def plot_entropy_ccdf():
entropy = read_pickle('output/normalized_entropy.obj')
fig = plt.figure()
ax = fig.add_subplot(111)
powerlaw.plot_ccdf(entropy, ax, label='normalized entropy')
# further plotting
ax.set_xlabel("Normalized entropy e")
ax.set_ylabel("Pr(X>=e)")
plt.legend(fancybox=True, loc='lower left', ncol=1, prop={'size': 5})
plt.tight_layout()
plt.savefig('output/normalized_entropy_distribution_ccdf.pdf')
fig = plt.figure()
ax = fig.add_subplot(111)
powerlaw.plot_cdf(entropy, ax, label='normalized entropy', color='r')
# further plotting
ax.set_xlabel("Normalized entropy e")
ax.set_ylabel("Pr(X<=e)")
plt.legend(fancybox=True, loc='lower left', ncol=1, prop={'size': 5})
plt.tight_layout()
plt.savefig('output/normalized_entropy_distribution_cdf.pdf')
def plot_entropy_ccdf():
entropy = read_pickle('output/normalized_entropy.obj')
fig = plt.figure()
ax = fig.add_subplot(111)
powerlaw.plot_ccdf(entropy, ax, label='normalized entropy')
# further plotting
ax.set_xlabel("Normalized entropy e")
ax.set_ylabel("Pr(X>=e)")
plt.legend(fancybox=True, loc='lower left', ncol=1,prop={'size':5})
plt.tight_layout()
plt.savefig('output/normalized_entropy_distribution_ccdf.pdf')
fig = plt.figure()
ax = fig.add_subplot(111)
powerlaw.plot_cdf(entropy, ax, label='normalized entropy',color='r')
# further plotting
ax.set_xlabel("Normalized entropy e")
ax.set_ylabel("Pr(X<=e)")
plt.legend(fancybox=True, loc='lower left', ncol=1,prop={'size':5})
plt.tight_layout()
plt.savefig('output/normalized_entropy_distribution_cdf.pdf')
def plot_counts_category_distributions_ccdf():
category_distributions = read_pickle(
HOME + 'output/category_counts_distribution.obj')
for i in category_distributions.values():
print len(i)
colors = {
'lead': 'r',
'infobox': 'b',
'body': 'g',
'left-body': 'm',
'navbox': 'c',
'counts': 'k'
}
fig = plt.figure()
ax = fig.add_subplot(111)
for category in [
'lead', 'infobox', 'body', 'left-body', 'navbox', 'counts'
]:
data = category_distributions[category]
data = [x[0] for x in data]
powerlaw.plot_ccdf(data, ax, label=category, color=colors[category])
# further plotting
ax.set_xlabel("Number of clicks n")
ax.set_ylabel("Pr(X>=n)")
plt.legend(fancybox=True, loc=3, ncol=2, prop={'size': 4})
#leg = plt.gca().get_legend()
#ltext = leg.get_texts() # all the text.Text instance in the legend
#llines = leg.get_lines()
#plt.setp(ltext, fontsize='small') # the legend text fontsize
#plt.setp(llines, linewidth=1)
plt.tight_layout()
plt.savefig('output/category_counts_distributions.pdf')
data = category_distributions['counts']
data = [int(x[0]) for x in data]
hist, bin_edges = np.histogram(data, 100, density=True)
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(bin_edges[:-1], hist, marker='o')
ax.set_xlabel('#Counts')
ax.set_ylabel('#Pages')
ax.set_yscale('log')
ax.set_xscale('log')
plt.legend(fancybox=True, loc=3, prop={'size': 4})
plt.tight_layout()
plt.savefig('output/counts_distribution.pdf')
def plot_counts_category_distributions_ccdf():
category_distributions = read_pickle(HOME+'output/category_counts_distribution.obj')
for i in category_distributions.values():
print len(i)
colors= {'lead':'r','infobox':'b', 'body':'g', 'left-body':'m','navbox':'c', 'counts':'k'}
fig = plt.figure()
ax = fig.add_subplot(111)
for category in ['lead', 'infobox', 'body', 'left-body', 'navbox', 'counts']:
data = category_distributions[category]
data = [x[0] for x in data]
powerlaw.plot_ccdf(data, ax, label=category,color=colors[category])
# further plotting
ax.set_xlabel("Number of clicks n")
ax.set_ylabel("Pr(X>=n)")
plt.legend(fancybox=True, loc=3, ncol=2, prop={'size':4})
#leg = plt.gca().get_legend()
#ltext = leg.get_texts() # all the text.Text instance in the legend
#llines = leg.get_lines()
#plt.setp(ltext, fontsize='small') # the legend text fontsize
#plt.setp(llines, linewidth=1)
plt.tight_layout()
plt.savefig('output/category_counts_distributions.pdf')
data = category_distributions['counts']
data = [int(x[0]) for x in data]
hist, bin_edges = np.histogram(data, 100, density=True)
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot( bin_edges[:-1],hist, marker='o')
ax.set_xlabel('#Counts')
ax.set_ylabel('#Pages')
ax.set_yscale('log')
ax.set_xscale('log')
plt.legend(fancybox=True, loc=3, prop={'size':4})
plt.tight_layout()
plt.savefig('output/counts_distribution.pdf')
def plot_ccdf(place, points, thresholds=None):
"""
plot ccdf
:param place: tuple
(name [string], (north_lat [float], south_lat [float], east_lon [float], west_lon [float]))
:param points: list of tuples (length [float], asymmetry_factor [float])
:param thresholds: list of floats of minimum length threshold to filter points and plot ccdf
:return:
"""
print(' Plotting ccdf ...')
name, bbox = place
cpoints = points
# cpoints = points.copy() # careful with overwriting list vs. memory overflow
if thresholds is None:
thresholds = [0, 250, 500, 1000, 1500, 3000, 4500]
cmap = plt.get_cmap('Set1')
colors = [cmap(i) for i in np.linspace(0, 1, len(thresholds))]
plt.figure()
for idx, threshold in enumerate(thresholds):
above_threshold = []
asymmetry_factors = []
while cpoints:
point = cpoints.pop()
length, asymmetry_factor = point
if length >= threshold:
above_threshold.append(point)
asymmetry_factors.append(asymmetry_factor)
powerlaw.plot_ccdf(asymmetry_factors,
color=colors[idx],
linewidth=1.5,
label='$Length \geq {0} \ m$'.format(threshold))
cpoints = above_threshold
plt.xlabel('Asymmetry Factor', fontsize=16)
plt.ylabel('$P(X \geq x)$', fontsize=16)
plt.legend()
plt.grid()
plt.savefig('./figs_dir/ccdf {0}.png'.format(name), format='png', dpi=200)
print(' Done!')
def plotView(self): self.clearView() f = Figure(figsize=(5,4), dpi=100) a = f.add_subplot(111) test = powerlaw.plot_ccdf(self.orderedFreq.values(), ax = a, color = 'b') a.plot() canvas = FigureCanvasTkAgg(f, master=self) canvas.show() canvas.get_tk_widget().pack(side=TOP, fill=BOTH, expand=1) toolbar = NavigationToolbar2TkAgg( canvas, self ) toolbar.update() canvas._tkcanvas.pack(side=TOP, fill=BOTH, expand=1)
def main():
timer = Timer()
timer.start()
app_name = 'cyberbullying'
sample_cascade_size = {}
sample_inter_arrival_time = []
sample_cascade_influence = {}
sample_cascade_influence_10m = defaultdict(int)
sample_cascade_influence_1h = defaultdict(int)
with open('../data/{0}_out/sample_retweet_{0}.txt'.format(app_name),
'r') as fin:
for line in fin:
root_tweet, cascades = line.rstrip().split(':')
cascades = cascades.split(',')
root_tweet = root_tweet.split('-')[0]
retweets = [x.split('-')[0] for x in cascades]
influences = [int(x.split('-')[1]) for x in cascades]
sample_cascade_size[root_tweet] = len(retweets)
sample_cascade_influence[root_tweet] = sum(influences)
root_timestamp = melt_snowflake(root_tweet)[0] / 1000
retweet_timestamp_list = [root_timestamp]
for i in range(len(retweets)):
retweet_time = melt_snowflake(retweets[i])[0] / 1000
relative_retweet_time = retweet_time - root_timestamp
retweet_timestamp_list.append(
melt_snowflake(retweets[i])[0] / 1000)
if relative_retweet_time < 10 * 60:
sample_cascade_influence_10m[root_tweet] += influences[i]
if relative_retweet_time < 60 * 60:
sample_cascade_influence_1h[root_tweet] += influences[i]
for i in range(len(retweet_timestamp_list) - 1):
sample_inter_arrival_time.append(retweet_timestamp_list[i +
1] -
retweet_timestamp_list[i])
complete_cascade_size = {}
complete_inter_arrival_time = []
complete_cascade_influence = {}
complete_cascade_influence_10m = defaultdict(int)
complete_cascade_influence_1h = defaultdict(int)
with open('../data/{0}_out/complete_retweet_{0}.txt'.format(app_name),
'r') as fin:
for line in fin:
root_tweet, cascades = line.rstrip().split(':')
cascades = cascades.split(',')
root_tweet = root_tweet.split('-')[0]
retweets = [x.split('-')[0] for x in cascades]
complete_cascade_size[root_tweet] = len(retweets)
if len(retweets) >= 50:
influences = [int(x.split('-')[1]) for x in cascades]
complete_cascade_influence[root_tweet] = sum(influences)
root_timestamp = melt_snowflake(root_tweet)[0] / 1000
retweet_timestamp_list = [root_timestamp]
for i in range(len(retweets)):
retweet_time = melt_snowflake(retweets[i])[0] / 1000
relative_retweet_time = retweet_time - root_timestamp
retweet_timestamp_list.append(
melt_snowflake(retweets[i])[0] / 1000)
if relative_retweet_time < 10 * 60:
complete_cascade_influence_10m[
root_tweet] += influences[i]
if relative_retweet_time < 60 * 60:
complete_cascade_influence_1h[
root_tweet] += influences[i]
for i in range(len(retweet_timestamp_list) - 1):
complete_inter_arrival_time.append(
retweet_timestamp_list[i + 1] -
retweet_timestamp_list[i])
print('number of cascades in the complete set', len(complete_cascade_size))
print('number of cascades in the sample set', len(sample_cascade_size))
print('mean complete size', np.mean(list(complete_cascade_size.values())))
print('mean sample size', np.mean(list(sample_cascade_size.values())))
print('complete #cascades (≥50 retweets)',
sum([1 for x in list(complete_cascade_size.values()) if x >= 50]))
print('sample #cascades (≥50 retweets)',
sum([1 for x in list(sample_cascade_size.values()) if x >= 50]))
num_complete_cascades_in_sample = 0
complete_cascades_in_sample_size_list = []
num_complete_cascades_in_sample_50 = 0
for root_tweet in sample_cascade_size:
if sample_cascade_size[root_tweet] == complete_cascade_size[
root_tweet]:
num_complete_cascades_in_sample += 1
complete_cascades_in_sample_size_list.append(
complete_cascade_size[root_tweet])
if complete_cascade_size[root_tweet] >= 50:
num_complete_cascades_in_sample_50 += 1
print('number of complete cascades in the sample set',
num_complete_cascades_in_sample)
print('number of complete cascades (>50 retweets) in the sample set',
num_complete_cascades_in_sample_50)
print('max: {0}, mean: {1}'.format(
max(complete_cascades_in_sample_size_list),
np.mean(complete_cascades_in_sample_size_list)))
fig, axes = plt.subplots(1, 2, figsize=(10, 3.3))
cc4 = ColorPalette.CC4
blue = cc4[0]
red = cc4[3]
sample_median = np.median(sample_inter_arrival_time)
complete_median = np.median(complete_inter_arrival_time)
plot_ccdf(sample_inter_arrival_time,
ax=axes[0],
color=blue,
ls='-',
label='sample')
plot_ccdf(complete_inter_arrival_time,
ax=axes[0],
color='k',
ls='-',
label='complete')
axes[0].plot([sample_median, sample_median], [0, 1],
color=blue,
ls='--',
lw=1)
axes[0].plot([complete_median, complete_median], [0, 1],
color='k',
ls='--',
lw=1)
print('\ninter_arrival_time sample median', sample_median)
print('inter_arrival_time complete median', complete_median)
axes[0].set_xscale('symlog')
axes[0].set_xticks([0, 1, 100, 10000, 1000000])
axes[0].set_yscale('linear')
axes[0].set_xlabel('inter-arrival time (sec)', fontsize=16)
axes[0].set_ylabel('$P(X \geq x)$', fontsize=16)
axes[0].legend(frameon=False,
fontsize=16,
ncol=1,
fancybox=False,
shadow=True,
loc='upper right')
axes[0].tick_params(axis='both', which='major', labelsize=16)
axes[0].set_title('(a)', fontsize=18, pad=-3 * 72, y=1.0001)
influence_list = []
influence_list_10m = []
influence_list_1h = []
for root_tweet in sample_cascade_size:
if complete_cascade_size[root_tweet] >= 50:
if complete_cascade_influence[root_tweet] > 0:
influence_list.append(sample_cascade_influence[root_tweet] /
complete_cascade_influence[root_tweet])
if complete_cascade_influence_10m[root_tweet] > 0:
influence_list_10m.append(
sample_cascade_influence_10m[root_tweet] /
complete_cascade_influence_10m[root_tweet])
if complete_cascade_influence_1h[root_tweet] > 0:
influence_list_1h.append(
sample_cascade_influence_1h[root_tweet] /
complete_cascade_influence_1h[root_tweet])
plot_ccdf(influence_list_10m, ax=axes[1], color=red, ls='-', label='10m')
plot_ccdf(influence_list_1h, ax=axes[1], color=blue, ls='-', label='1h')
plot_ccdf(influence_list, ax=axes[1], color='k', ls='-', label='14d')
print('influence_list median', np.median(influence_list))
print('influence_list_1h median', np.median(influence_list_1h))
print('influence_list_10m median', np.median(influence_list_10m))
print('influence_list 0.25', percentileofscore(influence_list, 0.25))
print('influence_list 0.25', percentileofscore(influence_list_1h, 0.25))
print('influence_list 0.25', percentileofscore(influence_list_10m, 0.25))
print('influence_list 0.75', percentileofscore(influence_list, 0.75))
print('influence_list 0.75', percentileofscore(influence_list_1h, 0.75))
print('influence_list 0.75', percentileofscore(influence_list_10m, 0.75))
axes[1].set_xscale('linear')
axes[1].set_yscale('linear')
axes[1].set_xlabel('relative potential reach', fontsize=16)
# axes[1].set_ylabel('$P(X \geq x)$', fontsize=16)
axes[1].legend(frameon=False,
fontsize=16,
ncol=1,
fancybox=False,
shadow=True,
loc='upper right')
axes[1].tick_params(axis='both', which='major', labelsize=16)
axes[1].set_title('(b)', fontsize=18, pad=-3 * 72, y=1.0001)
hide_spines(axes)
timer.stop()
plt.tight_layout(rect=[0, 0.05, 1, 1])
plt.savefig('../images/cascades_measures.pdf', bbox_inches='tight')
if not platform.system() == 'Linux':
plt.show()
for x in range(0, max(degree) + 1):
dist.append(degree.count(x) / float(g.vcount()))
#log
plt.xscale('log')
plt.yscale('log')
plt.xlabel('K')
plt.ylabel('Pk')
plt.plot(dist, linestyle=(0, (1, 3)))
results = pl.Fit(degree)
print("Alpha is {}".format(results.power_law.alpha))
print("Xmin is {}".format(results.power_law.xmin))
pl.plot_ccdf(degree, color='r')
plt.show()
print("The network diameter is {}".format(g.diameter()))
print('top betweenness')
#centrality top10
between = g.betweenness()
between.sort()
print(between[-10:])
print(g.vs.find(_degree=2)["id"])
degree.sort()
maxd = degree[-10:]
weight = float(route[2][:-1])
G.add_edge(airport1, airport2, weight=weight)
N = len(G)
L = len(G.edges())
degrees = nx.degree(G).values()
kmax = max(degrees)
kmin = min(degrees)
kavg = 1.0 * sum(degrees) / len(degrees)
print "Number of nodes:", N
print "Number of links:", L
print "Max degree:", kmax
print "Min degree:", kmin
print "Average degree:", kavg
powerlaw.plot_ccdf(degrees, marker="o", color="b", linestyle="none")
plt.ylabel(r"Cummulative $P(k)$", fontsize=16)
plt.xlabel(r"$k$", fontsize=16)
plt.savefig("Degree distribution" + "_Airline" + ".png")
# plt.show()
"""random walk"""
def rndWalk(G, T):
node_list = G.nodes()
"""initialization"""
walker_path = []
walker_path.append(random.choice(node_list))
"""let's walk!"""
for t in range(1, T + 1):
def plot_stats():
# wikipedia graph structural statistics
print 'before load'
network = load_graph("output/wikipedianetwork.xml.gz")
print 'after load'
out_hist = vertex_hist(network, "out")
plt.gca().set_yscale('log')
plt.gca().set_xscale('log')
plt.plot(out_hist[1][:-1], out_hist[0], marker='o')
plt.xlabel('Out-degree')
plt.ylabel('Frequency')
plt.gca().set_ylim([1, 10**6])
#plt.title('Out-degree Distribution')
plt.tight_layout()
plt.savefig('output/wikipedia-out-deg-dist.pdf')
plt.clf()
in_hist = vertex_hist(network, "in")
plt.gca().set_yscale('log')
plt.gca().set_xscale('log')
plt.plot(in_hist[1][:-1], in_hist[0], marker='o')
plt.xlabel('In-degree')
plt.ylabel('Frequency')
plt.gca().set_ylim([1, 10**6])
#plt.title('In-degree Distribution')
plt.tight_layout()
plt.savefig('output/wikipedia-in-deg-dist.pdf')
plt.clf()
total_hist = vertex_hist(network, "total")
plt.gca().set_yscale('log')
plt.gca().set_xscale('log')
plt.plot(total_hist[1][:-1], total_hist[0], marker='o')
plt.xlabel('Degree')
plt.ylabel('Frequency')
plt.gca().set_ylim([1, 10**6])
#plt.title('Degree Distribution')
plt.tight_layout()
plt.savefig('output/wikipedia-deg-dist.pdf')
plt.clf()
clust = network.vertex_properties["local_clust"]
#clust = local_clustering(network, undirected=False)
#hist, bin_edges = np.histogram(clust.get_array(), 100, density=True)
#cdf = np.cumsum(hist)
#plt.plot(bin_edges[1:], cdf, marker='o')
#plt.xlabel('Local Clustering Coefficient C')
#plt.ylabel('P(x<=C)')
#plt.title('Clustering Coefficient Distribution')
#plt.savefig('output/wikipedia-clust-cdf.pdf')
fig, ax = plt.subplots()
powerlaw.plot_cdf(clust.get_array(), ax)
#ax.set_title('Clustering Coefficient Distribution')
ax.set_xlabel('Local Clustering Coefficient $C')
ax.set_ylabel('P(x<=C)')
ax.set_ylim([0, 1])
fig.tight_layout()
fig.savefig('output/wikipedia-clust-cdf.pdf')
plt.clf()
fig, ax = plt.subplots()
powerlaw.plot_ccdf(clust.get_array(), ax)
#ax.set_title('Clustering Coefficient Distribution')
ax.set_xlabel('Local Clustering Coefficient C')
ax.set_ylabel('P(x>=C)')
ax.set_ylim([10**-4, 10**-0.5])
fig.tight_layout()
fig.savefig('output/wikipedia-clust-ccdf.pdf')
plt.clf()
prank = network.vertex_properties["page_rank"]
#hist, bin_edges = np.histogram(prank.get_array(), 100, density=True)
#cdf = np.cumsum(hist)
#plt.plot(bin_edges[1:], cdf, marker='o')
#plt.xlabel('Page rank Pr')
#plt.ylabel('P(x<=Pr)')
#plt.title('Page rank Distribution')
#plt.savefig('output/wikipedia-prank-cdf.pdf')
fig, ax = plt.subplots()
powerlaw.plot_cdf(prank.get_array(), ax)
#ax.set_title('Page Rank Distribution')
ax.set_xlabel('Page rank Pr')
ax.set_ylabel('P(x<=Pr)')
ax.set_ylim([0, 1])
fig.tight_layout()
fig.savefig('output/wikipedia-prank-cdf.pdf')
plt.clf()
fig, ax = plt.subplots()
powerlaw.plot_ccdf(prank.get_array(), ax)
#ax.set_title('Page Rank Distribution')
ax.set_xlabel('Page rank Pr')
ax.set_ylabel('P(x>=Pr)')
fig.tight_layout()
fig.savefig('output/wikipedia-prank-ccdf.pdf')
plt.clf()
kcore = network.vertex_properties["kcore"]
#hist, bin_edges = np.histogram(kcore.get_array(), 100, density=True)
#cdf = np.cumsum(hist)
#plt.plot(bin_edges[1:], cdf, marker='o')
#plt.xlabel('Kcore kC')
#plt.ylabel('P(x<=kC)')
#plt.title('K-Core Distribution')
#plt.savefig('output/wikipedia-kcore-cdf.pdf')
fig, ax = plt.subplots()
powerlaw.plot_cdf(kcore.get_array(), ax)
#ax.set_title('K-Core Distribution')
ax.set_xlabel('k-Core kC')
ax.set_ylabel('P(x<=kC)')
ax.set_ylim([0, 1])
fig.tight_layout()
fig.savefig('output/wikipedia-kcore-cdf.pdf')
plt.clf()
fig, ax = plt.subplots()
powerlaw.plot_ccdf(kcore.get_array(), ax)
#ax.set_title('K-Core Distribution')
ax.set_xlabel('k-Core kC')
ax.set_ylabel('P(x>=kC)')
fig.tight_layout()
fig.savefig('output/wikipedia-kcore-ccdf.pdf')
plt.clf()
eigenvector_centr = network.vertex_properties["eigenvector_centr"]
#hist, bin_edges = np.histogram(eigenvector_centr.get_array(), 100, density=True)
#cdf = np.cumsum(hist)
#plt.plot(bin_edges[1:], cdf, marker='o')
#plt.xlabel('Eigenvector Centrality E')
#plt.ylabel('P(x<=E)')
#plt.title('Eigenvector Centrality Distribution')
#plt.savefig('output/wikipedia-eigenvcentr-cdf.pdf')
fig, ax = plt.subplots()
powerlaw.plot_cdf(eigenvector_centr.get_array(), ax)
#ax.set_title('Eigenvector Centrality E')
ax.set_xlabel('Eigenvector Centrality E')
ax.set_ylabel('P(x<=E)')
ax.set_ylim([0, 1])
fig.tight_layout()
fig.savefig('output/wikipedia-eigenvcentr-cdf.pdf')
plt.clf()
fig, ax = plt.subplots()
powerlaw.plot_ccdf(eigenvector_centr.get_array(), ax)
#ax.set_title('Eigenvector Centrality E')
ax.set_xlabel('Eigenvector Centrality E')
ax.set_ylabel('P(x>=E)')
fig.tight_layout()
fig.savefig('output/wikipedia-eigenvcentr-ccdf.pdf')
plt.clf()
colors= {'local_clust':'r','eigenvector_centr':'b', 'page_rank': 'g', 'kcore':'m', 'hub': 'c', 'authority':'k'}
labels = {'local_clust': 'clust.', 'eigenvector_centr':'eigen. centr.','page_rank': 'page rank', 'kcore': 'kcore', 'hub':'hub', 'authority':'authority'}
fig = plt.figure()
ax = fig.add_subplot(111)
for f in ['local_clust','page_rank', 'hub', 'authority', 'kcore']:
feature = network.vertex_properties[f]
powerlaw.plot_cdf(feature.get_array(), ax, label=labels[f],color=colors[f])
ax.set_xlabel('Feature $f$')
ax.set_ylabel('$P(X>=f)$')
ax.set_ylim([0, 1])
plt.legend(fancybox=True, loc=3, ncol=2, prop={'size':4})
plt.tight_layout()
plt.savefig('output/wikipedia-features-cdf.pdf')
plt.clf()
colors= {'local_clust':'r','eigenvector_centr':'b', 'page_rank': 'g', 'kcore':'m', 'hub': 'c', 'authority':'k'}
labels = {'local_clust': 'clust.', 'eigenvector_centr':'eigen. centr.','page_rank': 'page rank', 'kcore': 'kcore', 'hub':'hub', 'authority':'authority'}
fig = plt.figure()
ax = fig.add_subplot(111)
for f in ['local_clust','eigenvector_centr','page_rank', 'hub', 'authority', 'kcore']:
feature = network.vertex_properties[f]
powerlaw.plot_cdf(feature.get_array(), ax, label=labels[f],color=colors[f])
ax.set_xlabel('Feature $f$')
ax.set_ylabel('$P(X<=f)$')
plt.legend(fancybox=True, loc=3, ncol=2, prop={'size':4})
plt.tight_layout()
plt.savefig('output/wikipedia-features-ccdf.pdf')
plt.clf()
# wikipedia transitions graph structural statistics
print 'before load'
network_transitions = load_graph("output/transitionsnetwork.xml.gz")
print 'after load'
out_hist = vertex_hist(network_transitions, "out")
plt.gca().set_yscale('log')
plt.gca().set_xscale('log')
plt.plot(out_hist[1][:-1], out_hist[0], marker='o')
plt.xlabel('Out-degree')
plt.ylabel('Frequency')
plt.gca().set_ylim([1, 10**6])
#plt.title('Out-degree Distribution')
plt.savefig('output/wikipedia-transitions-out-deg-dist.pdf')
plt.clf()
in_hist = vertex_hist(network_transitions, "in")
plt.gca().set_yscale('log')
plt.gca().set_xscale('log')
plt.plot(in_hist[1][:-1], in_hist[0], marker='o')
plt.xlabel('In-degree')
plt.ylabel('Frequency')
#plt.title('In-degree Distribution')
plt.gca().set_ylim([1, 10**6])
plt.savefig('output/wikipedia-transitions-in-deg-dist.pdf')
plt.clf()
total_hist = vertex_hist(network_transitions, "total")
plt.gca().set_yscale('log')
plt.gca().set_xscale('log')
plt.plot(total_hist[1][:-1], total_hist[0], marker='o')
plt.xlabel('Degree')
plt.ylabel('Frequency')
#plt.title('Degree Distribution')
plt.gca().set_ylim([1, 10**6])
plt.savefig('output/wikipedia-transitions-deg-dist.pdf')
plt.clf()
#clust = local_clustering(network_transitions, undirected=False)
clust = network_transitions.vertex_properties["local_clust"]
#hist, bin_edges = np.histogram(clust.get_array(), 100, density=True)
#cdf = np.cumsum(hist)
#plt.plot(bin_edges[1:], cdf, marker='o')
#plt.xlabel('Local Clustering Coefficient C')
#plt.ylabel('P(x<=C)')
#plt.title('Clustering Coefficient Distribution')
#plt.savefig('output/wikipedia-transitions-clust-cdf.pdf')
fig, ax = plt.subplots()
powerlaw.plot_cdf(clust.get_array(), ax)
#ax.set_title('Clustering Coefficient Distribution')
ax.set_xlabel('Local Clustering Coefficient C')
ax.set_ylabel('P(x<=C)')
fig.savefig('output/wikipedia-transitions-clust-cdf.pdf')
plt.clf()
fig, ax = plt.subplots()
powerlaw.plot_ccdf(clust.get_array(), ax)
ax.set_title('Clustering Coefficient Distribution')
ax.set_xlabel('Local Clustering Coefficient C')
ax.set_ylabel('P(x>=C)')
fig.savefig('output/wikipedia-transitions-clust-ccdf.pdf')
plt.clf()
prank = network_transitions.vertex_properties["page_rank"]
#hist, bin_edges = np.histogram(prank.get_array(), 100, density=True)
#cdf = np.cumsum(hist)
#plt.plot(bin_edges[1:], cdf, marker='o')
#plt.xlabel('Page rank Pr')
#plt.ylabel('P(x<=Pr)')
#plt.title('Page rank Distribution')
#plt.savefig('output/wikipedia-transitions-prank-cdf.pdf')
fig, ax = plt.subplots()
powerlaw.plot_cdf(prank.get_array(), ax)
#ax.set_title('Page Rank Distribution')
ax.set_xlabel('Page rank Pr')
ax.set_ylabel('P(x<=Pr)')
fig.savefig('output/wikipedia-transitions-prank-cdf.pdf')
plt.clf()
fig, ax = plt.subplots()
powerlaw.plot_ccdf(prank.get_array(), ax)
#ax.set_title('Page Rank Distribution')
ax.set_xlabel('Page rank Pr')
ax.set_ylabel('P(x>=Pr)')
fig.savefig('output/wikipedia-transitions-prank-ccdf.pdf')
plt.clf()
kcore = network_transitions.vertex_properties["kcore"]
#hist, bin_edges = np.histogram(kcore.get_array(), 100, density=True)
#cdf = np.cumsum(hist)
#plt.plot(bin_edges[1:], cdf, marker='o')
#plt.xlabel('Kcore kC')
#plt.ylabel('P(x<=kC)')
#plt.title('K-Core Distribution')
#plt.savefig('output/wikipedia-transitions-kcore-cdf.pdf')
fig, ax = plt.subplots()
powerlaw.plot_cdf(kcore.get_array(), ax)
#ax.set_title('K-Core Distribution')
ax.set_xlabel('k-Core kC')
ax.set_ylabel('P(x<=kC)')
fig.savefig('output/wikipedia-transitions-kcore-cdf.pdf')
plt.clf()
fig, ax = plt.subplots()
powerlaw.plot_ccdf(kcore.get_array(), ax)
#ax.set_title('K-Core Distribution')
ax.set_xlabel('k-Core kC')
ax.set_ylabel('P(x>=kC)')
fig.savefig('output/wikipedia-transitions-kcore-ccdf.pdf')
plt.clf()
eigenvector_centr = network_transitions.vertex_properties["eigenvector_centr"]
#hist, bin_edges = np.histogram(eigenvector_centr.get_array(), 100, density=True)
#cdf = np.cumsum(hist)
#plt.plot(bin_edges[1:], cdf, marker='o')
#plt.xlabel('Eingenvector centrality E')
#plt.ylabel('P(x<=E)')
#plt.title('Eigenvector Centrality Distribution')
#plt.savefig('output/wikipedia-transitions-eigenvcentr-cdf.pdf')
fig, ax = plt.subplots()
powerlaw.plot_cdf(eigenvector_centr.get_array(), ax)
#ax.set_title('Eigenvector Centrality Distribution')
ax.set_xlabel('Eingenvector centrality E')
ax.set_ylabel('P(x<=E)')
fig.savefig('output/wikipedia-transitions-eigenvcentr-cdf.pdf')
plt.clf()
fig, ax = plt.subplots()
powerlaw.plot_ccdf(eigenvector_centr.get_array(), ax)
#ax.set_title('Eigenvector Centrality Distribution')
ax.set_xlabel('Eingenvector centrality E')
ax.set_ylabel('P(x>=E)')
fig.savefig('output/wikipedia-transitions-eigenvcentr-ccdf.pdf')
plt.clf()
print 'before hits'
#ee, authority, hub = hits(network_transitions)
#network_transitions.vertex_properties["authority"] = authority
#network_transitions.vertex_properties["hub"] = hub
#network_transitions.save("output/transitionsnetwork.xml.gz")
print 'after hits'
colors= {'local_clust':'r','eigenvector_centr':'b', 'page_rank': 'g', 'kcore':'m', 'hub': 'c', 'authority':'k'}
labels = {'local_clust': 'clust.', 'eigenvector_centr':'eigen. centr.','page_rank': 'page rank', 'kcore': 'kcore', 'hub':'hub', 'authority':'authority'}
fig = plt.figure()
ax = fig.add_subplot(111)
for f in ['local_clust','page_rank', 'hub', 'authority', 'kcore']:
feature = network_transitions.vertex_properties[f]
powerlaw.plot_cdf(feature.get_array(), ax, label=labels[f],color=colors[f])
ax.set_xlabel('Feature $f$')
ax.set_ylabel('$P(X>=f)$')
ax.set_ylim([0, 1])
plt.legend(fancybox=True, loc=3, ncol=2, prop={'size':4})
plt.tight_layout()
plt.savefig('output/wikipedia-transitions-features-cdf.pdf')
plt.clf()
colors= {'local_clust':'r','eigenvector_centr':'b', 'page_rank': 'g', 'kcore':'m', 'hub': 'c', 'authority':'k'}
labels = {'local_clust': 'clust.', 'eigenvector_centr':'eigen. centr.','page_rank': 'page rank', 'kcore': 'kcore', 'hub':'hub', 'authority':'authority'}
fig = plt.figure()
ax = fig.add_subplot(111)
for f in ['local_clust','page_rank', 'hub', 'authority', 'kcore']:
feature = network_transitions.vertex_properties[f]
powerlaw.plot_cdf(feature.get_array(), ax, label=labels[f],color=colors[f])
ax.set_xlabel('Feature $f$')
ax.set_ylabel('$P(X<=f)$')
plt.legend(fancybox=True, loc=3, ncol=2, prop={'size':4})
plt.tight_layout()
plt.savefig('output/wikipedia-transitions-features-ccdf.pdf')
plt.clf()
def plot_stats():
# wikipedia graph structural statistics
print 'before load'
network = load_graph("output/wikipedianetwork.xml.gz")
print 'after load'
out_hist = vertex_hist(network, "out")
plt.gca().set_yscale('log')
plt.gca().set_xscale('log')
plt.plot(out_hist[1][:-1], out_hist[0], marker='o')
plt.xlabel('Out-degree')
plt.ylabel('Frequency')
plt.gca().set_ylim([1, 10**6])
#plt.title('Out-degree Distribution')
plt.tight_layout()
plt.savefig('output/wikipedia-out-deg-dist.pdf')
plt.clf()
in_hist = vertex_hist(network, "in")
plt.gca().set_yscale('log')
plt.gca().set_xscale('log')
plt.plot(in_hist[1][:-1], in_hist[0], marker='o')
plt.xlabel('In-degree')
plt.ylabel('Frequency')
plt.gca().set_ylim([1, 10**6])
#plt.title('In-degree Distribution')
plt.tight_layout()
plt.savefig('output/wikipedia-in-deg-dist.pdf')
plt.clf()
total_hist = vertex_hist(network, "total")
plt.gca().set_yscale('log')
plt.gca().set_xscale('log')
plt.plot(total_hist[1][:-1], total_hist[0], marker='o')
plt.xlabel('Degree')
plt.ylabel('Frequency')
plt.gca().set_ylim([1, 10**6])
#plt.title('Degree Distribution')
plt.tight_layout()
plt.savefig('output/wikipedia-deg-dist.pdf')
plt.clf()
clust = network.vertex_properties["local_clust"]
#clust = local_clustering(network, undirected=False)
#hist, bin_edges = np.histogram(clust.get_array(), 100, density=True)
#cdf = np.cumsum(hist)
#plt.plot(bin_edges[1:], cdf, marker='o')
#plt.xlabel('Local Clustering Coefficient C')
#plt.ylabel('P(x<=C)')
#plt.title('Clustering Coefficient Distribution')
#plt.savefig('output/wikipedia-clust-cdf.pdf')
fig, ax = plt.subplots()
powerlaw.plot_cdf(clust.get_array(), ax)
#ax.set_title('Clustering Coefficient Distribution')
ax.set_xlabel('Local Clustering Coefficient $C')
ax.set_ylabel('P(x<=C)')
ax.set_ylim([0, 1])
fig.tight_layout()
fig.savefig('output/wikipedia-clust-cdf.pdf')
plt.clf()
fig, ax = plt.subplots()
powerlaw.plot_ccdf(clust.get_array(), ax)
#ax.set_title('Clustering Coefficient Distribution')
ax.set_xlabel('Local Clustering Coefficient C')
ax.set_ylabel('P(x>=C)')
ax.set_ylim([10**-4, 10**-0.5])
fig.tight_layout()
fig.savefig('output/wikipedia-clust-ccdf.pdf')
plt.clf()
prank = network.vertex_properties["page_rank"]
#hist, bin_edges = np.histogram(prank.get_array(), 100, density=True)
#cdf = np.cumsum(hist)
#plt.plot(bin_edges[1:], cdf, marker='o')
#plt.xlabel('Page rank Pr')
#plt.ylabel('P(x<=Pr)')
#plt.title('Page rank Distribution')
#plt.savefig('output/wikipedia-prank-cdf.pdf')
fig, ax = plt.subplots()
powerlaw.plot_cdf(prank.get_array(), ax)
#ax.set_title('Page Rank Distribution')
ax.set_xlabel('Page rank Pr')
ax.set_ylabel('P(x<=Pr)')
ax.set_ylim([0, 1])
fig.tight_layout()
fig.savefig('output/wikipedia-prank-cdf.pdf')
plt.clf()
fig, ax = plt.subplots()
powerlaw.plot_ccdf(prank.get_array(), ax)
#ax.set_title('Page Rank Distribution')
ax.set_xlabel('Page rank Pr')
ax.set_ylabel('P(x>=Pr)')
fig.tight_layout()
fig.savefig('output/wikipedia-prank-ccdf.pdf')
plt.clf()
kcore = network.vertex_properties["kcore"]
#hist, bin_edges = np.histogram(kcore.get_array(), 100, density=True)
#cdf = np.cumsum(hist)
#plt.plot(bin_edges[1:], cdf, marker='o')
#plt.xlabel('Kcore kC')
#plt.ylabel('P(x<=kC)')
#plt.title('K-Core Distribution')
#plt.savefig('output/wikipedia-kcore-cdf.pdf')
fig, ax = plt.subplots()
powerlaw.plot_cdf(kcore.get_array(), ax)
#ax.set_title('K-Core Distribution')
ax.set_xlabel('k-Core kC')
ax.set_ylabel('P(x<=kC)')
ax.set_ylim([0, 1])
fig.tight_layout()
fig.savefig('output/wikipedia-kcore-cdf.pdf')
plt.clf()
fig, ax = plt.subplots()
powerlaw.plot_ccdf(kcore.get_array(), ax)
#ax.set_title('K-Core Distribution')
ax.set_xlabel('k-Core kC')
ax.set_ylabel('P(x>=kC)')
fig.tight_layout()
fig.savefig('output/wikipedia-kcore-ccdf.pdf')
plt.clf()
eigenvector_centr = network.vertex_properties["eigenvector_centr"]
#hist, bin_edges = np.histogram(eigenvector_centr.get_array(), 100, density=True)
#cdf = np.cumsum(hist)
#plt.plot(bin_edges[1:], cdf, marker='o')
#plt.xlabel('Eigenvector Centrality E')
#plt.ylabel('P(x<=E)')
#plt.title('Eigenvector Centrality Distribution')
#plt.savefig('output/wikipedia-eigenvcentr-cdf.pdf')
fig, ax = plt.subplots()
powerlaw.plot_cdf(eigenvector_centr.get_array(), ax)
#ax.set_title('Eigenvector Centrality E')
ax.set_xlabel('Eigenvector Centrality E')
ax.set_ylabel('P(x<=E)')
ax.set_ylim([0, 1])
fig.tight_layout()
fig.savefig('output/wikipedia-eigenvcentr-cdf.pdf')
plt.clf()
fig, ax = plt.subplots()
powerlaw.plot_ccdf(eigenvector_centr.get_array(), ax)
#ax.set_title('Eigenvector Centrality E')
ax.set_xlabel('Eigenvector Centrality E')
ax.set_ylabel('P(x>=E)')
fig.tight_layout()
fig.savefig('output/wikipedia-eigenvcentr-ccdf.pdf')
plt.clf()
colors = {
'local_clust': 'r',
'eigenvector_centr': 'b',
'page_rank': 'g',
'kcore': 'm',
'hub': 'c',
'authority': 'k'
}
labels = {
'local_clust': 'clust.',
'eigenvector_centr': 'eigen. centr.',
'page_rank': 'page rank',
'kcore': 'kcore',
'hub': 'hub',
'authority': 'authority'
}
fig = plt.figure()
ax = fig.add_subplot(111)
for f in ['local_clust', 'page_rank', 'hub', 'authority', 'kcore']:
feature = network.vertex_properties[f]
powerlaw.plot_cdf(feature.get_array(),
ax,
label=labels[f],
color=colors[f])
ax.set_xlabel('Feature $f$')
ax.set_ylabel('$P(X>=f)$')
ax.set_ylim([0, 1])
plt.legend(fancybox=True, loc=3, ncol=2, prop={'size': 4})
plt.tight_layout()
plt.savefig('output/wikipedia-features-cdf.pdf')
plt.clf()
colors = {
'local_clust': 'r',
'eigenvector_centr': 'b',
'page_rank': 'g',
'kcore': 'm',
'hub': 'c',
'authority': 'k'
}
labels = {
'local_clust': 'clust.',
'eigenvector_centr': 'eigen. centr.',
'page_rank': 'page rank',
'kcore': 'kcore',
'hub': 'hub',
'authority': 'authority'
}
fig = plt.figure()
ax = fig.add_subplot(111)
for f in [
'local_clust', 'eigenvector_centr', 'page_rank', 'hub',
'authority', 'kcore'
]:
feature = network.vertex_properties[f]
powerlaw.plot_cdf(feature.get_array(),
ax,
label=labels[f],
color=colors[f])
ax.set_xlabel('Feature $f$')
ax.set_ylabel('$P(X<=f)$')
plt.legend(fancybox=True, loc=3, ncol=2, prop={'size': 4})
plt.tight_layout()
plt.savefig('output/wikipedia-features-ccdf.pdf')
plt.clf()
# wikipedia transitions graph structural statistics
print 'before load'
network_transitions = load_graph("output/transitionsnetwork.xml.gz")
print 'after load'
out_hist = vertex_hist(network_transitions, "out")
plt.gca().set_yscale('log')
plt.gca().set_xscale('log')
plt.plot(out_hist[1][:-1], out_hist[0], marker='o')
plt.xlabel('Out-degree')
plt.ylabel('Frequency')
plt.gca().set_ylim([1, 10**6])
#plt.title('Out-degree Distribution')
plt.savefig('output/wikipedia-transitions-out-deg-dist.pdf')
plt.clf()
in_hist = vertex_hist(network_transitions, "in")
plt.gca().set_yscale('log')
plt.gca().set_xscale('log')
plt.plot(in_hist[1][:-1], in_hist[0], marker='o')
plt.xlabel('In-degree')
plt.ylabel('Frequency')
#plt.title('In-degree Distribution')
plt.gca().set_ylim([1, 10**6])
plt.savefig('output/wikipedia-transitions-in-deg-dist.pdf')
plt.clf()
total_hist = vertex_hist(network_transitions, "total")
plt.gca().set_yscale('log')
plt.gca().set_xscale('log')
plt.plot(total_hist[1][:-1], total_hist[0], marker='o')
plt.xlabel('Degree')
plt.ylabel('Frequency')
#plt.title('Degree Distribution')
plt.gca().set_ylim([1, 10**6])
plt.savefig('output/wikipedia-transitions-deg-dist.pdf')
plt.clf()
#clust = local_clustering(network_transitions, undirected=False)
clust = network_transitions.vertex_properties["local_clust"]
#hist, bin_edges = np.histogram(clust.get_array(), 100, density=True)
#cdf = np.cumsum(hist)
#plt.plot(bin_edges[1:], cdf, marker='o')
#plt.xlabel('Local Clustering Coefficient C')
#plt.ylabel('P(x<=C)')
#plt.title('Clustering Coefficient Distribution')
#plt.savefig('output/wikipedia-transitions-clust-cdf.pdf')
fig, ax = plt.subplots()
powerlaw.plot_cdf(clust.get_array(), ax)
#ax.set_title('Clustering Coefficient Distribution')
ax.set_xlabel('Local Clustering Coefficient C')
ax.set_ylabel('P(x<=C)')
fig.savefig('output/wikipedia-transitions-clust-cdf.pdf')
plt.clf()
fig, ax = plt.subplots()
powerlaw.plot_ccdf(clust.get_array(), ax)
ax.set_title('Clustering Coefficient Distribution')
ax.set_xlabel('Local Clustering Coefficient C')
ax.set_ylabel('P(x>=C)')
fig.savefig('output/wikipedia-transitions-clust-ccdf.pdf')
plt.clf()
prank = network_transitions.vertex_properties["page_rank"]
#hist, bin_edges = np.histogram(prank.get_array(), 100, density=True)
#cdf = np.cumsum(hist)
#plt.plot(bin_edges[1:], cdf, marker='o')
#plt.xlabel('Page rank Pr')
#plt.ylabel('P(x<=Pr)')
#plt.title('Page rank Distribution')
#plt.savefig('output/wikipedia-transitions-prank-cdf.pdf')
fig, ax = plt.subplots()
powerlaw.plot_cdf(prank.get_array(), ax)
#ax.set_title('Page Rank Distribution')
ax.set_xlabel('Page rank Pr')
ax.set_ylabel('P(x<=Pr)')
fig.savefig('output/wikipedia-transitions-prank-cdf.pdf')
plt.clf()
fig, ax = plt.subplots()
powerlaw.plot_ccdf(prank.get_array(), ax)
#ax.set_title('Page Rank Distribution')
ax.set_xlabel('Page rank Pr')
ax.set_ylabel('P(x>=Pr)')
fig.savefig('output/wikipedia-transitions-prank-ccdf.pdf')
plt.clf()
kcore = network_transitions.vertex_properties["kcore"]
#hist, bin_edges = np.histogram(kcore.get_array(), 100, density=True)
#cdf = np.cumsum(hist)
#plt.plot(bin_edges[1:], cdf, marker='o')
#plt.xlabel('Kcore kC')
#plt.ylabel('P(x<=kC)')
#plt.title('K-Core Distribution')
#plt.savefig('output/wikipedia-transitions-kcore-cdf.pdf')
fig, ax = plt.subplots()
powerlaw.plot_cdf(kcore.get_array(), ax)
#ax.set_title('K-Core Distribution')
ax.set_xlabel('k-Core kC')
ax.set_ylabel('P(x<=kC)')
fig.savefig('output/wikipedia-transitions-kcore-cdf.pdf')
plt.clf()
fig, ax = plt.subplots()
powerlaw.plot_ccdf(kcore.get_array(), ax)
#ax.set_title('K-Core Distribution')
ax.set_xlabel('k-Core kC')
ax.set_ylabel('P(x>=kC)')
fig.savefig('output/wikipedia-transitions-kcore-ccdf.pdf')
plt.clf()
eigenvector_centr = network_transitions.vertex_properties[
"eigenvector_centr"]
#hist, bin_edges = np.histogram(eigenvector_centr.get_array(), 100, density=True)
#cdf = np.cumsum(hist)
#plt.plot(bin_edges[1:], cdf, marker='o')
#plt.xlabel('Eingenvector centrality E')
#plt.ylabel('P(x<=E)')
#plt.title('Eigenvector Centrality Distribution')
#plt.savefig('output/wikipedia-transitions-eigenvcentr-cdf.pdf')
fig, ax = plt.subplots()
powerlaw.plot_cdf(eigenvector_centr.get_array(), ax)
#ax.set_title('Eigenvector Centrality Distribution')
ax.set_xlabel('Eingenvector centrality E')
ax.set_ylabel('P(x<=E)')
fig.savefig('output/wikipedia-transitions-eigenvcentr-cdf.pdf')
plt.clf()
fig, ax = plt.subplots()
powerlaw.plot_ccdf(eigenvector_centr.get_array(), ax)
#ax.set_title('Eigenvector Centrality Distribution')
ax.set_xlabel('Eingenvector centrality E')
ax.set_ylabel('P(x>=E)')
fig.savefig('output/wikipedia-transitions-eigenvcentr-ccdf.pdf')
plt.clf()
print 'before hits'
#ee, authority, hub = hits(network_transitions)
#network_transitions.vertex_properties["authority"] = authority
#network_transitions.vertex_properties["hub"] = hub
#network_transitions.save("output/transitionsnetwork.xml.gz")
print 'after hits'
colors = {
'local_clust': 'r',
'eigenvector_centr': 'b',
'page_rank': 'g',
'kcore': 'm',
'hub': 'c',
'authority': 'k'
}
labels = {
'local_clust': 'clust.',
'eigenvector_centr': 'eigen. centr.',
'page_rank': 'page rank',
'kcore': 'kcore',
'hub': 'hub',
'authority': 'authority'
}
fig = plt.figure()
ax = fig.add_subplot(111)
for f in ['local_clust', 'page_rank', 'hub', 'authority', 'kcore']:
feature = network_transitions.vertex_properties[f]
powerlaw.plot_cdf(feature.get_array(),
ax,
label=labels[f],
color=colors[f])
ax.set_xlabel('Feature $f$')
ax.set_ylabel('$P(X>=f)$')
ax.set_ylim([0, 1])
plt.legend(fancybox=True, loc=3, ncol=2, prop={'size': 4})
plt.tight_layout()
plt.savefig('output/wikipedia-transitions-features-cdf.pdf')
plt.clf()
colors = {
'local_clust': 'r',
'eigenvector_centr': 'b',
'page_rank': 'g',
'kcore': 'm',
'hub': 'c',
'authority': 'k'
}
labels = {
'local_clust': 'clust.',
'eigenvector_centr': 'eigen. centr.',
'page_rank': 'page rank',
'kcore': 'kcore',
'hub': 'hub',
'authority': 'authority'
}
fig = plt.figure()
ax = fig.add_subplot(111)
for f in ['local_clust', 'page_rank', 'hub', 'authority', 'kcore']:
feature = network_transitions.vertex_properties[f]
powerlaw.plot_cdf(feature.get_array(),
ax,
label=labels[f],
color=colors[f])
ax.set_xlabel('Feature $f$')
ax.set_ylabel('$P(X<=f)$')
plt.legend(fancybox=True, loc=3, ncol=2, prop={'size': 4})
plt.tight_layout()
plt.savefig('output/wikipedia-transitions-features-ccdf.pdf')
plt.clf()
# Plot adjacency matrix indexed by locations
ind1, ind2 = np.nonzero(np.triu(Z1new,
1)) # returns indices of non zero elements
fig, ax = plt.subplots()
ax.plot(x1[ind1], x1[ind2], 'b.', x1[ind2], x1[ind1], 'b.')
ax.set(xlabel='x_i', ylabel='x_j', title='Adjacency matrix')
# Plot degree distribution.
deg = deg[ind]
a = np.sum(deg <= 100)
fit = pl.Fit(np.sort(deg)[0:a],
discrete=True) # fit power law to low degrees? very empirical
figCCDF = pl.plot_ccdf(deg, label='alpha=10')
figCCDF.set(xlabel='degree',
ylabel='distribution',
title='Double power law degree distribution')
# TO DO: add lines of power law. This does not work.
y = np.linspace(1, 100, 100)
plt.plot(y, y**(-sigma))
y = np.linspace(100, 1000, 1000)
plt.plot(y, y**(-tau))
#fit.plot_ccdf(color='r', linewidth=2, ax=figCCDF)
#fit.power_law.plot_ccdf(color='r', linestyle='--', ax=figCCDF)
# second way: with Poisson
# accept = (np.random.poisson(XYw / (1 + XY ** beta)) > 0)
graph = nx.configuration_model(sequence) loops = graph.selfloop_edges() graph = nx.Graph(graph) graph.remove_edges_from(loops) Gcc=sorted(nx.connected_component_subgraphs(graph), key = len, reverse=True) G = Gcc[0] degrees = nx.degree(G) #powerlaw.plot_ccdf(degrees.values(),color='b',marker ='o',linestyle = "none") #plt.show() N_new.append(len(G)) print len(G) data = G.degree().values() powerlaw.plot_ccdf(data,color = color.pop(),marker = 'o',label = str(n)) fit = powerlaw.Fit(G.degree().values()) print fit.power_law.alpha, fit.power_law.sigma plt.show() node_list = G.nodes() WalkerNum = 300 T = [] walker = 0 #for walker in range(WalkerNum): while len(T)<=50000: #if walker<=1000: walker += 1 print walker # if walker%100==0: # print walker source,target = random.sample(node_list,2)
#np_edges = T.get_n_edge_lists(500)
for meas in range(N_meas):
edges = get_fast_edge_list(N, covariance, t)
ks = get_degrees_from_edge_list(N, edges).tolist()
k1.extend(ks)
k1 = np.array(k1, dtype=int)
k1pos = k1[k1 >= 1]
import powerlaw
results = powerlaw.Fit(k1pos, discrete=True, xmin=1)
fig = pl.figure()
powerlaw.plot_ccdf(k1pos)
#powerlaw.plot_pdf(k1)
#pl.hist(k1,bins=np.arange(1,max(k1)+1),histtype='step',density=True)
x = np.arange(1, max(k1pos))
results.lognormal.plot_ccdf(ax=pl.gca())
#results.lognormal.plot_pdf(ax=pl.gca())
pl.xscale('log')
pl.yscale('log')
fig = pl.figure()
pl.hist(
k1,
bins=np.arange(max(k1) + 1),
histtype='step',
density=True,
histplot(indian_6_fork, binsize, 'Users', 'Fork count', 'green',
'User Jan-Jun 2019 Forks Received by Count, LogLog Scale Plot')
plt.savefig('logscale_jan-jun_forks_received.png')
plt.close()
powerlaw.plot_pdf(russian_followers_all, color='black')
powerlaw.plot_pdf(chinese_followers_all, color='red')
powerlaw.plot_pdf(american_followers_all, color='blue')
powerlaw.plot_pdf(indian_followers_all, color='green')
plt.ylabel('Users')
plt.xlabel('Follow Count')
plt.title('All Follows Received by Count, PDF')
plt.savefig('pdf_all_follows_received.png')
plt.close()
powerlaw.plot_ccdf(russian_followers_all, color='black')
powerlaw.plot_ccdf(chinese_followers_all, color='red')
powerlaw.plot_ccdf(american_followers_all, color='blue')
powerlaw.plot_ccdf(indian_followers_all, color='green')
plt.ylabel('Users')
plt.xlabel('Follow Count')
plt.title('All Follows Received by Count, CCDF')
plt.savefig('ccdf_all_follows_received.png')
plt.close()
powerlaw.plot_pdf(russian_watchers_all, color='black')
powerlaw.plot_pdf(chinese_watchers_all, color='red')
powerlaw.plot_pdf(american_watchers_all, color='blue')
powerlaw.plot_pdf(indian_watchers_all, color='green')
plt.ylabel('Users')
plt.xlabel('Star Count')
def main():
# == == == == == == Part 1: Set up environment == == == == == == #
timer = Timer()
timer.start()
data_prefix = '../data/'
target_day_indices = [0, 15, 30, 45]
color_cycle_4 = ColorPalette.CC4
date_labels = [
'Sep 01, 2018', 'Sep 16, 2018', 'Oct 01, 2018', 'Oct 16, 2018'
]
# == == == == == == Part 2: Load video views == == == == == == #
data_loader = DataLoader()
data_loader.load_video_views()
embed_view_dict = data_loader.embed_view_dict
embed_avg_view_dict = data_loader.embed_avg_view_dict
num_videos = data_loader.num_videos
target_day_view_list = [[], [], [], []]
for embed in range(num_videos):
for target_idx, target_day in enumerate(target_day_indices):
target_day_view_list[target_idx].append(
embed_view_dict[embed][target_day])
# == == == == == == Part 3: Load dynamic network snapshot == == == == == == #
embed_indegree_dict = {
embed: np.zeros((T, ))
for embed in np.arange(num_videos)
} # daily indegree for each embed
zero_indegree_list = [] # percentage of zero indegree for each day
num_edges_list = [] # number of total edges for each day
for t in range(T):
filename = 'network_{0}.p'.format(
(datetime(2018, 9, 1) + timedelta(days=t)).strftime('%Y-%m-%d'))
indegree_list = []
with open(os.path.join(data_prefix, 'network_pickle', filename),
'rb') as fin:
network_dict = pickle.load(fin)
# embed_tar: [(embed_src, pos_src, view_src), ...]
for tar_embed in range(num_videos):
indegree_value = len(
[1 for x in network_dict[tar_embed] if x[1] < NUM_REL])
embed_indegree_dict[tar_embed][t] = indegree_value
indegree_list.append(indegree_value)
indegree_counter = Counter(indegree_list)
zero_indegree_list.append(indegree_counter[0] / num_videos)
num_edges_list.append(sum(indegree_list))
print('>>> Finish loading day {0}...'.format(t + 1))
print('>>> Network structure has been loaded!')
print('\n>>> Average number of edges: {0:.0f}, max: {1:.0f}, min: {2:.0f}'.
format(
sum(num_edges_list) / len(num_edges_list), max(num_edges_list),
min(num_edges_list)))
fig, axes = plt.subplots(1, 3, figsize=(12, 4.5))
ax1, ax2, ax3 = axes.ravel()
# == == == == == == Part 4: Plot ax1 indegree CCDF == == == == == == #
embed_avg_indegree_dict = defaultdict(float)
for t in range(T):
for embed in range(num_videos):
embed_avg_indegree_dict[embed] += embed_indegree_dict[embed][t] / T
indegree_ranked_embed_list = [
x[0] for x in sorted(embed_avg_indegree_dict.items(),
key=lambda kv: kv[1],
reverse=True)
]
top_20_indegree_embeds = indegree_ranked_embed_list[:20]
popular_ranked_embed_list = [
x[0] for x in sorted(
embed_avg_view_dict.items(), key=lambda kv: kv[1], reverse=True)
]
top_20_popular_embeds = popular_ranked_embed_list[:20]
for target_idx, target_day in enumerate(target_day_indices):
indegree_list = []
for embed in range(num_videos):
indegree_list.append(embed_indegree_dict[embed][target_day])
print(
'video with 10 indegree has more in-links than {0:.2f}% videos on date {1}'
.format(percentileofscore(indegree_list, 10),
date_labels[target_idx]))
print(
'video with 20 indegree has more in-links than {0:.2f}% videos on date {1}'
.format(percentileofscore(indegree_list, 20),
date_labels[target_idx]))
plot_ccdf(indegree_list,
ax=ax1,
color=color_cycle_4[target_idx],
label=date_labels[target_idx])
# compute the powerlaw fit
powerlaw_fit = Fit(list(embed_avg_indegree_dict.values()))
infer_alpha = powerlaw_fit.power_law.alpha
p = powerlaw_fit.power_law.ccdf()
ins_x_axis = powerlaw_fit.power_law.__dict__['parent_Fit'].__dict__[
'data'][:int(0.9 * len(p))]
ins_y_axis = 0.1 * p[:int(0.9 * len(p))]
ax1.plot(ins_x_axis, ins_y_axis, 'k:')
ax1.text(0.4,
0.6,
r'$x^{{{0:.2f}}}$'.format(-infer_alpha + 1),
size=12,
ha='right',
va='bottom',
transform=ax1.transAxes)
ax1.set_xscale('log')
ax1.set_yscale('log')
ax1.set_xlabel('indegree', fontsize=11)
ax1.set_ylabel('$P(X) \geq x$', fontsize=11)
ax1.tick_params(axis='both', which='major', labelsize=10)
ax1.set_title('(a) indegree distribution', fontsize=12)
ax1.legend(frameon=False, fontsize=11, ncol=1, fancybox=False, shadow=True)
mean_zero_indegree = sum(zero_indegree_list) / len(zero_indegree_list)
ax1.axhline(y=1 - mean_zero_indegree, color='k', linestyle='--', zorder=30)
ax1.text(0.96,
0.9,
'{0:.0f}% with 0 indegree'.format(mean_zero_indegree * 100),
size=11,
transform=ax1.transAxes,
ha='right',
va='top')
# == == == == == == Part 5: Plot ax2 views distribution == == == == == == #
for target_idx, views_list in enumerate(target_day_view_list):
x_values = range(100)
y_values = [np.percentile(views_list, x) for x in x_values]
ax2.plot(x_values,
y_values,
color=color_cycle_4[target_idx],
label=date_labels[target_idx])
ax2.set_yscale('log')
ax2.set_xlabel('views percentile', fontsize=11)
ax2.set_ylabel('num of views', fontsize=11)
ax2.tick_params(axis='both', which='major', labelsize=10)
ax2.set_title('(b) daily views vs. its percentile', fontsize=12)
avg_views_list = sorted(list(embed_avg_view_dict.values()), reverse=True)
gini_coef = gini(avg_views_list)
print('top 1% videos occupy {0:.2f}% views'.format(
sum(avg_views_list[:int(0.01 * num_videos)]) / sum(avg_views_list) *
100))
print('top 10% videos occupy {0:.2f}% views'.format(
sum(avg_views_list[:int(0.1 * num_videos)]) / sum(avg_views_list) *
100))
print('Gini coef: {0:.3f}'.format(gini_coef))
spearman_degree = [
embed_avg_indegree_dict[embed] for embed in range(num_videos)
]
spearman_views = [
embed_avg_view_dict[embed] for embed in range(num_videos)
]
print(
'Spearman correlation between views and indegree: {0:.4f}, pvalue: {1:.2f}'
.format(*spearmanr(spearman_views, spearman_degree)))
median_views = np.median(avg_views_list)
top_views_90th = np.percentile(avg_views_list, 90)
top_views_99th = np.percentile(avg_views_list, 99)
ax2_xmin = ax2.get_xlim()[0]
ax2_ymin = ax2.get_ylim()[0]
ax2.plot((50, 50), (ax2_ymin, median_views),
color='k',
linestyle='--',
zorder=30)
ax2.plot((ax2_xmin, 50), (median_views, median_views),
color='k',
linestyle='--',
zorder=30)
ax2.text(0.49,
0.45,
'median views {0:,.0f}'.format(median_views),
size=11,
transform=ax2.transAxes,
ha='right',
va='bottom')
ax2.plot((90, 90), (ax2_ymin, top_views_90th),
color='k',
linestyle='--',
zorder=30)
ax2.plot((ax2_xmin, 90), (top_views_90th, top_views_90th),
color='k',
linestyle='--',
zorder=30)
ax2.text(0.88,
0.75,
'90th views {0:,.0f}'.format(top_views_90th),
size=11,
transform=ax2.transAxes,
ha='right',
va='bottom')
ax2.plot((99, 99), (ax2_ymin, top_views_99th),
color='k',
linestyle='--',
zorder=30)
ax2.plot((ax2_xmin, 99), (top_views_99th, top_views_99th),
color='k',
linestyle='--',
zorder=30)
ax2.text(0.91,
0.95,
'99th views {0:,.0f}'.format(top_views_99th),
size=11,
transform=ax2.transAxes,
ha='right',
va='bottom')
# == == == == == == Part 7: Plot ax3 video uploading trend == == == == == == #
x_axis = range(2009, 2018)
x_labels = ["'09", "'10", "'11", "'12", "'13", "'14", "'15", "'16", "'17"]
upload_mat = np.zeros((len(x_axis), 8))
target_topics = [
'Pop_music', 'Rock_music', 'Hip_hop_music', 'Independent_music',
'Country_music', 'Electronic_music', 'Soul_music', 'Others'
]
topic_labels = [
'Pop', 'Rock', 'Hip hop', 'Independent', 'Country', 'Electronic',
'Soul', 'Others'
]
color_cycle_8 = ColorPalette.CC8
data_loader.load_embed_content_dict()
embed_title_dict = data_loader.embed_title_dict
embed_uploadtime_dict = data_loader.embed_uploadtime_dict
embed_genre_dict = data_loader.embed_genre_dict
for embed in range(num_videos):
upload_year = int(embed_uploadtime_dict[embed][:4])
if 2009 <= upload_year <= 2017:
year_idx = upload_year - 2009
genres = embed_genre_dict[embed]
if len(genres) == 0:
# add one to "Others" genre
upload_mat[year_idx, 7] += 1
else:
for genre in genres:
upload_mat[year_idx,
target_topics.index(genre)] += 1 / len(genres)
print()
print([
'{0}: {1}'.format(topic, int(num))
for topic, num in zip(target_topics, np.sum(upload_mat, axis=0))
])
stackedBarPlot(ax=ax3,
data=upload_mat,
cols=color_cycle_8,
edgeCols=['#000000'] * 8,
xlabel='uploaded year',
ylabel='num of videos',
scale=False,
endGaps=True)
ax3.tick_params(axis='both', which='major', labelsize=9)
ax3.set_xticks(np.arange(len(x_axis)))
ax3.set_xticklabels(x_labels)
ax3.yaxis.set_major_formatter(FuncFormatter(concise_fmt))
ax3.legend([
plt.Rectangle((0, 0), 1, 1, fc=c, ec='k', alpha=0.6)
for c in color_cycle_8
],
topic_labels,
fontsize=9,
frameon=False,
handletextpad=0.2,
columnspacing=0.3,
ncol=4,
bbox_to_anchor=(1, -0.12),
bbox_transform=ax3.transAxes,
fancybox=False,
shadow=True)
ax3.set_title('(c) VEVO videos uploading trend', fontsize=12)
union_top_set = set(top_20_indegree_embeds).union(top_20_popular_embeds)
print('\n>>> Size of the union set at cutoff 15:', len(union_top_set))
print('{0:>24} | {1:>17} | {2:>5} | {3:>8} | {4:>6} | {5:>10} | {6:>5}'.
format('Video title', 'Artist', 'Age', 'Indegree', '-rank', 'Views',
'-rank'))
for embed in top_20_indegree_embeds:
print(
'{0:>24} & {1:>17} & {2:>5} & {3:>8} & {4:>6} & {5:>10} & {6:>5} \\\\'
.format(
embed_title_dict[embed].split(
' - ', 1)[1].split('(')[0].split('ft')[0].strip(),
embed_title_dict[embed].split(
' - ',
1)[0].split('&')[0].split(',')[0].strip(), '{0:,}'.format(
(datetime(2018, 11, 2) -
str2obj(embed_uploadtime_dict[embed])).days),
'{0:,}'.format(int(embed_avg_indegree_dict[embed])),
'{0:,}'.format(top_20_indegree_embeds.index(embed) + 1),
'{0:,}'.format(int(embed_avg_view_dict[embed])),
'{0:,}'.format(popular_ranked_embed_list.index(embed) + 1)))
print('\n{0:>24} | {1:>17} | {2:>5} | {3:>8} | {4:>6} | {5:>10} | {6:>5}'.
format('Video title', 'Artist', 'Age', 'Indegree', '-rank', 'Views',
'-rank'))
for embed in top_20_popular_embeds:
print(
'{0:>24} & {1:>17} & {2:>5} & {3:>8} & {4:>6} & {5:>10} & {6:>5} \\\\'
.format(
embed_title_dict[embed].split(
' - ', 1)[1].split('(')[0].split('ft')[0].strip(),
embed_title_dict[embed].split(
' - ',
1)[0].split('&')[0].split(',')[0].strip(), '{0:,}'.format(
(datetime(2018, 11, 2) -
str2obj(embed_uploadtime_dict[embed])).days),
'{0:,}'.format(int(embed_avg_indegree_dict[embed])),
'{0:,}'.format(indegree_ranked_embed_list.index(embed) + 1),
'{0:,}'.format(int(embed_avg_view_dict[embed])),
'{0:,}'.format(top_20_popular_embeds.index(embed) + 1)))
hide_spines(axes)
timer.stop()
plt.tight_layout()
plt.savefig('../images/measure_basic_statistics.pdf', bbox_inches='tight')
if not platform.system() == 'Linux':
plt.show()
print 'Mu = ', fit.lognormal.mu
print 'Sigma = ', fit.lognormal.sigma
step_data_xmin = [i for i in step_data if i > fit.power_law.xmin]
figure()
powerlaw.plot_pdf(step_data_xmin, color = 'b', linewidth = 2) # PDF of data
fit.power_law.plot_pdf(color = 'b', linestyle = '--') # PL theoretical fit
fit.exponential.plot_pdf(color = 'r', linestyle = '--') # EXP theoretical fit
fit.lognormal.plot_pdf(color = 'g', linestyle = '--') # LN theoretical fit
xlabel('Step Length, x [cm]')
ylabel('P(x)')
plt.legend(('Data', 'Power Law Fit', 'Exponential Fit', 'Lognormal Fit'))
figure()
powerlaw.plot_ccdf(step_data_xmin, color = 'b', linewidth = 2) # PDF of data
fit.power_law.plot_ccdf(color = 'b', linestyle = '--') # PL theoretical fit
fit.exponential.plot_ccdf(color = 'r', linestyle = '--') # EXP theoretical fit
fit.lognormal.plot_ccdf(color = 'g', linestyle = '--') # LN theoretical fit
xlabel('Step Length, x [cm]')
ylabel('P(x)')
plt.legend(('Data', 'Power Law Fit', 'Exponential Fit', 'Lognormal Fit'))
##print '\nCompare PL with TRUNCATED PL:'
##
##R1, p1 = fit.distribution_compare('power_law', 'truncated_power_law')
##
##if R1 > 0:
## print 'Power law more likely for data. R = ', R1, ' and p = ', p1
##else:
## print 'Truncated PL more likely for data. R = ', R1, 'and p = ', p1
bins=np.linspace(np.log10(np.min(grado)),
np.log10(np.max(grado)),
15))
#Ajuste a ley de potencias, vease: https://github.com/jeffalstott/powerlaw
ajuste = powerlaw.Fit(grado, xmin=1.0)
print(ajuste.power_law.alpha)
print(ajuste.power_law.xmin)
R, p = ajuste.distribution_compare('power_law', 'lognormal')
#El alpha de la ley de potencias esta dado por ajuste.power_law.alpha
#Plotting
fig = plt.figure(figsize=(15, 10))
#plt.suptitle('Histogramas Datos Newman', fontsize=22)
#plt.subplot(2, 2, 1)
powerlaw.plot_pdf(grado, color='b')
ajuste.power_law.plot_pdf(color='b', linestyle='--')
#plt.subplot(2, 2, 2)
#powerlaw.plot_cdf(grado, color='b')
#plt.subplot(2, 2, 3)
powerlaw.plot_ccdf(grado, color='r')
#plt.subplot(2, 2, 4)
A = np.diff(bines_log)
ydata = np.divide(datos_log + 0.0, np.amax(datos_log))
print ydata
plt.loglog(np.diff(bines_log), ydata, 'o')
#plt.plot(np.diff(bines_log)*ajuste.power_law.alpha,datos_log,'-')
plt.show()
#plt.savefig('maps.png', dpi=300)
legend( legend_refs[::-1], theoretical_alphas[::-1], loc = 'center right', bbox_to_anchor = (.1,0,1,1),
bbox_transform = plt.gcf().transFigure, title=r'$\alpha$ of Data' )
savefig('Fig_powerlaw_validation_%itrials_%idata.pdf'%(int(n_trials),int(n_data)), bbox_inches='tight')
# <markdowncell>
# # Validation of Simulated Data Generators for Other Distributions
# <codecell>
param = [2.5, .5]
dist = powerlaw.Truncated_Power_Law
theoretical_dist = dist(xmin=2.0, parameters=param,discrete=True)
simulated_data = theoretical_dist.generate_random(1000)
powerlaw.plot_ccdf(simulated_data, linewidth=2, linestyle='--')
theoretical_dist.plot_ccdf(simulated_data)
figure()
powerlaw.plot_pdf(simulated_data, linewidth=2, linestyle='--')
theoretical_dist.plot_pdf(simulated_data)
theoretical_dist = dist(xmin=2.0, parameters=param,discrete=False)
figure()
simulated_data = theoretical_dist.generate_random(1000)
powerlaw.plot_ccdf(simulated_data, linewidth=2, linestyle='--')
theoretical_dist.plot_ccdf(simulated_data)
figure()
powerlaw.plot_pdf(simulated_data, linewidth=2, linestyle='--')
theoretical_dist.plot_pdf(simulated_data)
binsize = int(np.max(indian_all)/multiplier)
histplot(indian_6, binsize, 'Users', 'Star Count', 'green', 'All Stars Given by Count, LogLog Scale Plot')
plt.savefig('logscale_all_stars_given.png')
plt.close()
powerlaw.plot_pdf(russian_6, color='black')
powerlaw.plot_pdf(chinese_6, color='red')
powerlaw.plot_pdf(american_6, color='blue')
powerlaw.plot_pdf(indian_6, color='green')
plt.ylabel('Users')
plt.xlabel('Star Count')
plt.title('Jan-Jun 2019 Stars Given by Count, PDF')
plt.savefig('pdf_jan-jun_stars_given.png')
plt.close()
powerlaw.plot_ccdf(russian_6, color='black')
powerlaw.plot_ccdf(chinese_6, color='red')
powerlaw.plot_ccdf(american_6, color='blue')
powerlaw.plot_ccdf(indian_6, color='green')
plt.ylabel('Users')
plt.xlabel('Star Count')
plt.title('Jan-Jun 2019 Stars Given by Count, CCDF')
plt.savefig('ccdf_jan-jun_stars_given.png')
plt.close()
powerlaw.plot_pdf(russian_all, color='black')
powerlaw.plot_pdf(chinese_all, color='red')
powerlaw.plot_pdf(american_all, color='blue')
powerlaw.plot_pdf(indian_all, color='green')
plt.ylabel('Users')
plt.xlabel('Star Count')
def main():
timer = Timer()
timer.start()
app_name = 'cyberbullying'
archive_dir = '../data/{0}_out'.format(app_name)
entities = ['user', 'hashtag']
rho = 0.5272
fig, axes = plt.subplots(1, 2, figsize=(10, 3.3))
cc4 = ColorPalette.CC4
blue = cc4[0]
for ax_idx, entity in enumerate(entities):
sample_datefile = open(os.path.join(
archive_dir, '{0}_{1}_all.txt'.format(entity, app_name)),
'r',
encoding='utf-8')
complete_datefile = open(os.path.join(
archive_dir, 'complete_{0}_{1}.txt'.format(entity, app_name)),
'r',
encoding='utf-8')
sample_entity_freq_dict = defaultdict(int)
complete_entity_freq_dict = defaultdict(int)
uni_random_entity_freq_dict = defaultdict(int)
if entity == 'user':
for line in sample_datefile:
sample_entity_freq_dict[line.rstrip().split(',')[1]] += 1
for line in complete_datefile:
complete_entity_freq_dict[line.rstrip().split(',')[1]] += 1
toss = np.random.random_sample()
if toss <= rho:
uni_random_entity_freq_dict[line.rstrip().split(',')
[1]] += 1
else:
for line in sample_datefile:
for item in line.rstrip().split(',')[1:]:
sample_entity_freq_dict[item.lower()] += 1
for line in complete_datefile:
for item in line.rstrip().split(',')[1:]:
complete_entity_freq_dict[item.lower()] += 1
toss = np.random.random_sample()
if toss <= rho:
for item in line.rstrip().split(',')[1:]:
uni_random_entity_freq_dict[item.lower()] += 1
sample_datefile.close()
complete_datefile.close()
# compute the powerlaw fit in the complete set
complete_freq_list = list(complete_entity_freq_dict.values())
complete_powerlaw_fit = Fit(complete_freq_list)
complete_alpha = complete_powerlaw_fit.power_law.alpha
complete_xmin = complete_powerlaw_fit.power_law.xmin
print('{0} complete set alpha {1}, xmin {2}'.format(
entity, complete_alpha, complete_xmin))
plot_ccdf(complete_freq_list,
ax=axes[ax_idx],
color='k',
ls='-',
label='complete')
# compute the powerlaw fit in the sample set
# infer the number of missing entities
sample_freq_list = list(sample_entity_freq_dict.values())
sample_freq_counter = Counter(sample_freq_list)
# we observe the frequency of entities appearing less than 100 times
num_interest = 100
sample_freq_list_top100 = [0] * num_interest
for freq in range(1, num_interest + 1):
sample_freq_list_top100[freq - 1] = sample_freq_counter[freq]
inferred_num_missing = infer_missing_num(sample_freq_list_top100,
rho=rho,
m=num_interest)
corrected_sample_freq_list = sample_freq_list + [
0
] * inferred_num_missing
sample_powerlaw_fit = Fit(corrected_sample_freq_list)
sample_alpha = sample_powerlaw_fit.power_law.alpha
sample_xmin = sample_powerlaw_fit.power_law.xmin
print('{0} sample set alpha {1}, xmin {2}'.format(
entity, sample_alpha, sample_xmin))
plot_ccdf(corrected_sample_freq_list,
ax=axes[ax_idx],
color=blue,
ls='-',
label='sample')
# compute the powerlaw fit in uniform random sample
uni_random_num_missing = len(complete_entity_freq_dict) - len(
uni_random_entity_freq_dict)
uni_random_freq_list = list(uni_random_entity_freq_dict.values())
uni_random_freq_list = uni_random_freq_list + [
0
] * uni_random_num_missing
uni_random_powerlaw_fit = Fit(uni_random_freq_list)
uni_random_alpha = uni_random_powerlaw_fit.power_law.alpha
uni_random_xmin = uni_random_powerlaw_fit.power_law.xmin
print('{0} uniform random sampling alpha {1}, xmin {2}'.format(
entity, uni_random_alpha, uni_random_xmin))
plot_ccdf(uni_random_freq_list,
ax=axes[ax_idx],
color='k',
ls='--',
label='uniform random')
print('inferred missing', inferred_num_missing)
print('empirical missing',
len(complete_entity_freq_dict) - len(sample_entity_freq_dict))
print('uniform random missing', uni_random_num_missing)
print('KS test (sample, uniform)')
print(stats.ks_2samp(corrected_sample_freq_list, uni_random_freq_list))
print('KS test (sample, complete)')
print(stats.ks_2samp(corrected_sample_freq_list, complete_freq_list))
print('KS test (uniform, complete)')
print(stats.ks_2samp(uni_random_freq_list, complete_freq_list))
axes[ax_idx].set_xscale('symlog')
axes[ax_idx].set_yscale('log')
axes[ax_idx].set_xlabel('frequency', fontsize=16)
axes[ax_idx].tick_params(axis='both', which='major', labelsize=16)
axes[0].set_xticks([0, 1, 100, 10000])
axes[0].set_yticks([1, 0.01, 0.0001, 0.000001])
axes[0].set_ylabel('$P(X \geq x)$', fontsize=16)
axes[0].legend(frameon=False,
fontsize=16,
ncol=1,
fancybox=False,
shadow=True,
loc='lower left')
axes[0].set_title('(a) user posting', fontsize=18, pad=-3 * 72, y=1.0001)
axes[1].set_xticks([0, 1, 100, 10000, 1000000])
axes[1].set_yticks([1, 0.1, 0.001, 0.00001])
axes[1].set_title('(b) hashtag', fontsize=18, pad=-3 * 72, y=1.0001)
hide_spines(axes)
timer.stop()
plt.tight_layout(rect=[0, 0.05, 1, 1])
plt.savefig('../images/entity_freq_dist.pdf', bbox_inches='tight')
if not platform.system() == 'Linux':
plt.show()
# stashfig("degree-synapse-sequences")
# %%
from powerlaw import plot_ccdf, plot_cdf, plot_pdf
fig, axs = plt.subplots(4, 5, figsize=(20, 20), sharex=True)
for i in range(len(GRAPH_TYPES)):
g_type = GRAPH_TYPES[i]
g_type_label = GRAPH_TYPE_LABELS[i]
adj = load_everything(g_type, version=BRAIN_VERSION)
in_sum = np.sort(adj.sum(axis=0))
out_sum = np.sort(adj.sum(axis=1))
ax = plot_ccdf(in_sum, ax=axs[0, i])
# ax.set(yscale="log")
ax.set_xticklabels([])
ax = plot_ccdf(out_sum, ax=axs[1, i])
# ax.set(yscale="log")
ax.set_xticklabels([])
in_degree = np.sort(np.count_nonzero(adj, axis=0))
out_degree = np.sort(np.count_nonzero(adj, axis=1))
ax = plot_ccdf(in_degree, ax=axs[2, i])
# ax.set(yscale="log")
ax.set_xticklabels([])
ax = plot_ccdf(out_degree, ax=axs[3, i])
import powerlaw
import matplotlib.pyplot as plt
"""C.Elegan"""
G = nx.read_gml("celegansneural/celegansneural.gml")
G = nx.DiGraph(G)
print "C.Elegan"
print "Number of Nodes: ",len(G)
print "Number of Edges: ",len(G.edges())
degrees = G.degree().values()
in_degrees = G.in_degree().values()
out_degrees = G.out_degree().values()
plt.figure(1)
powerlaw.plot_ccdf(degrees,marker = 'o',color = 'b',linestyle = "none")
plt.xlabel(r"$k$",fontsize = 16)
plt.ylabel(r"$P(k)$",fontsize = 16)
plt.title("Degree Distribution of C.Elegan")
plt.savefig("C.Elegan - Degree Distribution.png")
plt.figure(2)
powerlaw.plot_ccdf(in_degrees,marker = 'o',color = 'b',linestyle = "none")
plt.xlabel(r"$k$",fontsize = 16)
plt.ylabel(r"$P(k)$",fontsize = 16)
plt.title("In Degree Distribution of C.Elegan")
plt.savefig("C.Elegan - In Degree Distribution.png")
plt.figure(3)
powerlaw.plot_ccdf(out_degrees,marker = 'o',color = 'b',linestyle = "none")
plt.xlabel(r"$k$",fontsize = 16)