def perform_classification():
# get list of subjects (subjects list specified or get from the pattern)
if '*' in subjects_names.get() and \
len(subjects_names.get().split(' ')) == 1:
subjects_pattern = subjects_names.get()
subjects_list = get_subject_names(
var_base_dir.get(), subjects_pattern.replace('*', '')
)
else:
subjects_list = subjects_names.get().split(' ')
# number of subjects
subs_num = len(subjects_list)
# get list of hands (can be only one hand) or get the pattern
if len(hands_names.get().split(' ')[0]) == 0:
hands_list = ['Left', 'Right']
else:
hands_list = hands_names.get().split(' ')
hands_num = len(hands_list)
# get the information required from Load_data and Classifier/Performance
# subs_num = subs_num.get()
# hands_num = hands_num.get()
# rois_num = rois_num.get()
n_times_num = var_n_times.get()
if var_rois_apply.get():
# get list of rois
rois_list = rois_names.get().split(' ')
rois_num = len(rois_list)
# create an array to store results of the classification performance
results = np.zeros(shape=(subs_num, hands_num, rois_num, n_times_num))
results_subjects = np.zeros(results.shape[:-1])
proportions_test_dataset = np.zeros(shape=results.shape)
proportions_mean = np.zeros(results.shape[:-2])
else:
# create an array to store results of the classification performance
results = np.zeros(shape=(subs_num, hands_num, n_times_num))
results_subjects = np.zeros(results.shape[:-1])
proportions_test_dataset = np.zeros(shape=results.shape)
proportions_mean = np.zeros(results.shape[:-1])
# result's labels - we have to know which result comes from which subject,
# hand, iteration, etc.
labels = []
# which iteration of the cross validation is that (e.g. which fold)
var_n_time_current = tk.IntVar()
# Main loop of the program
# for subject in number of subjects, etc.
for sub in range(subs_num):
# sublist of labels for this subject
labels.append([])
for hand in range(hands_num):
# sublist for labels fot this subject's hand
labels[-1].append([])
# Set mvpa directory containing bold signal file and the target.
# Use current subject and hand of this subject
mvpa_directory = os.path.join(
var_base_dir.get() +
schema.get() % (subjects_list[sub], hands_list[hand])
)
print(mvpa_directory)
# Load dataset using variables from load_data frame
# (load_data tab). Here volumens will be restricted to particular,
# chosen contrasts (e.g. plan vs rest).
dataset = load_data(mvpa_directory)
# If any rois are specified apply them.
if var_rois_apply.get():
rois_header = []
for roi in range(rois_num):
# get the data from specified import ROIs
roi_path = os.path.join(
mvpa_directory + 'ROIs/' + rois_list[roi] + '.nii.gz'
)
rois_header.append(rois_list[roi])
# reduce number of features in the dataset
dataset_reduced = feature_reduction(dataset, roi_path)
var_n_time_current.set('0')
for n_time in range(n_times_num):
# create Classifier specified in Classifier tab
cls = create_classifier()
# split dataset use Classifier/Performance settings
training_data, test_data = split_data(
dataset_reduced, var_n_time_current.get()
)
proportions_test_dataset[sub][hand][roi][n_time] = \
test_data[1].sum()/float(test_data[1].shape[0])
# train and test classifier
cls = train_and_test_classifier(
cls, training_data, test_data
)
accuracy = get_accuracy(cls)
del cls
var_n_time_current.set(var_n_time_current.get() + 1)
results[sub][hand][roi][n_time] = accuracy
print(
'%s, %s, %s, %d ==> %0.2f' % (
subjects_list[sub], hands_list[hand],
rois_list[roi], n_time, accuracy
)
)
print(
'%s, %s, %s <mean> ==> %0.2f' % (
subjects_list[sub], hands_list[hand],
rois_list[roi], results[sub][hand][roi].mean()
)
)
results_subjects[sub][hand][roi] = \
results[sub][hand][roi].mean()
proportions_mean[sub][hand] = \
proportions_test_dataset[sub][hand][roi].mean()
else:
dataset_reduced = feature_reduction(dataset)
var_n_time_current.set('0')
for n_time in range(n_times_num):
# create Classifier specified in Classifier tab
cls = create_classifier()
# split dataset use Classifier/Performance settings
training_data, test_data = split_data(
dataset_reduced, var_n_time_current.get()
)
proportions_test_dataset[sub][hand][n_time] = \
test_data[1].sum()/float(test_data[1].shape[0])
# train and test classifier
cls = train_and_test_classifier(
cls, training_data, test_data
)
accuracy = get_accuracy(cls)
del cls
var_n_time_current.set(var_n_time_current.get() + 1)
results[sub][hand][n_time] = accuracy
print(
'%s, %s, %d ==> %0.2f' % (
subjects_list[sub], hands_list[hand],
n_time, accuracy
)
)
print(
'%s, %s <mean> ==> %0.2f' % (
subjects_list[sub], hands_list[hand],
results[sub][hand].mean()
)
)
results_subjects[sub][hand] = \
results[sub][hand].mean()
proportions_mean[sub][hand] = \
proportions_test_dataset[sub][hand].mean()
# delimiter = ','
# np.savetxt(
# os.path.join(
# var_output_dir.get() +
# subjects_list[sub] + '_' + hands_list[hand] + '.txt'
# ),
# results[sub][hand][...][...].T,
# delimiter=delimiter,
# header=delimiter.join(rois_header)
# )
print('RESULTS MEAN: %f' % results.mean())
if var_rois_apply.get():
for i in range(rois_num):
print(
'ROI 00%s: %f (%s)' %
(i, results[:, :, i].mean(), rois_list[i])
)
'''
Statistical significance vs prior chance level
'''
from scipy import stats
if var_rois_apply.get():
for roi in range(len(rois_list)):
print(
'\n%s statistical difference vs prior chance' % rois_list[roi]
)
print(
'p_value = %f' %
stats.ttest_1samp(
results_subjects[..., roi], proportions_mean.mean()
)[1]
)
results_rois = np.array(
[
[
results_subjects[..., i].mean(),
stats.sem(results_subjects[..., i].flatten()),
results_subjects[..., i].std()
]
for i in range(results_subjects.shape[-1])
]
)
print('results for particular ROIs: %s' % results_rois.T[0].flatten())
else:
print('\nstatistical difference vs prior chance')
print(
'p_value = %f' %
stats.ttest_1samp(
results_subjects.mean(), proportions_mean.mean()
)[1]
)
import datetime
results_output_filename = datetime.datetime.now().strftime("%Y%m%d%H%M")
if not os.path.exists(var_output_dir.get()):
os.makedirs(var_output_dir.get())
np.save(
os.path.join(
var_output_dir.get(),
results_output_filename + '_results'
),
results
)
np.save(
os.path.join(
var_output_dir.get(),
results_output_filename + '_results_subjects'
),
results_subjects
)
np.save(
os.path.join(
var_output_dir.get(),
results_output_filename + '_results_rois'
),
results_rois
)
np.save(
os.path.join(
var_output_dir.get(),
results_output_filename + '_proportions_mean'
),
proportions_mean
)
# from pymri.visualization.percent_bars import plot_percent_bars
# plot_percent_bars(percents=results_rois.flatten()*100)
import ipdb
ipdb.set_trace()
return results
import nipype.interfaces.utility as util
from pymri.utils.paths_dirs_info import get_subject_names
flirt_apply_all_subs = Workflow(name='flirt_apply_all_subs')
inputsub = Node(
interface=util.IdentityInterface(
fields=['sub']
),
name='inputsub'
)
# inputsub.inputs.sub = ['GK011RZJA', 'GK012OHPA']
# inputsub.iterables = ('sub', ['GK011RZJA', 'GK012OHPA'])
inputsub.iterables = (
'sub', get_subject_names(base_directory, subject_template)
)
inputhand = Node(
interface=util.IdentityInterface(
fields=['hand']
),
name='inputhand'
)
inputhand.iterables = ('hand', ['Left', 'Right'])
inputnode = Node(
interface=util.IdentityInterface(
fields=['in_sub', 'in_hand']
),
def perform_classification():
import numpy as np
# subs_num = 21
# hands_num = 2
# rois_num = 2
# n_times_num = 100
# get list of subjects (subjects list specified or get from the pattern)
if '*' in subjects_names.get() and \
len(subjects_names.get().split(' ')) == 1:
subjects_pattern = subjects_names.get()
from pymri.utils.paths_dirs_info import get_subject_names
subjects_list = get_subject_names(
var_base_dir.get(), subjects_pattern.replace('*', '')
)
else:
subjects_list = subjects_names.get().split(' ')
subs_num = len(subjects_list)
# get list of hands (can be only one hand) or get the pattern
if len(hands_names.get().split(' ')[0]) == 0:
hands_list = ['Left', 'Right']
else:
hands_list = hands_names.get().split(' ')
hands_num = len(hands_list)
# get the information required from Load_data and Classifier/Performance
# subs_num = subs_num.get()
# hands_num = hands_num.get()
# rois_num = rois_num.get()
n_times_num = var_n_times.get()
if var_rois_apply.get():
# get list of rois
rois_list = rois_names.get().split(' ')
rois_num = len(rois_list)
# create an array to store results of the classification performance
results = np.zeros(shape=(subs_num, hands_num, rois_num, n_times_num))
results_subjects = np.zeros(results.shape[:-1])
proportions_test_dataset = np.zeros(shape=results.shape)
proportions_mean = np.zeros(results.shape[:-2])
else:
# create an array to store results of the classification performance
results = np.zeros(shape=(subs_num, hands_num, n_times_num))
results_subjects = np.zeros(results.shape[:-1])
proportions_test_dataset = np.zeros(shape=results.shape)
proportions_mean = np.zeros(results.shape[:-1])
# result's labels
labels = []
# which time of the cross validation is that
var_n_time_current = tk.IntVar()
# for subject in number of subjects, etc.
for sub in range(subs_num):
labels.append([])
for hand in range(hands_num):
labels[-1].append([])
mvpa_directory = os.path.join(
var_base_dir.get() +
schema.get() % (subjects_list[sub], hands_list[hand])
)
print(mvpa_directory)
# load dataset using variables from load_data frame (load_data tab)
dataset = load_data(mvpa_directory)
# if any rois to apply first do it, else classify once
if var_rois_apply.get():
rois_header = []
for roi in range(rois_num):
# get the data from specified import ROIs
roi_path = os.path.join(
mvpa_directory + 'ROIs/' + rois_list[roi] + '.nii.gz'
)
rois_header.append(rois_list[roi])
dataset_reduced = feature_reduction(dataset, roi_path)
var_n_time_current.set('0')
for n_time in range(n_times_num):
# create Classifier specified in Classifier tab
cls = create_classifier()
# split dataset use Classifier/Performance settings
training_data, test_data = split_data(
dataset_reduced, var_n_time_current.get()
)
proportions_test_dataset[sub][hand][roi][n_time] = \
test_data[1].sum()/float(test_data[1].shape[0])
# train and test classifier
cls = train_and_test_classifier(
cls, training_data, test_data
)
accuracy = get_accuracy(cls)
del cls
var_n_time_current.set(var_n_time_current.get() + 1)
results[sub][hand][roi][n_time] = accuracy
print(
'%s, %s, %s, %d ==> %0.2f' % (
subjects_list[sub], hands_list[hand],
rois_list[roi], n_time, accuracy
)
)
print(
'%s, %s, %s <mean> ==> %0.2f' % (
subjects_list[sub], hands_list[hand],
rois_list[roi], results[sub][hand][roi].mean()
)
)
results_subjects[sub][hand][roi] = \
results[sub][hand][roi].mean()
proportions_mean[sub][hand] = \
proportions_test_dataset[sub][hand][roi].mean()
else:
dataset_reduced = feature_reduction(dataset)
var_n_time_current.set('0')
for n_time in range(n_times_num):
# create Classifier specified in Classifier tab
cls = create_classifier()
# split dataset use Classifier/Performance settings
training_data, test_data = split_data(
dataset_reduced, var_n_time_current.get()
)
proportions_test_dataset[sub][hand][n_time] = \
test_data[1].sum()/float(test_data[1].shape[0])
# train and test classifier
cls = train_and_test_classifier(
cls, training_data, test_data
)
accuracy = get_accuracy(cls)
del cls
var_n_time_current.set(var_n_time_current.get() + 1)
results[sub][hand][n_time] = accuracy
print(
'%s, %s, %d ==> %0.2f' % (
subjects_list[sub], hands_list[hand],
n_time, accuracy
)
)
print(
'%s, %s <mean> ==> %0.2f' % (
subjects_list[sub], hands_list[hand],
results[sub][hand].mean()
)
)
results_subjects[sub][hand] = \
results[sub][hand].mean()
proportions_mean[sub][hand] = \
proportions_test_dataset[sub][hand].mean()
# delimiter = ','
# np.savetxt(
# os.path.join(
# var_output_dir.get() +
# subjects_list[sub] + '_' + hands_list[hand] + '.txt'
# ),
# results[sub][hand][...][...].T,
# delimiter=delimiter,
# header=delimiter.join(rois_header)
# )
print('RESULTS MEAN: %f' % results.mean())
if var_rois_apply.get():
for i in range(rois_num):
print(
'ROI 00%s: %f (%s)' %
(i, results[:, :, i].mean(), rois_list[i])
)
'''
Statistical significance vs prior chance level
'''
from scipy import stats
if var_rois_apply.get():
for roi in range(len(rois_list)):
print(
'\n%s statistical difference vs prior chance' % rois_list[roi]
)
print(
'p_value = %f' %
stats.ttest_1samp(
results_subjects[..., roi], proportions_mean.mean()
)[1]
)
results_rois = np.array(
[
[
results_subjects[..., i].mean(),
stats.sem(results_subjects[..., i].flatten()),
results_subjects[..., i].std()
]
for i in range(results_subjects.shape[-1])
]
)
print('results for particular ROIs: %s' % results_rois.T[0].flatten())
else:
print('\nstatistical difference vs prior chance')
print(
'p_value = %f' %
stats.ttest_1samp(
results_subjects.mean(), proportions_mean.mean()
)[1]
)
import datetime
results_output_filename = datetime.datetime.now().strftime("%Y%m%d%H%M")
if not os.path.exists(var_output_dir.get()):
os.makedirs(var_output_dir.get())
np.save(
os.path.join(
var_output_dir.get(),
results_output_filename + '_results'
),
results
)
np.save(
os.path.join(
var_output_dir.get(),
results_output_filename + '_results_subjects'
),
results_subjects
)
np.save(
os.path.join(
var_output_dir.get(),
results_output_filename + '_results_rois'
),
results_rois
)
np.save(
os.path.join(
var_output_dir.get(),
results_output_filename + '_proportions_mean'
),
proportions_mean
)
# from pymri.visualization.percent_bars import plot_percent_bars
# plot_percent_bars(percents=results_rois.flatten()*100)
import ipdb
ipdb.set_trace()
return results