def main():
logging.info('%s: Starting script' % proj_utils.ctime())
bands = ['delta', 'theta', 'alpha', 'beta', 'gamma']
data_df = proj_utils.load_connectivity_data(drop_behavior=True)
dpath = os.path.abspath('./../data/subject_adjacency_matrices/')
if not os.path.isdir(dpath):
os.mkdir(dpath)
# print('%s: Creating adjacency dicts' % proj_utils.ctime())
# adj_dict = create_adjacency_dict(data_df, bands)
# print('%s: Creating subject adjacency matrices' % proj_utils.ctime())
# rois = parse_roi_names(list(data_df))
# create_subj_adjacency_mats(adj_dict, bands, rois, dpath)
test_res = test_graph_functions()
logging.info('%s: Running graph theory analyses' % proj_utils.ctime())
columns = list(test_res)
subjects = np.arange(0, len(data_df.index))
outpath = './../data/graph_theory_res/'
if not os.path.isdir(outpath):
os.mkdir(outpath)
for band in bands:
filelist = sorted([os.path.join(dpath, f) for f in os.listdir(dpath) if band in f])
run_graph_theory(band, filelist, subjects, columns, outpath)
logging.info('%s: Finished' % proj_utils.ctime())
def main():
output_dir = './../data/eeg_second_level/'
if not os.path.isdir(output_dir):
os.mkdir(output_dir)
behavior = proj_utils.load_behavior_data()
ml_targets = ['loudness_VAS', 'distress_TQ', 'distress_VAS']
covariates_df = dummy_code_categorical(behavior)
covariates_df.drop(labels=ml_targets, axis=1, inplace=True)
data_df = proj_utils.load_connectivity_data()
data_df_filt = data_df.filter(items=covariates_df.index, axis=0)
wz = 'dep'
if wz is 'ind':
output_path = os.path.join(
output_dir, 'second_level_f_tests_zero_as_independent_var.pkl')
else:
output_path = os.path.join(
output_dir, 'second_level_f_tests_zero_as_dependent_var.pkl')
res = run_ancova(connectivity_data=data_df_filt,
covariates=covariates_df,
where_zero=wz,
output_path=output_path)
print(res)
truth, corrected_p_df = multiple_correction_ancova_res(output_path,
method='bonferroni',
alpha=1e-20)
print(corrected_p_df)
print(np.count_nonzero(truth))
def load_data():
# Remove EEG subjects that don't have behavior data
behavior_df = pu.load_behavior_data()
conn_df = pu.load_connectivity_data()
filt_df = conn_df.filter(
items=behavior_df.index,
axis=0) # Remove EEG subjects with missing rowvals in behavior_df
return behavior_df, filt_df
def plot_extra_trees_features():
variables = ['tinnitus_side', 'tinnitus_type', 'TQ_grade', 'TQ_high_low']
conn_data = pu.load_connectivity_data()
conn_variables = list(conn_data)
band_list, roi_list = [], []
for c in conn_variables:
band = c.split('_')[0]
roi_1 = c.split('_')[1]
roi_2 = c.split('_')[2]
band_list.append(band)
roi_list.append(roi_1)
roi_list.append(roi_2)
bands = pd.unique(band_list)
rois = pd.unique(roi_list)
conn_matrix = pd.DataFrame(index=rois, columns=rois)
band_matrices_master = {}
for band in bands:
band_matrices_master[band] = conn_matrix
for tin_variable in variables:
output_dir = './../data/%s/' % tin_variable
for model in listdir(output_dir):
if 'extra_trees' in model:
tin_dir = join(output_dir, model)
xls = pd.ExcelFile(join(tin_dir, 'coefficients.xlsx'))
fold_data = {}
for sheet in xls.sheet_names:
band_matrices = deepcopy(band_matrices_master)
feature_df = pd.read_excel(xls,
sheet_name=sheet,
index_col=0)
for feat in list(feature_df):
feat_str = feat.split('_')
if any([True for b in bands if b in feat_str
]): # check if feature is connectivity data
feat_band, r1, r2 = feat_str[0], feat_str[
1], feat_str[2]
input_matrix = band_matrices[feat_band]
input_matrix.loc[r1][r2] = feature_df[feat].values[
0]
fold_data[sheet] = band_matrices
with open(join(tin_dir, 'connectivity_matrices.pkl'),
'wb') as file:
pkl.dump(obj=fold_data, file=file)
score_df = find_n_components(data, step=5)
score_df.to_excel('./pca_cross_val_scores_test.xlsx')
def grand_pca(data, res_dir=None):
if res_dir is None:
res_dir = os.path.dirname(__file__)
print(pu.ctime() + 'Running grand PCA')
pca = PCA(n_components=.99, whiten=True)
zdata = StandardScaler().fit_transform(data)
pca.fit(zdata)
print(pca.n_components_)
true_df = pretty_pca_res(pca)
plot_scree(true_df,
percent=False,
fname=os.path.join(res_dir, 'grand_pca_scree.png'))
true_df.to_excel(os.path.join(res_dir, 'grand_pca_res.xlsx'))
if __name__ == "__main__":
print(pu.ctime() + 'Loading data')
data = pu.load_connectivity_data()
res_dir = os.path.abspath('./../results/pca')
if not os.path.isdir(res_dir):
os.mkdir(res_dir)
grand_pca(data)
pca_by_band(data, n_iters=0, res_dir=res_dir)