def main():
parser = argparse.ArgumentParser()
parser.add_argument("gc_clustering")
parser.add_argument("other_clustering")
opts = parser.parse_args()
gc_clusters = io.read_clusters(opts.gc_clustering)
other_clusters = io.read_clusters(opts.other_clustering)
clusters = resolve_clusters(gc_clusters, other_clusters)
io.output_clusters(clusters, '')
def main():
parser = argparse.ArgumentParser()
parser.add_argument("network_file", help="Network file used for initial\
clustering")
parser.add_argument("cluster_file", help="Clustering results file")
parser.add_argument("-c", "--no_conversion", action="store_true")
parser.add_argument("-d", "--directed", action="store_true",
help="Flag specifying if the input represents\
a directed graph. Defaults to false.")
parser.add_argument("-n", "--node_list", nargs="?",
help="Optionally specify a list of the nodes in\
the DSD file. Default is all the nodes in the\
graph.")
parser.add_argument("-s", "--simple_conversion", action="store_true")
opts = parser.parse_args()
if opts.node_list:
node_list = io.get_node_list(opts.node_list)
clusters = io.read_clusters(opts.cluster_file)
if opts.node_list:
G = io.build_ig_graph_from_matrix(opts.network_file, False, node_list)
else:
G = ig.Graph.Read_Ncol(opts.network_file, directed=opts.directed)
clusters_to_process, final_clusters = [], []
for cluster in clusters:
if len(cluster) > MAX_CL_SIZE:
clusters_to_process.append(cluster)
else:
final_clusters.append(cluster)
# if all nodes have been clustered, stop looping, otherwise continue to
# recurse on each large cluster
step = 1
while clusters_to_process:
processing = clusters_to_process
clusters_to_process = []
for cluster in processing:
id_cluster = names_to_ids(G, cluster)
SG = G.subgraph(cluster)
cluster_size = len(cluster)
num_clusters = 2
'''
num_clusters = (int(cluster_size / float(100)) if cluster_size > 200
else 2)
'''
clusters = cl.spectral_clustering(SG, num_clusters,
no_conversion=opts.no_conversion,
simple_conversion=opts.simple_conversion)
for cluster in clusters:
if len(cluster) > MAX_CL_SIZE:
clusters_to_process.append([SG.vs[i]['name'] for i in cluster])
else:
final_clusters.append([SG.vs[i]['name'] for i in cluster])
step += 1
io.output_clusters(final_clusters, '')
def main():
parser = argparse.ArgumentParser()
parser.add_argument("dsd_file",
help="Distance (i.e. DSD) matrix for network")
parser.add_argument("cluster_file", help="Clustering results file")
parser.add_argument("-n",
"--node_list",
nargs="?",
help="Optionally specify a list of the nodes in\
the DSD file. Default is all the nodes in the\
graph.")
opts = parser.parse_args()
node_list = io.get_node_list(opts.node_list)
clusters = io.read_clusters(opts.cluster_file)
G = io.build_ig_graph_from_matrix(opts.dsd_file, False, node_list)
clusters_to_process, final_clusters = [], []
for cluster in clusters:
if len(cluster) > MAX_CL_SIZE:
clusters_to_process.append(cluster)
else:
final_clusters.append(cluster)
# if all nodes have been clustered, stop looping, otherwise continue to
# recurse on each large cluster
step = 1
while clusters_to_process:
processing = clusters_to_process
clusters_to_process = []
for cluster in processing:
id_cluster = names_to_ids(G, cluster)
SG = G.subgraph(cluster)
cluster_size = len(cluster)
num_clusters = (int(cluster_size /
float(100)) if cluster_size > 200 else 2)
mat = SG.get_adjacency(attribute='weight')
dist_matrix = np.array(mat.data)
del mat
clusters = cl.spectral_clustering(dist_matrix, num_clusters)
del dist_matrix
for cluster in clusters:
if len(cluster) > MAX_CL_SIZE:
clusters_to_process.append(
[SG.vs[i]['name'] for i in cluster])
else:
final_clusters.append([SG.vs[i]['name'] for i in cluster])
step += 1
io.output_clusters(final_clusters, '')
def main():
parser = argparse.ArgumentParser()
parser.add_argument("input_file", help="Original clusters input file")
parser.add_argument("-c",
"--cutoff",
nargs="?",
default=DEFAULT_MIN_SIZE,
help="Cutoff for filtering cluster size")
opts = parser.parse_args()
clusters = io.read_clusters(opts.input_file)
filtered_clusters = [c for c in clusters if len(c) >= int(opts.cutoff)]
io.output_clusters(filtered_clusters, '')
def main():
parser = argparse.ArgumentParser()
parser.add_argument("gc_file", help='GeneCentric cluster file')
parser.add_argument("cluster_file",
help="File containing cluster filepaths")
opts = parser.parse_args()
cluster_nodes = get_cluster_nodes(opts.cluster_file)
gc_nodes = get_cluster_nodes(opts.gc_file)
gc_clusters = io.read_clusters(opts.gc_file)
difference_nodes = list(set(cluster_nodes) - set(gc_nodes))
gc_clusters.append(difference_nodes)
io.output_clusters(gc_clusters, '')
def main():
parser = argparse.ArgumentParser()
parser.add_argument("network_file", help="Original network input file")
parser.add_argument("cluster_file", help="A cluster results file")
parser.add_argument("-n",
"--node_list",
nargs="?",
default=[],
help="Optionally specify a list of the nodes in\
the graph.")
parser.add_argument("-o",
"--output_prefix",
nargs="?",
default="",
help="Optionally specify a prefix for output files")
opts = parser.parse_args()
nodes = io.get_node_list(opts.node_list) if opts.node_list else []
output_pref = opts.output_prefix if opts.output_prefix else './clusters_'
G = io.build_ig_graph_from_matrix(opts.network_file,
is_directed=False,
node_list=nodes)
if opts.node_list: G.vs['name'] = nodes
clusters = io.read_clusters(opts.cluster_file)
for idx, cluster in enumerate(clusters):
try:
output_file = '{}{}.txt'.format(output_pref, idx)
output_fp = open(output_file, 'w')
except IOError:
sys.exit("Could not open file: {}".format(output_file))
id_cluster = names_to_ids(G, cluster)
SG = G.subgraph(id_cluster)
for e in SG.es:
output_fp.write('{}\t{}\t{}\n'.format(SG.vs[e.source]['name'],
SG.vs[e.target]['name'],
e['weight']))
output_fp.close()
def plot_grand_averages_source_estimates_cluster_masked(
name, save_dir_averages, lowpass, subjects_dir, method, time_window,
save_plots, figures_path, independent_variable_1,
independent_variable_2, mne_evoked_time, p_threshold):
if mne_evoked_time < time_window[0] or mne_evoked_time > time_window[1]:
raise ValueError('"mne_evoked_time" must be within "time_window"')
n_subjects = 20 ## should be corrected
independent_variables = [independent_variable_1, independent_variable_2]
stcs = dict()
for stc_type in independent_variables:
filename = join(save_dir_averages,
stc_type + filter_string(lowpass) + \
'_morphed_data_' + method)
stc = mne.read_source_estimate(filename)
stc.comment = stc_type
stcs[stc_type] = stc
difference_stc = stcs[independent_variable_1] - stcs[independent_variable_2]
## load clusters
cluster_dict = io.read_clusters(save_dir_averages, independent_variable_1,
independent_variable_2, time_window,
lowpass)
cluster_p_values = cluster_dict['cluster_p_values']
clusters = cluster_dict['clusters']
T_obs = cluster_dict['T_obs']
n_sources = T_obs.shape[0]
cluster_p_threshold = 0.05
indices = np.where(cluster_p_values <= cluster_p_threshold)[0]
sig_clusters = []
for index in indices:
sig_clusters.append(clusters[index])
cluster_T = np.zeros(n_sources)
for sig_cluster in sig_clusters:
# start = sig_cluster[0].start
# stop = sig_cluster[0].stop
sig_indices = np.unique(np.where(sig_cluster == 1)[0])
cluster_T[sig_indices] = 1
t_mask = np.copy(T_obs)
t_mask[cluster_T == 0] = 0
cutoff = stats.t.ppf(1 - p_threshold / 2, df=n_subjects - 1)
time_index = mne_evoked_time * 1e3 + 200
time_window_times = np.linspace(
time_window[0], time_window[1],
int((time_window[1] - time_window[0]) * 1e3) + 2)
time_index_mask = np.where(time_window_times == mne_evoked_time)[0]
difference_stc._data[:,
time_index] = np.reshape(t_mask[:, time_index_mask],
n_sources)
mayavi.mlab.close(None, True)
clim = dict(kind='value', lims=[cutoff, 2 * cutoff, 4 * cutoff])
mayavi.mlab.figure(figure=0, size=(800, 800))
brain = difference_stc.plot(subject='fsaverage',
subjects_dir=subjects_dir,
time_viewer=False,
hemi='both',
figure=0,
clim=clim,
views='dorsal')
time = mne_evoked_time
brain.set_time(time)
message = independent_variable_1 + ' vs ' + independent_variable_2
brain.add_text(0.01, 0.9, message, str(0), font_size=14)
if save_plots:
save_path = join(figures_path, 'grand_averages',
'source_space/statistics',
message + '_' + name + \
filter_string(lowpass) + '.jpg' + '_' + str(time * 1e3) + \
'_msec.jpg')
brain.save_single_image(save_path)
print 'figure: ' + save_path + ' has been saved'
else:
print 'Not saving plots; set "save_plots" to "True" to save'