In [1]:
import networkx
import math
import scipy.optimize
import numpy
from lib.time_graph import *
from lib.vis import *
from lib.syn import *
from lib.experiments import *
from IPython.display import Image
/usr/local/lib/python3.4/dist-packages/matplotlib/__init__.py:1350: UserWarning: This call to matplotlib.use() has no effect because the backend has already been chosen; matplotlib.use() must be called *before* pylab, matplotlib.pyplot, or matplotlib.backends is imported for the first time. warnings.warn(_use_error_msg)
Size Graph¶
In [4]:
algos = [TemporalCuts("FSTC-16", "fast-sparse", eps=1e-5, k=16),
TemporalCuts("FSTC-64", "fast-sparse", eps=1e-5, k=64),
TemporalCuts("STC", "diff-sparse", eps=1e-5),
TemporalCuts("LAP", "laplacian-sparse"),
TemporalCuts("UNION", "union-sparse"),
TemporalCuts("SINGLE", "indep-sparse")]
size = [1000, 1500, 2000, 2500]
res = size_experiments(algos, size, True, n=10)
In [4]:
res
Out[4]:
[[{'sparsity': 0.00041837537080828107, 'time': 7.2947828769683838},
{'sparsity': 0.00032344381593990654, 'time': 15.226266622543335},
{'sparsity': 0.00022693042297480297, 'time': 78.253204822540283},
{'sparsity': 0.00073140410722163137, 'time': 178.47454023361206},
{'sparsity': 0.00022693042297480451, 'time': 0.50150251388549805},
{'sparsity': 0.00073604644551906984, 'time': 5.0997660160064697}],
[{'sparsity': 0.00027111227672103796, 'time': 11.592995405197144},
{'sparsity': 0.00032548426669283802, 'time': 23.956495046615601},
{'sparsity': 0.00012389056501414217, 'time': 191.90035247802734},
{'sparsity': 0.00012487060559604037, 'time': 43.609651803970337},
{'sparsity': 0.0001238957381495161, 'time': 0.9593660831451416},
{'sparsity': 0.00055354486422367591, 'time': 10.006524801254272}],
[{'sparsity': 0.00019964964459508698, 'time': 16.924439907073975},
{'sparsity': 0.00024393352891823175, 'time': 30.094156742095947},
{'sparsity': 8.2831986978613048e-05, 'time': 313.08514285087585},
{'sparsity': 8.6475823470633019e-05, 'time': 49.587661266326904},
{'sparsity': 8.2831986978612994e-05, 'time': 1.4889810085296631},
{'sparsity': 0.00035962085587008423, 'time': 16.079641103744507}],
[{'sparsity': 0.00022861893183529858, 'time': 16.390578269958496},
{'sparsity': 0.00019810995619673865, 'time': 36.908218622207642},
{'sparsity': 5.7211145349334895e-05, 'time': 503.3889594078064},
{'sparsity': 5.7935117478231834e-05, 'time': 63.00629997253418},
{'sparsity': 5.7211145349334848e-05, 'time': 2.1148567199707031},
{'sparsity': 0.0003092175094376406, 'time': 22.440906286239624}]]
In [5]:
output_file_name = "figs/syn_size_slide.png"
plot_size_experiments(res, algos, size, output_file_name, 0, 500, 2000)
Image(filename=output_file_name)
Out[5]:
In [2]:
algos = [TemporalCuts("FSTC-16", "fast-norm", eps=1e-5, k=16),
TemporalCuts("FSTC-64", "fast-norm", eps=1e-5, k=64),
TemporalCuts("STC", "diff-norm", eps=1e-5),
TemporalCuts("LAP", "laplacian-norm"),
TemporalCuts("UNION", "union-norm"),
TemporalCuts("SINGLE", "indep-norm")]
size = [1000, 1500, 2000, 2500]
res = size_experiments(algos, size, True, n=10)
In [3]:
output_file_name = "figs/syn_norm_size_slide.png"
plot_size_experiments(res, algos, size, output_file_name, 0, 500, 2000)
Image(filename=output_file_name)
Out[3]:
Density¶
In [ ]:
algos = [TemporalCuts("FSTC-16", "fast-sparse", eps=1e-5, k=16),
TemporalCuts("FSTC-64", "fast-sparse", eps=1e-5, k=64),
TemporalCuts("STC", "diff-sparse", eps=1e-5),
TemporalCuts("LAP", "laplacian-sparse"),
TemporalCuts("UNION", "union-sparse"),
TemporalCuts("SINGLE", "indep-sparse")]
hop = [1, 2, 3, 4]
res = hop_experiments(algos, hop, True, 10)
In [ ]:
output_file_name = "figs/syn_hop_slide.png"
plot_hop_experiments(res, algos, hop, output_file_name, 0, 500, 1000)
Image(filename=output_file_name)
In [ ]:
algos = [TemporalCuts("FSTC-16", "fast-norm", eps=1e-5, k=16),
TemporalCuts("FSTC-64", "fast-norm", eps=1e-5, k=64),
TemporalCuts("STC", "diff-norm", eps=1e-5),
TemporalCuts("LAP", "laplacian-norm"),
TemporalCuts("UNION", "union-norm"),
TemporalCuts("SINGLE", "indep-norm")]
hop = [1, 2, 3, 4]
res = hop_experiments(algos, hop, True, 10)
In [ ]:
output_file_name = "figs/syn_norm_hop_slide.png"
plot_hop_experiments(res, algos, hop, output_file_name, 0, 500, 2000)
Image(filename=output_file_name)
Snapshots¶
In [2]:
algos = [TemporalCuts("FSTC-10", "fast-sparse", eps=1e-5, k=10),
TemporalCuts("FSTC-50", "fast-sparse", eps=1e-5, k=50),
TemporalCuts("STC", "diff-sparse", eps=1e-5),
TemporalCuts("LAP", "laplacian-sparse"),
TemporalCuts("UNION", "union-sparse"),
TemporalCuts("SINGLE", "indep-sparse")]
n_snaps = [5, 10, 15, 20]
res = num_snaps_experiments(algos, n_snaps, True, 10)
In [4]:
output_file_name = "figs/syn_num_snaps_slide.png"
plot_num_snaps_experiments(res, algos, n_snaps, output_file_name, 0, 500, 2000)
Image(filename=output_file_name)
Out[4]:
Rank¶
In [ ]:
output_file_name = "figs/syn_norm_rank_time_slide.png"
plot_rank_time_experiments(res, rank, output_file_name)
Image(filename=output_file_name)
In [ ]:
output_file_name = "figs/syn_norm_rank_time_slide.png"
plot_rank_time_experiments(res, rank, output_file_name)
Image(filename=output_file_name)