1 | #!/usr/bin/env python3 |
---|
2 | |
---|
3 | import sys |
---|
4 | import os |
---|
5 | import time |
---|
6 | import random |
---|
7 | import tempfile |
---|
8 | import argparse |
---|
9 | import socket |
---|
10 | import json |
---|
11 | |
---|
12 | import numpy |
---|
13 | import matplotlib.mlab as mlab |
---|
14 | import matplotlib.pyplot as plt |
---|
15 | |
---|
16 | |
---|
17 | VERSION = "{DEVELOPMENT}" |
---|
18 | if VERSION == "{DEVELOPMENT}": |
---|
19 | script_dir = '.' |
---|
20 | try: |
---|
21 | script_dir = os.path.dirname(os.path.realpath(__file__)) |
---|
22 | except: |
---|
23 | try: |
---|
24 | script_dir = os.path.dirname(os.path.abspath(sys.argv[0])) |
---|
25 | except: |
---|
26 | pass |
---|
27 | sys.path.append("%s/../lib" % script_dir) |
---|
28 | |
---|
29 | from nanownlib import * |
---|
30 | from nanownlib.stats import * |
---|
31 | import nanownlib.storage |
---|
32 | |
---|
33 | |
---|
34 | parser = argparse.ArgumentParser( |
---|
35 | description="") |
---|
36 | parser.add_argument('db_file', default=None, |
---|
37 | help='') |
---|
38 | options = parser.parse_args() |
---|
39 | db = nanownlib.storage.db(options.db_file) |
---|
40 | |
---|
41 | |
---|
42 | def differences(db, unusual_case, rtt_type='packet'): |
---|
43 | ret_val = [s['unusual_'+rtt_type]-s['other_'+rtt_type] for s in db.subseries('train', unusual_case)] |
---|
44 | ret_val += [s['unusual_'+rtt_type]-s['other_'+rtt_type] for s in db.subseries('test', unusual_case)] |
---|
45 | return ret_val |
---|
46 | |
---|
47 | def null_differences(db, unusual_case, rtt_type='packet'): |
---|
48 | ret_val = [s['unusual_'+rtt_type]-s['other_'+rtt_type] for s in db.subseries('train_null', unusual_case)] |
---|
49 | return ret_val |
---|
50 | |
---|
51 | |
---|
52 | def timeSeries(db, probe_type, unusual_case): |
---|
53 | cursor = db.conn.cursor() |
---|
54 | query=""" |
---|
55 | SELECT time_of_day,packet_rtt AS uc,(SELECT avg(packet_rtt) FROM probes,analysis |
---|
56 | WHERE analysis.probe_id=probes.id AND probes.test_case!=:unusual_case AND probes.type=:probe_type AND sample=u.sample) AS oc |
---|
57 | FROM (SELECT time_of_day,probes.sample,packet_rtt FROM probes,analysis |
---|
58 | WHERE analysis.probe_id=probes.id AND probes.test_case =:unusual_case AND probes.type=:probe_type) u |
---|
59 | """ |
---|
60 | |
---|
61 | params = {"probe_type":probe_type,"unusual_case":unusual_case} |
---|
62 | cursor.execute(query, params) |
---|
63 | for row in cursor: |
---|
64 | yield {'time_of_day':row['time_of_day'],unusual_case:row['uc'],'other_cases':row['oc']} |
---|
65 | #samples,derived,null_derived = parse_data(input1) |
---|
66 | |
---|
67 | #trust = trustValues(derived, sum) |
---|
68 | #weights = linearWeights(derived, trust, 0.25) |
---|
69 | #print('(test): %f' % weightedMean(derived,weights)) |
---|
70 | |
---|
71 | diffs = list(differences(db, 'long')) |
---|
72 | reported_diffs = list(differences(db, 'long', 'reported')) |
---|
73 | #shorts = [s['packet_rtt'] for s in samples.values() if s['test_case']=='short'] |
---|
74 | #longs = [s['packet_rtt'] for s in samples.values() if s['test_case']=='long'] |
---|
75 | |
---|
76 | short_overtime = [(sample['time_of_day'],sample['short']) for sample in timeSeries(db,'train','short')] |
---|
77 | long_overtime = [(sample['time_of_day'],sample['long']) for sample in timeSeries(db,'train','long')] |
---|
78 | diff_overtime = [(sample['time_of_day'],sample['long']-sample['other_cases']) for sample in timeSeries(db,'train','long')] |
---|
79 | short_overtime.sort() |
---|
80 | long_overtime.sort() |
---|
81 | diff_overtime.sort() |
---|
82 | |
---|
83 | print('packet_rtt diff mean: %f' % statistics.mean(diffs)) |
---|
84 | print('packet_rtt diff median: %f' % statistics.median(diffs)) |
---|
85 | print('packet_rtt diff midhinge: %f' % midsummary(diffs)) |
---|
86 | print('packet_rtt diff trimean: %f' % trimean(diffs)) |
---|
87 | print('packet_rtt diff quadsummary: %f' % quadsummary(diffs)) |
---|
88 | print('packet_rtt diff ubersummary: %f' % ubersummary(diffs)) |
---|
89 | print('packet_rtt diff septasummary: %f' % septasummary(diffs)) |
---|
90 | print('packet_rtt diff MAD: %f' % mad(diffs)) |
---|
91 | try: |
---|
92 | print('reported diff trimean: %f' % trimean(reported_diffs)) |
---|
93 | print('reported diff quadsummary: %f' % quadsummary(reported_diffs)) |
---|
94 | print('reported diff ubersummary: %f' % ubersummary(reported_diffs)) |
---|
95 | print('reported diff septasummary: %f' % septasummary(reported_diffs)) |
---|
96 | print('reported diff MAD: %f' % mad(reported_diffs)) |
---|
97 | |
---|
98 | #import cProfile |
---|
99 | #start = time.time() |
---|
100 | #kresults = kfilter({},diffs) |
---|
101 | #print('packet_rtt diff kfilter: ', numpy.mean(kresults['est']), kresults['var']) |
---|
102 | #print('packet_rtt diff kfilter: ', kresults['est'][-1], kresults['var'][-1]) |
---|
103 | #kresults = kfilter({},reported_diffs) |
---|
104 | #print('reported diff kfilter: ', numpy.mean(kresults['est']), kresults['var'][-1]) |
---|
105 | #print('reported diff kfilter: ', kresults['est'][-1], kresults['var'][-1]) |
---|
106 | #print("kfilter time: %f" % (time.time()-start)) |
---|
107 | except: |
---|
108 | pass |
---|
109 | |
---|
110 | #print('tsval diff mean: %f' % numpy.mean(differences(db, 'long', 'tsval'))) |
---|
111 | #print('tsval null diff mean: %f' % numpy.mean(null_differences(db, 'long', 'tsval'))) |
---|
112 | #print('tsval diff weighted mean: %f' % tsvalwmean(db.subseries('train','long')+db.subseries('test','long'))) |
---|
113 | #print('tsval null diff weighted mean: %f' % tsvalwmean(db.subseries('train_null','long'))) |
---|
114 | |
---|
115 | |
---|
116 | |
---|
117 | |
---|
118 | def testKalman4D(params=None): |
---|
119 | from pykalman import KalmanFilter |
---|
120 | train = db.subseries('train','long', offset=0) |
---|
121 | test = db.subseries('test','long', offset=0) |
---|
122 | null = db.subseries('train_null','long', offset=0) |
---|
123 | measurements = numpy.asarray([(s['unusual_packet'],s['other_packet'],s['unusual_tsval'],s['other_tsval']) for s in (train+test)]) |
---|
124 | null_measurements = numpy.asarray([(s['unusual_packet'],s['other_packet'],s['unusual_tsval'],s['other_tsval']) for s in null]) |
---|
125 | |
---|
126 | if params == None: |
---|
127 | kf = KalmanFilter(n_dim_obs=4, n_dim_state=4, |
---|
128 | initial_state_mean=[quadsummary([s['unusual_packet'] for s in train]), |
---|
129 | quadsummary([s['other_packet'] for s in train]), |
---|
130 | numpy.mean([s['unusual_tsval'] for s in train]), |
---|
131 | numpy.mean([s['other_tsval'] for s in train])]) |
---|
132 | kf = KalmanFilter(n_dim_obs=4, n_dim_state=4) |
---|
133 | |
---|
134 | start=time.time() |
---|
135 | kf = kf.em(measurements[0:len(train)]+null_measurements[0:50000], n_iter=10, |
---|
136 | em_vars=('transition_matrices', |
---|
137 | 'observation_matrices', |
---|
138 | 'transition_offsets', |
---|
139 | 'observation_offsets', |
---|
140 | 'transition_covariance', |
---|
141 | 'observation_covariance', |
---|
142 | 'initial_state_mean', |
---|
143 | 'initial_state_covariance')) |
---|
144 | params = {'transition_matrices': kf.transition_matrices.tolist(), |
---|
145 | 'observation_matrices': kf.observation_matrices.tolist(), |
---|
146 | 'transition_offsets': kf.transition_offsets.tolist(), |
---|
147 | 'observation_offsets': kf.observation_offsets.tolist(), |
---|
148 | 'transition_covariance': kf.transition_covariance.tolist(), |
---|
149 | 'observation_covariance': kf.observation_covariance.tolist(), |
---|
150 | 'initial_state_mean': kf.initial_state_mean.tolist(), |
---|
151 | 'initial_state_covariance': kf.initial_state_covariance.tolist()} |
---|
152 | print("Learned Params:\n") |
---|
153 | import pprint |
---|
154 | pprint.pprint(params) |
---|
155 | print("pykalman em time: %f" % (time.time()-start)) |
---|
156 | |
---|
157 | #kf = KalmanFilter(n_dim_obs=2, n_dim_state=2, **params) |
---|
158 | |
---|
159 | num_obs=5000 |
---|
160 | for offset in range(50000,100000+num_obs,num_obs): |
---|
161 | start=time.time() |
---|
162 | m = measurements[offset:offset+num_obs] |
---|
163 | #params['initial_state_mean']=[quadsummary([s[0] for s in m]), |
---|
164 | # quadsummary([s[1] for s in m]), |
---|
165 | # numpy.mean([s[2] for s in m]), |
---|
166 | # numpy.mean([s[3] for s in m])] |
---|
167 | kf = KalmanFilter(n_dim_obs=4, n_dim_state=4, **params) |
---|
168 | (smoothed_state_means, smoothed_state_covariances) = kf.smooth(m) |
---|
169 | #print("pykalman smooth time: %f" % (time.time()-start)) |
---|
170 | up = numpy.mean([m[0] for m in smoothed_state_means]) |
---|
171 | op = numpy.mean([m[1] for m in smoothed_state_means]) |
---|
172 | #print("packet_rtt pykalman final:", smoothed_state_means[-1][0]-smoothed_state_means[-1][1]) |
---|
173 | print("packet_rtt pykalman mean:", up-op) |
---|
174 | print("packet_rtt mean:", numpy.mean([s[0]-s[1] for s in m])) |
---|
175 | #up = numpy.mean([m[2] for m in smoothed_state_means]) |
---|
176 | #op = numpy.mean([m[3] for m in smoothed_state_means]) |
---|
177 | #print("tsval_rtt pykalman final:", smoothed_state_means[-1][2]-smoothed_state_means[-1][3]) |
---|
178 | #print("tsval_rtt pykalman mean:", up-op) |
---|
179 | #print("tsval_rtt mean:", numpy.mean([s[2]-s[3] for s in m])) |
---|
180 | |
---|
181 | for offset in range(0,len(null_measurements)+num_obs,num_obs): |
---|
182 | start=time.time() |
---|
183 | m = null_measurements[offset:offset+num_obs] |
---|
184 | #params['initial_state_mean']=[quadsummary([s[0] for s in m]), |
---|
185 | # quadsummary([s[1] for s in m]), |
---|
186 | # numpy.mean([s[2] for s in m]), |
---|
187 | # numpy.mean([s[3] for s in m])] |
---|
188 | kf = KalmanFilter(n_dim_obs=4, n_dim_state=4, **params) |
---|
189 | (smoothed_state_means, smoothed_state_covariances) = kf.smooth(m) |
---|
190 | up = numpy.mean([m[0] for m in smoothed_state_means]) |
---|
191 | op = numpy.mean([m[1] for m in smoothed_state_means]) |
---|
192 | #print("null packet_rtt pykalman final:", smoothed_state_means[-1][0]-smoothed_state_means[-1][1]) |
---|
193 | print("null packet_rtt pykalman mean:", up-op) |
---|
194 | print("null packet_rtt mean:", numpy.mean([s[0]-s[1] for s in m])) |
---|
195 | #up = numpy.mean([m[2] for m in smoothed_state_means]) |
---|
196 | #op = numpy.mean([m[3] for m in smoothed_state_means]) |
---|
197 | #print("null tsval_rtt pykalman final:", smoothed_state_means[-1][2]-smoothed_state_means[-1][3]) |
---|
198 | #print("null tsval_rtt pykalman mean:", up-op) |
---|
199 | #print("null tsval_rtt mean:", numpy.mean([s[2]-s[3] for s in m])) |
---|
200 | |
---|
201 | |
---|
202 | |
---|
203 | echo_vm_5k={'initial_state_covariance': [[33599047.5, |
---|
204 | -18251285.25, |
---|
205 | 3242535690.59375, |
---|
206 | -8560730487.84375], |
---|
207 | [-18251285.25, |
---|
208 | 9914252.3125, |
---|
209 | -1761372688.59375, |
---|
210 | 4650260880.1875], |
---|
211 | [3242535690.59375, |
---|
212 | -1761372688.59375, |
---|
213 | 312926663745.03125, |
---|
214 | -826168494791.7188], |
---|
215 | [-8560730487.84375, |
---|
216 | 4650260880.1875, |
---|
217 | -826168494791.7188, |
---|
218 | 2181195982530.4688]], |
---|
219 | 'initial_state_mean': [12939012.5625, |
---|
220 | 12934563.71875, |
---|
221 | 13134751.608, |
---|
222 | 13138990.9985], |
---|
223 | 'observation_covariance': [[11960180434.411114, |
---|
224 | 4760272534.795976, |
---|
225 | 8797551081.431936, |
---|
226 | 6908794128.927051], |
---|
227 | [4760272534.795962, |
---|
228 | 12383598172.428213, |
---|
229 | 5470747537.2599745, |
---|
230 | 11252625555.297853], |
---|
231 | [8797551081.431955, |
---|
232 | 5470747537.2601185, |
---|
233 | 1466222848395.7058, |
---|
234 | 72565713883.12643], |
---|
235 | [6908794128.927095, |
---|
236 | 11252625555.297981, |
---|
237 | 72565713883.12654, |
---|
238 | 1519760903943.507]], |
---|
239 | 'observation_matrices': [[1.4255288693095167, |
---|
240 | -0.4254638445329988, |
---|
241 | 0.0003406844036817347, |
---|
242 | -0.0005475021956726778], |
---|
243 | [-0.46467270827589857, |
---|
244 | 1.4654311778340343, |
---|
245 | -0.0003321330280128265, |
---|
246 | -0.0002853945703691352], |
---|
247 | [-0.2644570970067974, |
---|
248 | -0.33955835481495455, |
---|
249 | 1.7494161615202275, |
---|
250 | -0.15394117603733548], |
---|
251 | [-0.3419097544041847, |
---|
252 | -0.23992883666045373, |
---|
253 | -0.15587790880447727, |
---|
254 | 1.7292393175137022]], |
---|
255 | 'observation_offsets': [165.2279084503762, |
---|
256 | 157.76807691937614, |
---|
257 | 168.4235495099334, |
---|
258 | 225.33433430227353], |
---|
259 | 'transition_covariance': [[2515479496.145993, |
---|
260 | -401423541.70620924, |
---|
261 | 1409951418.1627903, |
---|
262 | 255932902.74454522], |
---|
263 | [-401423541.706214, |
---|
264 | 2744353887.676857, |
---|
265 | 1162316.2019491254, |
---|
266 | 1857251491.3987627], |
---|
267 | [1409951418.1628358, |
---|
268 | 1162316.2020361447, |
---|
269 | 543279068599.8229, |
---|
270 | -39399311190.5746], |
---|
271 | [255932902.74459982, |
---|
272 | 1857251491.398838, |
---|
273 | -39399311190.574585, |
---|
274 | 537826124257.5266]], |
---|
275 | 'transition_matrices': [[0.52163952865412, |
---|
276 | 0.47872618354122665, |
---|
277 | -0.0004322286766109684, |
---|
278 | 0.00017293351811531466], |
---|
279 | [0.5167436693545113, |
---|
280 | 0.48319044922845933, |
---|
281 | 7.765428142114672e-05, |
---|
282 | -0.00021518950285326355], |
---|
283 | [0.2091705950622469, |
---|
284 | 0.41051399729482796, |
---|
285 | 0.19341113299389256, |
---|
286 | 0.19562916616052917], |
---|
287 | [0.368592004009912, |
---|
288 | 0.22263632461118732, |
---|
289 | 0.20756792378812872, |
---|
290 | 0.20977025833570906]], |
---|
291 | 'transition_offsets': [592.5708159274, |
---|
292 | 583.3804671015271, |
---|
293 | 414.4187239098291, |
---|
294 | 562.166786712371]} |
---|
295 | |
---|
296 | echo_vm_5k={'initial_state_covariance': [[0.375, 0.0, 0.0, 0.0], |
---|
297 | [0.0, 0.375, 0.0, 0.0], |
---|
298 | [0.0, 0.0, 0.375, 0.0], |
---|
299 | [0.0, 0.0, 0.0, 0.375]], |
---|
300 | 'initial_state_mean': [15997944.198361743, |
---|
301 | 16029825.435899183, |
---|
302 | 17093077.26228404, |
---|
303 | 17524263.088803563], |
---|
304 | 'observation_covariance': [[36572556646.179054, |
---|
305 | 21816054953.37006, |
---|
306 | 31144379008.310543, |
---|
307 | 19651005729.823025], |
---|
308 | [21816054953.372543, |
---|
309 | 440428106325.20325, |
---|
310 | 41103447776.740585, |
---|
311 | 427146570672.51227], |
---|
312 | [31144379008.31037, |
---|
313 | 41103447776.74027, |
---|
314 | 3280009435458.6953, |
---|
315 | 458734528073.65686], |
---|
316 | [19651005729.82234, |
---|
317 | 427146570672.5109, |
---|
318 | 458734528073.6557, |
---|
319 | 3769493190697.773]], |
---|
320 | 'observation_matrices': [[1.0248853427592337, |
---|
321 | -0.031198859962501047, |
---|
322 | 0.001613706836380402, |
---|
323 | 0.004720209443291878], |
---|
324 | [-0.8604422900368718, |
---|
325 | 1.8583369609057172, |
---|
326 | -0.0022646214457040514, |
---|
327 | 0.004437933935378169], |
---|
328 | [-0.5814771409524866, |
---|
329 | 0.22228184387142846, |
---|
330 | 1.6259599749174072, |
---|
331 | -0.271594798325566], |
---|
332 | [-0.5862601003257453, |
---|
333 | 0.2598285939005791, |
---|
334 | -0.28286590143513024, |
---|
335 | 1.604087079832425]], |
---|
336 | 'observation_offsets': [1979.4518332096984, |
---|
337 | 1889.3380163762793, |
---|
338 | 2132.9112026744906, |
---|
339 | 1750.7759421584785], |
---|
340 | 'transition_covariance': [[6176492087.271547, |
---|
341 | 762254719.4171592, |
---|
342 | 4584288694.652873, |
---|
343 | 3044796192.4357214], |
---|
344 | [762254719.4185101, |
---|
345 | 173302376079.4761, |
---|
346 | 5261303152.757347, |
---|
347 | 167562483383.9925], |
---|
348 | [4584288694.651718, |
---|
349 | 5261303152.755746, |
---|
350 | 1056156956874.4131, |
---|
351 | -115859156952.07962], |
---|
352 | [3044796192.434162, |
---|
353 | 167562483383.9901, |
---|
354 | -115859156952.08018, |
---|
355 | 1225788436266.3086]], |
---|
356 | 'transition_matrices': [[0.9673912485796876, |
---|
357 | 0.03252962227543321, |
---|
358 | 0.0006756067792537124, |
---|
359 | -0.0006566638567164773], |
---|
360 | [0.9548761966068113, |
---|
361 | 0.03841774395880293, |
---|
362 | 0.00426067282319309, |
---|
363 | 0.002303362691861821], |
---|
364 | [0.6215040230859188, |
---|
365 | -0.2584476837756142, |
---|
366 | 0.3176491193420503, |
---|
367 | 0.3241682768126566], |
---|
368 | [0.6634028281470279, |
---|
369 | -0.33548335246018723, |
---|
370 | 0.3298144902195048, |
---|
371 | 0.3475836278392421]], |
---|
372 | 'transition_offsets': [1751.3049487348183, |
---|
373 | 1764.989515773476, |
---|
374 | 1986.8405778425586, |
---|
375 | 2232.830254345267]} |
---|
376 | #testKalman4D(echo_vm_5k) |
---|
377 | |
---|
378 | |
---|
379 | |
---|
380 | def testKalman(params=None): |
---|
381 | from pykalman import AdditiveUnscentedKalmanFilter,KalmanFilter |
---|
382 | train = db.subseries('train','long', offset=0) |
---|
383 | test = db.subseries('test','long', offset=0) |
---|
384 | measurements = numpy.asarray([(s['unusual_packet'],s['other_packet']) for s in (train+test)]) |
---|
385 | |
---|
386 | #kf = KalmanFilter(transition_matrices = [[1, 1], [0, 1]], observation_matrices = [[0.1, 0.5], [-0.3, 0.0]]) |
---|
387 | kf = KalmanFilter(n_dim_obs=2, n_dim_state=2, |
---|
388 | initial_state_mean=[quadsummary([s['unusual_packet'] for s in train]), |
---|
389 | quadsummary([s['other_packet'] for s in train])]) |
---|
390 | #kf = AdditiveUnscentedKalmanFilter(n_dim_obs=2, n_dim_state=2) |
---|
391 | |
---|
392 | if params == None: |
---|
393 | start=time.time() |
---|
394 | kf = kf.em(measurements[0:len(train)], n_iter=10, |
---|
395 | em_vars=('transition_matrices', |
---|
396 | 'observation_matrices', |
---|
397 | 'transition_offsets', |
---|
398 | 'observation_offsets', |
---|
399 | 'transition_covariance', |
---|
400 | 'observation_covariance', |
---|
401 | 'initial_state_covariance')) |
---|
402 | params = {'transition_matrices': kf.transition_matrices.tolist(), |
---|
403 | 'observation_matrices': kf.observation_matrices.tolist(), |
---|
404 | 'transition_offsets': kf.transition_offsets.tolist(), |
---|
405 | 'observation_offsets': kf.observation_offsets.tolist(), |
---|
406 | 'transition_covariance': kf.transition_covariance.tolist(), |
---|
407 | 'observation_covariance': kf.observation_covariance.tolist(), |
---|
408 | 'initial_state_mean': kf.initial_state_mean.tolist(), |
---|
409 | 'initial_state_covariance': kf.initial_state_covariance.tolist()} |
---|
410 | print("Learned Params:\n") |
---|
411 | import pprint |
---|
412 | pprint.pprint(params) |
---|
413 | print("pykalman em time: %f" % (time.time()-start)) |
---|
414 | |
---|
415 | #kf = KalmanFilter(n_dim_obs=2, n_dim_state=2, **params) |
---|
416 | |
---|
417 | num_obs=10000 |
---|
418 | for offset in range(50000,100000+num_obs,num_obs): |
---|
419 | start=time.time() |
---|
420 | kf = KalmanFilter(n_dim_obs=2, n_dim_state=2, **params) |
---|
421 | m = measurements[offset:offset+num_obs] |
---|
422 | (smoothed_state_means, smoothed_state_covariances) = kf.smooth(m) |
---|
423 | print("pykalman smooth time: %f" % (time.time()-start)) |
---|
424 | up = numpy.mean([m[0] for m in smoothed_state_means]) |
---|
425 | op = numpy.mean([m[1] for m in smoothed_state_means]) |
---|
426 | print("packet_rtt pykalman final:", smoothed_state_means[-1][0]-smoothed_state_means[-1][1]) |
---|
427 | print("packet_rtt pykalman mean:", up-op) |
---|
428 | print("packet_rtt mean:", numpy.mean([s[0]-s[1] for s in m])) |
---|
429 | |
---|
430 | |
---|
431 | five_iter = {'observation_offsets': [-54.53185823, -55.25219184], |
---|
432 | 'observation_covariance': [[ 1.15059170e+10, 4.36743765e+09], |
---|
433 | [ 4.36743765e+09, 1.19410313e+10]], |
---|
434 | 'initial_state_mean': [ 12939012.5625 , 12934563.71875], |
---|
435 | 'transition_covariance': [[ 2.98594543e+09, 6.86355073e+07], |
---|
436 | [ 6.86355073e+07, 3.21368699e+09]], |
---|
437 | 'initial_state_covariance': [[ 2.36836696e+09, 1.63195635e+09], |
---|
438 | [ 1.63195635e+09, 1.12452233e+09]], |
---|
439 | 'transition_offsets': [ 343.69740217, 338.5042467 ], |
---|
440 | 'observation_matrices': [[ 1.42539895, -0.4255261 ], |
---|
441 | [-0.46280375, 1.46295189]], |
---|
442 | 'transition_matrices': [[ 0.56151623, 0.4385931 ], |
---|
443 | [ 0.47309189, 0.52673508]]} |
---|
444 | ten_iter = {'initial_state_covariance': [[229936928.28125, 41172601.0], |
---|
445 | [41172601.0, 7372383.46875]], |
---|
446 | 'initial_state_mean': [12939012.5625, 12934563.71875], |
---|
447 | 'observation_covariance': [[11958914107.88334, 4761048283.066559], |
---|
448 | [4761048283.066557, 12388186543.42032]], |
---|
449 | 'observation_matrices': [[1.4258395826727792, -0.42598392357467674], |
---|
450 | [-0.4647443890462455, 1.4648767294384015]], |
---|
451 | 'observation_offsets': [165.409715349344, 157.96206130876212], |
---|
452 | 'transition_covariance': [[2515594742.7187943, -401728959.41375697], |
---|
453 | [-401728959.41375697, 2743831805.402682]], |
---|
454 | 'transition_matrices': [[0.521306461057975, 0.47879632652984583], |
---|
455 | [0.5167881285851763, 0.483006520280469]], |
---|
456 | 'transition_offsets': [592.4419187566978, 583.2272403965366]} |
---|
457 | #testKalman(ten_iter) |
---|
458 | |
---|
459 | |
---|
460 | def getTCPTSPrecision(): |
---|
461 | cursor = db.conn.cursor() |
---|
462 | query="""SELECT tcpts_mean FROM meta""" |
---|
463 | cursor.execute(query) |
---|
464 | row = cursor.fetchone() |
---|
465 | if row: |
---|
466 | return row[0] |
---|
467 | return None |
---|
468 | |
---|
469 | |
---|
470 | def tsFilteredHistogram(): |
---|
471 | tcpts_precision = getTCPTSPrecision() |
---|
472 | |
---|
473 | num_bins = 500 |
---|
474 | all = db.subseries('train','long')+db.subseries('test','long') |
---|
475 | diffs = [s['unusual_packet']-s['other_packet'] for s in all] |
---|
476 | ts0_diffs = [s['unusual_packet']-s['other_packet'] for s in all if s['unusual_tsval']-s['other_tsval'] == 0] |
---|
477 | ts1_diffs = [s['unusual_packet']-s['other_packet'] for s in all if abs(s['unusual_tsval']-s['other_tsval']) > 0] |
---|
478 | ts2_diffs = [s['unusual_packet']-s['other_packet'] for s in all if abs(round((s['unusual_tsval']-s['other_tsval'])/tcpts_precision)) <= 1.0] |
---|
479 | |
---|
480 | ts_mode = statistics.mode([s['unusual_tsval'] for s in all]+[s['other_tsval'] for s in all]) |
---|
481 | ts_diff_mode = statistics.mode([s['unusual_tsval']-s['other_tsval'] for s in all]) |
---|
482 | ts_common_mode = [s['unusual_packet']-s['other_packet'] for s in all if s['unusual_tsval']<=ts_mode and s['other_tsval']<=ts_mode] |
---|
483 | ts_common_diff_mode = [s['unusual_packet']-s['other_packet'] for s in all if s['unusual_tsval']-s['other_tsval']==ts_diff_mode] |
---|
484 | |
---|
485 | print('packet_rtt diff quadsummary: %f' % quadsummary(diffs)) |
---|
486 | print('packet_rtt tsval diff=0 quadsummary: %f' % quadsummary(ts0_diffs)) |
---|
487 | print('packet_rtt tsval diff>0 quadsummary: %f' % quadsummary(ts1_diffs)) |
---|
488 | print('packet_rtt tsval diff<=1 quadsummary: %f' % quadsummary(ts2_diffs)) |
---|
489 | print('packet_rtt tsval mode quadsummary: %f' % quadsummary(ts_common_mode)) |
---|
490 | print(len(diffs), len(ts0_diffs)+len(ts1_diffs)) |
---|
491 | diffs.sort() |
---|
492 | cut_off_low = diffs[int(len(diffs)*0.005)] |
---|
493 | cut_off_high = diffs[int(len(diffs)*0.995)] |
---|
494 | |
---|
495 | plt.clf() |
---|
496 | # the histogram of the data |
---|
497 | n, bins, patches = plt.hist(diffs, num_bins, normed=0, color='black', histtype='step', alpha=0.8, |
---|
498 | range=(cut_off_low,cut_off_high), label='all') |
---|
499 | n, bins, patches = plt.hist(ts0_diffs, num_bins, normed=0, color='blue', histtype='step', alpha=0.8, |
---|
500 | range=(cut_off_low,cut_off_high), label='tsval diff=0') |
---|
501 | n, bins, patches = plt.hist(ts1_diffs, num_bins, normed=0, color='red', histtype='step', alpha=0.8, |
---|
502 | range=(cut_off_low,cut_off_high), label='tsval diff>0') |
---|
503 | n, bins, patches = plt.hist(ts2_diffs, num_bins, normed=0, color='orange', histtype='step', alpha=0.8, |
---|
504 | range=(cut_off_low,cut_off_high), label='tsval diff<=1') |
---|
505 | #n, bins, patches = plt.hist(ts_common_mode, num_bins, normed=0, color='green', histtype='step', alpha=0.8, |
---|
506 | # range=(cut_off_low,cut_off_high), label='tsval common mode') |
---|
507 | n, bins, patches = plt.hist(ts_common_diff_mode, num_bins, normed=0, color='green', histtype='step', alpha=0.8, |
---|
508 | range=(cut_off_low,cut_off_high), label='tsval common diff mode') |
---|
509 | plt.xlabel('RTT Difference') |
---|
510 | plt.ylabel('Probability') |
---|
511 | plt.title(r'Histogram - distribution of differences by tsval') |
---|
512 | |
---|
513 | # Tweak spacing to prevent clipping of ylabel |
---|
514 | plt.subplots_adjust(left=0.15) |
---|
515 | plt.legend() |
---|
516 | plt.show() |
---|
517 | #plt.savefig('paper/graphs/dists-vs-dist-of-diffs2.svg') |
---|
518 | |
---|
519 | #tsFilteredHistogram() |
---|
520 | |
---|
521 | |
---|
522 | |
---|
523 | |
---|
524 | |
---|
525 | #all_data = longs+shorts |
---|
526 | #all_data.sort() |
---|
527 | #cut_off_low = all_data[0] |
---|
528 | #cut_off_high = all_data[int(len(all_data)*0.997)] |
---|
529 | |
---|
530 | |
---|
531 | def plotSingleProbe(probe_id=None): |
---|
532 | if probe_id == None: |
---|
533 | cursor = db.conn.cursor() |
---|
534 | query="""SELECT probe_id FROM analysis WHERE suspect='' ORDER BY probe_id DESC limit 1 OFFSET 10""" |
---|
535 | cursor.execute(query) |
---|
536 | probe_id = cursor.fetchone()[0] |
---|
537 | |
---|
538 | cursor = db.conn.cursor() |
---|
539 | query="""SELECT observed,payload_len FROM packets WHERE probe_id=? AND sent=1""" |
---|
540 | cursor.execute(query, (probe_id,)) |
---|
541 | pkts = cursor.fetchall() |
---|
542 | sent_payload = [row[0] for row in pkts if row[1] != 0] |
---|
543 | sent_other = [row[0] for row in pkts if row[1] == 0] |
---|
544 | |
---|
545 | query="""SELECT observed,payload_len FROM packets WHERE probe_id=? AND sent=0""" |
---|
546 | cursor.execute(query, (probe_id,)) |
---|
547 | pkts = cursor.fetchall() |
---|
548 | rcvd_payload = [row[0] for row in pkts if row[1] != 0] |
---|
549 | rcvd_other = [row[0] for row in pkts if row[1] == 0] |
---|
550 | |
---|
551 | #query="""SELECT reported,time_of_day FROM probes WHERE id=?""" |
---|
552 | #cursor.execute(query, (probe_id,)) |
---|
553 | #reported,tod = cursor.fetchone() |
---|
554 | #userspace_times = [sent_times[0]-reported/3.0, sent_times[0]+reported] |
---|
555 | |
---|
556 | print("single probe counts:",len(sent_payload),len(sent_other),len(rcvd_payload),len(rcvd_other)) |
---|
557 | plt.clf() |
---|
558 | plt.title("Single HTTP Request - Packet Times") |
---|
559 | sp = plt.eventplot(sent_payload, colors=('red',), lineoffsets=8, linewidths=2, alpha=0.6,label='sent') |
---|
560 | so = plt.eventplot(sent_other, colors=('red',), lineoffsets=6, linewidths=2, alpha=0.6,label='sent') |
---|
561 | rp = plt.eventplot(rcvd_payload, colors=('blue',), lineoffsets=4, linewidths=2, alpha=0.6,label='received') |
---|
562 | ro = plt.eventplot(rcvd_other, colors=('blue',), lineoffsets=2, linewidths=2, alpha=0.6,label='received') |
---|
563 | #plt.legend((s,r), ('sent','received')) |
---|
564 | #plt.savefig('../img/http-packet-times.svg') |
---|
565 | plt.show() |
---|
566 | |
---|
567 | #plotSingleProbe() |
---|
568 | |
---|
569 | |
---|
570 | def graphTestResults(): |
---|
571 | plt.clf() |
---|
572 | plt.title("Test Results") |
---|
573 | plt.xlabel('sample size') |
---|
574 | plt.ylabel('error rate') |
---|
575 | legend = [] |
---|
576 | colors = ['red','blue','green','purple','orange','black','brown'] |
---|
577 | color_id = 0 |
---|
578 | |
---|
579 | cursor = db.conn.cursor() |
---|
580 | query = """ |
---|
581 | SELECT classifier FROM classifier_results GROUP BY classifier ORDER BY classifier; |
---|
582 | """ |
---|
583 | cursor.execute(query) |
---|
584 | classifiers = [] |
---|
585 | for c in cursor: |
---|
586 | classifiers.append(c[0]) |
---|
587 | |
---|
588 | max_obs = 0 |
---|
589 | for classifier in classifiers: |
---|
590 | query=""" |
---|
591 | SELECT params FROM classifier_results |
---|
592 | WHERE trial_type='test' |
---|
593 | AND classifier=:classifier |
---|
594 | AND (false_positives+false_negatives)/2.0 < 5.0 |
---|
595 | ORDER BY num_observations,(false_positives+false_negatives) |
---|
596 | LIMIT 1 |
---|
597 | """ |
---|
598 | cursor.execute(query, {'classifier':classifier}) |
---|
599 | row = cursor.fetchone() |
---|
600 | if row == None: |
---|
601 | query=""" |
---|
602 | SELECT params FROM classifier_results |
---|
603 | WHERE trial_type='test' and classifier=:classifier |
---|
604 | ORDER BY (false_positives+false_negatives),num_observations |
---|
605 | LIMIT 1 |
---|
606 | """ |
---|
607 | cursor.execute(query, {'classifier':classifier}) |
---|
608 | row = cursor.fetchone() |
---|
609 | if row == None: |
---|
610 | sys.stderr.write("WARN: couldn't find test results for classifier '%s'.\n" % classifier) |
---|
611 | continue |
---|
612 | |
---|
613 | best_params = row[0] |
---|
614 | query=""" |
---|
615 | SELECT num_observations,(false_positives+false_negatives)/2.0 FROM classifier_results |
---|
616 | WHERE trial_type='test' |
---|
617 | AND classifier=:classifier |
---|
618 | AND params=:params |
---|
619 | ORDER BY num_observations |
---|
620 | """ |
---|
621 | cursor.execute(query, {'classifier':classifier,'params':best_params}) |
---|
622 | |
---|
623 | num_obs = [] |
---|
624 | performance = [] |
---|
625 | for row in cursor: |
---|
626 | max_obs = max(max_obs, row[0]) |
---|
627 | num_obs.append(row[0]) |
---|
628 | performance.append(row[1]) |
---|
629 | #print(num_obs,performance) |
---|
630 | path = plt.scatter(num_obs, performance, color=colors[color_id], s=4, alpha=0.8, linewidths=3.0) |
---|
631 | plt.plot(num_obs, performance, color=colors[color_id], alpha=0.8) |
---|
632 | legend.append((classifier,path)) |
---|
633 | color_id = (color_id+1) % len(colors) |
---|
634 | |
---|
635 | plt.legend([l[1] for l in legend], [l[0] for l in legend], scatterpoints=1, fontsize='xx-small') |
---|
636 | plt.plot([0, max_obs], [5.0, 5.0], "k--") |
---|
637 | plt.show() |
---|
638 | |
---|
639 | graphTestResults() |
---|
640 | |
---|
641 | sys.exit(0) |
---|
642 | |
---|
643 | plt.clf() |
---|
644 | plt.title("Packet RTT over time") |
---|
645 | plt.xlabel('Time of Day') |
---|
646 | plt.ylabel('RTT') |
---|
647 | s = plt.scatter([t for t,rtt in short_overtime], [rtt for t,rtt in short_overtime], s=1, color='red', alpha=0.6) |
---|
648 | l = plt.scatter([t for t,rtt in long_overtime], [rtt for t,rtt in long_overtime], s=1, color='blue', alpha=0.6) |
---|
649 | d = plt.scatter([t for t,rtt in diff_overtime], [rtt for t,rtt in diff_overtime], s=1, color='purple', alpha=0.6) |
---|
650 | plt.legend((s,l,d), ('short','long','difference'), scatterpoints=1) |
---|
651 | #plt.savefig('paper/figures/comcast-powerboost1.png') |
---|
652 | plt.show() |
---|
653 | |
---|
654 | |
---|
655 | |
---|
656 | plt.clf() |
---|
657 | plt.title("Simple HTTP Request") |
---|
658 | plt.xlabel('Time of Day') |
---|
659 | plt.ylabel('') |
---|
660 | s = plt.scatter(sent_times, [2]*len(sent_times), s=3, color='red', alpha=0.9) |
---|
661 | r = plt.scatter(rcvd_times, [1]*len(rcvd_times), s=3, color='blue', alpha=0.9) |
---|
662 | plt.legend((s,r), ('sent','received'), scatterpoints=1) |
---|
663 | plt.show() |
---|
664 | |
---|
665 | sys.exit(0) |
---|
666 | short_overtime,long_overtime,diff_overtime = None,None,None |
---|
667 | |
---|
668 | |
---|
669 | num_bins = 300 |
---|
670 | reported_diffs.sort() |
---|
671 | cut_off_low = reported_diffs[int(len(diffs)*0.003)] |
---|
672 | cut_off_high = reported_diffs[int(len(diffs)*0.997)] |
---|
673 | |
---|
674 | plt.clf() |
---|
675 | # the histogram of the data |
---|
676 | n, bins, patches = plt.hist(reported_diffs, num_bins, normed=1, color='black', histtype='step', alpha=0.8, |
---|
677 | range=(cut_off_low,cut_off_high)) |
---|
678 | plt.xlabel('RTT Difference') |
---|
679 | plt.ylabel('Probability') |
---|
680 | plt.title(r'Histogram - distribution of differences') |
---|
681 | |
---|
682 | # Tweak spacing to prevent clipping of ylabel |
---|
683 | plt.subplots_adjust(left=0.15) |
---|
684 | #plt.legend() |
---|
685 | plt.show() |
---|
686 | #plt.savefig('paper/graphs/dists-vs-dist-of-diffs2.svg') |
---|
687 | |
---|
688 | |
---|
689 | |
---|
690 | |
---|
691 | num_bins = 300 |
---|
692 | diffs.sort() |
---|
693 | cut_off_low = diffs[int(len(diffs)*0.003)] |
---|
694 | cut_off_high = diffs[int(len(diffs)*0.997)] |
---|
695 | |
---|
696 | plt.clf() |
---|
697 | # the histogram of the data |
---|
698 | n, bins, patches = plt.hist(diffs, num_bins, normed=1, color='purple', histtype='step', alpha=0.8, |
---|
699 | range=(cut_off_low,cut_off_high)) |
---|
700 | plt.xlabel('RTT Difference') |
---|
701 | plt.ylabel('Probability') |
---|
702 | plt.title(r'Histogram - distribution of differences') |
---|
703 | |
---|
704 | # Tweak spacing to prevent clipping of ylabel |
---|
705 | plt.subplots_adjust(left=0.15) |
---|
706 | #plt.legend() |
---|
707 | plt.show() |
---|
708 | #plt.savefig('paper/graphs/dists-vs-dist-of-diffs2.svg') |
---|
709 | |
---|
710 | sys.exit(0) |
---|
711 | |
---|
712 | |
---|
713 | |
---|
714 | num_bins = 150 |
---|
715 | # the histogram of the data |
---|
716 | n, bins, patches = plt.hist((shorts,longs), num_bins, normed=1, label=['short', 'long'], color=['red','blue'], histtype='step', alpha=0.8, |
---|
717 | range=(cut_off_low,cut_off_high)) |
---|
718 | #n, bins, patches = plt.hist(shorts2+longs2, num_bins, normed=1, facecolor='blue', histtype='step', alpha=0.3) |
---|
719 | # add a 'best fit' line |
---|
720 | #y = mlab.normpdf(bins, mu, sigma) |
---|
721 | #plt.plot(bins, y, 'r--') |
---|
722 | plt.xlabel('packet_rtt') |
---|
723 | plt.ylabel('Probability') |
---|
724 | plt.title(r'Histogram - RTT short and long') |
---|
725 | |
---|
726 | # Tweak spacing to prevent clipping of ylabel |
---|
727 | plt.subplots_adjust(left=0.15) |
---|
728 | plt.legend() |
---|
729 | #plt.show() |
---|
730 | plt.savefig('paper/figures/comcast-powerboost2.svg') |
---|
731 | |
---|
732 | |
---|
733 | |
---|
734 | |
---|
735 | num_trials = 200 |
---|
736 | |
---|
737 | |
---|
738 | subsample_sizes = (50,150,300,500,700,1000,2000,3000,5000,7000,10000,15000,20000) |
---|
739 | estimator = functools.partial(boxTest, 0.07, 0.08) |
---|
740 | performance = [] |
---|
741 | for subsample_size in subsample_sizes: |
---|
742 | estimates = bootstrap(derived, subsample_size, num_trials, estimator) |
---|
743 | performance.append(100.0*len([e for e in estimates if e == 1])/num_trials) |
---|
744 | |
---|
745 | null_performance = [] |
---|
746 | for subsample_size in subsample_sizes: |
---|
747 | null_estimates = bootstrap(null_derived, subsample_size, num_trials, estimator) |
---|
748 | null_performance.append(100.0*len([e for e in null_estimates if e == 0])/num_trials) |
---|
749 | |
---|
750 | plt.clf() |
---|
751 | plt.title("boxTest bootstrap") |
---|
752 | plt.xlabel('sample size') |
---|
753 | plt.ylabel('performance') |
---|
754 | plt.scatter(subsample_sizes, performance, s=2, color='red', alpha=0.6) |
---|
755 | plt.scatter(subsample_sizes, null_performance, s=2, color='blue', alpha=0.6) |
---|
756 | plt.show() |
---|
757 | |
---|
758 | |
---|
759 | |
---|
760 | subsample_sizes = (50,150,300,400,500,700,1000,2000,3000,4000,5000,7000,10000) |
---|
761 | estimator = diffMedian |
---|
762 | performance = [] |
---|
763 | for subsample_size in subsample_sizes: |
---|
764 | estimates = bootstrap(derived, subsample_size, num_trials, estimator) |
---|
765 | performance.append(100.0*len([e for e in estimates if e > expected_mean*0.9 and e < expected_mean*1.1])/num_trials) |
---|
766 | |
---|
767 | plt.clf() |
---|
768 | plt.title("diff median bootstrap") |
---|
769 | plt.xlabel('sample size') |
---|
770 | plt.ylabel('performance') |
---|
771 | plt.scatter(subsample_sizes, performance, s=1, color='red', alpha=0.6) |
---|
772 | plt.show() |
---|
773 | |
---|
774 | |
---|
775 | |
---|
776 | |
---|
777 | subsample_sizes = (50,150,300,400,500,700,1000,2000,3000,4000,5000,7000,10000) |
---|
778 | weight_funcs = (linearWeights, prunedWeights) |
---|
779 | for wf in weight_funcs: |
---|
780 | estimator = functools.partial(estimateMean, hypotenuse, wf, 0.40) |
---|
781 | performance = [] |
---|
782 | for subsample_size in subsample_sizes: |
---|
783 | estimates = bootstrap(derived, subsample_size, num_trials, estimator) |
---|
784 | performance.append(100.0*len([e for e in estimates if e > expected_mean*0.9 and e < expected_mean*1.1])/num_trials) |
---|
785 | |
---|
786 | plt.clf() |
---|
787 | plt.title(repr(wf)) |
---|
788 | plt.xlabel('sample size') |
---|
789 | plt.ylabel('performance') |
---|
790 | plt.scatter(subsample_sizes, performance, s=1, color='red', alpha=0.6) |
---|
791 | plt.show() |
---|
792 | |
---|
793 | |
---|
794 | |
---|
795 | num_bins = 300 |
---|
796 | # the histogram of the data |
---|
797 | n, bins, patches = plt.hist((tsshorts,tslongs), num_bins, normed=1, label=['short', 'long'], color=['red','blue'], histtype='step', alpha=0.8) |
---|
798 | #n, bins, patches = plt.hist(shorts2+longs2, num_bins, normed=1, facecolor='blue', histtype='step', alpha=0.3) |
---|
799 | # add a 'best fit' line |
---|
800 | #y = mlab.normpdf(bins, mu, sigma) |
---|
801 | #plt.plot(bins, y, 'r--') |
---|
802 | plt.xlabel('packet_rtt') |
---|
803 | plt.ylabel('Probability') |
---|
804 | plt.title(r'Histogram - tsval_rtt short vs long') |
---|
805 | |
---|
806 | # Tweak spacing to prevent clipping of ylabel |
---|
807 | plt.subplots_adjust(left=0.15) |
---|
808 | plt.legend() |
---|
809 | plt.show() |
---|
810 | |
---|
811 | |
---|
812 | |
---|
813 | |
---|
814 | #### |
---|
815 | #trust_methods = [min,max,sum,difference,product] |
---|
816 | trust_methods = [sum,product,hypotenuse] |
---|
817 | colors = ['red','blue','green','purple','orange','black'] |
---|
818 | weight_methods = [prunedWeights, linearWeights] |
---|
819 | alphas = [i/100.0 for i in range(0,100,2)] |
---|
820 | |
---|
821 | |
---|
822 | |
---|
823 | |
---|
824 | plt.clf() |
---|
825 | plt.title(r'Trust Method Comparison - Linear') |
---|
826 | plt.xlabel('Alpha') |
---|
827 | plt.ylabel('Mean error') |
---|
828 | paths = [] |
---|
829 | for tm in trust_methods: |
---|
830 | trust = trustValues(derived, tm) |
---|
831 | series = [] |
---|
832 | for alpha in alphas: |
---|
833 | weights = linearWeights(derived, trust, alpha) |
---|
834 | series.append(weightedMean(derived, weights) - expected_mean) |
---|
835 | |
---|
836 | paths.append(plt.scatter(alphas, series, s=1, color=colors[len(paths)],alpha=0.6)) |
---|
837 | |
---|
838 | plt.legend(paths, [repr(tm) for tm in trust_methods], scatterpoints=1) |
---|
839 | plt.show() |
---|
840 | |
---|
841 | |
---|
842 | |
---|
843 | plt.clf() |
---|
844 | plt.title(r'Trust Method Comparison - Pruned') |
---|
845 | plt.xlabel('Alpha') |
---|
846 | plt.ylabel('Mean error') |
---|
847 | paths = [] |
---|
848 | for tm in trust_methods: |
---|
849 | trust = trustValues(derived, tm) |
---|
850 | series = [] |
---|
851 | for alpha in alphas: |
---|
852 | weights = prunedWeights(derived, trust, alpha) |
---|
853 | series.append(weightedMean(derived, weights) - expected_mean) |
---|
854 | |
---|
855 | paths.append(plt.scatter(alphas, series, s=1, color=colors[len(paths)],alpha=0.6)) |
---|
856 | |
---|
857 | plt.legend(paths, [repr(tm) for tm in trust_methods], scatterpoints=1) |
---|
858 | plt.show() |
---|
859 | |
---|
860 | |
---|
861 | sys.exit(0) |
---|
862 | |
---|
863 | plt.clf() |
---|
864 | plt.title(r'Trust Method Comparison - Inverted') |
---|
865 | plt.xlabel('Alpha') |
---|
866 | plt.ylabel('Mean error') |
---|
867 | paths = [] |
---|
868 | for tm in trust_methods: |
---|
869 | trust = trustValues(derived, tm) |
---|
870 | series = [] |
---|
871 | for alpha in alphas: |
---|
872 | weights = invertedWeights(derived, trust, alpha) |
---|
873 | series.append(weightedMean(derived, weights) - expected_mean) |
---|
874 | |
---|
875 | paths.append(plt.scatter(alphas, series, s=1, color=colors[len(paths)],alpha=0.6)) |
---|
876 | |
---|
877 | plt.legend(paths, [repr(tm) for tm in trust_methods], scatterpoints=1) |
---|
878 | plt.show() |
---|
879 | |
---|
880 | |
---|
881 | plt.clf() |
---|
882 | plt.title(r'Trust Method Comparison - Arctangent') |
---|
883 | plt.xlabel('Alpha') |
---|
884 | plt.ylabel('Mean error') |
---|
885 | paths = [] |
---|
886 | for tm in trust_methods: |
---|
887 | trust = trustValues(derived, tm) |
---|
888 | series = [] |
---|
889 | for alpha in alphas: |
---|
890 | weights = arctanWeights(derived, trust, alpha) |
---|
891 | series.append(weightedMean(derived, weights) - expected_mean) |
---|
892 | |
---|
893 | paths.append(plt.scatter(alphas, series, s=1, color=colors[len(paths)],alpha=0.6)) |
---|
894 | |
---|
895 | plt.legend(paths, [repr(tm) for tm in trust_methods], scatterpoints=1) |
---|
896 | plt.show() |
---|