def number_of_lp_lattice():
for D in [2]:
myfile = open(str(D)+'number_lp_lattice', 'w')
myfile.write('N_side' + '\t' + 'N'+ '\t'+ 'lp length' + '\t'+ 'no. lp'+ '\n')
start_time = time.time()
for N_side in range(10,16,1):
N = N_side**2
# model = models.COd(2, N)
model = models.square_lattice_model(D, N_side)
DAG = model[0]
extremes = model[1]
tr_DAG = tr.trans_red(DAG)
lp = dl.lpd(tr_DAG, extremes[1], extremes[0])
length_lp = lp[2]
j=0
paths_list = list(nx.all_simple_paths(tr_DAG, extremes[1], extremes[0], cutoff=length_lp+1))
for i in range(len(paths_list)):
if len(paths_list[i])==length_lp+1:
j+=1
myfile.write(str(N_side) + '\t' + str(N) +'\t' + str(length_lp)+ '\t' + str(j) + '\n')
print 'done', N_side
elapsed = time.time() - start_time
print 'finished.',D,'Dimension. Time elapsed = ',elapsed
return
def test(N, D):
box = dl.box_generator(N, D)
DAG = box[0]
ext = box[1]
start = ext[1]
end = ext[0]
print DAG.node[start]["birthday"]
print "!!!!!"
start_time = time.clock()
the_greedy_path = greedy_path(DAG, start, max_depth=50)
greedy_time = time.clock() - start_time
start_time = time.clock()
lp = dl.lpd(DAG, start, end)
lp_time = time.clock() - start_time
print "Greedy"
greedy_path_length = len(the_greedy_path)
# print the_greedy_path
print "Longest"
lp_length = lp[2]
# print lp[1]
print "Greedy Time = %s" % str(greedy_time)
print "LP Time = %s" % str(lp_time)
return (greedy_path_length, greedy_time, lp_length, lp_time)
def BA_lp(m=50, N_range = range(51,555,50)):
number_of_trials = 100
myfile = open('BA_lp', 'w')
myfile.write('N' + '\t' + 'average lp length'+ '\t'+'std err'+'\n')
for N in N_range:
lp_list = []
comparison_lp_list = []
for _ in range(number_of_trials):
model = models.barabasi_albert_graph(N,m)
# model = models.COd(D,N)
G = model[0]
extremes = model[1]
# average_in_degree = float(m)*float((N-1))/(float(N))
# print average_in_degree
average_in_degree = float(nx.number_of_edges(G)) /float(nx.number_of_nodes(G))
comparison_model = oneD_random_comparison(N,average_in_degree)
comparison_G = comparison_model[0]
comparison_extremes = comparison_model[1]
if nx.has_path(comparison_G, comparison_extremes[1], comparison_extremes[0]):
comparison_lp = dl.lpd(comparison_G, comparison_extremes[1], comparison_extremes[0])
comparison_lp_length = comparison_lp[2]
else: comparison_lp_length=None
#tr_DAG = tr.trans_red(G)
lp = dl.lpd(G,extremes[1],extremes[0])
lp_length = lp[2]
lp_list.append(lp_length)
comparison_lp_list.append(comparison_lp_length)
statistics = stats.list_stats(lp_list)
lp_av = statistics[3]
lp_std_err = statistics[0]
comparison_stats = stats.list_stats(comparison_lp_list)
comparison_lp_av = comparison_stats[3]
comparison_lp_std_err = comparison_stats[0]
print "done ", N
myfile.write(str(N) + '\t' + str(lp_av) + '\t' + str(lp_std_err) +'\t'+ str(comparison_lp_av) + '\t' + str(comparison_lp_std_err) + '\n')
#nx.draw_random(G, with_labels=False, node_colour ='k', node_size=50, node_color = 'k', width=0.5)
#nx.draw_networkx(G, pos=random, with_labels=False, node_colour ='k', node_size=50, node_color = 'k', width=0.5)
#plt.show() # display figure
return
def pythag_distance(DAG, node1, node2):
bday1 = DAG.node[node1]["birthday"]
bday2 = DAG.node[node2]["birthday"]
rank1 = DAG.node[node1]["rank"]
rank2 = DAG.node[node2]["rank"]
if bday1 > bday2:
lp = dl.lpd(DAG, node1, node2)[2]
else:
lp = dl.lpd(DAG, node1, node2)[2]
dbday = bday1 - bday2
drank = rank1 - rank2
distance_bday = math.sqrt(lp ** 2 - dbday ** 2) # unit mismatch
distance_rank = math.sqrt(lp ** 2 - drank ** 2)
print "The distance between %s and %s is %f for bday and %f for rank" % (node1, node2, distance_bday, distance_rank)
def test(N, D):
box = dl.box_generator(N, D, 'minkowski')
#box = mod2.COd(D,N)
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])
length = lp[2]
print length
return length
def lpd_test(N, D):
box = dl.box_generator(N, D, 'minkowski')
dag = box[0]
ext = box[1]
tr_dag = tr.trans_red(dag)
print ext[0]
print ext[1]
lp = dl.lpd(tr_dag, ext[1], ext[0])
print lp[1]
return lp
def number_of_lp_BA(m_range=[1,5,10,50], n_max=50, n_step=5):
for m in m_range:
n_range=range(m+1,n_max,n_step)
# n_range=range(101,201,10)
myfile = open(str(m)+'C_for_BA', 'w')
myfile.write('n' + '\t' + 'lp_av'+'\t' + 'lp_err'+ '\t' + 'no._av' +'\t' + 'no._err'+ '\n')
start_time = time.time()
trials = 1000
for n in n_range:
lp_length_list = []
j_list = []
for _ in range(trials):
# model = models.COd(2, N)
model = models.barabasi_albert_graph(n, m)
DAG = model[0]
extremes = model[1]
tr_DAG = tr.trans_red(DAG)
lp = dl.lpd(tr_DAG, extremes[1], extremes[0])
length_lp = lp[2]
lp_length_list.append(length_lp)
j=0
paths_list = list(nx.all_simple_paths(tr_DAG, extremes[1], extremes[0], cutoff=length_lp+1))
for i in range(len(paths_list)):
if len(paths_list[i])==length_lp+1:
j+=1
j_list.append(j)
print j_list
lp_stats = stats.list_stats(lp_length_list)
lp_av = lp_stats[3]
lp_err = lp_stats[1]
j_stats = stats.list_stats(j_list)
j_av = j_stats[3]
j_err = j_stats[1]
print j_av
print j_err
myfile.write(str(n) + '\t' + str(lp_av)+'\t' + str(lp_err)+ '\t' + str(j_av) +'\t' + str(j_err)+ '\n')
print 'done', n
elapsed = time.time() - start_time
print 'finished.',m,'m. Time elapsed = ',elapsed
return
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 axis_end(DAG, apex, type, surface):
out = open("./axis_%s.txt" % apex, "w")
cone_list = lightcone_list(DAG, apex, type)
print "There are %d nodes in the cone of %s" % (len(cone_list), apex)
print "There are %d nodes along the top of the DAG" % len(surface)
cone_top = []
for thing in surface:
if thing in cone_list:
cone_top.append(thing)
print "There are %d nodes on the top of the cone" % len(cone_top)
max = 0
axis_node = []
T = float(len(cone_top))
i = 0.0 # use to print out progress bar
for point in cone_top:
DAG2 = DAG.copy()
if type == "forward":
start = point
end = apex
else: # type = 'backward'
start = apex
end = point
size = len(finish_interval(DAG2, end, start, cone_list, type))
lp = dl.lpd(DAG2, start, end)[2] + 1 # to get lp in nodes, not edges
out.write(str(point) + "\t" + str(size) + "\t" + str(lp) + "\n")
# find which node in point gives the largest interval (in terms of number of nodes)
if size > 0:
if size > max:
max = size
axis_node = [point]
elif size == max:
axis_node.append(point)
i += 1
print (i / T) * 100.0
return [axis_node, max]
def number_of_lp():
for D in [2,3,4]:
myfile = open(str(D)+'how many longest paths?', 'w')
myfile.write('N' + '\t' + 'L_scale=N^1/D'+ '\t'+ 'average lp length'+ '\t'+'std err'+ '\t'+ 'average no. lp'+ '\t'+'std err' +'\n')
start_time = time.time()
trials = 100
for N in range(2,40,1):
lp_length_list = []
j_list = []
for _ in range(trials):
model = models.COd(2, N)
# model = models.barabasi_albert_graph(n, m, seed)
DAG = model[0]
extremes = model[1]
tr_DAG = tr.trans_red(DAG)
lp = dl.lpd(tr_DAG, extremes[1], extremes[0])
length_lp = lp[2]
lp_length_list.append(length_lp)
j=0
paths_list = list(nx.all_simple_paths(tr_DAG, extremes[1], extremes[0], cutoff=length_lp+1))
for i in range(len(paths_list)):
if len(paths_list[i])==length_lp+1:
j+=1
j_list.append(j)
lp_stats = stats.list_stats(lp_length_list)
lp_av = lp_stats[3]
lp_err = lp_stats[1]
j_stats = stats.list_stats(j_list)
j_av = j_stats[3]
j_err = j_stats[1]
l_scale = (N**(1.0/float(D)))
myfile.write(str(N) + '\t' + str(l_scale) +'\t' + str(lp_av)+'\t' + str(lp_err)+ '\t' + str(j_av) +'\t' + str(j_err)+ '\n')
print 'done', N
elapsed = time.time() - start_time
print 'finished.',D,'Dimension. Time elapsed = ',elapsed
return
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]
m = 1
number_of_trials = 100
D = 1
myfile = open("BA_lp", "w")
myfile.write("N" + "\t" + "average lp length" + "\t" + "std err" + "\n")
for N in range(2, 100, 5):
lp_list = []
for trial in range(number_of_trials):
model = models.barabasi_albert_graph(N, m)
# model = models.COd(D,N)
G = model[0]
extremes = model[1]
# tr_DAG = tr.trans_red(G)
lp = dl.lpd(G, extremes[1], extremes[0])
lp_length = lp[2]
lp_list.append(lp_length)
statistics = stats.list_stats(lp_list)
lp_av = statistics[3]
lp_std_err = statistics[0]
print "done ", N
myfile.write(str(N) + "\t" + str(lp_av) + "\t" + str(lp_std_err) + "\n")
# nx.draw_random(G, with_labels=False, node_colour ='k', node_size=50, node_color = 'k', width=0.5)
# nx.draw_networkx(G, pos=random, with_labels=False, node_colour ='k', node_size=50, node_color = 'k', width=0.5)
# plt.show() # display figure
# D=3
# filename = './' + str(D) + 'lp_with_N.txt'
import trans_red as tr
import matplotlib.pyplot as plt
import networkx as nx
import numpy as np
import time
start_time = time.time()
model = models.COd(2, 200)
DAG = model[0]
extremes = model[1]
print 'made model'
tr_DAG = tr.trans_red(DAG)
print 'done transitive reduction'
lp = dl.lpd(tr_DAG, extremes[1], extremes[0])
length_lp = lp[2]
path = lp[1]
print 'calculated lp'
t_list = []
x_list = []
path_t_list = []
path_x_list = []
#
for node in range(len(DAG.nodes())):
t_list.append(DAG.nodes()[node][0])
x_list.append(DAG.nodes()[node][1])
#
#for node in range(len(path)):
# path_t_list.append(path[node][0])
def lp_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 = 10.0/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' + 'l(p)' +'\t' + 'std error' + '\n') #send column headings to output file
#initialize lists for each output variable
p_list = []
lp_average_list = []
lp_std_error_list = []
x_range = np.arange(1.0,10.0+p_step,p_step) #defines list of x values to loop over
for x in x_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)
lp_list = []
p = math.log10(x)
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
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.
lp_list.append(length_of_longest_path)
statistics = stats(lp_list)
lp_average = statistics[3] #calculates average lp over all trials for the current probability
if p == 0.0:
lp_0 = lp_average #calculate average longest path for p==0 and use as normalization constant
lp_average = lp_average / lp_0 #normalize average longest paths so can compare results of different dimensions
for i in range(len(lp_list)):
lp_list[i] /= lp_0 #normalize longest paths (need to do this for std error calculation)
statistics = stats(lp_list)
lp_std_error = statistics[0]
p_list.append(p)
lp_average_list.append(lp_average)
lp_std_error_list.append(lp_std_error)
myfile.write(str(p)+ '\t' + str(lp_average) + '\t' + str(lp_std_error) + '\n')
print "finished ", p , "probability"
elapsed = (time.time() - start_time) #calculate time for method completion
print "finished. Time elapsed = " , elapsed
return [p_list, lp_average_list, lp_std_error_list]
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]
no_in = []
for line in no_in_file:
no_in.append(line.strip())
print 'Length no_in is %d' %len(no_in)
#print lc.cone_axis(DAG,'9910429','forward',no_in)
start = '0302265'
end = '9205221'
'''lc.pythag_distance(DAG,start,end)
start = '9706432'
end = '9205221'''
lp = dl.lpd(DAG,start,end)
path = lp[1]
start_2 = choice(DAG.nodes())
#print start_2
'''cone = lc.lightcone(DAG,start_2,'backward')
print cone.number_of_nodes()
print cone.number_of_edges()
print 'Doing TC'
tr.tc_recur(cone,start_2)
print 'Done TC!'
for node in cone:
end = node2
else:
start = node2
end = node1
if nx.has_path(DAG,start,end):
if (DAG.node[start]['rank']-DAG.node[end]['rank']) < 3000:
try:
intvl = lc.interval(DAG,start,end)
sample -= 1 #reduce sample number by 1 as we have found an eligable candidate pair
N = len(intvl)
E = intvl.number_of_edges()
dbday = abs(bday1 - bday2)
rankS = DAG.node[start]['rank']
rankE = DAG.node[end]['rank']
lp_result = dl.lpd(DAG,start,end)
lp = lp_result[2]
path = lp_result[1]
print 'Finding MM'
MM_result = MM.MM_dimension(intvl,node_list)
intvl.clear() #for memory purposes
MMd = MM_result[0]
E_TC = MM_result[1]
print 'Find MPSD'
#MPS_result = mp.mpsd(DAG,path)
#MPSd = MPS_result[0]
#out.write(str(start) + '\t' + str(end) + '\t' + str(N) + '\t' + str(E) + '\t' + str(lp) + '\t' + str(E_TC) + '\t' + str(MMd) + '\t' + str(MPSd) + '\n')
out.write(str(start) + '\t' + str(end) + '\t' + str(dbday) + '\t' + str(rankS) + '\t' + str(rankE) + '\t' + str(N) + '\t' + str(E) + '\t' + str(lp) + '\t' + str(E_TC) + '\t' + str(MMd) + '\n')
print sample
except:
print 'Memory error with %s to %s' %(start,end)