sj311_bertopic_2018_2021_hf
This is a BERTopic model. BERTopic is a flexible and modular topic modeling framework that allows for the generation of easily interpretable topics from large datasets.
Usage
To use this model, please install BERTopic:
pip install -U bertopic
You can use the model as follows:
from bertopic import BERTopic
topic_model = BERTopic.load("digitalprivacy-sanjoseca/sj311_bertopic_2018_2021_hf")
topic_model.get_topic_info()
Topic overview
- Number of topics: 79
- Number of training documents: 183097
Click here for an overview of all topics.
Topic ID | Topic Keywords | Topic Frequency | Label |
---|---|---|---|
-1 | caller - number - wanted - caller wanted - garbage | 106 | Outlier |
0 | street - parked - car - parking - vehicle | 54894 | Vehicle/Utilities inquiry |
1 | junk - junk pick - pick junk - junk pick junk - pick junk pick | 63877 | Junk pick up |
2 | business tax - tax - tax business tax - tax business - business tax business | 8274 | Business tax |
3 | inquiry inquiry - inquiry inquiry inquiry - inquiry - inquiry inquiry caller - muni water inquiry | 4575 | Bill inquiry |
4 | service start - start service - service start service - service - start | 4234 | Start/stop service |
5 | missed - pick missed - missed pick missed - missed pick - pick missed pick | 2980 | Missed pick up |
6 | water billing question - question caller water - caller water billing - water billing - billing question caller | 2522 | Water billing question |
7 | payment line transfer - line transfer payment - line transfer - transfer payment line - transfer payment | 1825 | Transfer to payment line |
8 | cws caller wanted - wanted number cws - number cws caller - cws caller - number cws | 1604 | Wanted number for CWS |
9 | bin replace - replace bin replace - replace bin - replace - bin replace bin | 1467 | Replace garbage bins |
10 | question caller garbage - garbage billing question - caller garbage billing - caller garbage - garbage billing | 1419 | Garbage billing question |
11 | water payment caller - payment caller - payment caller water - caller water payment - water payment | 1280 | Caller made water payment |
12 | license business license - license business - business license business - business license - license | 1260 | Business license |
13 | water inquiry water - inquiry water - water inquiry - water water - inquiry water inquiry | 1231 | Water bill inquiry |
14 | inquiry payment inquiry - inquiry payment - payment inquiry - payment inquiry payment - inquiry billing | 1214 | Payment/billing inquiry |
15 | pu - pu junk - pu junk pu - junk pu - junk pu junk | 1148 | Junk pickup/missed pickup |
16 | code enforcement - enforcement - code - enforcement caller wanted - enforcement caller | 1127 | Wanted number for Code Enforcement |
17 | service inquiry service - inquiry service inquiry - inquiry service - service inquiry - service | 1072 | Service inquiry |
18 | number gcs - gcs - gcs caller - number gcs caller - wanted number gcs | 1061 | Wanted number for GCS |
19 | water start - start water start - water start water - start water - start | 1059 | Start water service |
20 | number greenteam - greenteam - greenteam caller - number greenteam caller - wanted number greenteam | 1034 | Wanted number for GreenTeam |
21 | police issue police - issue police - police issue - issue police issue - police | 988 | Police issue/report |
22 | look employee - employee look employee - employee look - employee - look | 978 | Employee look up |
23 | stop water - water stop - stop - stop water stop - water stop water | 949 | Stop water service |
24 | shut shut - shut shut shut - shut - hang - hang hang | 949 | Shut off call/hung up call |
25 | garbage inquiry garbage - inquiry garbage - garbage inquiry - inquiry garbage inquiry - garbage | 912 | Garbage bill inquiry |
26 | wanted number dot - number dot - dot caller wanted - number dot caller - dot caller | 903 | Wanted number for DOT Streets Dispatch |
27 | que - los - la - 2447 - solicitudes | 886 | Single user - repeated abandoned vehicle request |
28 | cart - garbage cart - cart garbage cart - damaged cart - broken garbage cart | 852 | Broken/replace garbage cart |
29 | tax bus tax - bus tax bus - tax bus - bus tax - bus | 838 | Bus tax |
30 | broken - broken broken - broken garbage - broken garbage broken - garbage broken | 791 | Broken/replace garbage cart |
31 | mw shut mw - shut mw shut - shut mw - mw shut - mw | 772 | MW shutoff |
32 | water service caller - service caller - caller started water - caller started - started water service | 764 | Start water service |
33 | parking compliance - parking compliance parking - compliance parking - compliance - compliance parking compliance | 725 | Parking compliance/illegal parking |
34 | online - online help - online help online - help online - online assistance | 650 | Online assistance/HR |
35 | garbage billing garbage - billing garbage - billing garbage billing - garbage billing - billing | 643 | Garbage billing/payment |
36 | emergency non emergency - emergency non - non emergency non - non emergency - emergency | 641 | Non-emergency |
37 | number wrong number - wrong number wrong - number wrong - wrong number - wrong | 581 | Wrong number |
38 | dot rollover dot - rollover dot - rollover dot rollover - dot rollover - rollover | 560 | DOT rollover |
39 | recycle - missed recycle - recycle missed recycle - recycle missed - recycle broken | 488 | Missed/broken/replace recycling |
40 | company water company - company water - water company water - water company - company | 454 | Other water company |
41 | sewer sewer - sewer - sewer sewer sewer - sewer billing sewer - billing sewer | 443 | Sewer backed up |
42 | balance - inquire balance - inquire - balance inquiry - balance inquire | 439 | Balance inquiry |
43 | payment water payment - water payment water - payment water - water payment - payment | 425 | Water billing |
44 | billing mfd - mfd billing mfd - billing mfd billing - mfd billing - mfd | 407 | MFD billing |
45 | emergency police caller - police caller - number non - number non emergency - non emergency police | 388 | Wanted number for non-emergency police |
46 | courtesy courtesy courtesy - courtesy courtesy - courtesy - courtesy courtesy caller - courtesy caller needed | 385 | Courtesy call |
47 | large - item pick large - pick large - pick large item - large item pick | 358 | Large item pick up |
48 | animal - services animal - animal services animal - animal services - care animal | 348 | Animal services |
49 | water payment water - payment water payment - payment water - water payment - payment | 341 | Water payment - new owner |
50 | abandoned vehicle abandoned - vehicle abandoned vehicle - vehicle abandoned - abandoned vehicle - abandoned | 311 | Abandoned vehicle |
51 | wanted number muni - muni water caller - number muni water - number muni - muni water | 292 | Wanted number of Muni Water |
52 | animal dead - dead animal dead - animal dead animal - dead animal - dead | 290 | Dead animal |
53 | paid balance paid - balance paid - balance paid balance - paid balance - paid | 269 | Paid balance |
54 | covid 19 closure - 19 closure - 19 closure inquiry - inquiry covid 19 - closure inquiry | 247 | COVID-19 inquiry |
55 | sj water sj - water sj - water sj water - sj water - sj | 234 | San Jose Water |
56 | garbage exchange - exchange garbage exchange - garbage exchange garbage - exchange garbage - exchange | 213 | Exchange garbage |
57 | ad hoc ad - hoc ad hoc - hoc ad - ad hoc - ad | 203 | Ad hoc bill |
58 | public works public - works public - works public works - public works - works | 196 | Public works |
59 | missing cart missing - cart missing cart - missing cart - cart missing - missing | 183 | Missing cart |
60 | oil - jugs - oil jugs - jugs oil - oil jugs oil | 181 | Used motor oil filter/jug pickup |
61 | bulky pick - bulky pick bulky - pick bulky - pick bulky pick - bulky | 177 | Bulky pick up |
62 | speaker spanish - spanish speaker spanish - speaker spanish speaker - spanish speaker - speaker | 174 | Spanish speaker |
63 | services retirement - retirement - retirement services retirement - services retirement services - retirement services | 172 | Retirement services |
64 | express issue caller - issue caller express - caller express issue - express issue - caller express | 167 | Ebill express issue |
65 | response response - response response response - response - wedged bushes left - left 1359 | 164 | No response |
66 | sweeping street sweeping - sweeping street - street sweeping street - street sweeping - sweeping | 159 | Street sweeping |
67 | repaired sidewalk needs - repaired sidewalk - needs repaired sidewalk - sidewalk needs repaired - needs repaired | 153 | Sidewalk repair |
68 | inq inq - inq inq inq - inq - employment verification inq - verification inq | 141 | Bill inquiry |
69 | pay pay - pay pay pay - pay - pay pay termination - pay pay like | 140 | Pay bill |
70 | water company caller - company caller - needed number san - number san - number san jose | 130 | Wanted number of San Jose Water |
71 | desk auto desk - desk auto - auto desk auto - auto desk - desk | 116 | Auto desk |
72 | report violation - violation report violation - report violation report - violation report - violation | 115 | Report violation |
73 | gb gb gb - gb gb - gb - mhp gb gb - gb mhp gb | 113 | Gb bill |
74 | rights rental - rights rental rights - rental rights rental - rental rights - rights | 110 | Rental rights |
75 | bus tx - tx - tx bus - tx bus tx - bus tx bus | 110 | Bus tx |
76 | ebill exp ebill - exp ebill - exp ebill exp - ebill exp - exp | 108 | Ebill express |
77 | new gb ct - ct new gb - gb ct new - ct new - new gb | 108 | New gb ct |
Training hyperparameters
- calculate_probabilities: False
- language: None
- low_memory: False
- min_topic_size: 30
- n_gram_range: (1, 3)
- nr_topics: auto
- seed_topic_list: None
- top_n_words: 10
- verbose: True
- zeroshot_min_similarity: 0.7
- zeroshot_topic_list: None
Framework versions
- Numpy: 1.25.2
- HDBSCAN: 0.8.33
- UMAP: 0.5.5
- Pandas: 1.5.3
- Scikit-Learn: 1.2.2
- Sentence-transformers: 2.5.1
- Transformers: 4.38.2
- Numba: 0.58.1
- Plotly: 5.15.0
- Python: 3.10.12
- Downloads last month
- 4
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.