def run_mini_pipeline():
atlas = datasets.fetch_atlas_msdl()
atlas_img = atlas['maps']
labels = pd.read_csv(atlas['labels'])['name']
masker = NiftiMapsMasker(maps_img=atlas_img, standardize=True,
memory='/tmp/nilearn', verbose=0)
data = datasets.fetch_adhd(number_subjects)
figures_folder = '../figures/'
count=0
for func_file, confound_file in zip(data.func, data.confounds):
# fit the data to the atlas mask, regress out confounds
time_series = masker.fit_transform(func_file, confounds=confound_file)
correlation = np.corrcoef(time_series.T)
#plotting starts here
plt.figure(figsize=(10, 10))
plt.imshow(correlation, interpolation="nearest")
x_ticks = plt.xticks(range(len(labels)), labels, rotation=90)
y_ticks = plt.yticks(range(len(labels)), labels)
corr_file = figures_folder+'subject_number_' + str(count) + '_correlation.pdf'
plt.savefig(corr_file)
atlas_region_coords = [plotting.find_xyz_cut_coords(img) for img in image.iter_img(atlas_img)]
threshold = 0.6
plotting.plot_connectome(correlation, atlas_region_coords, edge_threshold=threshold)
connectome_file = figures_folder+'subject_number_' + str(count) + '_connectome.pdf'
plt.savefig(connectome_file)
#graph setup
#binarize correlation matrix
correlation[correlation<threshold] = 0
correlation[correlation != 0] = 1
graph = nx.from_numpy_matrix(correlation)
partition=louvain.best_partition(graph)
values = [partition.get(node) for node in graph.nodes()]
plt.figure()
nx.draw_spring(graph, cmap = plt.get_cmap('jet'), node_color = values, node_size=30, with_labels=True)
graph_file = figures_folder+'subject_number_' + str(count) + '_community.pdf'
plt.savefig(graph_file)
count += 1
plt.close('all')
def vk_test():
user_id = 1
#graph = vk.get_friends_to_friends_graph(user_id)
#vk.get_friends_to_friends_file(user_id, file_path="./data/friends_my.txt")
graph = rg.read_from_file("./data/friends_my_without_single.txt")
print(graph.number_of_edges())
print(graph.number_of_nodes())
print(graph.number_of_selfloops())
pa = louvain.best_partition(graph)
sg.print_graph_communities(pa)
sg.show_graph_communities(graph, pa)
def vk_test():
user_id = 1
#graph = vk.get_friends_to_friends_graph(user_id)
#vk.get_friends_to_friends_file(user_id, file_path="./data/friends_my.txt")
graph = rg.read_from_file("./data/friends_my_without_single.txt")
print(graph.number_of_edges())
print(graph.number_of_nodes())
print(graph.number_of_selfloops())
pa = louvain.best_partition(graph)
sg.print_graph_communities(pa)
sg.show_graph_communities(graph, pa)
def louvain_test(graph):
'''
:param graph: networkx.Graph
:return: None
'''
print("Louvain has been started started")
start_time = time.time()
pa = louvain.best_partition(graph)
print("time : ", time.time() - start_time)
modular = louvain.modularity(pa, graph)
print('Louvain modularity: ', modular)
# sg.print_graph_communities(pa)
sg.write_graph_communities(pa, "./data/vk_louvain_source.txt")
print('\n')
def louvain_test(graph):
'''
:param graph: networkx.Graph
:return: None
'''
print("Louvain has been started started")
start_time = time.time()
pa = louvain.best_partition(graph)
print("time : ", time.time() - start_time)
modular = louvain.modularity(pa, graph)
print('Louvain modularity: ', modular)
# sg.print_graph_communities(pa)
sg.write_graph_communities(pa, "./data/vk_louvain_source.txt")
print('\n')
def analyse_community(graph, save_name):
partition = louvain.best_partition(graph)
dendro = louvain.generate_dendrogram(graph)
print 'Number of communities: ' + str(len(set(partition.values())))
logging.info('Number of communities: ' + str(len(set(partition.values()))))
com_node_map = {}
for community in set(partition.values()):
com_node_map[community] = len([nodes for nodes in partition.keys() if partition[nodes] == community])
for k, v in com_node_map.items():
print 'Community ' + str(k+1) + ' has ' + str(v) + ' nodes'
logging.info('Community ' + str(k+1) + ' has ' + str(v) + ' nodes')
nx.set_node_attributes(graph, 'community', partition)
no_pe_com_map_list = nodes_per_community(dendro)
community_size_distribution(no_pe_com_map_list, save_name)
drawNetwork(graph, save_name)
import sys
sys.path.append("louvain")
import louvain
sys.path.append("infomap")
import infomap
import matplotlib.pyplot as plt
import matplotlib.colors as colors
import logging
global_frame_list = []
dispatch = {
'infomap_partition': infomap.infomap(graph)
'louvain_partition': louvain.best_partition(graph)
'infomap_dendro': infomap.iteration_loop(graph)
'louvain_dendro': louvain.generate_dendrogram(graph)
}
def run_mini_pipeline():
datadir = 'data'
for root, dirs, filenames in os.walk(datadir):
for file in filenames:
print 'computing subject ' + str(filenames.index(file))
logging.info('computing subject ' + str(filenames.index(file)))
file_handle = os.path.join(root, file)
df = pd.read_csv(file_handle, sep='\t')
np_ts_matrix=df.as_matrix()
correlation_matrix = np.corrcoef(np_ts_matrix.T)
# For some reason the type of this is still a multigraph, so louvain aborts.
# Sledge hammer time
und_G1 = nx.Graph(data=list(set(und_G0.edges())))
# Might as well just do the large connected component while were at it.
components = nx.connected_components(und_G1)
und_G = nx.subgraph(und_G1,components[0])
#######################################################################
##
## F i n d i n g C o m m u n i t i e s
##
#######################################################################
#partition = community.best_partition(und_G)
partition = louvain.best_partition(und_G)
#######################################################################
##
## D r a w i n g
##
#######################################################################
colors = get_partition_coloring(und_G,partition)
pos = nx.spring_layout(und_G)
#count = 0.
nx.draw_networkx_nodes(und_G, pos, und_G.nodes(), node_size = 80,
node_color = colors)
nx.draw_networkx_edges(und_G,pos, alpha=0.5)
plt.show()
def run_mini_pipeline():
atlas = datasets.fetch_atlas_msdl()
atlas_img = atlas['maps']
labels = pd.read_csv(atlas['labels'])['name']
masker = NiftiMapsMasker(maps_img=atlas_img,
standardize=True,
memory='/tmp/nilearn',
verbose=0)
data = datasets.fetch_adhd(number_subjects)
figures_folder = '../figures/'
count = 0
for func_file, confound_file in zip(data.func, data.confounds):
# fit the data to the atlas mask, regress out confounds
time_series = masker.fit_transform(func_file, confounds=confound_file)
correlation = np.corrcoef(time_series.T)
#plotting starts here
plt.figure(figsize=(10, 10))
plt.imshow(correlation, interpolation="nearest")
x_ticks = plt.xticks(range(len(labels)), labels, rotation=90)
y_ticks = plt.yticks(range(len(labels)), labels)
corr_file = figures_folder + 'subject_number_' + str(
count) + '_correlation.pdf'
plt.savefig(corr_file)
atlas_region_coords = [
plotting.find_xyz_cut_coords(img)
for img in image.iter_img(atlas_img)
]
threshold = 0.6
plotting.plot_connectome(correlation,
atlas_region_coords,
edge_threshold=threshold)
connectome_file = figures_folder + 'subject_number_' + str(
count) + '_connectome.pdf'
plt.savefig(connectome_file)
#graph setup
#binarize correlation matrix
correlation[correlation < threshold] = 0
correlation[correlation != 0] = 1
graph = nx.from_numpy_matrix(correlation)
partition = louvain.best_partition(graph)
values = [partition.get(node) for node in graph.nodes()]
plt.figure()
nx.draw_spring(graph,
cmap=plt.get_cmap('jet'),
node_color=values,
node_size=30,
with_labels=True)
graph_file = figures_folder + 'subject_number_' + str(
count) + '_community.pdf'
plt.savefig(graph_file)
count += 1
plt.close('all')