def get_node_size(matrix, absolute=True):
matrix = np.nan_to_num(copy_matrix(matrix, diagonal_filler=0))
if absolute == True:
matrix = np.abs(matrix)
return matrix.sum(axis=0)
def get_node_size(matrix, absolute=True):
matrix = np.nan_to_num(copy_matrix(matrix, diagonal_filler=0))
if absolute == True:
matrix = np.abs(matrix)
return matrix.sum(axis=0)
def plot_states_matrices(
X,
labels,
node_number=[6, 5, 8, 10, 4, 5, 7],
node_networks=['DAN', 'VAN', 'SMN', 'VIS', 'AUD', 'LAN', 'DMN'],
use_centroid=False,
n_cols=3,
save_fig=False,
save_path="/media/robbis/DATA/fmri/movie_viviana",
save_name_condition=None,
**kwargs):
"""
Plots the centroids in square matrix form.
It could be used with original data and labels but also
with the original centroids if you set use_centroids as True.
"""
position = [sum(node_number[:i + 1]) for i in range(len(node_number))]
if not use_centroid:
centroids = get_centroids(X, labels)(X, labels)
n_states = len(np.unique(labels))
else:
centroids = X.copy()
n_states = X.shape[0]
position_label = [
-0.5 + position[i] - node_number[i] / 2.
for i in range(len(node_number))
]
n_rows = np.ceil(n_states / float(n_cols))
fig = pl.figure()
for i in np.arange(n_states):
ax = fig.add_subplot(n_rows, n_cols, i + 1)
matrix_ = copy_matrix(array_to_matrix(centroids[i]), diagonal_filler=0)
n_nodes = matrix_.shape[0]
ax.imshow(matrix_, interpolation='nearest', vmin=0, cmap=pl.cm.bwr)
for _, end_network in zip(node_networks, position):
ax.vlines(end_network - 0.5, -0.5, n_nodes - 0.5)
ax.hlines(end_network - 0.5, -0.5, n_nodes - 0.5)
ax.set_title('State ' + str(i + 1))
ax.set_xticks(position_label)
ax.set_xticklabels(node_networks)
ax.set_yticks(position_label)
ax.set_yticklabels(node_networks)
#pl.colorbar()
if save_fig:
fname = "%s_state_%s.png" % (str(save_name_condition), str(i + 1))
fig.savefig(os.path.join(save_path, fname))
pl.close('all')
return fig
def plot_states_matrices(X,
labels,
node_number=[6,5,8,10,4,5,7],
node_networks=['DAN','VAN','SMN','VIS','AUD','LAN','DMN'],
use_centroid=False,
n_cols=3,
save_fig=False,
save_path="/media/robbis/DATA/fmri/movie_viviana",
save_name_condition=None,
**kwargs
):
"""
Plots the centroids in square matrix form.
It could be used with original data and labels but also
with the original centroids if you set use_centroids as True.
"""
position = [sum(node_number[:i+1]) for i in range(len(node_number))]
if not use_centroid:
centroids = get_centroids(X, labels)
n_states = len(np.unique(labels))
else:
centroids = X.copy()
n_states = X.shape[0]
position_label = [-0.5+position[i]-node_number[i]/2. for i in range(len(node_number))]
n_rows = np.ceil(n_states / float(n_cols))
print n_rows, n_cols
fig = pl.figure()
for i in np.arange(n_states):
ax = fig.add_subplot(n_rows, n_cols, i+1)
matrix_ = copy_matrix(array_to_matrix(centroids[i]), diagonal_filler=0)
n_nodes = matrix_.shape[0]
ax.imshow(matrix_, interpolation='nearest', vmin=0, cmap=pl.cm.inferno)
for _, end_network in zip(node_networks, position):
ax.vlines(end_network-0.5, -0.5, n_nodes-0.5)
ax.hlines(end_network-0.5, -0.5, n_nodes-0.5)
ax.set_title('State '+str(i+1))
ax.set_xticks(position_label)
ax.set_xticklabels(node_networks)
ax.set_yticks(position_label)
ax.set_yticklabels(node_networks)
#pl.colorbar()
if save_fig:
fname = "%s_state_%s.png" % (str(save_name_condition), str(i+1))
fig.savefig(os.path.join(save_path, fname))
pl.close('all')
return fig
def aggregate_networks(matrix, roi_list, aggregation_fx=np.sum):
"""
Function used to aggregate matrix values using
aggregative information provided by roi_list
Parameters
----------
matrix : numpy 2D array, shape n x n
Connectivity matrix in squared form
roi_list : list of string, length = n
List of each ROI's network name. Each element represents
the network that includes the ROI in that particular position.
Returns
-------
aggregate_matrix : numpy 2D array, p x p
The matrix obtained, by pairwise network sum
of nodes within networks.
"""
unique_rois = np.unique(roi_list)
n_roi = unique_rois.shape[0]
aggregate_matrix = np.zeros((n_roi, n_roi), dtype=np.float)
network_pairs = itertools.combinations(unique_rois, 2)
indexes = np.vstack(np.triu_indices(n_roi, k=1)).T
# This is to fill upper part of the aggregate matrix
for i, (n1, n2) in enumerate(network_pairs):
x = indexes[i][0]
y = indexes[i][1]
mask1 = roi_list == n1
mask2 = roi_list == n2
# Build the mask of the intersection between
mask_roi = np.meshgrid(mask1, mask1)[1] * np.meshgrid(mask2, mask2)[0]
value = aggregation_fx(matrix * mask_roi)
#value /= np.sum(mask_roi)
aggregate_matrix[x, y] = value
# Copy matrix in the lower part
aggregate_matrix = copy_matrix(aggregate_matrix)
# This is to fill the diagonal with within-network sum of elements
for i, n in enumerate(unique_rois):
diag_matrix, _ = network_connections(matrix, n, roi_list)
aggregate_matrix[i, i] = aggregation_fx(diag_matrix)
# aggregate_matrix[i, i] = np.mean(diag_matrix)
return aggregate_matrix
def aggregate_networks(matrix, roi_list):
"""
Function used to aggregate matrix values using
aggregative information provided by roi_list
Parameters
----------
matrix : numpy 2D array, shape n x n
Connectivity matrix in squared form
roi_list : list of string, length = n
List of each ROI's network name. Each element represents
the network that includes the ROI in that particular position.
Returns
-------
aggregate_matrix : numpy 2D array, p x p
The matrix obtained, by pairwise network sum
of nodes within networks.
"""
unique_rois = np.unique(roi_list)
n_roi = unique_rois.shape[0]
aggregate_matrix = np.zeros((n_roi, n_roi), dtype=np.float)
network_pairs = itertools.combinations(unique_rois, 2)
indexes = np.vstack(np.triu_indices(n_roi, k=1)).T
# This is to fill upper part of the aggregate matrix
for i, (n1, n2) in enumerate(network_pairs):
x = indexes[i][0]
y = indexes[i][1]
mask1 = roi_list == n1
mask2 = roi_list == n2
# Build the mask of the intersection between
mask_roi = np.meshgrid(mask1, mask1)[1] * np.meshgrid(mask2, mask2)[0]
value = np.sum(matrix * mask_roi)
#value /= np.sum(mask_roi)
aggregate_matrix[x, y] = value
# Copy matrix in the lower part
aggregate_matrix = copy_matrix(aggregate_matrix)
# This is to fill the diagonal with within-network sum of elements
for i, n in enumerate(unique_rois):
diag_matrix, _ = network_connections(matrix, n, roi_list)
aggregate_matrix[i, i] = np.sum(diag_matrix)
# aggregate_matrix[i, i] = np.mean(diag_matrix)
return aggregate_matrix
def get_feature_selection_matrix(feature_set, n_features, mask):
h_values_, _ = np.histogram(feature_set.flatten(),
bins=np.arange(0, n_features + 1))
mask = np.triu(mask, k=1)
mask_indices = np.nonzero(mask)
mask[mask_indices] = h_values_
return np.nan_to_num(copy_matrix(mask, diagonal_filler=0))
def get_feature_selection_matrix(feature_set, n_features, mask):
h_values_, _ = np.histogram(feature_set.flatten(),
bins=np.arange(0, n_features+1))
mask = np.triu(mask, k=1)
mask_indices = np.nonzero(mask)
mask[mask_indices] = h_values_
return np.nan_to_num(copy_matrix(mask, diagonal_filler=0))
def transform(self, ds):
data = np.dstack([copy_matrix(array_to_matrix(a)) for a in ds.samples])
data = np.hstack([d for d in data[:, :]]).T
attr = self._edit_attr(ds, data.shape)
ds_ = Dataset.from_wizard(data)
ds_ = add_attributes(ds_, attr)
return ds_
def plot_seaborn(features, node_names=None, node_idx=None, **kwargs):
from mne.viz import circular_layout
node_angles = circular_layout(
node_names.tolist(),
node_names[node_idx].tolist(),
start_pos=90,
group_boundaries=[0, len(node_names) / 2. + 1])
matrix = copy_matrix(array_to_matrix(features.values[0]),
diagonal_filler=0.)
return plot_connectivity_seaborn(matrix,
node_names=node_names,
con_thresh=400,
node_angles=node_angles,
node_colors=sns.dark_palette(
kwargs['color']))
def get_feature_weights_matrix(weights, sets, mask, indices=None):
"""
Function used to compute the average weight matrix in case of
several cross-validation folds and feature selection for each
fold.
Parameters
----------
weights : ndarray shape=(n_folds, n_selected_features)
The weights matrix with the shape specified in the signature
sets : ndarray shape=(n_folds, n_selected_features)
This represents the index in the square matrix of the feature selected
by the algorithm in each cross-validation fold
mask : ndarray shape=(n_roi, n_roi)
The mask matrix of the valid ROIs selected. Important: this matrix
should be triangular with the lower part set to zero.
indices : tuple
This is equal to np.nonzero(mask)
Returns
-------
matrix: ndarray n_roi x n_roi
It returns the average weights across cross-validation fold in
square form.
"""
if indices is None:
indices = np.nonzero(mask)
weights = weights.squeeze()
filling_vector = np.zeros(np.count_nonzero(mask))
counting_vector = np.zeros(np.count_nonzero(mask))
for s, w in zip(sets, weights):
filling_vector[s] += zscore(w)
counting_vector[s] += 1
avg_weigths = np.nan_to_num(filling_vector / counting_vector)
mask[indices] = avg_weigths
matrix = np.nan_to_num(copy_matrix(mask, diagonal_filler=0))
return matrix
def plot_center_matrix(X, clustering, n_cluster=5, **kwargs):
configuration = {
'node_number':[6,5,8,10,4,5,7],
'node_networks':['DAN','VAN','SMN','VIS','AUD','LAN','DMN'],
'save_fig':True,
'save_path':"/media/robbis/DATA/fmri/movie_viviana",
'save_name_condition':None
}
configuration.update(**kwargs)
node_number = configuration['node_number']
node_networks = configuration['node_networks']
position = [sum(node_number[:i+1]) for i in range(len(node_number))]
position_label = [-0.5+position[i]-node_number[i]/2. for i in range(len(node_number))]
matrix_indices = np.arange(n_cluster**2).reshape(n_cluster, n_cluster) + 1
fig = pl.figure(figsize=(25,20))
for i in range(n_cluster-1):
centers = get_centroids(X, clustering[i])
for j, matrix in enumerate(centers):
pos = matrix_indices[j,i+1]
ax = fig.add_subplot(n_cluster, n_cluster, pos)
matrix = copy_matrix(array_to_matrix(matrix), diagonal_filler=0)
total_nodes = matrix.shape[0]
ax.imshow(matrix, interpolation='nearest', vmin=0)
for name, n_nodes in zip(node_networks, position):
ax.vlines(n_nodes-0.5, -0.5, total_nodes-0.5)
ax.hlines(n_nodes-0.5, -0.5, total_nodes-0.5)
ax.set_xticks(position_label)
ax.set_xticklabels(node_networks)
ax.set_yticks(position_label)
ax.set_yticklabels(node_networks)
return fig
def plot_center_matrix(X, clustering, n_cluster=5, **kwargs):
configuration = {
'node_number': [6, 5, 8, 10, 4, 5, 7],
'node_networks': ['DAN', 'VAN', 'SMN', 'VIS', 'AUD', 'LAN', 'DMN'],
'save_fig': True,
'save_path': "/media/robbis/DATA/fmri/movie_viviana",
'save_name_condition': None
}
configuration.update(**kwargs)
node_number = configuration['node_number']
node_networks = configuration['node_networks']
position = [sum(node_number[:i + 1]) for i in range(len(node_number))]
position_label = [
-0.5 + position[i] - node_number[i] / 2.
for i in range(len(node_number))
]
matrix_indices = np.arange(n_cluster**2).reshape(n_cluster, n_cluster) + 1
fig = pl.figure(figsize=(25, 20))
for i in range(n_cluster - 1):
centers = get_centroids(X, clustering[i])
for j, matrix in enumerate(centers):
pos = matrix_indices[j, i + 1]
ax = fig.add_subplot(n_cluster, n_cluster, pos)
matrix = copy_matrix(array_to_matrix(matrix), diagonal_filler=0)
total_nodes = matrix.shape[0]
ax.imshow(matrix, interpolation='nearest', vmin=0)
for _, n_nodes in zip(node_networks, position):
ax.vlines(n_nodes - 0.5, -0.5, total_nodes - 0.5)
ax.hlines(n_nodes - 0.5, -0.5, total_nodes - 0.5)
ax.set_xticks(position_label)
ax.set_xticklabels(node_networks)
ax.set_yticks(position_label)
ax.set_yticklabels(node_networks)
return fig
def get_feature_weights_matrix(weights, sets, mask, indices):
"""
Function used to compute the average weight matrix in case of
several cross-validation folds and feature selection for each
fold.
Parameters
----------
weights : ndarray shape n_folds x n_selected_features
The weights matrix with the shape specified in the signature
sets : ndarray shape n_folds x n_selected_features
This represents the index in the square matrix of the feature selected
by the algorithm in each cross-validation fold
mask : ndarray shape n_roi x n_roi
The mask matrix of the valid ROIs selected. Important: this matrix
should be triangular with the lower part set to zero.
indices : tuple
This is equal to np.nonzero(mask)
Returns
-------
matrix: ndarray n_roi x n_roi
It returns the average weights across cross-validation fold in
square form.
"""
weights = weights.squeeze()
filling_vector = np.zeros(np.count_nonzero(mask))
counting_vector = np.zeros(np.count_nonzero(mask))
for s, w in zip(sets, weights):
filling_vector[s] += zscore(w)
counting_vector[s] += 1
avg_weigths = np.nan_to_num(filling_vector/counting_vector)
mask[indices] = avg_weigths
matrix = np.nan_to_num(copy_matrix(mask, diagonal_filler=0))
return matrix
def plot_condition_centers(X, labels, **kwargs):
configuration = {
'node_number': [6, 5, 8, 10, 4, 5, 7],
'node_networks': ['DAN', 'VAN', 'SMN', 'VIS', 'AUD', 'LAN', 'DMN'],
'save_fig': True,
'save_path': "/media/robbis/DATA/fmri/movie_viviana",
'save_name_condition': None,
'vmax': 1
}
configuration.update(**kwargs)
vmax = configuration['vmax']
node_number = configuration['node_number']
node_networks = configuration['node_networks']
centroids = get_centroids(X, labels)
position = [sum(node_number[:i + 1]) for i in range(len(node_number))]
position_label = [
-0.5 + position[i] - node_number[i] / 2.
for i in range(len(node_number))
]
n_rows = np.floor(np.sqrt(len(np.unique(labels))))
n_cols = np.ceil(len(np.unique(labels)) / n_rows)
fig = pl.figure(figsize=(16, 13))
for j, matrix in enumerate(centroids):
ax = fig.add_subplot(n_rows, n_cols, j + 1)
matrix = copy_matrix(array_to_matrix(matrix), diagonal_filler=0)
total_nodes = matrix.shape[0]
ax.imshow(matrix, interpolation='nearest', vmin=0, vmax=vmax)
for _, n_nodes in zip(node_networks, position):
ax.vlines(n_nodes - 0.5, -0.5, total_nodes - 0.5)
ax.hlines(n_nodes - 0.5, -0.5, total_nodes - 0.5)
ax.set_xticks(position_label)
ax.set_xticklabels(node_networks, rotation=45)
ax.set_yticks(position_label)
ax.set_yticklabels(node_networks)
return fig
def plot_states_matrices(X,
labels,
save_path,
condition_label,
node_number=[6,5,8,10,4,5,7],
node_networks = ['DAN','VAN','SMN','VIS','AUD','LAN','DMN'],
use_centroid=False,
):
position = [sum(node_number[:i+1]) for i in range(len(node_number))]
if not use_centroid:
centroids = get_centroids(X, labels)
total_nodes = len(np.unique(labels))
else:
centroids = X.copy()
total_nodes = X.shape[0]
position_label = [-0.5+position[i]-node_number[i]/2. for i in range(len(node_number))]
for i in np.arange(total_nodes):
fig = pl.figure()
matrix_ = copy_matrix(array_to_matrix(centroids[i]))
total_nodes = matrix_.shape[0]
pl.imshow(matrix_, interpolation='nearest', vmin=0, vmax=1)
for name, n_nodes in zip(node_networks, position):
pl.vlines(n_nodes-0.5, -0.5, total_nodes-0.5)
pl.hlines(n_nodes-0.5, -0.5, total_nodes-0.5)
pl.title('State '+str(i+1))
pl.xticks(position_label, node_networks)
pl.yticks(position_label, node_networks)
pl.colorbar()
fname = "%s_state_%s.png" % (condition_label, str(i+1))
pl.savefig(os.path.join(save_path, fname))
def plot_condition_centers(X, labels, **kwargs):
configuration = {
'node_number':[6,5,8,10,4,5,7],
'node_networks':['DAN','VAN','SMN','VIS','AUD','LAN','DMN'],
'save_fig':True,
'save_path':"/media/robbis/DATA/fmri/movie_viviana",
'save_name_condition':None,
'vmax':1
}
configuration.update(**kwargs)
vmax = configuration['vmax']
node_number = configuration['node_number']
node_networks = configuration['node_networks']
centroids = get_centroids(X, labels)
position = [sum(node_number[:i+1]) for i in range(len(node_number))]
position_label = [-0.5+position[i]-node_number[i]/2. for i in range(len(node_number))]
n_rows = np.floor(np.sqrt(len(np.unique(labels))))
n_cols = np.ceil(len(np.unique(labels))/n_rows)
fig = pl.figure(figsize=(16,13))
for j, matrix in enumerate(centroids):
ax = fig.add_subplot(n_rows, n_cols, j+1)
matrix = copy_matrix(array_to_matrix(matrix), diagonal_filler=0)
total_nodes = matrix.shape[0]
ax.imshow(matrix, interpolation='nearest', vmin=0, vmax=vmax)
for _, n_nodes in zip(node_networks, position):
ax.vlines(n_nodes-0.5, -0.5, total_nodes-0.5)
ax.hlines(n_nodes-0.5, -0.5, total_nodes-0.5)
ax.set_xticks(position_label)
ax.set_xticklabels(node_networks, rotation=45)
ax.set_yticks(position_label)
ax.set_yticklabels(node_networks)
return fig
def write_correlation_matrices(directory, condition):
subjects = np.loadtxt(
'/media/robbis/DATA/fmri/monks/attributes_struct.txt', dtype=np.str)
roi_list = np.loadtxt(
'/media/robbis/DATA/fmri/templates_fcmri/findlab_rois.txt',
delimiter=',',
dtype=np.str)
path = '/media/robbis/DATA/fmri/monks/0_results/'
conn = ConnectivityLoader(path, subjects, directory, roi_list)
nan_mask = conn.get_results(['Samatha', 'Vipassana'])
#nan_mask = conn.get_results(['Rest'])
ds = conn.get_dataset()
mask_ = np.float_(~np.bool_(nan_mask))
mask_ = np.triu(mask_, k=1)
mask_indices = np.nonzero(mask_)
ds_ = ds[np.logical_and(ds.targets == condition, ds.sa.groups == 'E')]
array_ = ds_.samples.mean(0)
mask_[mask_indices] = array_
matrix = np.nan_to_num(copy_matrix(mask_, diagonal_filler=0))
names_lr, colors_lr, index_, coords, networks = get_atlas_info('findlab')
plot_connectomics(
matrix,
20 + 8 * np.abs(matrix.sum(axis=1))**2,
save_path=os.path.join(path, directory),
prename=condition + '_correlation',
save=True,
colormap='bwr',
vmin=np.abs(matrix).max() * -1,
vmax=np.abs(matrix).max(),
node_names=names_lr,
node_colors=colors_lr,
node_coords=coords,
node_order=index_,
networks=networks,
threshold=0.5,
title=condition + ' Correlation',
zscore=False,
)
w_aggregate = aggregate_networks(matrix, roi_list.T[-2])
_, idx = np.unique(networks, return_index=True)
plot_connectomics(w_aggregate,
5 * np.abs(w_aggregate.sum(axis=1))**2,
save_path=os.path.join(path, directory),
prename=condition + '_aggregate_correlation',
save=True,
colormap='bwr',
vmin=-1 * w_aggregate.max(),
vmax=w_aggregate.max(),
node_names=np.unique(networks),
node_colors=colors_lr[idx],
node_coords=coords[idx],
node_order=np.arange(0, len(idx)),
networks=np.unique(networks),
threshold=4,
zscore=False)
w_array = feature_weights[med].copy()
f_nz = f_array[np.nonzero(f_array)]
# We selected only feature selected often
threshold = f_nz.mean() + 0.5 * f_nz.std()
# f_array[f_array < threshold] = 0
# w_array[f_array < threshold] = 0 # Weights selected based on chosen features
# zscoring weights
w_nz = w_array[np.nonzero(w_array)]
w_nz = (w_nz - np.mean(w_nz)) / np.std(w_nz)
w_array[np.nonzero(w_array)] = w_nz
f_matrix = copy_matrix(array_to_matrix(f_array, nan_mask), diagonal_filler=0)
w_matrix = copy_matrix(array_to_matrix(w_array, nan_mask), diagonal_filler=0)
title = "%s %s" % (med, l_)
# f_matrix[f_matrix == 0] = np.nan
##################################################################################
condition = med
w_aggregate = aggregate_networks(w_matrix, roi_list.T[-2])
names_lr, colors_lr, index_, coords, networks = get_atlas_info("findlab")
_, idx = np.unique(networks, return_index=True)
##########################################################################
plot_connectomics(
def analyze_results(directory,
conditions,
n_permutations=1000.):
"""Write the results of the regression analysis
Parameters
----------
directory : string or list of strings
Path or list of paths where put results.
condition : string or list of strings
Conditions to be analyzed.
Returns
-------
fig : instance of matplotlib.pyplot.Figure
The figure handle.
"""
res_path = '/media/robbis/DATA/fmri/monks/0_results/'
subjects = np.loadtxt('/media/robbis/DATA/fmri/monks/attributes_struct.txt',
dtype=np.str)
path = '/media/robbis/DATA/fmri/monks/'
roi_list = []
roi_list = np.loadtxt('/media/robbis/DATA/fmri/templates_fcmri/findlab_rois.txt',
delimiter=',',
dtype=np.str)
if isinstance(directory, str):
directory = [directory]
if isinstance(conditions, str):
conditions = [conditions]
for dir_ in directory:
for cond_ in conditions:
fname_ = os.path.join(res_path, dir_, cond_+'_values_1000_50.npz')
results_ = np.load(fname_)
values_ = results_['arr_0'].tolist()
errors_ = values_['error'] #values_['errors_']
sets_ = values_['features'] #values_['sets_']
weights_ = values_['weights'] #values_['weights_']
samples_ = values_['subjects'] #values_['samples_']
fname_ = os.path.join(res_path, dir_, cond_+'_permutation_1000_50.npz')
results_ = np.load(fname_)
values_p = results_['arr_0'].tolist()
errors_p = values_p['error'] #values_p['errors_p']
sets_p = values_p['features'] #values_p['sets_p']
weights_p = values_p['weights'] #values_p['weights_p']
samples_p = values_p['subjects'] #values_p['samples_p']
errors_p = np.nanmean(errors_p, axis=1)
print('-----------'+dir_+'-------------')
print(cond_)
print ('MSE = '+str(errors_[:,0].mean())+' -- p '+ \
str(np.count_nonzero(errors_p[:,0] < errors_[:,0].mean())/n_permutations))
print('COR = '+str(np.nanmean(errors_[:,1]))+' -- p '+ \
str(np.count_nonzero(errors_p[:,1] > np.nanmean(errors_[:,1]))/n_permutations))
directory_ = dir_
learner_ = "SVR_C_1"
prename = "%s_%s" %(cond_, learner_)
######## Get matrix infos ###############
conn_test = ConnectivityLoader(res_path,
subjects,
directory_,
roi_list)
# Get nan mask to correctly fill matrix
nan_mask = conn_test.get_results(['Samatha', 'Vipassana'])
# Transform matrix into float of ones
mask_ = np.float_(~np.bool_(nan_mask))
# Get the upper part of the matrix
mask_ = np.triu(mask_, k=1)
mask_indices = np.nonzero(mask_)
n_bins = np.count_nonzero(mask_)
###### Plot of distributions of errors and permutations #########
#errors_p = np.nanmean(errors_p, axis=1)
fig_ = pl.figure()
bpp = pl.boxplot(errors_p, showfliers=False, showmeans=True, patch_artist=True)
bpv = pl.boxplot(errors_, showfliers=False, showmeans=True, patch_artist=True)
fname = "%s_perm_1000_boxplot.png" %(prename)
for box_, boxp_ in zip(bpv['boxes'], bpp['boxes']):
box_.set_facecolor('lightgreen')
boxp_.set_facecolor('lightslategrey')
pl.xticks(np.array([1,2]), ['MSE', 'COR'])
pl.savefig(os.path.join(res_path, directory_, fname))
pl.close()
n_permutations = np.float(errors_p[:,0].shape[0])
##### Plot of connection distributions ########
pl.figure()
h_values_p, _ = np.histogram(sets_p.flatten(), bins=np.arange(0, n_bins+1))
#pl.plot(zscore(h_values_p))
pl.hist(zscore(h_values_p), bins=25)
fname = "%s_features_set_dist.png" %(prename)
pl.savefig(os.path.join(res_path, directory_, fname))
pl.figure()
h_values_, _ = np.histogram(sets_.flatten(), bins=np.arange(0, n_bins+1))
pl.plot(zscore(h_values_))
fname = "%s_features_set_cross_validation.png" %(prename)
pl.savefig(os.path.join(res_path, directory_, fname))
pl.close('all')
######## Plot connectivity stuff ###########
weights_ = weights_.squeeze()
filling_vector = np.zeros(np.count_nonzero(mask_))
counting_vector = np.zeros(np.count_nonzero(mask_))
for s, w in zip(sets_, weights_):
filling_vector[s] += zscore(w)
counting_vector[s] += 1
# Calculate the average weights and then zscore
avg_weigths = np.nan_to_num(filling_vector/counting_vector)
mask_[mask_indices] = avg_weigths
matrix_ = np.nan_to_num(copy_matrix(mask_, diagonal_filler=0))
names_lr, colors_lr, index_, coords, _ = get_atlas_info(dir_)
'''
matrix_[matrix_ == 0] = np.nan
matrix_[np.abs(matrix_) < 1] = np.nan
'''
size_w = np.zeros_like(matrix_)
size_w[mask_indices] = np.abs(avg_weigths)
size_w = np.nan_to_num(copy_matrix(size_w, diagonal_filler=0))
size_w = np.sum(size_w, axis=0)
f, _ = plot_connectivity_circle_edited(matrix_[index_][:,index_],
names_lr[index_],
node_colors=colors_lr[index_],
node_size=2*size_w[index_]**2,
con_thresh = 1.4,
title=cond_,
node_angles=circular_layout(names_lr,
list(names_lr),
),
fontsize_title=19,
fontsize_names=13,
fontsize_colorbar=13,
colorbar_size=0.3,
colormap='bwr',
#colormap=cm_,
vmin=-3.,
vmax=3.,
fig=pl.figure(figsize=(16,16))
)
fname = "%s_features_weight.png" %(prename)
f.savefig(os.path.join(res_path, directory_, fname),
facecolor='black',
dpi=150)
for d_ in ['x', 'y', 'z']:
fname = "%s_connectome_feature_weight_%s.png" %(prename, d_)
fname = os.path.join(res_path, directory_, fname)
plot_connectome(matrix_,
coords,
colors_lr,
2*size_w**2,
1.4,
fname,
#cmap=pl.cm.bwr,
title=None,
display_=d_,
#max_=3.,
#min_=3.
)
fname = "%s_connections_list_feature_weights.txt" %(prename)
fname = os.path.join(res_path, directory_, fname)
#print_connections(matrix_, names_lr, fname)
#########
mask_ = np.float_(~np.bool_(nan_mask))
mask_ = np.triu(mask_, k=1)
mask_indices = np.nonzero(mask_)
mask_[mask_indices] = h_values_
matrix_ = np.nan_to_num(copy_matrix(mask_, diagonal_filler=0))
size_ = np.zeros_like(matrix_)
size_[mask_indices] = counting_vector
size_ = np.nan_to_num(copy_matrix(size_, diagonal_filler=0))
size_ = np.sum(size_, axis=0)
f, _ = plot_connectivity_circle_edited(matrix_[index_][:,index_],
names_lr[index_],
node_colors=colors_lr[index_],
node_size=size_[index_]*5,
con_thresh = 15.,
title=cond_,
node_angles=circular_layout(names_lr,
list(names_lr),
),
fontsize_title=19,
fontsize_names=13,
fontsize_colorbar=13,
colorbar_size=0.3,
#colormap='bwr',
#colormap='terrain',
#vmin=40,
fig=pl.figure(figsize=(16,16))
)
fname = "%s_features_choices.png" %(prename)
f.savefig(os.path.join(res_path, directory_, fname),
facecolor='black',
dpi=150)
for d_ in ['x', 'y', 'z']:
fname = "%s_connectome_feature_choices_%s.png" %(prename, d_)
fname = os.path.join(res_path, directory_, fname)
plot_connectome(matrix_,
coords,
colors_lr,
4.*size_,
15.,
fname,
title=None,
max_=50.,
min_=0.,
display_=d_
)
fname = "%s_connections_list_feature_choices.txt" %(prename)
fname = os.path.join(res_path, directory_, fname)
#print_connections(matrix_, names_lr,fname)
pl.close('all')
def write_correlation_matrices(directory, condition):
subjects = np.loadtxt('/media/robbis/DATA/fmri/monks/attributes_struct.txt',
dtype=np.str)
roi_list = np.loadtxt('/media/robbis/DATA/fmri/templates_fcmri/findlab_rois.txt',
delimiter=',',
dtype=np.str)
path = '/media/robbis/DATA/fmri/monks/0_results/'
conn = ConnectivityLoader(path, subjects, directory, roi_list)
nan_mask = conn.get_results(['Samatha', 'Vipassana'])
#nan_mask = conn.get_results(['Rest'])
ds = conn.get_dataset()
mask_ = np.float_(~np.bool_(nan_mask))
mask_ = np.triu(mask_, k=1)
mask_indices = np.nonzero(mask_)
ds_ = ds[np.logical_and(ds.targets == condition, ds.sa.groups == 'E')]
array_ = ds_.samples.mean(0)
mask_[mask_indices] = array_
matrix = np.nan_to_num(copy_matrix(mask_, diagonal_filler=0))
names_lr, colors_lr, index_, coords, networks = get_atlas_info('findlab')
plot_connectomics(matrix,
20+8*np.abs(matrix.sum(axis=1))**2,
save_path=os.path.join(path, directory),
prename=condition+'_correlation',
save=True,
colormap='bwr',
vmin=np.abs(matrix).max()*-1,
vmax=np.abs(matrix).max(),
node_names=names_lr,
node_colors=colors_lr,
node_coords=coords,
node_order=index_,
networks=networks,
threshold=0.5,
title=condition+' Correlation',
zscore=False,
)
w_aggregate = aggregate_networks(matrix, roi_list.T[-2])
_, idx = np.unique(networks, return_index=True)
plot_connectomics(w_aggregate,
5*np.abs(w_aggregate.sum(axis=1))**2,
save_path=os.path.join(path, directory),
prename=condition+'_aggregate_correlation',
save=True,
colormap='bwr',
vmin=-1*w_aggregate.max(),
vmax=w_aggregate.max(),
node_names=np.unique(networks),
node_colors=colors_lr[idx],
node_coords=coords[idx],
node_order=np.arange(0, len(idx)),
networks=np.unique(networks),
threshold=4,
zscore=False
)
