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 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 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 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_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))
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(
