def node_presence(graphs, path):
if __name__ == '__main__':
if len(sys.argv) != 3:
print 'usage: make_paths <filename> <npaths>'
sys.exit(-1)
filename = sys.argv[1]
npaths = int(sys.argv[2])
print 'loading clean training files'
edge_lists = loader.load_train_files(train_format, file_low, file_high)
graphs = loader.get_graphs_from_edge_lists(edge_lists)
print 'making paths file %s' % filename
with open(filename, 'w') as outfile:
for i in range(npaths):
outfile.write(delim.join(random_shortest_path(graphs)))
outfile.write('\n')
def write_analysis_matrix(data, pred, filename):
m, nd = data.shape
m, np = pred.shape
with open(filename, 'w') as f:
for i in range(m):
for j in range(nd):
f.write('%d,' % data[i,j])
for j in range(np):
f.write('%f,' % pred[i,j])
f.write('\n')
if __name__ == '__main__':
print 'loading clean training files'
edge_lists = loader.load_train_files(train_format, file_low, file_high)
graphs = loader.get_graphs_from_edge_lists(edge_lists)
print 'loading paths file'
paths = loader.load_paths_file(paths_file)
print 'loading shortest path files'
scosts = loader.load_shortest_path_costs(costs_format, file_low, file_high)
print 'computing path costs'
pcosts = loader.compute_path_costs(graphs, paths)
print 'getting shortest path matrix'
data = loader.get_shortest_path_matrix(graphs, paths, scosts, pcosts)
print 'running logistic regression'
ytest, ypred, yprob = loader.logistic_regression(data)
