def target(self, file_name):
""" Display sampled points (noisy), read from file the input/target
pairs and draw the resulting points.
:param file_name - str, name of the file with the data.
"""
x, t, e = DataIO.read_data(file_name)
self.AX1.plot(x,
t,
marker='o',
markersize=7,
linestyle='none',
color=self.CLR_DOT,
zorder=2)
def download_data(self, pair, start, end):
"""Download trade data and store as .csv file.
Args:
pair (str): Currency pair.
start (int): Start UNIX of trade data to download.
end (int): End UNIX of trade data to download.
"""
dataio = DataIO(savedir=self._savedir, fieldnames=self.FIELDNAMES)
if dataio.csv_check(pair):
last_row = dataio.csv_get_last(pair)
newest_id = int(last_row['trade_id']) + 1
newest_t = int(last_row['time'])
else:
newest_id = self.__find_start_trade_id(pair, start)
newest_t = 0
while newest_t < end:
# new -> old
r = self.__get_slice(pair, newest_id)
# old -> new, add unix timestamp
new_r = []
for row in r:
row['time'] = row['T'] // 1000
row['date'] = timeutil.unix_to_iso(row['time'])
row['price'] = row['p']
row['size'] = row['q']
row['side'] = 'sell' if row['m'] == True else 'buy'
row['best_price_match'] = row['M']
row['trade_id'] = row['a']
row.pop('a', None)
row.pop('p', None)
row.pop('q', None)
row.pop('f', None)
row.pop('l', None)
row.pop('T', None)
row.pop('m', None)
row.pop('M', None)
new_r.append(row)
# save to file
dataio.csv_append(pair, new_r)
# break condition
if len(r) < self.__MAX_LIMIT:
break
# prepare next iteration
newest_id = new_r[-1]['trade_id'] + 1
newest_t = new_r[-1]['time']
print('Binance\t| {} : {}'.format(timeutil.unix_to_iso(newest_t),
pair))
print('Binance\t| Download complete : {}'.format(pair))
def download_data(self, pair, start, end):
"""Download trade data and store as .csv file.
Args:
pair (str): Currency pair.
start (int): Start UNIX of trade data to download.
end (int): End UNIX of trade data to download.
"""
dataio = DataIO(savedir=self._savedir, fieldnames=self.FIELDNAMES)
if dataio.csv_check(pair):
last_row = dataio.csv_get_last(pair)
newest_id = int(last_row['trade_id']) + 1
newest_t = int(last_row['time'])
else:
newest_id = self.__find_start_trade_id(pair, start)
newest_t = 0
last_trade_id = self.__find_last_trade_id(pair)
while newest_t < end:
# new -> old
r = self.__get_slice(pair, newest_id + self.__MAX_LIMIT)
# break condition
to_break = False
# old -> new, add unix timestamp
new_r = []
for row in reversed(r):
if row['trade_id'] > newest_id:
row['date'] = row['time']
row['time'] = timeutil.iso_to_unix(row['time'])
new_r.append(row)
if row['trade_id'] == last_trade_id:
to_break = True
# save to file
dataio.csv_append(pair, new_r)
# break condition
if to_break:
break
# prepare next iteration
newest_id = new_r[-1]['trade_id']
newest_t = new_r[-1]['time']
print('GDAX\t| {} : {}'.format(timeutil.unix_to_iso(newest_t),
pair))
print('GDAX\t| Download complete : {}'.format(pair))
def download_data(self, pair, start, end):
"""Download trade data and store as .csv file.
Args:
pair (str): Currency pair.
start (int): Start UNIX of trade data to download.
end (int): End UNIX of trade data to download.
"""
dataio = DataIO(savedir=self._savedir, fieldnames=self.FIELDNAMES)
if dataio.csv_check(pair):
last_row = dataio.csv_get_last(pair)
newest_id = int(last_row['trade_id']) + 1
newest_t = int(last_row['time'])
else:
newest_id = self.__find_start_trade_id(pair, start)
newest_t = 0
while newest_t < end:
# new -> old
r = self.__get_slice(pair, newest_id)
# old -> new, add unix timestamp
new_r = []
for i, row in enumerate(r):
row['time'] = timeutil.iso_to_unix(row['timestamp'])
row['date'] = row['timestamp']
row['trade_id'] = newest_id + i
row['side'] = row['side'].lower()
row.pop('timestamp', None)
row.pop('symbol', None)
new_r.append(row)
# save to file
dataio.csv_append(pair, new_r)
# break condition
if len(r) < self.__MAX_LIMIT:
break
# prepare next iteration
newest_id = new_r[-1]['trade_id'] + 1
newest_t = new_r[-1]['time']
print('Bitmex\t| {} : {}'.format(
timeutil.unix_to_iso(newest_t), pair))
print('Bitmex\t| Download complete : {}'.format(pair))
def download_data(self, pair, start, end):
"""Download trade data and store as .csv file.
Args:
pair (str): Currency pair.
start (int): Start UNIX of trade data to download.
end (int): End UNIX of trade data to download.
"""
dataio = DataIO(savedir=self._savedir, fieldnames=self.FIELDNAMES)
last_row = None
if dataio.csv_check(pair):
last_row = dataio.csv_get_last(pair)
newest_t = int(last_row['time'])
else:
newest_t = self.__find_start_trade_time(pair, start) - 1
# break condition
last_trade_time = self.__find_last_trade_time(pair)
while newest_t < end:
# new -> old
r = self.__get_slice(pair, newest_t)
# old -> new; remove duplicate data by trade ID
new_r = []
for row in reversed(r):
if last_row is not None:
if int(last_row['tradeID']) >= row['tradeID']:
continue # remove duplicates
last_row = row
row['time'] = timeutil.iso_to_unix(row['date'])
new_r.append(row)
if newest_t > last_trade_time:
break
# save to file
dataio.csv_append(pair, new_r)
# prepare next iteration
newest_t += self.__MAX_RANGE
print('Poloniex| {} : {}'.format(
timeutil.unix_to_iso(newest_t), pair))
print('Poloniex| Download complete : {}'.format(pair))
def data_preprocess(params):
### Record Concatenation
dataio = DataIO(params['input_path'], params['map_path'], params['domain'])
dataio.read_data()
dataio.read_label()
ctn = Concatenation(dataio, params['domain'])
patient_info, n_feature, feature_list, feature_range = ctn.get_concatenation()
# patient id: Patient
# static feature and dynamic feature
# dynamic feature{time:feature_value}
### Data Imputation
imp_method = 'simple'
imp = Imputation(patient_info, n_feature)
patient_array, patient_time = imp.get_imputation(imp_method)
### Clinical Data with DTI Generation
cli = CliGen(feature_list, feature_range, ctn.dti_time)
subject_array = cli.get_data(patient_array, patient_time, params['time'])
if True == params['binary']: # only works for discrete clinical features
subject_array = cli.get_binarization()
subject_label = cli.get_label(patient_info, params['labels'], params['time'])
return subject_array, subject_label
def plots_fitmixtmodel_rcscale_effect(data_pbs, generator_module=None):
'''
Reload runs from PBS
'''
#### SETUP
#
savefigs = True
savedata = True
plots_all_T = True
plots_per_T = True
# do_relaunch_bestparams_pbs = True
colormap = None # or 'cubehelix'
plt.rcParams['font.size'] = 16
#
#### /SETUP
print "Order parameters: ", data_pbs.dataset_infos['parameters']
# parameters: M, ratio_conj, sigmax
# Extract data
T_space = data_pbs.loaded_data['datasets_list'][0]['T_space']
result_em_fits_flat = np.array(data_pbs.dict_arrays['result_em_fits']['results_flat'])
result_precisions_flat = np.array(data_pbs.dict_arrays['result_all_precisions']['results_flat'])
result_dist_bays09_flat = np.array(data_pbs.dict_arrays['result_dist_bays09']['results_flat'])
result_dist_gorgo11_flat = np.array(data_pbs.dict_arrays['result_dist_gorgo11']['results_flat'])
result_dist_bays09_emmixt_KL = np.array(data_pbs.dict_arrays['result_dist_bays09_emmixt_KL']['results_flat'])
result_dist_gorgo11_emmixt_KL = np.array(data_pbs.dict_arrays['result_dist_gorgo11_emmixt_KL']['results_flat'])
result_parameters_flat = np.array(data_pbs.dict_arrays['result_em_fits']['parameters_flat'])
rc_scale_space = data_pbs.loaded_data['parameters_uniques']['rc_scale']
num_repetitions = generator_module.num_repetitions
parameter_names_sorted = data_pbs.dataset_infos['parameters']
dataio = DataIO(output_folder=generator_module.pbs_submission_infos['simul_out_dir'] + '/outputs/', label='global_' + dataset_infos['save_output_filename'])
# Load bays09
data_bays09 = load_experimental_data.load_data_bays09(fit_mixture_model=True)
bays09_nitems = data_bays09['data_to_fit']['n_items']
bays09_em_target = np.nan*np.empty((bays09_nitems.max(), 4)) #kappa, prob_target, prob_nontarget, prob_random
bays09_em_target[bays09_nitems - 1] = data_bays09['em_fits_nitems_arrays']['mean'].T
bays09_emmixt_target = bays09_em_target[:, 1:]
## Compute some stuff
result_parameters_flat = result_parameters_flat.flatten()
result_em_fits_all_avg = utils.nanmean(result_em_fits_flat, axis=-1)
result_em_kappa_allT = result_em_fits_all_avg[..., 0]
result_em_emmixt_allT = result_em_fits_all_avg[..., 1:4]
result_precisions_all_avg = utils.nanmean(result_precisions_flat, axis=-1)
# Square distance to kappa
result_dist_bays09_allT_avg = utils.nanmean(result_dist_bays09_flat, axis=-1)
result_dist_bays09_emmixt_KL_allT_avg = utils.nanmean(result_dist_bays09_emmixt_KL, axis=-1)
result_dist_bays09_kappa_allT = result_dist_bays09_allT_avg[..., 0]
# result_dist_bays09_allT_avg = utils.nanmean((result_em_fits_flat[:, :, :4] - bays09_em_target[np.newaxis, :, :, np.newaxis])**2, axis=-1)
# result_dist_bays09_kappa_sum = np.nansum(result_dist_bays09_allT_avg[:, :, 0], axis=-1)
# result_dist_bays09_kappa_T1_sum = result_dist_bays09_allT_avg[:, 0, 0]
# result_dist_bays09_kappa_T25_sum = np.nansum(result_dist_bays09_allT_avg[:, 1:, 0], axis=-1)
# # Square and KL distance for EM Mixtures
# result_dist_bays09_emmixt_sum = np.nansum(np.nansum(result_dist_bays09_allT_avg[:, :, 1:], axis=-1), axis=-1)
# result_dist_bays09_emmixt_T1_sum = np.nansum(result_dist_bays09_allT_avg[:, 0, 1:], axis=-1)
# result_dist_bays09_emmixt_T25_sum = np.nansum(np.nansum(result_dist_bays09_allT_avg[:, 1:, 1:], axis=-1), axis=-1)
# result_dist_bays09_emmixt_KL = utils.nanmean(utils.KL_div(result_em_fits_flat[:, :, 1:4], bays09_emmixt_target[np.newaxis, :, :, np.newaxis], axis=-2), axis=-1) # KL over dimension of mixtures, then mean over repetitions
# result_dist_bays09_emmixt_KL_sum = np.nansum(result_dist_bays09_emmixt_KL, axis=-1) # sum over T
# result_dist_bays09_emmixt_KL_T1_sum = result_dist_bays09_emmixt_KL[:, 0]
# result_dist_bays09_emmixt_KL_T25_sum = np.nansum(result_dist_bays09_emmixt_KL[:, 1:], axis=-1)
# result_dist_bays09_both_normalised = result_dist_bays09_emmixt_sum/np.max(result_dist_bays09_emmixt_sum) + result_dist_bays09_kappa_sum/np.max(result_dist_bays09_kappa_sum)
# # Mask kappa for performance too bad
# result_dist_bays09_kappa_sum_masked = np.ma.masked_greater(result_dist_bays09_kappa_sum, 2*np.median(result_dist_bays09_kappa_sum))
# result_dist_bays09_emmixt_KL_sum_masked = np.ma.masked_greater(result_dist_bays09_emmixt_KL_sum, 2*np.median(result_dist_bays09_emmixt_KL_sum))
# result_dist_bays09_both_normalised_mult_masked = 1-(1. - result_dist_bays09_emmixt_KL_sum/np.max(result_dist_bays09_emmixt_KL_sum))*(1. - result_dist_bays09_kappa_sum_masked/np.max(result_dist_bays09_kappa_sum_masked))
# Compute optimal rc_scale
all_args = data_pbs.loaded_data['args_list']
specific_arg = all_args[0]
specific_arg['autoset_parameters'] = True
(_, _, _, sampler) = launchers.init_everything(specific_arg)
optimal_rc_scale = sampler.random_network.rc_scale[0]
if plots_all_T:
# Show Kappa evolution wrt rc_scale
f, ax = plt.subplots()
# utils.plot_mean_std_from_samples(result_parameters_flat, np.nansum(result_em_kappa_allT, axis=-1), bins=60, bins_y=150, xlabel='rc_scale', ylabel='EM kappa', title='Kappa, summed T', ax_handle=ax, show_scatter=False)
utils.plot_mean_std_from_samples_rolling(result_parameters_flat, np.nansum(result_em_kappa_allT, axis=-1), window=35, xlabel='rc_scale', ylabel='EM kappa', title='Kappa, summed T', ax_handle=ax, show_scatter=False)
ax.axvline(x=optimal_rc_scale, color='g', linewidth=2)
ax.axvline(x=2*optimal_rc_scale, color='r', linewidth=2)
f.canvas.draw()
if savefigs:
dataio.save_current_figure('rcscaleeffect_kappa_summedT_{label}_{unique_id}.pdf')
# Show Mixt proportions
f, ax = plt.subplots()
for i in xrange(3):
# utils.plot_mean_std_from_samples(result_parameters_flat, np.nansum(result_em_emmixt_allT[..., i], axis=-1), bins=60, bins_y=100, xlabel='rc_scale', ylabel='EM mixt proportions', title='EM mixtures, summed T', ax_handle=ax, show_scatter=False)
utils.plot_mean_std_from_samples_rolling(result_parameters_flat, np.nansum(result_em_emmixt_allT[..., i], axis=-1), window=35, xlabel='rc_scale', ylabel='EM mixt proportions', title='EM mixtures, summed T', ax_handle=ax, show_scatter=False)
ax.axvline(x=optimal_rc_scale, color='g', linewidth=2)
ax.axvline(x=2*optimal_rc_scale, color='r', linewidth=2)
f.canvas.draw()
if savefigs:
dataio.save_current_figure('rcscaleeffect_mixtprop_summedT_{label}_{unique_id}.pdf')
# Show Precision
f, ax = plt.subplots()
# utils.plot_mean_std_from_samples(result_parameters_flat, np.nansum(result_precisions_all_avg, axis=-1), bins=60, bins_y=150, xlabel='rc_scale', ylabel='Precision', title='Precision, summed T', ax_handle=ax, show_scatter=False)
utils.plot_mean_std_from_samples_rolling(result_parameters_flat, np.nansum(result_precisions_all_avg, axis=-1), window=35, xlabel='rc_scale', ylabel='Precision', title='Precision, summed T', ax_handle=ax, show_scatter=False)
ax.axvline(x=optimal_rc_scale, color='g', linewidth=2)
ax.axvline(x=2*optimal_rc_scale, color='r', linewidth=2)
f.canvas.draw()
if savefigs:
dataio.save_current_figure('rcscaleeffect_precision_summedT_{label}_{unique_id}.pdf')
plt.close('all')
if plots_per_T:
for T_i, T in enumerate(T_space):
# Show Kappa evolution wrt rc_scale
f, ax = plt.subplots()
# utils.plot_mean_std_from_samples(result_parameters_flat, result_em_kappa_allT[:, T_i], bins=40, bins_y=100, xlabel='rc_scale', ylabel='EM kappa', title='Kappa, T %d' % T, ax_handle=ax, show_scatter=False)
utils.plot_mean_std_from_samples_rolling(result_parameters_flat, result_em_kappa_allT[:, T_i], window=35, xlabel='rc_scale', ylabel='EM kappa', title='Kappa, T %d' % T, ax_handle=ax, show_scatter=False)
ax.axvline(x=optimal_rc_scale, color='g', linewidth=2)
ax.axvline(x=2*optimal_rc_scale, color='r', linewidth=2)
f.canvas.draw()
if savefigs:
dataio.save_current_figure('rcscaleeffect_kappa_T%d_{label}_{unique_id}.pdf' % T)
# Show Mixt proportions
f, ax = plt.subplots()
for i in xrange(3):
# utils.plot_mean_std_from_samples(result_parameters_flat, result_em_emmixt_allT[:, T_i, i], bins=40, bins_y=100, xlabel='rc_scale', ylabel='EM mixt proportions', title='EM mixtures, T %d' % T, ax_handle=ax, show_scatter=False)
utils.plot_mean_std_from_samples_rolling(result_parameters_flat, result_em_emmixt_allT[:, T_i, i], window=35, xlabel='rc_scale', ylabel='EM mixt proportions', title='EM mixtures, T %d' % T, ax_handle=ax, show_scatter=False)
ax.axvline(x=optimal_rc_scale, color='g', linewidth=2)
ax.axvline(x=2*optimal_rc_scale, color='r', linewidth=2)
f.canvas.draw()
if savefigs:
dataio.save_current_figure('rcscaleeffect_mixtprop_T%d_{label}_{unique_id}.pdf' % T)
# Show Precision
f, ax = plt.subplots()
# utils.plot_mean_std_from_samples(result_parameters_flat, result_precisions_all_avg[:, T_i], bins=40, bins_y=100, xlabel='rc_scale', ylabel='Precision', title='Precision, T %d' % T, ax_handle=ax, show_scatter=False)
utils.plot_mean_std_from_samples_rolling(result_parameters_flat, result_precisions_all_avg[:, T_i], window=35, xlabel='rc_scale', ylabel='Precision', title='Precision, T %d' % T, ax_handle=ax, show_scatter=False)
ax.axvline(x=optimal_rc_scale, color='g', linewidth=2)
ax.axvline(x=2*optimal_rc_scale, color='r', linewidth=2)
f.canvas.draw()
if savefigs:
dataio.save_current_figure('rcscaleeffect_precision_T%d_{label}_{unique_id}.pdf' % T)
plt.close('all')
# # Interpolate
# if plots_interpolate:
# sigmax_target = 0.9
# M_interp_space = np.arange(6, 625, 5)
# ratio_interp_space = np.linspace(0.01, 1.0, 50)
# # sigmax_interp_space = np.linspace(0.01, 1.0, 50)
# sigmax_interp_space = np.array([sigmax_target])
# params_crossspace = np.array(utils.cross(M_interp_space, ratio_interp_space, sigmax_interp_space))
# interpolated_data = rbf_interpolator(params_crossspace[:, 0], params_crossspace[:, 1], params_crossspace[:, 2]).reshape((M_interp_space.size, ratio_interp_space.size))
# utils.pcolor_2d_data(interpolated_data, M_interp_space, ratio_interp_space, 'M', 'ratio', 'interpolated, fixing sigmax= %.2f' % sigmax_target)
# points_closeby = ((result_parameters_flat[:, 2] - sigmax_target)**2)< 0.01
# plt.figure()
# # plt.imshow(interpolated_data, extent=(M_interp_space.min(), M_interp_space.max(), ratio_interp_space.min(), ratio_interp_space.max()))
# plt.imshow(interpolated_data)
# plt.scatter(result_parameters_flat[points_closeby, 0], result_parameters_flat[points_closeby, 1], s=100, c=result_fitexperiments_bic_avg[points_closeby], marker='o')
# if plot_per_ratio:
# # Plot the evolution of loglike as a function of sigmax, with std shown
# for ratio_conj_i, ratio_conj in enumerate(ratio_space):
# ax = utils.plot_mean_std_area(sigmax_space, result_log_posterior_mean[ratio_conj_i], result_log_posterior_std[ratio_conj_i])
# ax.get_figure().canvas.draw()
# if savefigs:
# dataio.save_current_figure('results_fitexp_%s_loglike_ratioconj%.2f_{label}_global_{unique_id}.pdf' % (exp_dataset, ratio_conj))
all_args = data_pbs.loaded_data['args_list']
variables_to_save = ['parameter_names_sorted']
if savedata:
dataio.save_variables_default(locals(), variables_to_save)
dataio.make_link_output_to_dropbox(dropbox_current_experiment_folder='rcscale_characterisation')
plt.show()
return locals()
def plots_fit_mixturemodels_random(data_pbs, generator_module=None):
'''
Reload runs from PBS
'''
#### SETUP
#
savefigs = True
savedata = True
savemovies = False
plots_dist_bays09 = True
do_scatters_3d = True
do_best_points_extended_plots = True
# do_relaunch_bestparams_pbs = True
colormap = None # or 'cubehelix'
plt.rcParams['font.size'] = 16
#
#### /SETUP
print "Order parameters: ", data_pbs.dataset_infos['parameters']
# parameters: M, ratio_conj, sigmax
# Extract data
result_em_fits_flat = np.array(data_pbs.dict_arrays['result_em_fits']['results_flat'])
result_dist_bays09_flat = np.array(data_pbs.dict_arrays['result_dist_bays09']['results_flat'])
result_dist_gorgo11_flat = np.array(data_pbs.dict_arrays['result_dist_gorgo11']['results_flat'])
result_parameters_flat = np.array(data_pbs.dict_arrays['result_em_fits']['parameters_flat'])
M_space = data_pbs.loaded_data['parameters_uniques']['M']
sigmax_space = data_pbs.loaded_data['parameters_uniques']['sigmax']
ratio_space = data_pbs.loaded_data['parameters_uniques']['sigmax']
num_repetitions = generator_module.num_repetitions
parameter_names_sorted = data_pbs.dataset_infos['parameters']
T_space = data_pbs.loaded_data['datasets_list'][0]['T_space']
all_args = data_pbs.loaded_data['args_list']
all_repeats_completed = data_pbs.dict_arrays['result_em_fits']['repeats_completed']
dataio = DataIO(output_folder=generator_module.pbs_submission_infos['simul_out_dir'] + '/outputs/', label='global_' + dataset_infos['save_output_filename'])
# Load bays09
data_bays09 = load_experimental_data.load_data_bays09(fit_mixture_model=True)
bays09_nitems = data_bays09['data_to_fit']['n_items']
bays09_em_target = np.nan*np.empty((bays09_nitems.max(), 4)) #kappa, prob_target, prob_nontarget, prob_random
bays09_em_target[bays09_nitems - 1] = data_bays09['em_fits_nitems_arrays']['mean'].T
bays09_emmixt_target = bays09_em_target[:, 1:]
# All parameters info
plotting_parameters = launcher_memorycurve.load_prepare_datasets()
## Compute some stuff
# result_dist_bays09_kappa_T1_avg = utils.nanmean(result_dist_bays09_flat[:, 0, 0], axis=-1)
# result_dist_bays09_kappa_allT_avg = np.nansum(utils.nanmean(result_dist_bays09_flat[:, :, 0], axis=-1), axis=1)
# Square distance to kappa
result_dist_bays09_allT_avg = utils.nanmean((result_em_fits_flat[:, :, :4] - bays09_em_target[np.newaxis, :, :, np.newaxis])**2, axis=-1)
result_dist_bays09_kappa_sum = np.nansum(result_dist_bays09_allT_avg[:, :, 0], axis=-1)
result_dist_bays09_kappa_sum_masked = np.ma.masked_greater(result_dist_bays09_kappa_sum, 1e8)
result_dist_bays09_kappa_T1_sum = result_dist_bays09_allT_avg[:, 0, 0]
result_dist_bays09_kappa_T25_sum = np.nansum(result_dist_bays09_allT_avg[:, 1:, 0], axis=-1)
# Square and KL distance for EM Mixtures
result_dist_bays09_emmixt_sum = np.nansum(np.nansum(result_dist_bays09_allT_avg[:, :, 1:], axis=-1), axis=-1)
result_dist_bays09_emmixt_T1_sum = np.nansum(result_dist_bays09_allT_avg[:, 0, 1:], axis=-1)
result_dist_bays09_emmixt_T25_sum = np.nansum(np.nansum(result_dist_bays09_allT_avg[:, 1:, 1:], axis=-1), axis=-1)
result_dist_bays09_emmixt_KL = utils.nanmean(utils.KL_div(result_em_fits_flat[:, :, 1:4], bays09_emmixt_target[np.newaxis, :, :, np.newaxis], axis=-2), axis=-1) # KL over dimension of mixtures, then mean over repetitions
result_dist_bays09_emmixt_KL_sum = np.nansum(result_dist_bays09_emmixt_KL, axis=-1) # sum over T
result_dist_bays09_emmixt_KL_T1_sum = result_dist_bays09_emmixt_KL[:, 0]
result_dist_bays09_emmixt_KL_T25_sum = np.nansum(result_dist_bays09_emmixt_KL[:, 1:], axis=-1)
result_dist_bays09_both_normalised = result_dist_bays09_emmixt_sum/np.max(result_dist_bays09_emmixt_sum) + result_dist_bays09_kappa_sum/np.max(result_dist_bays09_kappa_sum)
result_dist_bays09_kappaKL_normalised_summed = result_dist_bays09_emmixt_KL_sum/np.max(result_dist_bays09_emmixt_KL_sum) + result_dist_bays09_kappa_sum/np.max(result_dist_bays09_kappa_sum)
if plots_dist_bays09:
nb_best_points = 30
size_normal_points = 8
size_best_points = 50
nb_best_points_extended_plots = 3
def plot_memorycurve(result_em_fits, args_used, suptitle=''):
packed_data = dict(T_space=T_space, result_em_fits=result_em_fits, all_parameters=args_used)
if suptitle:
plotting_parameters['suptitle'] = suptitle
if savefigs:
packed_data['dataio'] = dataio
plotting_parameters['reuse_axes'] = False
launcher_memorycurve.do_memory_plots(packed_data, plotting_parameters)
def plot_scatter(result_dist_to_use, best_points_result_dist_to_use, result_dist_to_use_name='', title=''):
fig = plt.figure()
ax = Axes3D(fig)
utils.scatter3d(result_parameters_flat[:, 0], result_parameters_flat[:, 1], result_parameters_flat[:, 2], s=size_normal_points, c=np.log(result_dist_to_use), xlabel=parameter_names_sorted[0], ylabel=parameter_names_sorted[1], zlabel=parameter_names_sorted[2], title=title, ax_handle=ax)
utils.scatter3d(result_parameters_flat[best_points_result_dist_to_use, 0], result_parameters_flat[best_points_result_dist_to_use, 1], result_parameters_flat[best_points_result_dist_to_use, 2], c='r', s=size_best_points, ax_handle=ax)
print "Best points, %s:" % title
print '\n'.join(['M %d, ratio %.2f, sigmax %.2f: %f' % (result_parameters_flat[i, 0], result_parameters_flat[i, 1], result_parameters_flat[i, 2], result_dist_to_use[i]) for i in best_points_result_dist_to_use])
if savefigs:
dataio.save_current_figure('scatter3d_%s_{label}_{unique_id}.pdf' % result_dist_to_use_name)
if savemovies:
try:
utils.rotate_plot3d(ax, dataio.create_formatted_filename('scatter3d_%s_{label}_{unique_id}.mp4' % result_dist_to_use_name), bitrate=8000, min_duration=8)
utils.rotate_plot3d(ax, dataio.create_formatted_filename('scatter3d_%s_{label}_{unique_id}.gif' % result_dist_to_use_name), nb_frames=30, min_duration=8)
except Exception:
# Most likely wrong aggregator...
print "failed when creating movies for ", result_dist_to_use_name
ax.view_init(azim=90, elev=10)
dataio.save_current_figure('scatter3d_%s_view2_{label}_{unique_id}.pdf' % result_dist_to_use_name)
return ax
def plots_redirects(all_vars, result_dist_to_use_name, log_color=True, title='', avoid_incomplete_repeats=True):
result_dist_to_use = all_vars[result_dist_to_use_name]
if avoid_incomplete_repeats:
result_dist_to_use = np.ma.masked_where(~(all_repeats_completed == num_repetitions-1), result_dist_to_use)
if not log_color:
result_dist_to_use = np.exp(result_dist_to_use)
best_points_result_dist_to_use = np.argsort(result_dist_to_use)[:nb_best_points]
# Scatter
if do_scatters_3d:
plot_scatter(result_dist_to_use, best_points_result_dist_to_use, result_dist_to_use_name, title=title)
# Now do the additional plots if required
if do_best_points_extended_plots:
for best_point_index in best_points_result_dist_to_use[:nb_best_points_extended_plots]:
print "extended plot for M %d, ratio %.2f, sigmax %.2f: score %f" % (result_parameters_flat[best_point_index, 0], result_parameters_flat[best_point_index, 1], result_parameters_flat[best_point_index, 2], result_dist_to_use[best_point_index])
plot_memorycurve(result_em_fits_flat[best_point_index], all_args[best_point_index], suptitle=result_dist_to_use_name)
# Distance for kappa, all T
plots_redirects(locals(), 'result_dist_bays09_kappa_sum', title='kappa all T')
# Distance for em fits, all T, Squared distance
plots_redirects(locals(), 'result_dist_bays09_emmixt_sum', title='em fits, all T')
# Distance for em fits, all T, KL distance
plots_redirects(locals(), 'result_dist_bays09_emmixt_KL_sum', title='em fits, all T, KL')
# Distance for sum of normalised em fits + normalised kappa, all T
plots_redirects(locals(), 'result_dist_bays09_both_normalised', title='summed normalised em mixt + kappa')
# Distance kappa T = 1
plots_redirects(locals(), 'result_dist_bays09_kappa_T1_sum', title='Kappa T=1')
# Distance kappa T = 2...5
plots_redirects(locals(), 'result_dist_bays09_kappa_T25_sum', title='Kappa T=2/5')
# Distance em fits T = 1
plots_redirects(locals(), 'result_dist_bays09_emmixt_T1_sum', title='em fits T=1')
# Distance em fits T = 2...5
plots_redirects(locals(), 'result_dist_bays09_emmixt_T25_sum', title='em fits T=2/5')
# Distance em fits T = 1, KL
plots_redirects(locals(), 'result_dist_bays09_emmixt_KL_T1_sum', title='em fits T=1, KL')
# Distance em fits T = 2...5, KL
plots_redirects(locals(), 'result_dist_bays09_emmixt_KL_T25_sum', title='em fits T=2/5, KL')
# if plots_per_T:
# for T in T_space:
# currT_indices = result_parameters_flat[:, 2] == T
# utils.contourf_interpolate_data_interactive_maxvalue(result_parameters_flat[currT_indices][..., :2], result_fitexperiments_bic_avg[currT_indices], xlabel='Ratio_conj', ylabel='sigma x', title='BIC, T %d' % T, interpolation_numpoints=200, interpolation_method='nearest', log_scale=False)
# # Interpolate
# if plots_interpolate:
# sigmax_target = 0.9
# M_interp_space = np.arange(6, 625, 5)
# ratio_interp_space = np.linspace(0.01, 1.0, 50)
# # sigmax_interp_space = np.linspace(0.01, 1.0, 50)
# sigmax_interp_space = np.array([sigmax_target])
# params_crossspace = np.array(utils.cross(M_interp_space, ratio_interp_space, sigmax_interp_space))
# interpolated_data = rbf_interpolator(params_crossspace[:, 0], params_crossspace[:, 1], params_crossspace[:, 2]).reshape((M_interp_space.size, ratio_interp_space.size))
# utils.pcolor_2d_data(interpolated_data, M_interp_space, ratio_interp_space, 'M', 'ratio', 'interpolated, fixing sigmax= %.2f' % sigmax_target)
# points_closeby = ((result_parameters_flat[:, 2] - sigmax_target)**2)< 0.01
# plt.figure()
# # plt.imshow(interpolated_data, extent=(M_interp_space.min(), M_interp_space.max(), ratio_interp_space.min(), ratio_interp_space.max()))
# plt.imshow(interpolated_data)
# plt.scatter(result_parameters_flat[points_closeby, 0], result_parameters_flat[points_closeby, 1], s=100, c=result_fitexperiments_bic_avg[points_closeby], marker='o')
# if plot_per_ratio:
# # Plot the evolution of loglike as a function of sigmax, with std shown
# for ratio_conj_i, ratio_conj in enumerate(ratio_space):
# ax = utils.plot_mean_std_area(sigmax_space, result_log_posterior_mean[ratio_conj_i], result_log_posterior_std[ratio_conj_i])
# ax.get_figure().canvas.draw()
# if savefigs:
# dataio.save_current_figure('results_fitexp_%s_loglike_ratioconj%.2f_{label}_global_{unique_id}.pdf' % (exp_dataset, ratio_conj))
variables_to_save = ['parameter_names_sorted', 'all_repeats_completed', 'T_space']
if savedata:
dataio.save_variables_default(locals(), variables_to_save)
dataio.make_link_output_to_dropbox(dropbox_current_experiment_folder='fit_mixturemodels')
plt.show()
return locals()
def main():
result_path = 'results/'
subtype_method = "Algorithm"
K = 3 # number of subtypes(clusters)
############################## LOAD DATA ######################################
print('patients loading...')
dataio = DataIO(K)
dataio.load_demographics('../ufm/patient.csv')
dataio.load_feature('Motor', 'MDS UPDRS PartI')
dataio.load_feature('Motor', 'MDS UPDRS PartII')
dataio.load_feature('Motor', 'MDS UPDRS PartIII')
dataio.load_feature('Motor', 'MDS UPDRS PartIV')
dataio.load_feature('Non-Motor', 'BJLO')
dataio.load_feature('Non-Motor', 'ESS')
dataio.load_feature('Non-Motor', 'GDS')
dataio.load_feature('Non-Motor', 'HVLT')
dataio.load_feature('Non-Motor', 'LNS')
dataio.load_feature('Non-Motor', 'MoCA')
dataio.load_feature('Non-Motor', 'QUIP')
dataio.load_feature('Non-Motor', 'RBD')
dataio.load_feature('Non-Motor', 'SCOPA-AUT')
dataio.load_feature('Non-Motor', 'SF')
dataio.load_feature('Non-Motor', 'STAI')
dataio.load_feature('Non-Motor', 'SDM')
dataio.load_feature('Non-Motor', 'MCI')
dataio.load_feature('Biospecimen', 'DNA')
dataio.load_feature('Biospecimen', 'CSF', 'Total tau')
dataio.load_feature('Biospecimen', 'CSF', 'Abeta 42')
dataio.load_feature('Biospecimen', 'CSF', 'p-Tau181P')
dataio.load_feature('Biospecimen', 'CSF', 'CSF Alpha-synuclein')
dataio.load_feature('Image', 'DaTScan SBR')
dataio.load_feature('Image', 'MRI')
dataio.load_feature('Medication', 'MED USE')
suffix = 'normalized_clusters_Deep'
dataio.load_clustering_result('input/clustering_by_lstm.csv')
############################# STATISTICS ######################################
print('-----------------------')
print('statistics analyzing...')
var = Variable(K)
ftype = 'demographics'
p = var.get_variables(dataio, ftype)
var.p_value.extend(p)
ftype = 'motor'
_ = var.get_variables(dataio, ftype, 'MDS UPDRS PartI')
_ = var.get_variables(dataio, ftype, 'MDS UPDRS PartII')
_ = var.get_variables(dataio, ftype, 'MDS UPDRS PartIII', 'MDS-UPDRS')
_ = var.get_variables(dataio, ftype, 'MDS UPDRS PartIII', 'H&Y')
p = var.get_variables(dataio, ftype, 'MDS UPDRS PartIV')
var.p_value.extend(p)
ftype = 'nonmotor'
_ = var.get_variables(dataio, ftype, 'BJLO')
_ = var.get_variables(dataio, ftype, 'ESS')
_ = var.get_variables(dataio, ftype, 'GDS')
_ = var.get_variables(dataio, ftype, 'HVLT', 'Immediate Recall')
_ = var.get_variables(dataio, ftype, 'HVLT', 'Discrimination Recognition')
_ = var.get_variables(dataio, ftype, 'HVLT', 'Retention')
_ = var.get_variables(dataio, ftype, 'LNS')
print(var.pat_edu)
_ = var.get_variables(dataio, ftype, 'MoCA', pat_edu=var.pat_edu)
_ = var.get_variables(dataio, ftype, 'QUIP')
_ = var.get_variables(dataio, ftype, 'RBD')
_ = var.get_variables(dataio, ftype, 'SCOPA-AUT')
_ = var.get_variables(dataio, ftype, 'SF')
_ = var.get_variables(dataio, ftype, 'STAI')
_ = var.get_variables(dataio, ftype, 'SDM')
p = var.get_variables(dataio, ftype, 'MCI')
var.p_value.extend(p)
ftype = 'biospecimen'
var.get_variables(dataio, ftype, 'DNA')
_ = var.get_variables(dataio, ftype, 'CSF', 'Total tau')
_ = var.get_variables(dataio, ftype, 'CSF', 'Abeta 42')
_ = var.get_variables(dataio, ftype, 'CSF', 'p-Tau181P')
p = var.get_variables(dataio, ftype, 'CSF', 'CSF Alpha-synuclein')
var.p_value.extend(p)
ftype = 'image'
_ = var.get_variables(dataio, ftype, 'DaTScan SBR', 'CAUDATE RIGHT')
_ = var.get_variables(dataio, ftype, 'DaTScan SBR', 'CAUDATE LEFT')
_ = var.get_variables(dataio, ftype, 'DaTScan SBR', 'PUTAMEN RIGHT')
_ = var.get_variables(dataio, ftype, 'DaTScan SBR', 'PUTAMEN LEFT')
p = var.get_variables(dataio, ftype, 'MRI')
var.p_value.extend(p)
ftype = 'medication'
p = var.get_variables(dataio, ftype, 'MED USE')
var.p_value.extend(p)
################################# DISPLAY ######################################
print('-----------------------')
print('value displaying...')
ds = Display(var)
print('heatmap of the final mean value')
figurename = 'results/heatmap_clustering_by_' + subtype_method.lower(
) + '_' + suffix + '.pdf'
ds.heatmap(figurename, is_progress=False, is_rotate=False)
print('heatmap of the first order difference mean value')
figurename = 'results/heatmap_clustering_by_' + subtype_method.lower(
) + '_progression_' + suffix + '.pdf'
ds.heatmap(figurename, is_progress=True, is_rotate=False)
############################## SAVE RESULTS ####################################
print('-----------------------')
filename = result_path + 'statistics_clustering_by_' + subtype_method.lower(
) + '_' + suffix + '.csv'
dataio.save_result(var, filename)
print('done!')
def plots_fit_mixturemodels_random(data_pbs, generator_module=None):
"""
Reload runs from PBS
"""
#### SETUP
#
savefigs = True
savedata = True
colormap = None # or 'cubehelix'
plt.rcParams["font.size"] = 16
#
#### /SETUP
print "Order parameters: ", data_pbs.dataset_infos["parameters"]
# parameters: M, ratio_conj, sigmax
# Extract data
T_space = data_pbs.loaded_data["datasets_list"][0]["T_space"]
result_responses_flat = np.array(data_pbs.dict_arrays["result_responses"]["results_flat"])
result_targets_flat = np.array(data_pbs.dict_arrays["result_target"]["results_flat"])
result_nontargets_flat = np.array(data_pbs.dict_arrays["result_nontargets"]["results_flat"])
result_parameters_flat = np.array(data_pbs.dict_arrays["result_responses"]["parameters_flat"])
all_repeats_completed = data_pbs.dict_arrays["result_responses"]["repeats_completed"]
all_args_arr = np.array(data_pbs.loaded_data["args_list"])
M_space = data_pbs.loaded_data["parameters_uniques"]["M"]
ratio_conj_space = data_pbs.loaded_data["parameters_uniques"]["ratio_conj"]
sigmax_space = data_pbs.loaded_data["parameters_uniques"]["sigmax"]
alpha_space = data_pbs.loaded_data["parameters_uniques"]["alpha"]
trecall_space = data_pbs.loaded_data["parameters_uniques"]["fixed_cued_feature_time"]
num_repetitions = generator_module.num_repetitions
parameter_names_sorted = data_pbs.dataset_infos["parameters"]
dataio = DataIO(
output_folder=generator_module.pbs_submission_infos["simul_out_dir"] + "/outputs/",
label="global_" + dataset_infos["save_output_filename"],
)
##### Because of lazyness, the responses are weird.
# Each run is for a given trecall. But we run N items= 1 .. Nmax anyway
# so if trecall > N, you have np.nan
# => Need to reconstruct the thing properly, to have lower triangle of Nitem x Trecall filled
# Also, trecall is the actual Time. Hence we need to change its meaning to be Tmax- (trecall + 1) or whatever.
# Load ground truth
data_gorgo11_sequ = load_experimental_data.load_data_gorgo11_sequential(fit_mixture_model=True)
## Filter everything with repeats_completed == num_repet and trecall=last
filter_data = (result_parameters_flat[:, 0] == (T_space.max() - 1)) & (all_repeats_completed == num_repetitions - 1)
result_parameters_flat = result_parameters_flat[filter_data]
result_responses_flat = result_responses_flat[filter_data]
result_targets_flat = result_targets_flat[filter_data]
result_nontargets_flat = result_nontargets_flat[filter_data]
all_args_arr = all_args_arr[filter_data]
all_repeats_completed = all_repeats_completed[filter_data]
print "Size post-filter: ", result_parameters_flat.shape[0]
def str_best_params(best_i, result_dist_to_use):
return (
" ".join(
[
"%s %.4f" % (parameter_names_sorted[param_i], result_parameters_flat[best_i, param_i])
for param_i in xrange(len(parameter_names_sorted))
]
)
+ " >> %f" % result_dist_to_use[best_i]
)
# all_args = data_pbs.loaded_data['args_list']
variables_to_save = ["parameter_names_sorted", "all_args_arr", "all_repeats_completed", "filter_data"]
if savedata:
dataio.save_variables_default(locals(), variables_to_save)
dataio.make_link_output_to_dropbox(dropbox_current_experiment_folder="gorgo11_sequential_fitmixturemodel")
plt.show()
return locals()
def plots_fit_collapsedmixturemodels_random(data_pbs, generator_module=None):
'''
Reload runs from PBS
Sequential data analysis.
'''
#### SETUP
#
plots_bestfits = True
plots_scatter3d = False
savefigs = True
savedata = True
colormap = None # or 'cubehelix'
plt.rcParams['font.size'] = 16
#
#### /SETUP
print "Order parameters: ", data_pbs.dataset_infos['parameters']
# parameters: M, ratio_conj, sigmax
# Extract data
T_space = data_pbs.loaded_data['datasets_list'][0]['T_space']
result_em_fits_collapsed_tr_flat = np.array(data_pbs.dict_arrays['result_em_fits_collapsed_tr']['results_flat'])
result_em_fits_collapsed_summary_flat = np.array(data_pbs.dict_arrays['result_em_fits_collapsed_summary']['results_flat'])
result_dist_gorgo11_sequ_collapsed_flat = np.array(data_pbs.dict_arrays['result_dist_gorgo11_sequ_collapsed']['results_flat'])
result_dist_gorgo11_sequ_collapsed_emmixt_KL_flat = np.array(data_pbs.dict_arrays['result_dist_gorgo11_sequ_collapsed_emmixt_KL']['results_flat'])
result_parameters_flat = np.array(data_pbs.dict_arrays['result_em_fits_collapsed_tr']['parameters_flat'])
all_repeats_completed = data_pbs.dict_arrays['result_em_fits_collapsed_tr']['repeats_completed']
all_args_arr = np.array(data_pbs.loaded_data['args_list'])
M_space = data_pbs.loaded_data['parameters_uniques']['M']
ratio_conj_space = data_pbs.loaded_data['parameters_uniques']['ratio_conj']
sigmax_space = data_pbs.loaded_data['parameters_uniques']['sigmax']
alpha_space = data_pbs.loaded_data['parameters_uniques']['alpha']
num_repetitions = generator_module.num_repetitions
parameter_names_sorted = data_pbs.dataset_infos['parameters']
dataio = DataIO(output_folder=generator_module.pbs_submission_infos['simul_out_dir'] + '/outputs/', label='global_' + dataset_infos['save_output_filename'])
# Load ground truth
data_gorgo11_sequ = load_experimental_data.load_data_gorgo11_sequential(fit_mixture_model=True)
## Filter everything with repeats_completed == num_repet
filter_data = all_repeats_completed == num_repetitions - 1
result_parameters_flat = result_parameters_flat[filter_data]
result_em_fits_collapsed_tr_flat = result_em_fits_collapsed_tr_flat[filter_data]
result_em_fits_collapsed_summary_flat = result_em_fits_collapsed_summary_flat[filter_data]
result_dist_gorgo11_sequ_collapsed_flat = result_dist_gorgo11_sequ_collapsed_flat[filter_data]
result_dist_gorgo11_sequ_collapsed_emmixt_KL_flat = result_dist_gorgo11_sequ_collapsed_emmixt_KL_flat[filter_data]
all_args_arr = all_args_arr[filter_data]
all_repeats_completed = all_repeats_completed[filter_data]
print "Size post-filter: ", result_parameters_flat.shape[0]
# Compute lots of averages over the repetitions
result_em_fits_collapsed_tr_flat_avg = utils.nanmean(result_em_fits_collapsed_tr_flat, axis=-1)
result_em_fits_collapsed_summary_flat_avg = utils.nanmean(result_em_fits_collapsed_summary_flat, axis=-1)
result_dist_gorgo11_sequ_collapsed_flat_avg = utils.nanmean(result_dist_gorgo11_sequ_collapsed_flat, axis=-1)
result_dist_gorgo11_sequ_collapsed_emmixt_KL_flat_avg = utils.nanmean(result_dist_gorgo11_sequ_collapsed_emmixt_KL_flat, axis=-1)
result_dist_gorgo11_sequ_collapsed_flat_avg_overall = np.nansum(np.nansum(np.nansum(result_dist_gorgo11_sequ_collapsed_flat_avg, axis=-1), axis=-1), axis=-1)
# We will now grid some of the parameters, to have a 2D/3D surface back.
# Let's fix the ratio_conj, as we know that the other models need around
# ratio =0.8 to fit data well.
def str_best_params(best_i, result_dist_to_use):
return ' '.join(["%s %.4f" % (parameter_names_sorted[param_i], result_parameters_flat[best_i, param_i]) for param_i in xrange(len(parameter_names_sorted))]) + ' >> %f' % result_dist_to_use[best_i]
###### Best fitting points
if plots_bestfits:
nb_best_points = 5
def plot_collapsed_modelfits(T_space, curr_result_emfits_collapsed_tr, labelplot='', dataio=None):
f, ax = plt.subplots()
for nitems_i, nitems in enumerate(T_space):
ax = plots_experimental_data.plot_kappa_mean_error(T_space[:nitems], curr_result_emfits_collapsed_tr[..., 0][nitems_i, :nitems], 0.0*curr_result_emfits_collapsed_tr[..., 0][nitems_i, :nitems], title='model fit fig7 %s' % labelplot , ax=ax, label='%d items' % nitems, xlabel='T_recall')
if dataio is not None:
dataio.save_current_figure('bestfit_doublepowerlaw_%s_kappa_{label}_{unique_id}.pdf' % labelplot)
_, ax_target = plt.subplots()
_, ax_nontarget = plt.subplots()
_, ax_random = plt.subplots()
for nitems_i, nitems in enumerate(T_space):
ax_target = plots_experimental_data.plot_emmixture_mean_error(T_space[:nitems], curr_result_emfits_collapsed_tr[..., 1][nitems_i, :nitems], curr_result_emfits_collapsed_tr[..., 1][nitems_i, :nitems]*0.0, title='Target model fit %s' % labelplot, ax=ax_target, label='%d items' % nitems, xlabel='T_recall')
ax_nontarget = plots_experimental_data.plot_emmixture_mean_error(T_space[:nitems], curr_result_emfits_collapsed_tr[..., 2][nitems_i, :nitems], curr_result_emfits_collapsed_tr[..., 2][nitems_i, :nitems]*0.0, title='Nontarget model fit %s' % labelplot, ax=ax_nontarget, label='%d items' % nitems, xlabel='T_recall')
ax_random = plots_experimental_data.plot_emmixture_mean_error(T_space[:nitems], curr_result_emfits_collapsed_tr[..., 3][nitems_i, :nitems], curr_result_emfits_collapsed_tr[..., 3][nitems_i, :nitems]*0.0, title='Random model fit %s' % labelplot, ax=ax_random, label='%d items' % nitems, xlabel='T_recall')
if dataio is not None:
plt.figure(ax_target.get_figure().number)
dataio.save_current_figure('bestfit_doublepowerlaw_%s_mixttarget_{label}_{unique_id}.pdf' % labelplot)
plt.figure(ax_nontarget.get_figure().number)
dataio.save_current_figure('bestfit_doublepowerlaw_%s_mixtnontarget_{label}_{unique_id}.pdf' % labelplot)
plt.figure(ax_random.get_figure().number)
dataio.save_current_figure('bestfit_doublepowerlaw_%s_mixtrandom_{label}_{unique_id}.pdf' % labelplot)
best_points_result_dist_gorgo11seq_all = np.argsort(result_dist_gorgo11_sequ_collapsed_flat_avg_overall)[:nb_best_points]
for best_point_i in best_points_result_dist_gorgo11seq_all:
plot_collapsed_modelfits(T_space, result_em_fits_collapsed_tr_flat_avg[best_point_i], labelplot='%.1f' % result_dist_gorgo11_sequ_collapsed_flat_avg_overall[best_point_i], dataio=dataio)
###### 3D scatter plots
if plots_scatter3d:
nb_best_points = 30
size_normal_points = 8
size_best_points = 50
def plot_scatter(all_vars, result_dist_to_use_name, title='', log_color=True, downsampling=1, label_file=''):
result_dist_to_use = all_vars[result_dist_to_use_name]
result_parameters_flat_3d = all_vars['result_parameters_flat_3d']
# Filter if downsampling
filter_downsampling = np.arange(0, result_dist_to_use.size, downsampling)
result_dist_to_use = result_dist_to_use[filter_downsampling]
result_parameters_flat_3d = result_parameters_flat_3d[filter_downsampling]
best_points_result_dist_to_use = np.argsort(result_dist_to_use)[:nb_best_points]
# Construct all permutations of 3 parameters, for 3D scatters
params_permutations = set([tuple(np.sort(np.random.choice(result_parameters_flat_3d.shape[-1], 3, replace=False)).tolist()) for i in xrange(1000)])
for param_permut in params_permutations:
fig = plt.figure()
ax = Axes3D(fig)
# One plot per parameter permutation
if log_color:
color_points = np.log(result_dist_to_use)
else:
color_points = result_dist_to_use
utils.scatter3d(result_parameters_flat_3d[:, param_permut[0]], result_parameters_flat_3d[:, param_permut[1]], result_parameters_flat_3d[:, param_permut[2]], s=size_normal_points, c=color_points, xlabel=parameter_names_sorted[param_permut[0]], ylabel=parameter_names_sorted[param_permut[1]], zlabel=parameter_names_sorted[param_permut[2]], title=title, ax_handle=ax)
utils.scatter3d(result_parameters_flat_3d[best_points_result_dist_to_use, param_permut[0]], result_parameters_flat_3d[best_points_result_dist_to_use, param_permut[1]], result_parameters_flat_3d[best_points_result_dist_to_use, param_permut[2]], c='r', s=size_best_points, ax_handle=ax)
if savefigs:
dataio.save_current_figure('scatter3d_%s_%s%s_{label}_{unique_id}.pdf' % (result_dist_to_use_name, '_'.join([parameter_names_sorted[i] for i in param_permut]), label_file))
if savemovies:
try:
utils.rotate_plot3d(ax, dataio.create_formatted_filename('scatter3d_%s_%s%s_{label}_{unique_id}.mp4' % (result_dist_to_use_name, '_'.join([parameter_names_sorted[i] for i in param_permut]), label_file)), bitrate=8000, min_duration=8)
utils.rotate_plot3d(ax, dataio.create_formatted_filename('scatter3d_%s_%s%s_{label}_{unique_id}.gif' % (result_dist_to_use_name, '_'.join([parameter_names_sorted[i] for i in param_permut]), label_file)), nb_frames=30, min_duration=8)
except Exception:
# Most likely wrong aggregator...
print "failed when creating movies for ", result_dist_to_use_name
if False and savefigs:
ax.view_init(azim=90, elev=10)
dataio.save_current_figure('scatter3d_view2_%s_%s%s_{label}_{unique_id}.pdf' % (result_dist_to_use_name, '_'.join([parameter_names_sorted[i] for i in param_permut]), label_file))
# plt.close('all')
print "Parameters: %s" % ', '.join(parameter_names_sorted)
print "Best points, %s:" % title
print '\n'.join([str_best_params(best_i, result_dist_to_use) for best_i in best_points_result_dist_to_use])
# all_args = data_pbs.loaded_data['args_list']
variables_to_save = ['parameter_names_sorted', 'all_args_arr', 'all_repeats_completed', 'filter_data']
if savedata:
dataio.save_variables_default(locals(), variables_to_save)
dataio.make_link_output_to_dropbox(dropbox_current_experiment_folder='gorgo11_sequential_fitmixturemodel')
plt.show()
return locals()
import numpy
from dataio import DataIO
if __name__ == '__main__':
filename = 'test'
fieldnames = ['time', 'low', 'high']
csvio = DataIO('test', fieldnames)
csvio.csv_newfile(filename)
test_row1 = {'time': 1.0, 'low': 100, 'high': 101}
test_row2 = {'time': 2.0, 'low': 101, 'high': 102}
test_rows = [{'time': 3.0, 'low': 102, 'high': 103},
{'time': 4.0, 'low': 103, 'high': 104}]
exists = csvio.csv_check(filename)
print(exists)
print(len(numpy.shape(test_row1)))
print(len(numpy.shape(test_rows)))
csvio.csv_append(filename, test_row1)
csvio.csv_append(filename, test_row2)
csvio.csv_append(filename, test_rows)
data = csvio.csv_get(filename)
print(data)
csvio.csv_rename(filename, 'test2')
def input(self, N, file_name):
x = self.random_state.uniform(self.X_LBU, self.X_UBU, N)
title = 'input'
DataIO.write_data([x], file_name, title)
def function(self, file_name):
x = np.linspace(self.X_LBU, self.X_UBU, self.NLARGE)
f = np.sin(2 * np.pi * x)
title = 'input\tsinus function'
DataIO.write_data([x, f], file_name, title)
def plots_fit_mixturemodels_random(data_pbs, generator_module=None):
'''
Reload runs from PBS
'''
#### SETUP
#
savefigs = True
savedata = True
savemovies = True
plots_dist_bays09 = True
plots_per_T = True
plots_interpolate = False
# do_relaunch_bestparams_pbs = True
colormap = None # or 'cubehelix'
plt.rcParams['font.size'] = 16
#
#### /SETUP
print "Order parameters: ", data_pbs.dataset_infos['parameters']
# parameters: M, ratio_conj, sigmax
# Extract data
T_space = data_pbs.loaded_data['datasets_list'][0]['T_space']
result_em_fits_flat = np.array(data_pbs.dict_arrays['result_em_fits']['results_flat'])
result_dist_bays09_flat = np.array(data_pbs.dict_arrays['result_dist_bays09']['results_flat'])
result_dist_gorgo11_flat = np.array(data_pbs.dict_arrays['result_dist_gorgo11']['results_flat'])
result_parameters_flat = np.array(data_pbs.dict_arrays['result_em_fits']['parameters_flat'])
sigmaoutput_space = data_pbs.loaded_data['parameters_uniques']['sigma_output']
sigmax_space = data_pbs.loaded_data['parameters_uniques']['sigmax']
ratio_space = data_pbs.loaded_data['parameters_uniques']['sigmax']
num_repetitions = generator_module.num_repetitions
parameter_names_sorted = data_pbs.dataset_infos['parameters']
dataio = DataIO(output_folder=generator_module.pbs_submission_infos['simul_out_dir'] + '/outputs/', label='global_' + dataset_infos['save_output_filename'])
# Load bays09
data_bays09 = load_experimental_data.load_data_bays09(fit_mixture_model=True)
bays09_nitems = data_bays09['data_to_fit']['n_items']
bays09_em_target = np.nan*np.empty((bays09_nitems.max(), 4)) #kappa, prob_target, prob_nontarget, prob_random
bays09_em_target[bays09_nitems - 1] = data_bays09['em_fits_nitems_arrays']['mean'].T
bays09_emmixt_target = bays09_em_target[:, 1:]
## Compute some stuff
# result_dist_bays09_kappa_T1_avg = utils.nanmean(result_dist_bays09_flat[:, 0, 0], axis=-1)
# result_dist_bays09_kappa_allT_avg = np.nansum(utils.nanmean(result_dist_bays09_flat[:, :, 0], axis=-1), axis=1)
# Square distance to kappa
result_dist_bays09_allT_avg = utils.nanmean((result_em_fits_flat[:, :, :4] - bays09_em_target[np.newaxis, :, :, np.newaxis])**2, axis=-1)
result_dist_bays09_kappa_sum = np.nansum(result_dist_bays09_allT_avg[:, :, 0], axis=-1)
result_dist_bays09_kappa_T1_sum = result_dist_bays09_allT_avg[:, 0, 0]
result_dist_bays09_kappa_T25_sum = np.nansum(result_dist_bays09_allT_avg[:, 1:, 0], axis=-1)
# Square and KL distance for EM Mixtures
result_dist_bays09_emmixt_sum = np.nansum(np.nansum(result_dist_bays09_allT_avg[:, :, 1:], axis=-1), axis=-1)
result_dist_bays09_emmixt_T1_sum = np.nansum(result_dist_bays09_allT_avg[:, 0, 1:], axis=-1)
result_dist_bays09_emmixt_T25_sum = np.nansum(np.nansum(result_dist_bays09_allT_avg[:, 1:, 1:], axis=-1), axis=-1)
result_dist_bays09_emmixt_KL = utils.nanmean(utils.KL_div(result_em_fits_flat[:, :, 1:4], bays09_emmixt_target[np.newaxis, :, :, np.newaxis], axis=-2), axis=-1) # KL over dimension of mixtures, then mean over repetitions
result_dist_bays09_emmixt_KL_sum = np.nansum(result_dist_bays09_emmixt_KL, axis=-1) # sum over T
result_dist_bays09_emmixt_KL_T1_sum = result_dist_bays09_emmixt_KL[:, 0]
result_dist_bays09_emmixt_KL_T25_sum = np.nansum(result_dist_bays09_emmixt_KL[:, 1:], axis=-1)
result_dist_bays09_both_normalised = result_dist_bays09_emmixt_sum/np.max(result_dist_bays09_emmixt_sum) + result_dist_bays09_kappa_sum/np.max(result_dist_bays09_kappa_sum)
if plots_dist_bays09:
nb_best_points = 30
size_normal_points = 8
size_best_points = 50
def plot_scatter(all_vars, result_dist_to_use_name, title='', log_color=True, downsampling=1, label_file=''):
fig = plt.figure()
ax = Axes3D(fig)
result_dist_to_use = all_vars[result_dist_to_use_name]
if not log_color:
result_dist_to_use = np.exp(result_dist_to_use)
utils.scatter3d(result_parameters_flat[:, 0], result_parameters_flat[:, 1], result_parameters_flat[:, 2], s=size_normal_points, c=np.log(result_dist_to_use), xlabel=parameter_names_sorted[0], ylabel=parameter_names_sorted[1], zlabel=parameter_names_sorted[2], title=title, ax_handle=ax)
best_points_result_dist_to_use = np.argsort(result_dist_to_use)[:nb_best_points]
utils.scatter3d(result_parameters_flat[best_points_result_dist_to_use, 0], result_parameters_flat[best_points_result_dist_to_use, 1], result_parameters_flat[best_points_result_dist_to_use, 2], c='r', s=size_best_points, ax_handle=ax)
print "Best points, %s:" % title
print '\n'.join(['sigma output %.2f, ratio %.2f, sigmax %.2f: %f' % (result_parameters_flat[i, 0], result_parameters_flat[i, 1], result_parameters_flat[i, 2], result_dist_to_use[i]) for i in best_points_result_dist_to_use])
if savefigs:
dataio.save_current_figure('scatter3d_%s%s_{label}_{unique_id}.pdf' % (result_dist_to_use_name, label_file))
if savemovies:
try:
utils.rotate_plot3d(ax, dataio.create_formatted_filename('scatter3d_%s%s_{label}_{unique_id}.mp4' % (result_dist_to_use_name, label_file)), bitrate=8000, min_duration=8)
utils.rotate_plot3d(ax, dataio.create_formatted_filename('scatter3d_%s%s_{label}_{unique_id}.gif' % (result_dist_to_use_name, label_file)), nb_frames=30, min_duration=8)
except Exception:
# Most likely wrong aggregator...
print "failed when creating movies for ", result_dist_to_use_name
ax.view_init(azim=90, elev=10)
dataio.save_current_figure('scatter3d_view2_%s%s_{label}_{unique_id}.pdf' % (result_dist_to_use_name, label_file))
return ax
# Distance for kappa, all T
plot_scatter(locals(), 'result_dist_bays09_kappa_sum', 'kappa all T')
# Distance for em fits, all T, Squared distance
plot_scatter(locals(), 'result_dist_bays09_emmixt_sum', 'em fits, all T')
# Distance for em fits, all T, KL distance
plot_scatter(locals(), 'result_dist_bays09_emmixt_KL_sum', 'em fits, all T, KL')
# Distance for sum of normalised em fits + normalised kappa, all T
plot_scatter(locals(), 'result_dist_bays09_both_normalised', 'summed normalised em mixt + kappa')
# Distance kappa T = 1
plot_scatter(locals(), 'result_dist_bays09_kappa_T1_sum', 'Kappa T=1')
# Distance kappa T = 2...5
plot_scatter(locals(), 'result_dist_bays09_kappa_T25_sum', 'Kappa T=2/5')
# Distance em fits T = 1
plot_scatter(locals(), 'result_dist_bays09_emmixt_T1_sum', 'em fits T=1')
# Distance em fits T = 2...5
plot_scatter(locals(), 'result_dist_bays09_emmixt_T25_sum', 'em fits T=2/5')
# Distance em fits T = 1, KL
plot_scatter(locals(), 'result_dist_bays09_emmixt_KL_T1_sum', 'em fits T=1, KL')
# Distance em fits T = 2...5, KL
plot_scatter(locals(), 'result_dist_bays09_emmixt_KL_T25_sum', 'em fits T=2/5, KL')
if plots_per_T:
for T_i, T in enumerate(T_space):
# Kappa per T, fit to Bays09
result_dist_bays09_kappa_currT = result_dist_bays09_allT_avg[:, T_i, 0]
result_dist_bays09_kappa_currT_masked = mask_outliers(result_dist_bays09_kappa_currT)
plot_scatter(locals(), 'result_dist_bays09_kappa_currT_masked', 'kappa T %d masked' % T, label_file="T{}".format(T))
# EM Mixt per T, fit to Bays09
result_dist_bays09_emmixt_sum_currT = np.nansum(result_dist_bays09_allT_avg[:, T_i, 1:], axis=-1)
result_dist_bays09_emmixt_sum_currT_masked = mask_outliers(result_dist_bays09_emmixt_sum_currT)
plot_scatter(locals(), 'result_dist_bays09_emmixt_sum_currT_masked', 'EM mixt T %d masked' % T, label_file="T{}".format(T))
# EM Mixt per T, fit to Bays09 KL divergence
result_dist_bays09_emmixt_KL_sum_currT = result_dist_bays09_emmixt_KL[:, T_i]
plot_scatter(locals(), 'result_dist_bays09_emmixt_KL_sum_currT', 'KL EM mixt T %d masked' % T, label_file="T{}".format(T))
# # Interpolate
# if plots_interpolate:
# sigmax_target = 0.9
# M_interp_space = np.arange(6, 625, 5)
# ratio_interp_space = np.linspace(0.01, 1.0, 50)
# # sigmax_interp_space = np.linspace(0.01, 1.0, 50)
# sigmax_interp_space = np.array([sigmax_target])
# params_crossspace = np.array(utils.cross(M_interp_space, ratio_interp_space, sigmax_interp_space))
# interpolated_data = rbf_interpolator(params_crossspace[:, 0], params_crossspace[:, 1], params_crossspace[:, 2]).reshape((M_interp_space.size, ratio_interp_space.size))
# utils.pcolor_2d_data(interpolated_data, M_interp_space, ratio_interp_space, 'M', 'ratio', 'interpolated, fixing sigmax= %.2f' % sigmax_target)
# points_closeby = ((result_parameters_flat[:, 2] - sigmax_target)**2)< 0.01
# plt.figure()
# # plt.imshow(interpolated_data, extent=(M_interp_space.min(), M_interp_space.max(), ratio_interp_space.min(), ratio_interp_space.max()))
# plt.imshow(interpolated_data)
# plt.scatter(result_parameters_flat[points_closeby, 0], result_parameters_flat[points_closeby, 1], s=100, c=result_fitexperiments_bic_avg[points_closeby], marker='o')
# if plot_per_ratio:
# # Plot the evolution of loglike as a function of sigmax, with std shown
# for ratio_conj_i, ratio_conj in enumerate(ratio_space):
# ax = utils.plot_mean_std_area(sigmax_space, result_log_posterior_mean[ratio_conj_i], result_log_posterior_std[ratio_conj_i])
# ax.get_figure().canvas.draw()
# if savefigs:
# dataio.save_current_figure('results_fitexp_%s_loglike_ratioconj%.2f_{label}_global_{unique_id}.pdf' % (exp_dataset, ratio_conj))
all_args = data_pbs.loaded_data['args_list']
variables_to_save = ['parameter_names_sorted']
if savedata:
dataio.save_variables_default(locals(), variables_to_save)
dataio.make_link_output_to_dropbox(dropbox_current_experiment_folder='output_noise')
plt.show()
return locals()
def plots_fitting_experiments_random(data_pbs, generator_module=None):
'''
Reload 2D volume runs from PBS and plot them
'''
#### SETUP
#
savefigs = True
savedata = True
savemovies = False
do_bays09 = True
do_gorgo11 = True
scatter3d_sumT = False
plots_flat_sorted_performance = False
plots_memorycurves_fits_best = True
nb_best_points = 20
nb_best_points_per_T = nb_best_points/6
size_normal_points = 8
size_best_points = 50
downsampling = 2
# do_relaunch_bestparams_pbs = True
colormap = None # or 'cubehelix'
plt.rcParams['font.size'] = 16
#
#### /SETUP
print "Order parameters: ", generator_module.dict_parameters_range.keys()
# parameters: ratio_conj, sigmax, T
# Extract data
result_fitexperiments_flat = np.array(data_pbs.dict_arrays['result_fitexperiments']['results_flat'])
result_fitexperiments_all_flat = np.array(data_pbs.dict_arrays['result_fitexperiments_all']['results_flat'])
result_fitexperiments_noiseconv_flat = np.array(data_pbs.dict_arrays['result_fitexperiments_noiseconv']['results_flat'])
result_fitexperiments_noiseconv_all_flat = np.array(data_pbs.dict_arrays['result_fitexperiments_noiseconv_all']['results_flat'])
result_parameters_flat = np.array(data_pbs.dict_arrays['result_fitexperiments']['parameters_flat'])
all_repeats_completed = data_pbs.dict_arrays['result_fitexperiments']['repeats_completed']
all_args = data_pbs.loaded_data['args_list']
all_args_arr = np.array(all_args)
num_repetitions = generator_module.num_repetitions
# Extract order of datasets
experiment_ids = data_pbs.loaded_data['datasets_list'][0]['fitexperiment_parameters']['experiment_ids']
parameter_names_sorted = data_pbs.dataset_infos['parameters']
T_space = data_pbs.loaded_data['datasets_list'][0]['T_space']
dataio = DataIO(output_folder=generator_module.pbs_submission_infos['simul_out_dir'] + '/outputs/', label='global_' + dataset_infos['save_output_filename'])
# filter_data = (result_parameters_flat[:, -1] < 1.0) & (all_repeats_completed == num_repetitions - 1)
# filter_data = (all_repeats_completed == num_repetitions - 1)
# result_fitexperiments_flat = result_fitexperiments_flat[filter_data]
# result_fitexperiments_all_flat = result_fitexperiments_all_flat[filter_data]
# result_fitexperiments_noiseconv_flat = result_fitexperiments_noiseconv_flat[filter_data]
# result_fitexperiments_noiseconv_all_flat = result_fitexperiments_noiseconv_all_flat[filter_data]
# result_parameters_flat = result_parameters_flat[filter_data]
# Compute some stuff
# Data is summed over all experiments for _flat, contains bic, ll and ll90.
# for _all_flat, contains bic, ll and ll90 per experiment. Given that Gorgo11 and Bays09 are incompatible, shouldn't really use the combined version directly!
result_fitexperiments_noiseconv_bic_avg_allT = utils.nanmean(result_fitexperiments_noiseconv_flat, axis=-1)[..., 0]
result_fitexperiments_noiseconv_allexp_bic_avg_allT = utils.nanmean(result_fitexperiments_noiseconv_all_flat, axis=-1)[:, :, 0]
result_fitexperiments_noiseconv_allexp_ll90_avg_allT = -utils.nanmean(result_fitexperiments_noiseconv_all_flat, axis=-1)[:, :, -1]
### BIC
# result_fitexperiments_noiseconv_allexp_bic_avg_allT: N x T x exp
result_fitexperiments_noiseconv_bays09_bic_avg_allT = result_fitexperiments_noiseconv_allexp_bic_avg_allT[..., 0]
result_fitexperiments_noiseconv_gorgo11_bic_avg_allT = result_fitexperiments_noiseconv_allexp_bic_avg_allT[..., 1]
result_fitexperiments_noiseconv_dualrecall_bic_avg_allT = result_fitexperiments_noiseconv_allexp_bic_avg_allT[..., 2]
# Summed T
result_fitexperiments_noiseconv_bays09_bic_avg_sumT = np.nansum(result_fitexperiments_noiseconv_bays09_bic_avg_allT, axis=-1)
result_fitexperiments_noiseconv_gorgo11_bic_avg_sumT = np.nansum(result_fitexperiments_noiseconv_gorgo11_bic_avg_allT, axis=-1)
result_fitexperiments_noiseconv_dualrecall_bic_avg_sumT = np.nansum(result_fitexperiments_noiseconv_dualrecall_bic_avg_allT, axis=-1)
### LL90
# N x T x exp
result_fitexperiments_noiseconv_bays09_ll90_avg_allT = result_fitexperiments_noiseconv_allexp_ll90_avg_allT[..., 0]
result_fitexperiments_noiseconv_gorgo11_ll90_avg_allT = result_fitexperiments_noiseconv_allexp_ll90_avg_allT[..., 1]
result_fitexperiments_noiseconv_dualrecall_ll90_avg_allT = result_fitexperiments_noiseconv_allexp_ll90_avg_allT[..., 2]
# Summed T
result_fitexperiments_noiseconv_bays09_ll90_avg_sumT = np.nansum(result_fitexperiments_noiseconv_bays09_ll90_avg_allT, axis=-1)
result_fitexperiments_noiseconv_gorgo11_ll90_avg_sumT = np.nansum(result_fitexperiments_noiseconv_gorgo11_ll90_avg_allT, axis=-1)
result_fitexperiments_noiseconv_dualrecall_ll90_avg_sumT = np.nansum(result_fitexperiments_noiseconv_dualrecall_ll90_avg_allT, axis=-1)
def mask_outliers_array(result_dist_to_use, sigma_outlier=3):
'''
Mask outlier datapoints.
Compute the mean of the results and assume that points with:
result > mean + sigma_outlier*std
are outliers.
As we want the minimum values, do not mask small values
'''
return np.ma.masked_greater(result_dist_to_use, np.mean(result_dist_to_use) + sigma_outlier*np.std(result_dist_to_use))
def best_points_allT(result_dist_to_use):
'''
Best points for all T
'''
return np.argsort(result_dist_to_use)[:nb_best_points]
def str_best_params(best_i, result_dist_to_use):
return ' '.join(["%s %.4f" % (parameter_names_sorted[param_i], result_parameters_flat[best_i, param_i]) for param_i in xrange(len(parameter_names_sorted))]) + ' >> %f' % result_dist_to_use[best_i]
def plot_scatter(all_vars, result_dist_to_use_name, title='', log_color=True, downsampling=1, label_file='', mask_outliers=True):
result_dist_to_use = all_vars[result_dist_to_use_name]
result_parameters_flat = all_vars['result_parameters_flat']
# Filter if downsampling
filter_downsampling = np.arange(0, result_dist_to_use.size, downsampling)
result_dist_to_use = result_dist_to_use[filter_downsampling]
result_parameters_flat = result_parameters_flat[filter_downsampling]
if mask_outliers:
result_dist_to_use = mask_outliers_array(result_dist_to_use)
best_points_result_dist_to_use = np.argsort(result_dist_to_use)[:nb_best_points]
# Construct all permutations of 3 parameters, for 3D scatters
params_permutations = set([tuple(np.sort(np.random.choice(result_parameters_flat.shape[-1], 3, replace=False)).tolist()) for i in xrange(1000)])
for param_permut in params_permutations:
fig = plt.figure()
ax = Axes3D(fig)
# One plot per parameter permutation
if log_color:
color_points = np.log(result_dist_to_use)
else:
color_points = result_dist_to_use
utils.scatter3d(result_parameters_flat[:, param_permut[0]], result_parameters_flat[:, param_permut[1]], result_parameters_flat[:, param_permut[2]], s=size_normal_points, c=color_points, xlabel=parameter_names_sorted[param_permut[0]], ylabel=parameter_names_sorted[param_permut[1]], zlabel=parameter_names_sorted[param_permut[2]], title=title, ax_handle=ax)
utils.scatter3d(result_parameters_flat[best_points_result_dist_to_use, param_permut[0]], result_parameters_flat[best_points_result_dist_to_use, param_permut[1]], result_parameters_flat[best_points_result_dist_to_use, param_permut[2]], c='r', s=size_best_points, ax_handle=ax)
if savefigs:
dataio.save_current_figure('scatter3d_%s_%s%s_{label}_{unique_id}.pdf' % (result_dist_to_use_name, '_'.join([parameter_names_sorted[i] for i in param_permut]), label_file))
if savemovies:
try:
utils.rotate_plot3d(ax, dataio.create_formatted_filename('scatter3d_%s_%s%s_{label}_{unique_id}.mp4' % (result_dist_to_use_name, '_'.join([parameter_names_sorted[i] for i in param_permut]), label_file)), bitrate=8000, min_duration=8)
utils.rotate_plot3d(ax, dataio.create_formatted_filename('scatter3d_%s_%s%s_{label}_{unique_id}.gif' % (result_dist_to_use_name, '_'.join([parameter_names_sorted[i] for i in param_permut]), label_file)), nb_frames=30, min_duration=8)
except Exception:
# Most likely wrong aggregator...
print "failed when creating movies for ", result_dist_to_use_name
if False and savefigs:
ax.view_init(azim=90, elev=10)
dataio.save_current_figure('scatter3d_view2_%s_%s%s_{label}_{unique_id}.pdf' % (result_dist_to_use_name, '_'.join([parameter_names_sorted[i] for i in param_permut]), label_file))
# plt.close('all')
print "Parameters: %s" % ', '.join(parameter_names_sorted)
print "Best points, %s:" % title
print '\n'.join([str_best_params(best_i, result_dist_to_use) for best_i in best_points_result_dist_to_use])
if scatter3d_sumT:
plot_scatter(locals(), 'result_fitexperiments_noiseconv_bays09_bic_avg_sumT', 'BIC Bays09')
plot_scatter(locals(), 'result_fitexperiments_noiseconv_bays09_ll90_avg_sumT', 'LL90 Bays09')
plot_scatter(locals(), 'result_fitexperiments_noiseconv_gorgo11_bic_avg_sumT', 'BIC Gorgo11')
plot_scatter(locals(), 'result_fitexperiments_noiseconv_gorgo11_ll90_avg_sumT', 'LL90 Gorgo11')
plot_scatter(locals(), 'result_fitexperiments_noiseconv_dualrecall_bic_avg_sumT', 'BIC Dual recall')
plot_scatter(locals(), 'result_fitexperiments_noiseconv_dualrecall_ll90_avg_sumT', 'LL90 Dual recall')
if plots_flat_sorted_performance:
result_dist_to_try = []
if do_bays09:
result_dist_to_try.extend(['result_fitexperiments_noiseconv_bays09_bic_avg_sumT', 'result_fitexperiments_noiseconv_bays09_ll90_avg_sumT'])
if do_gorgo11:
result_dist_to_try.extend(['result_fitexperiments_noiseconv_gorgo11_bic_avg_sumT', 'result_fitexperiments_noiseconv_gorgo11_ll90_avg_sumT'])
for result_dist in result_dist_to_try:
order_indices = np.argsort(locals()[result_dist])[::-1]
f, axes = plt.subplots(2, 1)
axes[0].plot(np.arange(4) + result_parameters_flat[order_indices]/np.max(result_parameters_flat[order_indices], axis=0))
axes[0].legend(parameter_names_sorted, loc='upper left')
axes[0].set_ylabel('Parameters')
axes[1].plot(locals()[result_dist][order_indices])
axes[1].set_ylabel(result_dist.split('result_dist_')[-1])
axes[0].set_title('Distance ordered ' + result_dist.split('result_dist_')[-1])
f.canvas.draw()
if savefigs:
dataio.save_current_figure('plot_sortedperf_full_%s_{label}_{unique_id}.pdf' % (result_dist))
if plots_memorycurves_fits_best:
# Alright, will actually reload the data from another set of runs, and find the closest parameter set to the ones found here.
data = utils.load_npy('normalisedsigmaxsigmaoutput_random_fitmixturemodels_sigmaxMratiosigmaoutput_repetitions3_280814/outputs/global_plots_fitmixtmodel_random_sigmaoutsigmaxnormMratio-plots_fit_mixturemodels_random-75eb9c74-72e0-4165-8014-92c1ef446f0a.npy')
result_em_fits_flat_fitmixture = data['result_em_fits_flat']
result_parameters_flat_fitmixture = data['result_parameters_flat']
all_args_arr_fitmixture = data['all_args_arr']
data_dir = None
if not os.environ.get('WORKDIR_DROP'):
data_dir = '../experimental_data/'
plotting_parameters = launchers_memorycurves_marginal_fi.load_prepare_datasets()
def plot_memorycurves_fits_fromexternal(all_vars, result_dist_to_use_name, nb_best_points=10):
result_dist_to_use = all_vars[result_dist_to_use_name]
result_em_fits_flat_fitmixture = all_vars['result_em_fits_flat_fitmixture']
result_parameters_flat_fitmixture = all_vars['result_parameters_flat_fitmixture']
all_args_arr_fitmixture = all_vars['all_args_arr_fitmixture']
best_point_indices_result_dist = np.argsort(result_dist_to_use)[:nb_best_points]
for best_point_index in best_point_indices_result_dist:
print "extended plot desired for: " + str_best_params(best_point_index, result_dist_to_use)
dist_best_points_fitmixture = np.abs(result_parameters_flat_fitmixture - result_parameters_flat[best_point_index])
dist_best_points_fitmixture -= np.min(dist_best_points_fitmixture, axis=0)
dist_best_points_fitmixture /= np.max(dist_best_points_fitmixture, axis=0)
best_point_index_fitmixture = np.argmax(np.prod(1-dist_best_points_fitmixture, axis=-1))
print "found closest: " + ' '.join(["%s %.4f" % (parameter_names_sorted[param_i], result_parameters_flat_fitmixture[best_point_index_fitmixture, param_i]) for param_i in xrange(len(parameter_names_sorted))])
# Update arguments
all_args_arr_fitmixture[best_point_index_fitmixture].update(dict(zip(parameter_names_sorted, result_parameters_flat_fitmixture[best_point_index_fitmixture])))
packed_data = dict(T_space=T_space, result_em_fits=result_em_fits_flat_fitmixture[best_point_index_fitmixture], all_parameters=all_args_arr_fitmixture[best_point_index_fitmixture])
plotting_parameters['suptitle'] = result_dist_to_use_name
plotting_parameters['reuse_axes'] = False
if savefigs:
packed_data['dataio'] = dataio
launchers_memorycurves_marginal_fi.do_memory_plots(packed_data, plotting_parameters)
plot_memorycurves_fits_fromexternal(locals(), 'result_external_fitexperiments_noiseconv_bays09_ll90_avg_sumT', nb_best_points=3)
plot_memorycurves_fits_fromexternal(locals(), 'result_external_fitexperiments_noiseconv_gorgo11_ll90_avg_sumT', nb_best_points=3)
plot_memorycurves_fits_fromexternal(locals(), 'result_external_fitexperiments_noiseconv_dualrecall_ll90_avg_sumT', nb_best_points=3)
all_args = data_pbs.loaded_data['args_list']
variables_to_save = ['experiment_ids', 'parameter_names_sorted', 'T_space', 'all_args_arr', 'all_repeats_completed', 'filter_data']
if savedata:
dataio.save_variables_default(locals(), variables_to_save)
dataio.make_link_output_to_dropbox(dropbox_current_experiment_folder='sigmaoutput_normalisedsigmax_random')
plt.show()
return locals()
def postprocess_dualrecall_fitmixturemodel(data_pbs, generator_module=None):
'''
Reload runs from PBS
To be plotted in Ipython later
'''
#### SETUP
#
savedata = True
colormap = None # or 'cubehelix'
plt.rcParams['font.size'] = 16
#
#### /SETUP
print "Order parameters: ", data_pbs.dataset_infos['parameters']
# parameters: M, ratio_conj, sigmax
# Extract data
result_em_fits = np.array(data_pbs.dict_arrays['result_em_fits']['results_flat'])
result_dist_dualrecall_angle = np.array(data_pbs.dict_arrays['result_dist_dualrecall_angle']['results_flat'])
result_dist_dualrecall_angle_emmixt_KL = np.array(data_pbs.dict_arrays['result_dist_dualrecall_angle_emmixt_KL']['results_flat'])
result_dist_dualrecall_colour = np.array(data_pbs.dict_arrays['result_dist_dualrecall_colour']['results_flat'])
result_dist_dualrecall_colour_emmixt_KL = np.array(data_pbs.dict_arrays['result_dist_dualrecall_colour_emmixt_KL']['results_flat'])
result_parameters_flat = np.array(data_pbs.dict_arrays['result_em_fits']['parameters_flat'])
all_repeats_completed = data_pbs.dict_arrays['result_em_fits']['repeats_completed']
all_args_arr = np.array(data_pbs.loaded_data['args_list'])
M_space = data_pbs.loaded_data['parameters_uniques']['M']
ratio_conj_space = data_pbs.loaded_data['parameters_uniques']['ratio_conj']
sigmax_space = data_pbs.loaded_data['parameters_uniques']['sigmax']
num_repetitions = generator_module.num_repetitions
parameter_names_sorted = data_pbs.dataset_infos['parameters']
dataio = DataIO(output_folder=generator_module.pbs_submission_infos['simul_out_dir'] + '/outputs/', label='global_' + dataset_infos['save_output_filename'])
# Load ground truth
data_dualrecall = load_experimental_data.load_data_dualrecall(fit_mixture_model=True)
## Filter everything with repeats_completed == num_repet
filter_data = all_repeats_completed == num_repetitions - 1
result_parameters_flat = result_parameters_flat[filter_data]
result_em_fits = result_em_fits[filter_data]
result_dist_dualrecall_angle = result_dist_dualrecall_angle[filter_data]
result_dist_dualrecall_angle_emmixt_KL = result_dist_dualrecall_angle_emmixt_KL[filter_data]
result_dist_dualrecall_colour = result_dist_dualrecall_colour[filter_data]
result_dist_dualrecall_colour_emmixt_KL = result_dist_dualrecall_colour_emmixt_KL[filter_data]
all_args_arr = all_args_arr[filter_data]
all_repeats_completed = all_repeats_completed[filter_data]
print "Size post-filter: ", result_parameters_flat.shape[0]
# Compute lots of averages over the repetitions
result_em_fits_avg = utils.nanmean(result_em_fits, axis=-1)
result_dist_dualrecall_angle_avg = utils.nanmean(result_dist_dualrecall_angle, axis=-1)
result_dist_dualrecall_angle_emmixt_KL_avg = utils.nanmean(result_dist_dualrecall_angle_emmixt_KL, axis=-1)
result_dist_dualrecall_colour_avg = utils.nanmean(result_dist_dualrecall_colour, axis=-1)
result_dist_dualrecall_colour_emmixt_KL_avg = utils.nanmean(result_dist_dualrecall_colour_emmixt_KL, axis=-1)
# all_args = data_pbs.loaded_data['args_list']
variables_to_save = ['parameter_names_sorted', 'all_args_arr', 'all_repeats_completed', 'filter_data']
if savedata:
dataio.save_variables_default(locals(), variables_to_save)
dataio.make_link_output_to_dropbox(dropbox_current_experiment_folder='dualrecall_fitmixturemodel')
plt.show()
return locals()
from dataio import DataIO, ImageHandler
from unet_model import UNet
from tensorflow.compat.v1 import ConfigProto
from tensorflow.compat.v1 import InteractiveSession
import tensorflow as tf
# Solving CUDNN Issues
config = ConfigProto()
config.gpu_options.allow_growth = True
# config.gpu_options.per_process_gpu_memory_fraction = 0.9
session = InteractiveSession(config=config)
# create all instances here
dat = DataIO().load_matfile_images_first('retina_training_STARE.mat')
display = ImageHandler()
# Run U-Net Model
model = UNet('Test_Model')
model.create_UNet_retina()
model.fit_model(*dat, nepochs=2000)
# get plot for training accuracy and loss
plot1 = model.plot_accuracy()
plot1.plot()
plot1.show()
plot2 = model.plot_loss()
plot2.plot()
plot2.show()
def plots_fit_mixturemodels_random(data_pbs, generator_module=None):
'''
Reload runs from PBS
!!!
IMPORTANT LOOK AT ME
!!!
'''
#### SETUP
#
savefigs = True
savedata = True
savemovies = False
do_bays09 = True
do_gorgo11 = True
plots_scatter3d = True
plots_scatter_per_T = False
plots_flat_sorted_performance = False
plots_memorycurves_fits_best = True
# do_relaunch_bestparams_pbs = True
colormap = None # or 'cubehelix'
plt.rcParams['font.size'] = 16
#
#### /SETUP
print "Order parameters: ", data_pbs.dataset_infos['parameters']
# parameters: M, ratio_conj, sigmax
# Extract data
T_space = data_pbs.loaded_data['datasets_list'][0]['T_space']
result_em_fits_flat = np.array(data_pbs.dict_arrays['result_em_fits']['results_flat'])
result_precisions_flat = np.array(data_pbs.dict_arrays['result_all_precisions']['results_flat'])
result_dist_bays09_flat = np.array(data_pbs.dict_arrays['result_dist_bays09']['results_flat'])
result_dist_gorgo11_flat = np.array(data_pbs.dict_arrays['result_dist_gorgo11']['results_flat'])
result_dist_bays09_emmixt_KL = np.array(data_pbs.dict_arrays['result_dist_bays09_emmixt_KL']['results_flat'])
result_dist_gorgo11_emmixt_KL = np.array(data_pbs.dict_arrays['result_dist_gorgo11_emmixt_KL']['results_flat'])
result_parameters_flat = np.array(data_pbs.dict_arrays['result_em_fits']['parameters_flat'])
all_repeats_completed = data_pbs.dict_arrays['result_em_fits']['repeats_completed']
all_args = data_pbs.loaded_data['args_list']
all_args_arr = np.array(all_args)
sigmaoutput_space = data_pbs.loaded_data['parameters_uniques']['sigma_output']
sigmax_space = data_pbs.loaded_data['parameters_uniques']['sigmax']
ratio_space = data_pbs.loaded_data['parameters_uniques']['sigmax']
num_repetitions = generator_module.num_repetitions
parameter_names_sorted = data_pbs.dataset_infos['parameters']
dataio = DataIO(output_folder=generator_module.pbs_submission_infos['simul_out_dir'] + '/outputs/', label='global_' + dataset_infos['save_output_filename'])
# Load bays09
# data_bays09 = load_experimental_data.load_data_bays09(fit_mixture_model=True)
# bays09_nitems = data_bays09['data_to_fit']['n_items']
# bays09_em_target = np.nan*np.empty((bays09_nitems.max(), 4)) #kappa, prob_target, prob_nontarget, prob_random
# bays09_em_target[bays09_nitems - 1] = data_bays09['em_fits_nitems_arrays']['mean'].T
# bays09_emmixt_target = bays09_em_target[:, 1:]
## Filter everything with sigma_output > 1.0 and repeats_completed == num_repet
filter_data = (result_parameters_flat[:, -1] < 1.0) & (all_repeats_completed == num_repetitions - 1)
result_em_fits_flat = result_em_fits_flat[filter_data]
result_precisions_flat = result_precisions_flat[filter_data]
result_dist_bays09_flat = result_dist_bays09_flat[filter_data]
result_dist_gorgo11_flat = result_dist_gorgo11_flat[filter_data]
result_dist_bays09_emmixt_KL = result_dist_bays09_emmixt_KL[filter_data]
result_dist_gorgo11_emmixt_KL = result_dist_gorgo11_emmixt_KL[filter_data]
result_parameters_flat = result_parameters_flat[filter_data]
all_args_arr = all_args_arr[filter_data]
all_repeats_completed = all_repeats_completed[filter_data]
# for _result_dist in ['result_em_fits_flat', 'result_precisions_flat', 'result_dist_bays09_flat', 'result_dist_gorgo11_flat', 'result_dist_bays09_emmixt_KL', 'result_dist_gorgo11_emmixt_KL', 'result_parameters_flat']:
# locals()[key] = locals()[key][filter_sigmaout]
# # exec("%s = %s[%s]" % (_result_dist, _result_dist, 'filter_sigmaout'))
## Compute some stuff
result_em_fits_all_avg = utils.nanmean(result_em_fits_flat, axis=-1)
result_em_kappa_allT = result_em_fits_all_avg[..., 0]
result_em_emmixt_allT = result_em_fits_all_avg[..., 1:4]
result_precisions_all_avg = utils.nanmean(result_precisions_flat, axis=-1)
##### Distance to Bays09
result_dist_bays09_allT_avg = utils.nanmean(result_dist_bays09_flat, axis=-1)
result_dist_bays09_emmixt_KL_allT_avg = utils.nanmean(result_dist_bays09_emmixt_KL, axis=-1)
result_dist_bays09_kappa_allT = result_dist_bays09_allT_avg[..., 0]
result_dist_bays09_kappa_sumT = np.nansum(result_dist_bays09_kappa_allT, axis=-1)
result_dist_bays09_logkappa_sumT = np.log(result_dist_bays09_kappa_sumT)
result_dist_bays09_emmixt_KL_sumT = np.nansum(result_dist_bays09_emmixt_KL_allT_avg, axis=-1)
# combined versions
result_dist_bays09_both_normalised = result_dist_bays09_emmixt_KL_sumT/np.max(result_dist_bays09_emmixt_KL_sumT) + result_dist_bays09_kappa_sumT/np.max(result_dist_bays09_kappa_sumT)
result_dist_bays09_logkappamixtKL = result_dist_bays09_logkappa_sumT + result_dist_bays09_emmixt_KL_sumT
result_dist_bays09_logkappamixtKL_normalised = result_dist_bays09_logkappa_sumT/np.max(result_dist_bays09_logkappa_sumT) + result_dist_bays09_emmixt_KL_sumT/np.max(result_dist_bays09_emmixt_KL_sumT)
result_dist_bays09_logkappa_sumT_forand = result_dist_bays09_logkappa_sumT - np.min(result_dist_bays09_logkappa_sumT)*np.sign(np.min(result_dist_bays09_logkappa_sumT))
result_dist_bays09_logkappa_sumT_forand /= np.max(result_dist_bays09_logkappa_sumT_forand)
result_dist_bays09_emmixt_KL_sumT_forand = result_dist_bays09_emmixt_KL_sumT - np.min(result_dist_bays09_emmixt_KL_sumT)*np.sign(np.min(result_dist_bays09_emmixt_KL_sumT))
result_dist_bays09_emmixt_KL_sumT_forand /= np.max(result_dist_bays09_emmixt_KL_sumT_forand)
result_dist_bays09_logkappamixtKL_AND = 1. - (1. - result_dist_bays09_logkappa_sumT_forand)*(1. - result_dist_bays09_emmixt_KL_sumT_forand)
# Mask kappa for bad performance
# result_dist_bays09_kappa_sumT_masked = np.ma.masked_greater(result_dist_bays09_kappa_sumT, 2*np.median(result_dist_bays09_kappa_sumT))
# result_dist_bays09_logkappa_sumT_masked = np.ma.masked_greater(result_dist_bays09_logkappa_sumT, 2*np.median(result_dist_bays09_logkappa_sumT))
# result_dist_bays09_emmixt_KL_sumT_masked = np.ma.masked_greater(result_dist_bays09_emmixt_KL_sumT, 2*np.median(result_dist_bays09_emmixt_KL_sumT))
# result_dist_bays09_both_normalised_mult_masked = 1-(1. - result_dist_bays09_emmixt_KL_sumT_masked/np.max(result_dist_bays09_emmixt_KL_sumT_masked))*(1. - result_dist_bays09_kappa_sumT_masked/np.max(result_dist_bays09_kappa_sumT_masked))
##### Distance to Gorgo11
result_dist_gorgo11_allT_avg = utils.nanmean(result_dist_gorgo11_flat, axis=-1)
result_dist_gorgo11_emmixt_KL_allT_avg = utils.nanmean(result_dist_gorgo11_emmixt_KL, axis=-1)
result_dist_gorgo11_kappa_allT = result_dist_gorgo11_allT_avg[..., 0]
result_dist_gorgo11_kappa_sumT = np.nansum(result_dist_gorgo11_kappa_allT, axis=-1)
result_dist_gorgo11_logkappa_sumT = np.log(result_dist_gorgo11_kappa_sumT)
result_dist_gorgo11_emmixt_KL_sumT = np.nansum(result_dist_gorgo11_emmixt_KL_allT_avg, axis=-1)
result_dist_gorgo11_emmixt_KL_sumT25 = np.nansum(result_dist_gorgo11_emmixt_KL_allT_avg[:, 1:], axis=-1)
result_dist_gorgo11_logkappa_sumT25 = np.log(np.nansum(result_dist_gorgo11_kappa_allT[..., 1:], axis=-1))
# combined versions
result_dist_gorgo11_both_normalised = result_dist_gorgo11_emmixt_KL_sumT/np.max(result_dist_gorgo11_emmixt_KL_sumT) + result_dist_gorgo11_kappa_sumT/np.max(result_dist_gorgo11_kappa_sumT)
result_dist_gorgo11_logkappamixtKL = result_dist_gorgo11_logkappa_sumT + result_dist_gorgo11_emmixt_KL_sumT
result_dist_gorgo11_logkappamixtKL_normalised = result_dist_gorgo11_logkappa_sumT/np.max(result_dist_gorgo11_logkappa_sumT) + result_dist_gorgo11_emmixt_KL_sumT/np.max(result_dist_gorgo11_emmixt_KL_sumT)
result_dist_gorgo11_logkappa_sumT_forand = result_dist_gorgo11_logkappa_sumT - np.min(result_dist_gorgo11_logkappa_sumT)*np.sign(np.min(result_dist_gorgo11_logkappa_sumT))
result_dist_gorgo11_logkappa_sumT_forand /= np.max(result_dist_gorgo11_logkappa_sumT_forand)
result_dist_gorgo11_logkappa_sumT25_forand = result_dist_gorgo11_logkappa_sumT25 - np.min(result_dist_gorgo11_logkappa_sumT25)*np.sign(np.min(result_dist_gorgo11_logkappa_sumT25))
result_dist_gorgo11_logkappa_sumT25_forand /= np.max(result_dist_gorgo11_logkappa_sumT25_forand)
result_dist_gorgo11_emmixt_KL_sumT_forand = result_dist_gorgo11_emmixt_KL_sumT - np.min(result_dist_gorgo11_emmixt_KL_sumT)*np.sign(np.min(result_dist_gorgo11_emmixt_KL_sumT))
result_dist_gorgo11_emmixt_KL_sumT_forand /= np.max(result_dist_gorgo11_emmixt_KL_sumT_forand)
result_dist_gorgo11_emmixt_KL_sumT25_forand = result_dist_gorgo11_emmixt_KL_sumT25 - np.min(result_dist_gorgo11_emmixt_KL_sumT25)*np.sign(np.min(result_dist_gorgo11_emmixt_KL_sumT25))
result_dist_gorgo11_emmixt_KL_sumT25_forand /= np.max(result_dist_gorgo11_emmixt_KL_sumT25_forand)
result_dist_gorgo11_logkappamixtKL_AND = 1. - (1. - result_dist_gorgo11_logkappa_sumT_forand)*(1. - result_dist_gorgo11_emmixt_KL_sumT_forand)
result_dist_gorgo11_logkappa25mixtKL_AND = 1. - (1. - result_dist_gorgo11_logkappa_sumT25_forand)*(1. - result_dist_gorgo11_emmixt_KL_sumT25_forand)
def str_best_params(best_i, result_dist_to_use):
return ' '.join(["%s %.4f" % (parameter_names_sorted[param_i], result_parameters_flat[best_i, param_i]) for param_i in xrange(len(parameter_names_sorted))]) + ' >> %f' % result_dist_to_use[best_i]
if plots_scatter3d:
nb_best_points = 30
size_normal_points = 8
size_best_points = 50
def plot_scatter(all_vars, result_dist_to_use_name, title='', log_color=True, downsampling=1, label_file=''):
result_dist_to_use = all_vars[result_dist_to_use_name]
result_parameters_flat = all_vars['result_parameters_flat']
# Filter if downsampling
filter_downsampling = np.arange(0, result_dist_to_use.size, downsampling)
result_dist_to_use = result_dist_to_use[filter_downsampling]
result_parameters_flat = result_parameters_flat[filter_downsampling]
best_points_result_dist_to_use = np.argsort(result_dist_to_use)[:nb_best_points]
# Construct all permutations of 3 parameters, for 3D scatters
params_permutations = set([tuple(np.sort(np.random.choice(result_parameters_flat.shape[-1], 3, replace=False)).tolist()) for i in xrange(1000)])
for param_permut in params_permutations:
fig = plt.figure()
ax = Axes3D(fig)
# One plot per parameter permutation
if log_color:
color_points = np.log(result_dist_to_use)
else:
color_points = result_dist_to_use
utils.scatter3d(result_parameters_flat[:, param_permut[0]], result_parameters_flat[:, param_permut[1]], result_parameters_flat[:, param_permut[2]], s=size_normal_points, c=color_points, xlabel=parameter_names_sorted[param_permut[0]], ylabel=parameter_names_sorted[param_permut[1]], zlabel=parameter_names_sorted[param_permut[2]], title=title, ax_handle=ax)
utils.scatter3d(result_parameters_flat[best_points_result_dist_to_use, param_permut[0]], result_parameters_flat[best_points_result_dist_to_use, param_permut[1]], result_parameters_flat[best_points_result_dist_to_use, param_permut[2]], c='r', s=size_best_points, ax_handle=ax)
if savefigs:
dataio.save_current_figure('scatter3d_%s_%s%s_{label}_{unique_id}.pdf' % (result_dist_to_use_name, '_'.join([parameter_names_sorted[i] for i in param_permut]), label_file))
if savemovies:
try:
utils.rotate_plot3d(ax, dataio.create_formatted_filename('scatter3d_%s_%s%s_{label}_{unique_id}.mp4' % (result_dist_to_use_name, '_'.join([parameter_names_sorted[i] for i in param_permut]), label_file)), bitrate=8000, min_duration=8)
utils.rotate_plot3d(ax, dataio.create_formatted_filename('scatter3d_%s_%s%s_{label}_{unique_id}.gif' % (result_dist_to_use_name, '_'.join([parameter_names_sorted[i] for i in param_permut]), label_file)), nb_frames=30, min_duration=8)
except Exception:
# Most likely wrong aggregator...
print "failed when creating movies for ", result_dist_to_use_name
if False and savefigs:
ax.view_init(azim=90, elev=10)
dataio.save_current_figure('scatter3d_view2_%s_%s%s_{label}_{unique_id}.pdf' % (result_dist_to_use_name, '_'.join([parameter_names_sorted[i] for i in param_permut]), label_file))
# plt.close('all')
print "Parameters: %s" % ', '.join(parameter_names_sorted)
print "Best points, %s:" % title
print '\n'.join([str_best_params(best_i, result_dist_to_use) for best_i in best_points_result_dist_to_use])
#### BAYS 09
if do_bays09:
# Distance for log kappa, all T
plot_scatter(locals(), 'result_dist_bays09_logkappa_sumT', 'Bays09 kappa all T', log_color=False)
# # Distance for em fits, all T, KL distance
plot_scatter(locals(), 'result_dist_bays09_emmixt_KL_sumT', 'Bays09 em fits, sum T, KL', log_color=False)
# Distance for product of normalised em fits KL + normalised log kappa, all T
plot_scatter(locals(), 'result_dist_bays09_logkappamixtKL', 'Bays09 em fits KL, log kappa')
# Distance for AND normalised em fits KL + log kappa
plot_scatter(locals(), 'result_dist_bays09_logkappamixtKL_AND', 'Bays09 em fits KL AND log kappa')
#### Gorgo 11
if do_gorgo11:
# Distance for product of normalised em fits KL + normalised log kappa, all T
plot_scatter(locals(), 'result_dist_gorgo11_logkappamixtKL', 'Gorgo11 em fits KL, log kappa')
# Distance for AND normalised em fits KL + log kappa
plot_scatter(locals(), 'result_dist_gorgo11_logkappamixtKL_AND', 'Gorgo11 em fits KL AND log kappa')
# Distance for logkappa
plot_scatter(locals(), 'result_dist_gorgo11_logkappa_sumT', 'Gorgo11 log kappa all T', log_color=False)
# Distance for EM mixture proportions
plot_scatter(locals(), 'result_dist_gorgo11_emmixt_KL_sumT', 'Gorgo11 em fits, sum T, KL', log_color=False)
if plots_flat_sorted_performance:
result_dist_to_try = []
if do_bays09:
result_dist_to_try.extend(['result_dist_bays09_logkappamixtKL_AND', 'result_dist_bays09_logkappamixtKL'])
if do_gorgo11:
result_dist_to_try.extend(['result_dist_gorgo11_logkappamixtKL_AND', 'result_dist_gorgo11_logkappamixtKL'])
for result_dist in result_dist_to_try:
order_indices = np.argsort(locals()[result_dist])[::-1]
f, axes = plt.subplots(2, 1)
axes[0].plot(np.arange(4) + result_parameters_flat[order_indices]/np.max(result_parameters_flat[order_indices], axis=0))
axes[0].legend(parameter_names_sorted, loc='upper left')
axes[0].set_ylabel('Parameters')
axes[1].plot(locals()[result_dist][order_indices])
axes[1].set_ylabel(result_dist.split('result_dist_')[-1])
axes[0].set_title('Distance ordered ' + result_dist.split('result_dist_')[-1])
f.canvas.draw()
if savefigs:
dataio.save_current_figure('plot_sortedperf_full_%s_{label}_{unique_id}.pdf' % (result_dist))
## Extra plot for logkappamixtKL_AND, it seems well behaved
def plot_flat_best(all_vars, result_name, order_indices_filter, filter_goodAND, ordering='fitness'):
f = plt.figure()
axp1 = plt.subplot2grid((3, 2), (0, 0))
axp2 = plt.subplot2grid((3, 2), (0, 1))
axp3 = plt.subplot2grid((3, 2), (1, 0))
axp4 = plt.subplot2grid((3, 2), (1, 1))
axfit = plt.subplot2grid((3, 2), (2, 0), colspan=2)
axp1.plot(result_parameters_flat[filter_goodAND][order_indices_filter, 0])
axp1.set_title(parameter_names_sorted[0])
axp2.plot(result_parameters_flat[filter_goodAND][order_indices_filter, 1], 'g')
axp2.set_title(parameter_names_sorted[1])
axp3.plot(result_parameters_flat[filter_goodAND][order_indices_filter, 2], 'r')
axp3.set_title(parameter_names_sorted[2])
axp4.plot(result_parameters_flat[filter_goodAND][order_indices_filter, 3], 'k')
axp4.set_title(parameter_names_sorted[3])
axfit.plot(all_vars[result_name][filter_goodAND][order_indices_filter])
axfit.set_ylabel('bays09_logkappamixtKL_AND')
plt.suptitle('Distance ordered bays09_logkappamixtKL_AND')
if savefigs:
dataio.save_current_figure('plot_sortedperf_best_%s_%s_{label}_{unique_id}.pdf' % (result_name, ordering))
if do_bays09:
filter_goodAND = result_dist_bays09_logkappamixtKL_AND < 0.2
# First order them by fitness
order_indices_filter = np.argsort(result_dist_bays09_logkappamixtKL_AND[filter_goodAND])[::-1]
plot_flat_best(locals(), 'result_dist_bays09_logkappamixtKL_AND', order_indices_filter, filter_goodAND, 'fitness')
# Then by M, to see if there is some structure
order_indices_filter = np.argsort(result_parameters_flat[filter_goodAND, 0])
plot_flat_best(locals(), 'result_dist_bays09_logkappamixtKL_AND', order_indices_filter, filter_goodAND, 'M')
if do_gorgo11:
filter_goodAND = result_dist_gorgo11_logkappamixtKL_AND < 0.5
# First order them by fitness
order_indices_filter = np.argsort(result_dist_gorgo11_logkappamixtKL_AND[filter_goodAND])[::-1]
plot_flat_best(locals(), 'result_dist_gorgo11_logkappamixtKL_AND', order_indices_filter, filter_goodAND, 'fitness')
# Then by M, to see if there is some structure
order_indices_filter = np.argsort(result_parameters_flat[filter_goodAND, 0])
plot_flat_best(locals(), 'result_dist_gorgo11_logkappamixtKL_AND', order_indices_filter, filter_goodAND, 'M')
# dist_cmaes_result = np.sum((result_parameters_flat - np.array([75, 1.0, 0.1537, 0.2724]))**2., axis=-1)
# filter_close_cmaes_result = np.argsort(dist_cmaes_result)[:20]
# order_indices_filter = np.argsort(result_dist_gorgo11_logkappamixtKL_AND[filter_close_cmaes_result])[::-1]
# plot_flat_best(locals(), 'result_dist_gorgo11_logkappamixtKL_AND', order_indices_filter, filter_close_cmaes_result, 'Like current CMA/ES run')
if plots_scatter_per_T:
for T_i, T in enumerate(T_space):
# Kappa per T, fit to Bays09
result_dist_bays09_kappa_currT = result_dist_bays09_kappa_allT[:, T_i]
result_dist_bays09_kappa_currT_masked = mask_outliers(result_dist_bays09_kappa_currT)
plot_scatter(locals(), 'result_dist_bays09_kappa_currT_masked', 'kappa T %d masked' % T, label_file="T{}".format(T))
# EM Mixt per T, fit to Bays09
result_dist_bays09_emmixt_KL_currT = result_dist_bays09_emmixt_KL_allT_avg[:, T_i]
result_dist_bays09_emmixt_KL_currT_masked = mask_outliers(result_dist_bays09_emmixt_KL_currT)
plot_scatter(locals(), 'result_dist_bays09_emmixt_KL_currT_masked', 'KL EM mixt T %d masked' % T, label_file="T{}".format(T), log_color=False)
if plots_memorycurves_fits_best:
data_dir = None
if not os.environ.get('WORKDIR_DROP'):
data_dir = '../experimental_data/'
plotting_parameters = launchers_memorycurves_marginal_fi.load_prepare_datasets(data_dir = data_dir)
def plot_memorycurves_fits(all_vars, result_dist_to_use_name, nb_best_points=10):
result_dist_to_use = all_vars[result_dist_to_use_name]
best_points_result_dist_to_use = np.argsort(result_dist_to_use)[:nb_best_points]
for best_point_index in best_points_result_dist_to_use:
print "extended plot for: " + str_best_params(best_point_index, result_dist_to_use)
# Update arguments
all_args_arr[best_point_index].update(dict(zip(parameter_names_sorted, result_parameters_flat[best_point_index])))
packed_data = dict(T_space=T_space, result_em_fits=result_em_fits_flat[best_point_index], all_parameters=all_args_arr[best_point_index])
plotting_parameters['suptitle'] = result_dist_to_use_name
plotting_parameters['reuse_axes'] = False
if savefigs:
packed_data['dataio'] = dataio
launchers_memorycurves_marginal_fi.do_memory_plots(packed_data, plotting_parameters)
plot_memorycurves_fits(locals(), 'result_dist_bays09_logkappamixtKL_AND', nb_best_points=3)
plot_memorycurves_fits(locals(), 'result_dist_gorgo11_logkappamixtKL_AND', nb_best_points=3)
# plot_memorycurves_fits(locals(), 'result_dist_gorgo11_logkappamixtKL', nb_best_points=3)
plot_memorycurves_fits(locals(), 'result_dist_gorgo11_logkappa25mixtKL_AND', nb_best_points=3)
# plot_memorycurves_fits(locals(), 'result_dist_gorgo11_logkappa_sumT', nb_best_points=3)
# # Interpolate
# if plots_interpolate:
# sigmax_target = 0.9
# M_interp_space = np.arange(6, 625, 5)
# ratio_interp_space = np.linspace(0.01, 1.0, 50)
# # sigmax_interp_space = np.linspace(0.01, 1.0, 50)
# sigmax_interp_space = np.array([sigmax_target])
# params_crossspace = np.array(utils.cross(M_interp_space, ratio_interp_space, sigmax_interp_space))
# interpolated_data = rbf_interpolator(params_crossspace[:, 0], params_crossspace[:, 1], params_crossspace[:, 2]).reshape((M_interp_space.size, ratio_interp_space.size))
# utils.pcolor_2d_data(interpolated_data, M_interp_space, ratio_interp_space, 'M', 'ratio', 'interpolated, fixing sigmax= %.2f' % sigmax_target)
# points_closeby = ((result_parameters_flat[:, 2] - sigmax_target)**2)< 0.01
# plt.figure()
# # plt.imshow(interpolated_data, extent=(M_interp_space.min(), M_interp_space.max(), ratio_interp_space.min(), ratio_interp_space.max()))
# plt.imshow(interpolated_data)
# plt.scatter(result_parameters_flat[points_closeby, 0], result_parameters_flat[points_closeby, 1], s=100, c=result_fitexperiments_bic_avg[points_closeby], marker='o')
# if plot_per_ratio:
# # Plot the evolution of loglike as a function of sigmax, with std shown
# for ratio_conj_i, ratio_conj in enumerate(ratio_space):
# ax = utils.plot_mean_std_area(sigmax_space, result_log_posterior_mean[ratio_conj_i], result_log_posterior_std[ratio_conj_i])
# ax.get_figure().canvas.draw()
# if savefigs:
# dataio.save_current_figure('results_fitexp_%s_loglike_ratioconj%.2f_{label}_global_{unique_id}.pdf' % (exp_dataset, ratio_conj))
# all_args = data_pbs.loaded_data['args_list']
variables_to_save = ['parameter_names_sorted', 'all_args_arr', 'all_repeats_completed', 'filter_data']
if savedata:
dataio.save_variables_default(locals(), variables_to_save)
dataio.make_link_output_to_dropbox(dropbox_current_experiment_folder='sigmaoutput_normalisedsigmax_random')
plt.show()
return locals()