def run():
citation_graph = alg_load_graph.load_graph(graph_url)
in_deg_graph = in_degree_distribution(citation_graph)
print in_deg_graph
in_deg_norm = normalize_in_deg_dist(in_deg_graph, len(citation_graph))
print in_deg_norm
draw_loglog_plot(in_deg_norm)
def run():
citation_graph = alg_load_graph.load_graph(graph_url)
in_deg_graph = in_degree_distribution(citation_graph)
print in_deg_graph
in_deg_norm = normalize_in_deg_dist(in_deg_graph, len(citation_graph))
print in_deg_norm
draw_loglog_plot(in_deg_norm)
def question_35():
citation_graph = alg_load_graph.load_graph(CITATION_URL)
out_degrees = 0
for node in citation_graph:
out_degrees += len(citation_graph[node])
x_vals, y_vals = [], []
norm = norm_dist(citation_graph)
for degree in norm:
x_vals.append(degree)
y_vals.append(norm[degree])
target_node = 27770
step_node = 13
dpa_graph = dpa_digraph_gen(target_node, step_node)
x_dpavals, y_dpavals = [], []
norm_dpa = norm_dist(dpa_graph)
for degree in norm_dpa:
x_dpavals.append(degree)
y_dpavals.append(norm_dpa[degree])
plt.loglog(x_vals,
y_vals,
color="cyan",
linestyle='None',
marker=".",
markersize=6)
plt.loglog(x_dpavals,
y_dpavals,
color="black",
linestyle='None',
marker=".",
markersize=6)
plt.xlabel("Log Number of Degrees")
plt.ylabel("Log Distribution")
plt.title("Normalized Distribution of High Energy Physics Theory Papers")
plt.show()
#question_35()
def Question_1():
'''
Your task for this question is to compute the in-degree distribution for this
citation graph. Once you have computed this distribution, you should normalize
the distribution (make the values in the dictionary sum to one) and then
compute a log/log plot of the points in this normalized distribution.
'''
# load data, calculate normalised in-degree distribution
import alg_load_graph
citation_graph = alg_load_graph.load_graph(alg_load_graph.CITATION_URL)
distribution = project1.in_degree_distribution(citation_graph)
factor = 1.0 / sum(distribution.itervalues())
normalised_distribution = {key : value * factor for key, value
in distribution.iteritems()}
# plot
loglog_plot_dictionary(normalised_distribution, 'Number of Citations',
'Normalized Citation Frequency',
'Log/Log Plot of In-Degree Distribution of Citation Graph\n')
return
def q1():
citation_graph = loader.load_graph(loader.CITATION_URL)
#citation_graph = helper.EX_GRAPH1
print 'start calculating degree distribution'
degree_distribution = helper.in_degree_distribution(citation_graph)
print 'finish calculating degree distribution'
print 'start normalizing'
degree_distribution = normalize(degree_distribution)
print 'finish normalizing'
print degree_distribution
print 'start plotting'
plt.yscale('log')
plt.xscale('log')
plt.xlabel('degree')
plt.ylabel('distribution')
plt.plot(degree_distribution.keys(), degree_distribution.values(),'ro')
plt.show()
def question_1():
citation_graph = alg_load_graph.load_graph(CITATION_URL)
out_degrees = 0
for node in citation_graph:
out_degrees += len(citation_graph[node])
x_vals, y_vals = [], []
norm = norm_dist(citation_graph)
for degree in norm:
x_vals.append(degree)
y_vals.append(norm[degree])
plt.loglog(x_vals,
y_vals,
color="blue",
linestyle='None',
marker=".",
markersize=6)
plt.xlabel("Log Number of Degrees")
plt.ylabel("Log Distribution")
plt.title("Normalized Distribution of High Energy Physics Theory Papers")
plt.show()
def q3(): citation_graph = loader.load_graph(loader.CITATION_URL) n = len(citation_graph) m = average_out_degree(citation_graph) print n, m
#create a set of all unique degree values
degree_distribution_dict = dict(Counter(in_degree_dict.values()))
num_nodes = len(in_degree_dict)
for key in degree_distribution_dict.keys():
degree_distribution_dict[key] = float(degree_distribution_dict[key])/float(num_nodes)
return degree_distribution_dict
#create a dictionary from the degree set initialized with 0 values
#for node in in_degree_dict.keys():
#deg_distribution_dict[in_degree_dict[node]] += 1
#calculating the number of nodes having same degree
#return deg_distribution_dict
return {}
#loading citation graph from url
citation_graph = alg_load_graph.load_graph(alg_load_graph.CITATION_URL)
def build_plot():
"""
Build log log plot of normalized indegree distribution
"""
#calculate in degree distribution (normalized) for citation graph
distribution_dict = in_degree_distribution(citation_graph)
#create the log/log plot of normalized indegree distribution
plot = []
for input_val in distribution_dict.keys():
if input_val != 0:
plot.append([math.log(input_val), math.log(distribution_dict[input_val])])
return plot
def run_example():
"""
Computing the popular nodes for an example graph
"""
my_graph = alg_load_graph.load_graph(GRAPH100_URL)
print "There are", len(find_popular_nodes(my_graph)), "popular nodes"
def question3(subplot=None, filename=None):
graph = alg_load_graph.load_graph('alg_phys-cite.txt')
print('avg_out_degree', avg_out_degree(graph))
dpa = algorithm_dpa(27700, 13)
normed = norm(project1.in_degree_distribution(dpa))
plot(normed, 'DPA-generated', subplot, filename)
def question1(subplot=None, filename=None):
graph = alg_load_graph.load_graph('alg_phys-cite.txt')
normed = norm(project1.in_degree_distribution(graph))
plot(normed, 'citation', subplot, filename)
def question_2():
citation_graph = alg_load_graph.load_graph(CITATION_URL)
out_degrees = 0
for node in citation_graph:
out_degrees += len(citation_graph[node])
x_vals, y_vals = [], []
norm = norm_dist(citation_graph)
for degree in norm:
x_vals.append(degree)
y_vals.append(norm[degree])
x_d0, y_d0 = [], []
d0 = digraph_rand(5000, 0.2)
norm_0 = norm_dist(d0)
for degree in norm_0:
x_d0.append(degree)
y_d0.append(norm_0[degree])
x_d1, y_d1 = [], []
d1 = digraph_rand(5000, 0.6)
norm_1 = norm_dist(d1)
for degree in norm_1:
x_d1.append(degree)
y_d1.append(norm_1[degree])
x_d2, y_d2 = [], []
d2 = digraph_rand(5000, 0.9)
norm_2 = norm_dist(d2)
for degree in norm_2:
x_d2.append(degree)
y_d2.append(norm_2[degree])
plt.loglog(x_vals,
y_vals,
color="cyan",
linestyle='None',
marker=".",
markersize=6)
plt.loglog(x_d0,
y_d0,
color="blue",
linestyle='None',
marker=".",
markersize=6)
plt.loglog(x_d1,
y_d1,
color="black",
linestyle='None',
marker=".",
markersize=6)
plt.loglog(x_d2,
y_d2,
color="red",
linestyle='None',
marker=".",
markersize=6)
plt.xlabel("Log Number of Degrees")
plt.ylabel("Log Distribution")
plt.title("Normalized Distribution for Random Generated Digraphs")
plt.show()
def question3(subplot=None, filename=None):
graph = alg_load_graph.load_graph('./data/alg_phys-cite.txt')
print('avg_out_degree', avg_out_degree(graph))
dpa = algorithm_dpa(27700, 13)
normed = norm(project1.in_degree_distribution(dpa))
plot(normed, 'DPA-generated', subplot, filename)
def question1(subplot=None, filename=None):
graph = alg_load_graph.load_graph('./data/alg_phys-cite.txt')
normed = norm(project1.in_degree_distribution(graph))
plot(normed, 'citation', subplot, filename)
import degree_distributions_for_graphs as degree_dis
import alg_load_graph
import matplotlib.pyplot as plt
def plot_distri(digraph):
"""
plot log/log distribution of digraph
"""
distri = degree_dis.in_degree_distribution(digraph)
sum_degree = float(sum(distri.values()))
distriy = [x/sum_degree for x in distri.values()]
distrix = distri.keys()
plt.loglog(distrix, distriy, "bo")
plt.xlabel("Cite Counts(log)")
plt.ylabel("Indegree Frequency(log)")
plt.title("Indegree Distribution for DPA Graph")
plt.show()
if __name__ == "__main__":
citation_graph = alg_load_graph.load_graph("http://temporary-files.qiniudn.com/alg_phys-cite-1.txt")
plot_distri(citation_graph)
if degree_dist.has_key(degree_value):
degree_dist[degree_value] += 1
else:
degree_dist[degree_value] = 1
return degree_dist
##############################################################
# For Application
import alg_load_graph
import alg_dpa_trial
CITATION_URL = "http://storage.googleapis.com/codeskulptor-alg/alg_phys-cite.txt"
citation_graph = alg_load_graph.load_graph(CITATION_URL)
cite_dist = in_degree_distribution(citation_graph)
"""
Question 3
"""
all_vertex = citation_graph.keys()
out_degree = 0
for dummy_vertex in citation_graph.keys():
out_degree += len(citation_graph[dummy_vertex])
ave_out = out_degree/27770.0
print ave_out
def run_example():
"""
Computing the popular nodes for an example graph
"""
my_graph = alg_load_graph.load_graph(GRAPH100_URL)
print "There are", len(find_popular_nodes(my_graph)), "popular nodes"
