Topic Modeling Results
MIKA supports multiple topic modeling algorthims and outputs results in a standard format. Results are typically saved with topic numbers, topic words, documents per topic, and best document per topic.
Just the topic model results can be saved, as well as a full set of results with a taxonomy, document-topic distribution, and coherence. To save just the topics:
tm.save_bert_topics(), tm.save_lda_topics(), or tm.save_hlda_topics()
To save the full set of results:
tm.save_bert_results(), tm.save_lda_results(), or tm.save_hlda_results()
topic number |
number of documents in topic |
topic words |
total number of words |
number of words |
best document |
coherence |
documents |
|---|---|---|---|---|---|---|---|
0 |
218 |
jettison, crash, crash rescue, jettison load, rescue, jettison retardant, … |
1585 |
250 |
00-1147 |
0.805071926 |
[‘97-0077’, ‘98-0027’, ‘98-0116’, ‘98-0154’,…] |
1 |
80 |
silver city, silver, trouble shot, shot, city, trouble, technician, crux, radio technician, … |
444 |
222 |
00-0267 |
0.825701749 |
[‘95-0036’, ‘95-0206’, ‘95-0262’, ‘97-0206’,,…] |
2 |
857 |
taxi, ramp, parking, runway, park, taxiway, stop, pit, brake, wing, left, right, … |
9772 |
330 |
08-0457 |
0.764096785 |
[‘95-0006’, ‘95-0024’, ‘95-0035’, ‘95-0216’, …] |
3 |
2692 |
tree, bucket, water, dip, site, drop, top, line, dip site, damage, water drop, … |
38772 |
276 |
12-0768 |
0.696187669 |
[‘95-0002’, ‘95-0013’, ‘95-0039’, ‘95-0042’, …] |
4 |
153 |
spring, hot spring, nothing ordinary, ordinary, warm, warm spring, … |
866 |
282 |
02-0834 |
0.846775067 |
[‘95-0028’, ‘95-0029’, ‘95-0236’, ‘97-0192’,…] |
5 |
332 |
caution, master caution, master, illuminate, light, light illuminate, caution light, … |
2696 |
158 |
12-0501 |
0.843005717 |
[‘97-0075’, ‘98-0144’, ‘98-0206’, ‘98-0471’, …] |
6 |
157 |
ppe, wear, helmet, flight helmet, glove, nomex, suit, flight suit, proper ppe, … |
1255 |
253 |
12-0593 |
0.87565009 |
[‘95-0039’, ‘95-0118’, ‘95-0123’, ‘95-0142’,…] |
7 |
1162 |
tfr, intrusion, fly, drone, agl, south, law, air, enforcement, area, air attack, … |
14831 |
293 |
03-0231 |
0.66449779 |
[‘95-0002’, ‘95-0007’, ‘95-0014’, ‘95-0163’,…] |
topic level |
topic number |
parent |
number of documents in topic |
topic words |
number of words |
best lesson |
coherence |
|
|---|---|---|---|---|---|---|---|---|
0 |
0 |
0 |
-1 |
1639 |
time, flight, require, control, problem, perform, component, failure, data, however |
67747 |
2496 |
0.626159891 |
1 |
1 |
8 |
0 |
248 |
base reliability, prefer, reliability, implementation method, technical, test benefit, reliability prefer, rationale, benefit, technical rationale |
11052 |
547 |
0.761625791 |
2 |
1 |
9 |
0 |
103 |
tunnel, transonic, aerodynamic, test mach, tunnel blade, transonic tunnel, mach, deflection, blade, vane |
719 |
1264 |
0.940507549 |
3 |
1 |
10 |
0 |
296 |
management, project, lack, formal, manager, organization, contractor, request, risk, development |
5382 |
1368 |
0.767053002 |
4 |
1 |
11 |
0 |
206 |
ssme, oxidizer, pump, liquid, fuel, propellant, shape, erosion, ring, space shuttle |
3176 |
113 |
0.812935519 |
5 |
1 |
12 |
0 |
301 |
valve, tank, pressure, leak, supply, line, vent, nitrogen, vent line, water |
4261 |
745 |
0.782795066 |
6 |
1 |
13 |
0 |
74 |
state microgravity, first united, microgravity, injury, fire occur, damage, first shift, ignite, united, mile |
895 |
1710 |
0.869355899 |
7 |
1 |
14 |
0 |
62 |
breaker, effective maintainability benefit, base maintainability, recommend technique, circuit breaker, cost saving, technique number, effective maintainability, fault, saving |
659 |
1208 |
0.871555471 |
8 |
1 |
15 |
0 |
172 |
orbiter, brake, fall, position, hydraulic fluid, mast, pull, operator, smoke, thermal protection system |
1252 |
861 |
0.856068957 |
9 |
2 |
16 |
8 |
19 |
follow recommendation, torque analog, base legacy, need great hinge, necessary torque include, great hinge, redesign accommodate, system redesign digital, redesign digital, flight pegasus |
1083 |
1609 |
0.999997592 |
10 |
2 |
17 |
9 |
3 |
shaker, random vibration, sine burst, open loop, random, quasi, fixturing, sine, impart, random vibration test |
240 |
6196 |
0.926993883 |
11 |
2 |
18 |
10 |
55 |
lander, exploration rover, rover, land, martian, additional word, exploration, entry descent land, entry, entry descent |
2513 |
1615 |
0.879423398 |
12 |
2 |
19 |
8 |
11 |
optic, spherical, aberration, lens, spie, optical, focal, plane, beam, mirror |
1174 |
718 |
0.888498485 |
topic number |
topic words |
number of words |
best documents |
documents |
number of documents in topic |
|---|---|---|---|---|---|
-1 |
terrain, area, steep, fires, access, resources, heavy, smoke, complex, limited, suppression, containment, continue, acres, fuels, incident, creek, difficult, crews, continues |
20 |
n/a |
[‘2000_CA-RRU-062485_VALLEY COMPLEX_6’, ‘2000_CA-RRU-062485_VALLEY COMPLEX_7’, …] |
68098 |
0 |
nonw, slow slow, slow, em wann bye, nonw fortunately, nonw em, fortunately confirm nonw, fortunately confirm, nonw fortunately confirm, em wann, confirm nonw em, confirm nonw, wann bye slow, bye slow slow, bye slow, bye, slow slow slow, wann bye, nonw em wann, fortunately |
20 |
[‘2000_CA-RRU-062485_VALLEY COMPLEX_0’, ‘2000_CA-RRU-062485_VALLEY COMPLEX_0’, ‘2000_CA-RRU-062485_VALLEY COMPLEX_0’] |
[‘2000_CA-RRU-062485_VALLEY COMPLEX_0’, ‘2000_CA-RRU-062485_VALLEY COMPLEX_1’, …] |
99828 |
1 |
road, closed, closure, closures, highway, traffic, road closures, hwy, effect, remain, remains, remains closed, open, roads, road closure, public, area, closures effect, remain closed, reopened |
20 |
[‘2010_CA-INF-934_MONO_1’, ‘2007_GA-GAS-070010_BUGABOO SCRUB 2_2’, ‘2009_AZ-KNF-0705_RIDGE_0’] |
[‘2006_AK-FAS-611163_PARKS HWY_0’, ‘2006_AK-FAS-611163_PARKS HWY_1’, …] |
11306 |
2 |
evacuation, evacuations, evacuated, lifted, level, effect, residents, mandatory, road, residences, remain, level evacuation, voluntary, community, homes, mandatory evacuation, evacuation orders, advisory, evacuation order, orders |
20 |
[‘2012_CA-SQF-1644_GULCH_1’, ‘2011_TX-TXS-011190_ROGERS ROAD_0’, ‘2006_CA-RRU-79875_RANCH_2’] |
[‘2006_AK-FAS-611163_PARKS HWY_0’, ‘2006_AK-FAS-611163_PARKS HWY_2’ ,…] |
7922 |
3 |
acres, contained, acreage, 100, burned, 100 contained, acres 100, fires, acres 100 contained, acre, acres burned, mapping, complex, 000 acres, 000, approximately, increase, size, ownership, private |
20 |
[‘2009_TX-BRR-E5LD_HALF MOON FIRE_0’, ‘2011_MT-BDF-052_STEWART FIRE_16’, ‘2006_TX-TXS-066138_GLASS MOUNTAIN COMPLEX_8’] |
[‘2005_OK-CHA-005077_WILLIS_0’,’2006_00276_MILLER COMPLEX_1’, …] |
6694 |
4 |
dry, low, humidity, weather, rain, conditions, drought, temperatures, hot, relative, fuel, humidities, fuels, precipitation, hot dry, moistures, fuel moistures, relative humidity, dry weather, drought conditions |
20 |
[‘2008_OR-MHF-000014_GNARL RIDGE_10’, ‘2006_AZ-ASF-060304_BEAVERHEAD_1’, ‘2006_UT-FIF-000215_DOG VALLEY_4’] |
[‘2006_AK-FAS-611163_PARKS HWY_13’, ‘2006_AK-FAS-611163_PARKS HWY_15’,…] |
7101 |
5 |
acres, acreage, private, blm, ownership, acre, nf, forest, national forest, national, acres private, acres acres, acres national, ir, acres national forest, acres acreage, breakdown, contained, wfu, 25 |
20 |
[‘2010_KS-KSX-000231_EAST KENNEDY CREEK_1’, ‘2010_AZ-CRD-100117_MITCHEL_3’, ‘2008_CA-LNF-002782_PETERSON COMPLEX_14’] |
[‘2000_CA-RRU-062485_VALLEY COMPLEX_10’, ‘2006_AK-FAS-611163_PARKS HWY_1’, …] |
6466 |
6 |
resources, demobilization, demob, excess resources, excess, demobilization resources, resource, demob resources, resources released, released, demobed, resources demobed, resources continue, demobilization excess resources, demobilization excess, demob excess, demob excess resources, today, available, continue |
20 |
[‘2009_AK-KKS-903088_MI.17 EAST END RD._5’, ‘2013_NM-N6S-000230_THOMPSON RIDGE_16’, ‘2009_CA-PNF-0961_SILVER_6’] |
[‘2000_CA-RRU-062485_VALLEY COMPLEX_1’, ‘2000_CA-RRU-062485_VALLEY COMPLEX_7’,…] |
9371 |