_data["args_list"]
variables_to_save = [
"gorgo11_experimental_precision",
"gorgo11_experimental_kappa",
"bays09_experimental_mixtures_mean_compatible",
"T_space",
]
if savedata:
dataio.save_variables_default(locals(), variables_to_save)
dataio.make_link_output_to_dropbox(dropbox_current_experiment_folder="memory_curves")
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_errors_distribution(data_pbs, generator_module=None):
'''
Reload responses
Plot errors distributions.
'''
#### SETUP
#
savefigs = True
savedata = True
plot_persigmax = True
do_best_nontarget = False
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
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 plot_persigmax:
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.empty(result_nontargets_all[sigmax_i].shape)
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]
for T_i, T in enumerate(T_space):
print "T: ", T
# Now, per T items, show the distribution of errors and of errors to non target
# Error to target
utils.hist_samples_density_estimation(utils.dropnan(errors_targets[T_i]), bins=angle_space, title='Errors between response and target, N=%d' % (T))
if savefigs:
dataio.save_current_figure('error_target_hist_sigmax%.2f_T%d_{label}_{unique_id}.pdf' % (sigmax, T))
if T > 1:
# Error to nontarget
ax_handle = utils.hist_samples_density_estimation(utils.dropnan(errors_nontargets[T_i, :, :T_i]), bins=angle_space, title='Errors between response and non targets, N=%d' % (T))
result_pval_vtest_nontargets[sigmax, T_i] = utils.V_test(utils.dropnan(errors_nontargets[T_i, :, :T_i]))['pvalue']
print result_pval_vtest_nontargets[sigmax, T_i]
ax_handle.text(0.02, 0.97, "Vtest pval: %.2f" % (result_pval_vtest_nontargets[sigmax, T_i]), transform=ax_handle.transAxes, horizontalalignment='left', fontsize=12)
if savefigs:
dataio.save_current_figure('error_nontargets_hist_sigmax%.2f_T%d_{label}_{unique_id}.pdf' % (sigmax, T))
# Error to best non target
if do_best_nontarget:
utils.hist_samples_density_estimation(utils.dropnan(errors_best_nontarget[T_i]), bins=angle_space, title='Errors between response and best non target, N=%d' % (T))
if savefigs:
dataio.save_current_figure('error_bestnontarget_hist_sigmax%.2f_T%d_{label}_{unique_id}.pdf' % (sigmax, T))
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()
def compute_bootstrap_samples(dataset, nb_bootstrap_samples, angle_space):
responses_resampled = np.empty(
(np.unique(dataset['n_items']).size,
nb_bootstrap_samples),
dtype=np.object)
error_nontargets_resampled = np.empty(
(np.unique(dataset['n_items']).size,
nb_bootstrap_samples),
dtype=np.object)
error_targets_resampled = np.empty(
(np.unique(dataset['n_items']).size,
nb_bootstrap_samples),
dtype=np.object)
hist_cnts_nontarget_bootstraps_nitems = np.empty(
(np.unique(dataset['n_items']).size,
nb_bootstrap_samples,
angle_space.size - 1))*np.nan
hist_cnts_target_bootstraps_nitems = np.empty(
(np.unique(dataset['n_items']).size,
nb_bootstrap_samples,
angle_space.size - 1))*np.nan
bootstrap_data = {
'responses_resampled': responses_resampled,
'error_nontargets_resampled': error_nontargets_resampled,
'error_targets_resampled': error_targets_resampled,
'hist_cnts_nontarget_bootstraps_nitems': hist_cnts_nontarget_bootstraps_nitems,
'hist_cnts_target_bootstraps_nitems': hist_cnts_target_bootstraps_nitems,
}
for n_items_i, n_items in enumerate(np.unique(dataset['n_items'])):
# Data collapsed accross subjects
ids_filtered = (dataset['n_items'] == n_items).flatten()
if n_items > 1:
# Get random bootstrap nontargets
bootstrap_nontargets = utils.sample_angle(
dataset['item_angle'][ids_filtered, 1:n_items].shape + (nb_bootstrap_samples, ))
# Compute associated EM fits
# bootstrap_results = []
for bootstrap_i in progress.ProgressDisplay(np.arange(nb_bootstrap_samples), display=progress.SINGLE_LINE):
em_fit = em_circularmixture.fit(
dataset['response'][ids_filtered, 0],
dataset['item_angle'][ids_filtered, 0],
bootstrap_nontargets[..., bootstrap_i])
# bootstrap_results.append(em_fit)
# Get EM samples
responses_resampled[n_items_i, bootstrap_i] = (
em_circularmixture.sample_from_fit(
em_fit,
dataset['item_angle'][ids_filtered, 0],
bootstrap_nontargets[..., bootstrap_i]))
# Compute the errors
error_nontargets_resampled[n_items_i, bootstrap_i] = (
utils.wrap_angles(
responses_resampled[n_items_i, bootstrap_i][:, np.newaxis] - bootstrap_nontargets[..., bootstrap_i]))
error_targets_resampled[n_items_i, bootstrap_i] = (
utils.wrap_angles(
responses_resampled[n_items_i, bootstrap_i] - dataset['item_angle'][ids_filtered, 0]))
# Bin everything
(hist_cnts_nontarget_bootstraps_nitems[n_items_i, bootstrap_i],
_, _) = (
utils.histogram_binspace(
utils.dropnan(
error_nontargets_resampled[n_items_i, bootstrap_i]),
bins=angle_space,
norm='density'))
(hist_cnts_target_bootstraps_nitems[n_items_i, bootstrap_i],
_, _) = (
utils.histogram_binspace(
utils.dropnan(
error_targets_resampled[n_items_i, bootstrap_i]),
bins=angle_space,
norm='density'))
return bootstrap_data
def enforce_distance(theta1, theta2, min_distance=0.1):
return np.abs(utils.wrap_angles(theta1 - theta2)) > min_distance
def plot_bootstrap_randomsamples():
'''
Do histograms with random samples from bootstrap nontarget estimates
'''
dataio = DataIO(label='plotpaper_bootstrap_randomized')
nb_bootstrap_samples = 200
use_precomputed = True
angle_space = np.linspace(-np.pi, np.pi, 51)
bins_center = angle_space[:-1] + np.diff(angle_space)[0]/2
data_bays2009 = load_experimental_data.load_data_bays09(fit_mixture_model=True)
## Super long simulation, use precomputed data maybe?
if use_precomputed:
data = pickle.load(open('/Users/loicmatthey/Dropbox/UCL/1-phd/Work/Visual_working_memory/code/git-bayesian-visual-working-memory/Data/cache_randomized_bootstrap_samples_plots_paper_theo_plotbootstrapsamples/bootstrap_histo_katz.npy', 'r'))
responses_resampled = data['responses_resampled']
error_nontargets_resampled = data['error_nontargets_resampled']
error_targets_resampled = data['error_targets_resampled']
hist_cnts_nontarget_bootstraps_nitems = data['hist_cnts_nontarget_bootstraps_nitems']
hist_cnts_target_bootstraps_nitems = data['hist_cnts_target_bootstraps_nitems']
else:
responses_resampled = np.empty((np.unique(data_bays2009['n_items']).size, nb_bootstrap_samples), dtype=np.object)
error_nontargets_resampled = np.empty((np.unique(data_bays2009['n_items']).size, nb_bootstrap_samples), dtype=np.object)
error_targets_resampled = np.empty((np.unique(data_bays2009['n_items']).size, nb_bootstrap_samples), dtype=np.object)
hist_cnts_nontarget_bootstraps_nitems = np.empty((np.unique(data_bays2009['n_items']).size, nb_bootstrap_samples, angle_space.size - 1))*np.nan
hist_cnts_target_bootstraps_nitems = np.empty((np.unique(data_bays2009['n_items']).size, nb_bootstrap_samples, angle_space.size - 1))*np.nan
for n_items_i, n_items in enumerate(np.unique(data_bays2009['n_items'])):
# Data collapsed accross subjects
ids_filtered = (data_bays2009['n_items'] == n_items).flatten()
if n_items > 1:
# Get random bootstrap nontargets
bootstrap_nontargets = utils.sample_angle(data_bays2009['item_angle'][ids_filtered, 1:n_items].shape + (nb_bootstrap_samples, ))
# Compute associated EM fits
bootstrap_results = []
for bootstrap_i in progress.ProgressDisplay(np.arange(nb_bootstrap_samples), display=progress.SINGLE_LINE):
em_fit = em_circularmixture_allitems_uniquekappa.fit(data_bays2009['response'][ids_filtered, 0], data_bays2009['item_angle'][ids_filtered, 0], bootstrap_nontargets[..., bootstrap_i])
bootstrap_results.append(em_fit)
# Get EM samples
responses_resampled[n_items_i, bootstrap_i] = em_circularmixture_allitems_uniquekappa.sample_from_fit(em_fit, data_bays2009['item_angle'][ids_filtered, 0], bootstrap_nontargets[..., bootstrap_i])
# Compute the errors
error_nontargets_resampled[n_items_i, bootstrap_i] = utils.wrap_angles(responses_resampled[n_items_i, bootstrap_i][:, np.newaxis] - bootstrap_nontargets[..., bootstrap_i])
error_targets_resampled[n_items_i, bootstrap_i] = utils.wrap_angles(responses_resampled[n_items_i, bootstrap_i] - data_bays2009['item_angle'][ids_filtered, 0])
# Bin everything
hist_cnts_nontarget_bootstraps_nitems[n_items_i, bootstrap_i], x, bins = utils.histogram_binspace(utils.dropnan(error_nontargets_resampled[n_items_i, bootstrap_i]), bins=angle_space, norm='density')
hist_cnts_target_bootstraps_nitems[n_items_i, bootstrap_i], x, bins = utils.histogram_binspace(utils.dropnan(error_targets_resampled[n_items_i, bootstrap_i]), bins=angle_space, norm='density')
# Now show average histogram
hist_cnts_target_bootstraps_nitems_mean = np.mean(hist_cnts_target_bootstraps_nitems, axis=-2)
hist_cnts_target_bootstraps_nitems_std = np.std(hist_cnts_target_bootstraps_nitems, axis=-2)
hist_cnts_target_bootstraps_nitems_sem = hist_cnts_target_bootstraps_nitems_std/np.sqrt(hist_cnts_target_bootstraps_nitems.shape[1])
hist_cnts_nontarget_bootstraps_nitems_mean = np.mean(hist_cnts_nontarget_bootstraps_nitems, axis=-2)
hist_cnts_nontarget_bootstraps_nitems_std = np.std(hist_cnts_nontarget_bootstraps_nitems, axis=-2)
hist_cnts_nontarget_bootstraps_nitems_sem = hist_cnts_nontarget_bootstraps_nitems_std/np.sqrt(hist_cnts_target_bootstraps_nitems.shape[1])
f1, axes1 = plt.subplots(ncols=np.unique(data_bays2009['n_items']).size-1, figsize=((np.unique(data_bays2009['n_items']).size-1)*6, 6), sharey=True)
for n_items_i, n_items in enumerate(np.unique(data_bays2009['n_items'])):
if n_items>1:
utils.plot_mean_std_area(bins_center, hist_cnts_nontarget_bootstraps_nitems_mean[n_items_i], hist_cnts_nontarget_bootstraps_nitems_sem[n_items_i], ax_handle=axes1[n_items_i-1], color='k')
# Now add the Data histograms
axes1[n_items_i-1].bar(bins_center, data_bays2009['hist_cnts_nontarget_nitems_stats']['mean'][n_items_i], width=2.*np.pi/(angle_space.size-1), align='center', yerr=data_bays2009['hist_cnts_nontarget_nitems_stats']['sem'][n_items_i])
# axes4[n_items_i-1].set_title('N=%d' % n_items)
axes1[n_items_i-1].set_xlim([bins_center[0]-np.pi/(angle_space.size-1), bins_center[-1]+np.pi/(angle_space.size-1)])
# axes3[n_items_i-1].set_ylim([0., 2.0])
axes1[n_items_i-1].set_xticks((-np.pi, -np.pi/2, 0, np.pi/2., np.pi))
axes1[n_items_i-1].set_xticklabels((r'$-\pi$', r'$-\frac{\pi}{2}$', r'$0$', r'$\frac{\pi}{2}$', r'$\pi$'), fontsize=16)
# axes1[n_items_i-1].bar(bins_center, hist_cnts_nontarget_bootstraps_nitems_mean[n_items_i], width=2.*np.pi/(angle_space.size-1), align='center', yerr=hist_cnts_nontarget_bootstraps_nitems_std[n_items_i])
axes1[n_items_i-1].get_figure().canvas.draw()
if dataio is not None:
plt.tight_layout()
dataio.save_current_figure("hist_error_nontarget_persubj_{label}_{unique_id}.pdf")
if False:
f2, axes2 = plt.subplots(ncols=np.unique(data_bays2009['n_items']).size-1, figsize=((np.unique(data_bays2009['n_items']).size-1)*6, 6), sharey=True)
for n_items_i, n_items in enumerate(np.unique(data_bays2009['n_items'])):
utils.plot_mean_std_area(bins_center, hist_cnts_target_bootstraps_nitems_mean[n_items_i], hist_cnts_target_bootstraps_nitems_std[n_items_i], ax_handle=axes2[n_items_i-1])
# axes2[n_items_i-1].bar(bins_center, hist_cnts_target_bootstraps_nitems_mean[n_items_i], width=2.*np.pi/(angle_space.size-1), align='center', yerr=hist_cnts_target_bootstraps_nitems_std[n_items_i])
return locals()
