def choose_rep(self):
"""Choses representative subject to be used as target for BrainSync"""
nsub = len(self.subids)
subs = range(nsub)
dist_mat = np.zeros((nsub, nsub))
for sub1no, sub2no in itertools.product(subs, subs):
sub1 = self.fmri_data[sub1no]
sub2 = self.fmri_data[sub2no]
sub1 = StandardScaler().fit_transform(sub1.T)
sub2 = StandardScaler().fit_transform(sub2.T) # .T to make it TxV
sub2s, _ = brainSync(sub1, sub2)
dist_mat[sub1no, sub2no] = np.linalg.norm(sub1.flatten() -
sub2s.flatten())
print(sub1no, sub2no)
self.ref_subno = np.argmin(np.sum(dist_mat, axis=1))
self.ref_data = self.fmri_data[self.ref_subno]
# Save the reference subject and ref subject data
np.savez_compressed(
self.data_dir_fmri + '/processed/Refdata.npz',
ref_data=self.ref_data,
ref_subno=self.ref_subno)
print('The most representative subject is %d' % self.ref_subno)
def sample_data(country):
population = df.loc[(df.Country == country) & (df.New_deaths > 0),
['Date_reported', 'New_deaths']]
after = population.loc[(population.Date_reported >= '2020-12-08 ') &
(population.Date_reported <= today), ['New_deaths']]
values = after.values
values = values.reshape((len(values), 1))
scaled_features = StandardScaler().fit_transform(values)
scaled_features = scaled_features.flatten()
return scaled_features
def population_data(country):
from sklearn.preprocessing import StandardScaler
from math import sqrt
population = df.loc[(df.Country == country) & (df.New_deaths > 0),
['New_deaths']]
values = population.values
values = values.reshape((len(values), 1))
scaled_features = StandardScaler().fit_transform(values)
scaled_features = scaled_features.flatten()
return scaled_features
normalizeFeatures = 'Mean'
if normalizeFeatures == 'MeanAndStd':
X_std = StandardScaler().fit_transform(vecPosMatrix)
elif normalizeFeatures == 'Mean':
X_std = vecPosMatrix - np.mean(vecPosMatrix,0)
print "Making sklearn_pca"
nComponents = 10
sklearn_pca = sklearnPCA(n_components=nComponents)
print "Making Y_sklearn"
# An important note -- we get a hash value for the raw data here
# as a unique identifier of this dataset. Then we save the initial
# PCA object to disk to reduce time on subsequent runs.
sklearn_pca_hash = str(hash(tuple(X_std.flatten()[::100])))[-10:]
#pca_result_hash = 'y_sklearn_hash_%s.cpickle' %(sklearn_pca_hash)
pca_result_hash = 'pca_obj_hash_%s.cpickle' %(sklearn_pca_hash)
if not(os.path.exists(pca_result_hash)):
#Y_sklearn = sklearn_pca.fit_transform(X_std)
sklearn_pca.fit(X_std)
with open(pca_result_hash,'wb') as of:
cPickle.dump(sklearn_pca, of)
Y_sklearn = sklearn_pca.transform(X_std)
#with open(pca_result_hash,'wb') as of:
# cPickle.dump(Y_sklearn, of)
else:
#Y_sklearn = cPickle.load(open(pca_result_hash))
sklearn_pca = cPickle.load(open(pca_result_hash))
Y_sklearn = sklearn_pca.transform(X_std)
normalizeFeatures = 'Mean'
if normalizeFeatures == 'MeanAndStd':
X_std = StandardScaler().fit_transform(vecPosMatrix)
elif normalizeFeatures == 'Mean':
X_std = vecPosMatrix - np.mean(vecPosMatrix, 0)
print("Making sklearn_pca")
nComponents = 10
sklearn_pca = sklearnPCA(n_components=nComponents)
print("Making Y_sklearn")
# An important note -- we get a hash value for the raw data here
# as a unique identifier of this dataset. Then we save the initial
# PCA object to disk to reduce time on subsequent runs.
sklearn_pca_hash = str(hash(tuple(X_std.flatten()[::100])))[-10:]
#pca_result_hash = 'y_sklearn_hash_%s.cpickle' %(sklearn_pca_hash)
pca_result_hash = 'pca_obj_hash_%s.cpickle' % (sklearn_pca_hash)
if not (os.path.exists(pca_result_hash)):
#Y_sklearn = sklearn_pca.fit_transform(X_std)
sklearn_pca.fit(X_std)
with open(pca_result_hash, 'wb') as of:
pickle.dump(sklearn_pca, of)
Y_sklearn = sklearn_pca.transform(X_std)
#with open(pca_result_hash,'wb') as of:
# cPickle.dump(Y_sklearn, of)
else:
#Y_sklearn = cPickle.load(open(pca_result_hash))
sklearn_pca = pickle.load(open(pca_result_hash))
Y_sklearn = sklearn_pca.transform(X_std)
def standardized(v_lst):
df = pd.DataFrame({'val': v_lst})
df.fillna(df.mean(), inplace=True)
v_lst = StandardScaler().fit_transform(df['val'].values.reshape(-1, 1))
v_lst = v_lst.flatten()
return list(v_lst)
def TsExtractor(labels,
labelmap,
func,
mask,
global_signal=True,
pca=False,
outfile="reg_timeseries.tsv",
outlabelmap="individual_gm_labelmap.nii.gz"):
import nibabel as nib
import pandas as pd
import numpy as np
func_data = nib.load(func).get_data()
labelmap_data = nib.load(labelmap).get_data()
mask_data = nib.load(mask).get_data()
labelmap_data[mask_data == 0] = 0 # background
outlab = nib.Nifti1Image(labelmap_data, nib.load(labelmap).affine)
nib.save(outlab, outlabelmap)
ret = []
if global_signal:
indices = np.argwhere(mask_data > 0)
X = []
for i in indices:
x = func_data[i[0], i[1], i[2], :]
if np.std(x) > 0.000001:
X.append(x.tolist())
if len(X) == 0:
x = np.repeat(0, func_data.shape[3])
elif pca:
import sklearn.decomposition as decomp
from sklearn.preprocessing import StandardScaler
X = StandardScaler().fit_transform(np.transpose(X))
PCA = decomp.PCA(n_components=1, svd_solver="arpack")
x = PCA.fit_transform(X).flatten()
else:
#from sklearn.preprocessing import StandardScaler
#X = StandardScaler().fit_transform(np.transpose(X))
x = np.mean(X, axis=0)
ret.append(x)
for l in range(1, len(labels) + 1):
indices = np.argwhere(labelmap_data == l)
X = []
for i in indices:
x = func_data[i[0], i[1], i[2], :]
if np.std(x) > 0.000001:
X.append(x.tolist())
X = np.array(X)
if X.shape[0] == 0:
x = np.repeat(0, func_data.shape[3])
elif X.shape[0] == 1:
x = X.flatten()
elif pca:
import sklearn.decomposition as decomp
from sklearn.preprocessing import StandardScaler
X = StandardScaler().fit_transform(np.transpose(X))
PCA = decomp.PCA(n_components=1, svd_solver="arpack")
x = PCA.fit_transform(X).flatten()
else:
#from sklearn.preprocessing import StandardScaler
#X = StandardScaler().fit_transform(np.transpose(X))
x = np.mean(X, axis=0)
ret.append(x)
ret = np.transpose(np.array(ret))
if global_signal:
labels = ["GlobSig"] + labels
import pandas as pd
ret = pd.DataFrame(data=ret, columns=labels)
ret.to_csv(outfile, sep="\t", index=False)
import os
return os.path.join(os.getcwd(),
outfile), labels, os.path.join(os.getcwd(),
outlabelmap)
