alpinetest

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("Wscherm19/alpinetest")

topic_model.get_topic_info()

Topic overview

  • Number of topics: 37
  • Number of training documents: 2788
Click here for an overview of all topics.
Topic ID Topic Keywords Topic Frequency Label
-1 unto - people - men - man - great 10 -1_unto_people_men_man
0 florentines - duke - pope - florence - city 1004 0_florentines_duke_pope_florence
1 man - men - things - good - virtue 274 1_man_men_things_good
2 army - enemy - soldiers - romans - chap 212 2_army_enemy_soldiers_romans
3 law - power - sovereign - commonwealth - nature 135 3_law_power_sovereign_commonwealth
4 prince - thou - ought - subjects - princes 118 4_prince_thou_ought_subjects
5 adam - right - power - dominion - children 79 5_adam_right_power_dominion
6 commonweal - aristotle - oligarchie - democratie - government 67 6_commonweal_aristotle_oligarchie_democratie
7 king - unto - charles - france - kingdom 57 7_king_unto_charles_france
8 turk - turks - forces - princes - christians 54 8_turk_turks_forces_princes
9 parliament - law - house - england - page 51 9_parliament_law_house_england
10 church - ceremonies - churches - things - god 49 10_church_ceremonies_churches_things
11 commonwealth - people - unto - senate - popular 48 11_commonwealth_people_unto_senate
12 trade - east - england - wares - india 48 12_trade_east_england_wares
13 scripture - church - god - christ - things 45 13_scripture_church_god_christ
14 earl - king - did - henry - richard 43 14_earl_king_did_henry
15 magistrates - power - unto - law - judges 36 15_magistrates_power_unto_law
16 god - moses - israel - kingdom - king 36 16_god_moses_israel_kingdom
17 prince - unto - tyrant - subjects - good 33 17_prince_unto_tyrant_subjects
18 fol - cities - city - great - miles 33 18_fol_cities_city_great
19 god - spirit - resurrection - shall - scripture 31 19_god_spirit_resurrection_shall
20 lord - oh - hamlet - thy - thou 31 20_lord_oh_hamlet_thy
21 silver - money - deniers - gold - thousand 30 21_silver_money_deniers_gold
22 church - christian - pope - civil - sovereign 27 22_church_christian_pope_civil
23 shall - unto - council - tribe - ballot 26 23_shall_unto_council_tribe
24 thou - war - thy - tac - hist 25 24_thou_war_thy_tac
25 chap - people - romans - senate - rome 23 25_chap_people_romans_senate
26 laws - king - monarchy - government - power 20 26_laws_king_monarchy_government
27 town - people - did - men - athenians 19 27_town_people_did_men
28 page - majesty - highness - chap - royal 19 28_page_majesty_highness_chap
29 christ - god - jesus - savior - apostles 19 29_christ_god_jesus_savior
30 senate - people - unto - power - magistrates 17 30_senate_people_unto_power
31 noble - alexander - man - wise - men 17 31_noble_alexander_man_wise
32 law - god - laws - things - reason 14 32_law_god_laws_things
33 citisens - slaves - citisen - strangers - unto 13 33_citisens_slaves_citisen_strangers
34 enquest - say - judges - man - law 13 34_enquest_say_judges_man
35 princes - empire - emperor - alliance - swissers 12 35_princes_empire_emperor_alliance

Training hyperparameters

  • calculate_probabilities: False
  • language: None
  • low_memory: False
  • min_topic_size: 10
  • n_gram_range: (1, 1)
  • nr_topics: None
  • seed_topic_list: None
  • top_n_words: 10
  • verbose: True
  • zeroshot_min_similarity: 0.7
  • zeroshot_topic_list: None

Framework versions

  • Numpy: 1.26.4
  • HDBSCAN: 0.8.39
  • UMAP: 0.5.7
  • Pandas: 2.2.2
  • Scikit-Learn: 1.5.2
  • Sentence-transformers: 3.2.1
  • Transformers: 4.46.1
  • Numba: 0.60.0
  • Plotly: 5.24.1
  • Python: 3.10.12
Downloads last month
4
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.