109 lines
3.8 KiB
Python
109 lines
3.8 KiB
Python
#!/usr/bin/env python3
|
|
|
|
import matplotlib.pyplot as plt
|
|
from datetime import datetime
|
|
import glob
|
|
import json
|
|
import reduce_edges
|
|
|
|
def load_json(path):
|
|
with open(path, 'r') as f:
|
|
return json.load(f)
|
|
|
|
|
|
def plot_in_out(n_crawlers, prc, data):
|
|
times = []
|
|
avg_in = []
|
|
known_in = []
|
|
known_out = []
|
|
# same value, independent of algo
|
|
algo = 'sr'
|
|
for when, d in sorted(data.items(), key=lambda kv: kv[0]):
|
|
times.append(when)
|
|
avg_in.append(d[algo]['avg_in'])
|
|
known_in.append(d[algo]['known_in'])
|
|
known_out.append(d[algo]['known_out'])
|
|
|
|
fig, ax = plt.subplots()
|
|
a = 'SensorRank' if algo == 'sr' else 'RageRank'
|
|
ax.set_ylabel(f'{a}')
|
|
ax.plot(times, avg_in, label='Avg. In')
|
|
# ax.plot(times, known_in, label='Known In') # TODO
|
|
ax.plot(times, known_in, label='Known In')
|
|
ax.plot(times, known_out, label='Known out')
|
|
title = f'In And Out after adding {n_crawlers} crawlers with {prc * 100}% edges'
|
|
ax.set_title(title)
|
|
|
|
fig.autofmt_xdate()
|
|
fig.legend()
|
|
plt.savefig(f'./plot_with_crawler/{n_crawlers:03d}_crawlers/{prc:.02f}_edges/in_out.png')
|
|
|
|
|
|
def plot(n_crawlers, prc, algo, data):
|
|
times = []
|
|
avg_rank = []
|
|
a_avg_in = []
|
|
known_rank = []
|
|
known_in = []
|
|
known_out = []
|
|
for when, d in sorted(data.items(), key=lambda kv: kv[0]):
|
|
times.append(when)
|
|
avg_rank.append(d[algo]['avg_rank'])
|
|
a_avg_in.append(d[algo]['avg_in'])
|
|
known_rank.append(d[algo]['known_rank'])
|
|
known_in.append(d[algo]['known_in'])
|
|
known_out.append(d[algo]['known_out'])
|
|
|
|
# avg_out = sum(known_out) / len(known_out)
|
|
# avg_in = sum(known_in) / len(known_in)
|
|
|
|
fig, ax = plt.subplots()
|
|
a = 'SensorRank' if algo == 'sr' else 'RageRank'
|
|
ax.set_ylabel(f'{a}')
|
|
ax.plot(times, avg_rank, label='Avg. Rank')
|
|
# ax.plot(times, known_in, label='Known In') # TODO
|
|
ax.plot(times, known_rank, label='Known Rank')
|
|
# title = f'{a} after removing {percentage * 100}% edges and adding {added_percentage * 100}%\nin = {avg_in:.02f} out = {avg_out:.02f}'
|
|
title = f'{a} with {n_crawlers} crawlers with {prc * 100}% edges each'
|
|
ax.set_title(title)
|
|
|
|
# ax2 = ax.twinx()
|
|
# ax2.set_ylabel('Edges')
|
|
# ax2.plot(times, known_in, label='Known In', color='red')
|
|
# ax2.plot(times, known_out, label='Known Out', color='green')
|
|
# # print(f'{len(times)=}, {len(a_avg_in)=}')
|
|
# # assert len(times) == len(a_avg_in)
|
|
# ax2.plot(times, a_avg_in, label='Avg. In', color='violet')
|
|
|
|
fig.autofmt_xdate()
|
|
fig.legend()
|
|
plt.savefig(f'./plot_with_crawler/{n_crawlers:03d}_crawlers/{prc:.02f}_edges/{algo}.png')
|
|
# print('created sr plot')
|
|
# plt.show()
|
|
|
|
|
|
def main():
|
|
for n_crawlers in [5,10,20,50]: #in reduce_edges.percentages:
|
|
for prc in [0.1, 0.5, 0.9]:
|
|
# for file in glob.glob(f'./edges_reduced/{reduced_percentage:.02f}/*.txt'):
|
|
# for file in glob.glob(f'./data_with_crawler/{n_crawlers:03d}_crawlers/{prc:.02f}_edges/*.json'):
|
|
# for reduced_percentage in reduce_edges.percentages:
|
|
# perc = reduce_edges.percentages.copy()
|
|
# perc.append(1.0)
|
|
# perc.append(1.2)
|
|
# for added_percentage in perc:
|
|
data = {}
|
|
for file in glob.glob(f'./data_with_crawler/{n_crawlers:03d}_crawlers/{prc:.02f}_edges/*.json'):
|
|
# for file in glob.glob(f'./data_with_crawler/{reduced_percentage:.02f}/{added_percentage:.02f}/*.json'):
|
|
when = datetime.fromtimestamp(float(file.split('/')[-1][:-5]))
|
|
print(f'{n_crawlers=:.02f}, {prc=:.02f}, {when=}')
|
|
data[when] = load_json(file)
|
|
|
|
plot(n_crawlers, prc, 'sr', data)
|
|
plot(n_crawlers, prc, 'pr', data)
|
|
plot_in_out(n_crawlers, prc, data)
|
|
|
|
|
|
if __name__ == '__main__':
|
|
main()
|