def test(N, D):
box = dl.box_generator(N, D)
dag = box[0]
ext = box[1]
tr_dag = tr.trans_red(dag)
good_dag = tr_dag
lp = dl.lpd(tr_dag, ext[1], ext[0])
path = lp[1]
tr_dag = good_dag
dim = mps.mpsd(tr_dag, path)
mm_dim = mmd.MM_dimension(dag)
print dim
print mm_dim
return [dim[0], mm_dim]
def interval_test(DAG,start,end):
lp = dl.lpd(DAG,start,end)
length = lp[2]
print 'The longest path between %s and %s is %d edges long' %(start,end,length)
interval = lc.interval(DAG,start,end)
N = interval.number_of_nodes()
E = interval.number_of_edges()
print 'The interval contains %d nodes and %d edges' %(N,E)
c = clus.clustering(interval)
print 'For the interval, c+ is %f, c0 is %f, c- is %f' %(c[0],c[1],c[2])
#MMd = MM.MM_dimension(interval)
MPSD = mp.mpsd(interval,lp[1])
#print 'The MM dimension of the interval is %f and the MPSD is %f' %(MMd,MPSD)
print 'The MPSD is %f' %MPSD[0]
def ms_dim_with_removal(number_of_trials, number_of_probabilities_considered, N, D, filename):
"""
arguments: number_of_trials for each probability, output data is averaged over this.
number_of_probabilities_considered = integer: number of data points
N = integer: number of nodes in network
D = integer: dimension of network
filename = string: output file path e.g. './testing.txt'
"""
start_time = time.time() #start clock
myfile = open(filename, 'w')
p_step = 1.0/number_of_probabilities_considered #define size of step in probability (prob = prob that edge is removed given it's causally allowed)
myfile.write(str(D)+"D box w/ random removal prob p, and longest path l. Number trials averaged over=" + str(number_of_trials) + " N="+ str(N) + '\n')
myfile.write('p' + '\t' + 'ms dimension (p)' +'\t' + 'std error' + '\n') #send column headings to output file
#initialize lists for each output variable
p_list_for_ms = []
ms_average_list = []
ms_std_error_list = []
p_range = np.arange(0.0,1.0+p_step,p_step)
for p in p_range: #Loop over x, where x=10^p, so we get more points around prob's closer to 1 and can see phase transition-y behavior more clearly.
#initialize lists for each quantity for which we require an individual value to be stored after every trial (e.g. for calculations stats)
ms_list = []
ms_diff_sq_list = []
ms_failed_trials = 0
ms_sum = ms_average = 0.0
for _ in range(int(number_of_trials)):
model = models.box_model(D, N,1-p) #create model with prob of no edge given edge is causally allowed = p
DAG_with_removal = model[0] #networkx DAG object from above model
tr_DAG_with_removal = tr.trans_red(DAG_with_removal) #transitively reduce DAG - doesn't effect lp or MM dimension, DOES MIDPOINT SCALING
extremes = model[1] #returns list of extremes from model
if nx.has_path(DAG_with_removal, extremes[1], extremes[0]):
longest_path_between_extremes = dl.lpd(tr_DAG_with_removal, extremes[1],extremes[0]) #calculate longest path between extremes
longest_path = longest_path_between_extremes[1]
length_of_longest_path = longest_path_between_extremes[2] #save length of longest path between extremes
else:
length_of_longest_path=0 #if no path between extremes, longest path = 0 is physical.
if length_of_longest_path > 2:
ms_dimension = ms.mpsd(DAG_with_removal, longest_path)[0] #need to trans red DAG first as otherwise lp method does not return the correct longest path. James said he'd sorted this?
else:
ms_dimension = 0
ms_failed_trials += 1
ms_list.append(ms_dimension)
if len(ms_list)<number_of_trials:
ms_list.append(None)
ms_sum = sum(ms_list)
if (number_of_trials - ms_failed_trials - 1)>0:
ms_average = ms_sum/float(number_of_trials-ms_failed_trials)
else: ms_average=None
ms_diff_sq_sum = 0.0
if (number_of_trials - ms_failed_trials - 1)>0:
for i in range(number_of_trials - ms_failed_trials):
ms_diff_sq_list.append((ms_list[i] - ms_average)**2)
ms_diff_sq_sum += ms_diff_sq_list[i]
ms_std_dev = math.sqrt(ms_diff_sq_sum/float(number_of_trials - ms_failed_trials -1))
ms_std_error = ms_std_dev/math.sqrt(float(number_of_trials - ms_failed_trials))
else:
ms_std_error = 0
p_list_for_ms.append(p)
ms_average_list.append(ms_average)
ms_std_error_list.append(ms_std_error)
myfile.write(str(p)+ '\t' + str(ms_average) + '\t' + str(ms_std_error) + '\n')
clean = clean_for_plotting(ms_average_list,p_list_for_ms, ms_std_error_list)
ms_average_list = clean[0]
p_list_for_ms = clean[1]
ms_std_error_list = clean[2]
print "finished ", p , "probability"
elapsed = (time.time() - start_time) #calculate time for method completion
print "finished. Time elapsed = " , elapsed
return [p_list_for_ms, ms_average_list, ms_std_error_list]
