Edit model card

bertopic-20-newsgroups

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("ctam8736/bertopic-20-newsgroups")

topic_model.get_topic_info()

Topic overview

  • Number of topics: 135
  • Number of training documents: 11314
Click here for an overview of all topics.
Topic ID Topic Keywords Topic Frequency Label
-1 article - information - subject - re - what 10 -1_article_information_subject_re
0 scsi - scsi2 - scsi1 - drives - bios 3737 0_scsi_scsi2_scsi1_drives
1 nhl - puck - leafs - flyers - pitching 976 1_nhl_puck_leafs_flyers
2 firearm - firearms - handgun - guns - gun 918 2_firearm_firearms_handgun_guns
3 ford - honda - nissan - bmw - dealer 409 3_ford_honda_nissan_bmw
4 encryption - encrypted - crypto - nsa - chip 387 4_encryption_encrypted_crypto_nsa
5 atheism - atheist - atheists - christianity - belief 377 5_atheism_atheist_atheists_christianity
6 hezbollah - gaza - lebanon - palestinians - lebanese 342 6_hezbollah_gaza_lebanon_palestinians
7 window - x11r5 - openwindows - x11 - x11r4 249 7_window_x11r5_openwindows_x11
8 modems - modem - mouse - ports - port 243 8_modems_modem_mouse_ports
9 anonymity - anonymous - mailing - usenet - newsgroups 151 9_anonymity_anonymous_mailing_usenet
10 armenians - armenia - armenian - azerbaijani - azerbaijan 147 10_armenians_armenia_armenian_azerbaijani
11 clinton - stephanopoulos - secretary - president - congress 135 11_clinton_stephanopoulos_secretary_president
12 os - windows - win32 - microsoft - win31 133 12_os_windows_win32_microsoft
13 diseases - disease - candida - infection - infections 113 13_diseases_disease_candida_infection
14 superstition - msg - sensitivity - glutamate - causes 100 14_superstition_msg_sensitivity_glutamate
15 laserjet - inkjet - printers - bubblejet - bubblejets 86 15_laserjet_inkjet_printers_bubblejet
16 billboard - billboards - nasa - space - advertising 75 16_billboard_billboards_nasa_space
17 radar - detectors - detector - detecting - radarjust 68 17_radar_detectors_detector_detecting
18 speeding - speeds - mph - speed - driving 64 18_speeding_speeds_mph_speed
19 ssto - moonbase - moon - lunar - billion 63 19_ssto_moonbase_moon_lunar
20 station - nasa - redesign - space - shuttle 61 20_station_nasa_redesign_space
21 eternity - afterlife - heaven - hell - judgement 49 21_eternity_afterlife_heaven_hell
22 testament - manuscripts - scripture - bible - hebrew 47 22_testament_manuscripts_scripture_bible
23 homosexuality - heterosexual - homosexual - homosexuals - gays 45 23_homosexuality_heterosexual_homosexual_homosexuals
24 libertarians - libertarian - libertarianism - regulation - governments 44 24_libertarians_libertarian_libertarianism_regulation
25 islamic - muslim - islam - muslims - koran 44 25_islamic_muslim_islam_muslims
26 tax - taxes - vat - deficits - income 44 26_tax_taxes_vat_deficits
27 oil - drain - engine - fuel - dumping 44 27_oil_drain_engine_fuel
28 helmet - helmets - head - protection - gloves 43 28_helmet_helmets_head_protection
29 fonts - font - ttfonts - truetype - printing 42 29_fonts_font_ttfonts_truetype
30 morality - moral - morals - instinctive - immoral 39 30_morality_moral_morals_instinctive
31 colormaps - colourmap - colormap - xalloccolor - cwcolormap 39 31_colormaps_colourmap_colormap_xalloccolor
32 homosexuals - molesters - homosexual - homosexuality - pedophilia 38 32_homosexuals_molesters_homosexual_homosexuality
33 migraine - migraines - headache - headaches - analgesics 37 33_migraine_migraines_headache_headaches
34 resurrection - gospels - tomb - testament - jesuss 37 34_resurrection_gospels_tomb_testament
35 graphics - copyright - images - siggraph - image 37 35_graphics_copyright_images_siggraph
36 mormon - mormons - lds - brigham - utah 35 36_mormon_mormons_lds_brigham
37 scientific - scipsychology - scientist - science - methodology 34 37_scientific_scipsychology_scientist_science
38 tapes - tape - backup - copy - floppy 34 38_tapes_tape_backup_copy
39 drugs - marijuana - drug - legalizing - legalization 34 39_drugs_marijuana_drug_legalizing
40 punishment - punish - murder - penalty - murderer 34 40_punishment_punish_murder_penalty
41 sphere - globe - radius - pointstruct - circle 34 41_sphere_globe_radius_pointstruct
42 surgery - patients - hernia - massager - pain 33 42_surgery_patients_hernia_massager
43 genocide - bosnia - atheism - serbs - christians 32 43_genocide_bosnia_atheism_serbs
44 insurance - liability - insureyear - deductible - accident 32 44_insurance_liability_insureyear_deductible
45 polygon - polygons - triangulation - hexagons - polyn 30 45_polygon_polygons_triangulation_hexagons
46 spacecraft - galileo - galileos - mission - magellan 29 46_spacecraft_galileo_galileos_mission
47 countersteering - countersteeringfaq - countersteer - riding - bikes 29 47_countersteering_countersteeringfaq_countersteer_riding
48 antenna - antennas - transmitters - transmitting - radios 28 48_antenna_antennas_transmitters_transmitting
49 canine - dogs - dog - spaniel - springer 28 49_canine_dogs_dog_spaniel
50 batteries - battery - electrolyte - galvanized - zinc 28 50_batteries_battery_electrolyte_galvanized
51 oscilloscope - scopes - scope - oscilliscopes - digital 27 51_oscilloscope_scopes_scope_oscilliscopes
52 xgrabkey - definekeys - accelerators - accelerator - shiftkeyq 27 52_xgrabkey_definekeys_accelerators_accelerator
53 protoncentaur - centaur - proton - accelerator - nuclear 27 53_protoncentaur_centaur_proton_accelerator
54 telephone - dial - phone - call - lines 26 54_telephone_dial_phone_call
55 marriages - wedding - vows - weddings - marriage 25 55_marriages_wedding_vows_weddings
56 ibm - levels - level - nasa - software 25 56_ibm_levels_level_nasa
57 nasa - aerospace - astronomy - spacecraft - astronomical 24 57_nasa_aerospace_astronomy_spacecraft
58 motif - neosoft - unix - platforms - software 24 58_motif_neosoft_unix_platforms
59 nuclear - cooling - reactor - tower - towers 23 59_nuclear_cooling_reactor_tower
60 injuries - struck - snot - rocks - warningplease 23 60_injuries_struck_snot_rocks
61 transmissions - shifter - automatics - autos - auto 22 61_transmissions_shifter_automatics_autos
62 lzr1260 - printing - mwt9caxaxaxaxaxaxaxaxaxaxaxaxax - m9l0qaxaxaxaxaxaxaxaxaxaxaxaxaxax - mi68qaxaxaxaxaxaxaxaxaxaxaxaxaxax 22 62_lzr1260_printing_mwt9caxaxaxaxaxaxaxaxaxaxaxaxax_m9l0qaxaxaxaxaxaxaxaxaxaxaxaxaxax
63 cview - files - directory - file - tmp 21 63_cview_files_directory_file
64 immaculate - mary - marys - conception - catholics 21 64_immaculate_mary_marys_conception
65 cryptology - cryptanalyst - crypt - cryptanalysis - ciphers 20 65_cryptology_cryptanalyst_crypt_cryptanalysis
66 hotelco - hotels - resorts - hotel - tickets 20 66_hotelco_hotels_resorts_hotel
67 3dos - 3do - 3ds - 3d - 3dstudio 20 67_3dos_3do_3ds_3d
68 comet - comets - jupiter - asteroids - jovian 20 68_comet_comets_jupiter_asteroids
69 polishing - scratches - paint - rubbing - glaze 20 69_polishing_scratches_paint_rubbing
70 newsgroup - groups - groupsplit - group - split 20 70_newsgroup_groups_groupsplit_group
71 koresh - koreshs - david - sermon - biblical 20 71_koresh_koreshs_david_sermon
72 parking - parked - liability - unsafe - stickers 20 72_parking_parked_liability_unsafe
73 trumpet - tcp - windows - winqvtnet - winsock 19 73_trumpet_tcp_windows_winqvtnet
74 freon - heater - coolant - r12 - vents 19 74_freon_heater_coolant_r12
75 sabbath - commandments - sunday - worship - church 19 75_sabbath_commandments_sunday_worship
76 geekdom - computer - fourdcom - csws18icsunysbedu - psychnet 19 76_geekdom_computer_fourdcom_csws18icsunysbedu
77 bosnia - serbs - sanctions - somalia - war 18 77_bosnia_serbs_sanctions_somalia
78 soundblaster - midi - midimapper - soundexe - wavfiles 18 78_soundblaster_midi_midimapper_soundexe
79 condo - remodeled - townhome - bedroom - rent 18 79_condo_remodeled_townhome_bedroom
80 odometers - odometer - sensor - mileage - sensors 18 80_odometers_odometer_sensor_mileage
81 joystick - joysticks - joyport - joyread - hardware 17 81_joystick_joysticks_joyport_joyread
82 abortion - abortions - roe - proabortion - fetus 17 82_abortion_abortions_roe_proabortion
83 seizures - seizure - allergies - corn - cereal 17 83_seizures_seizure_allergies_corn
84 sobriety - sober - drinking - drink - drinks 17 84_sobriety_sober_drinking_drink
85 nubus - lciiipowerpc - pds - powerpcs - powerpc 17 85_nubus_lciiipowerpc_pds_powerpcs
86 mining - miners - minerals - miner - mineral 17 86_mining_miners_minerals_miner
87 outlets - outlet - electrical - wiring - grounded 16 87_outlets_outlet_electrical_wiring
88 rosicrucianum - rosicrucian - orders - order - organization 16 88_rosicrucianum_rosicrucian_orders_order
89 tempest - shielding - surveillance - encryption - electromagnetic 16 89_tempest_shielding_surveillance_encryption
90 monitor - monitors - screen - scrolling - display 16 90_monitor_monitors_screen_scrolling
91 krillean - photographs - photography - kirlian - pictures 16 91_krillean_photographs_photography_kirlian
92 scanner - scanners - scanning - scans - scanman 16 92_scanner_scanners_scanning_scans
93 sexism - sexist - extramarital - islamic - marriage 16 93_sexism_sexist_extramarital_islamic
94 noisy - noise - noises - rattled - quiets 16 94_noisy_noise_noises_rattled
95 orion - astronomy - museum - prototype - space 15 95_orion_astronomy_museum_prototype
96 easter - pagan - celebrating - feast - celebration 15 96_easter_pagan_celebrating_feast
97 batf - assault - waco - blasting - blast 15 97_batf_assault_waco_blasting
98 batchfile - ini - updating - file - winfileini 15 98_batchfile_ini_updating_file
99 copyprotect - copying - protected - copy - protection 15 99_copyprotect_copying_protected_copy
100 42 - tiff - tiff6 - significance - universe 14 100_42_tiff_tiff6_significance
101 stove - stoves - splitfires - splitfire - burns 14 101_stove_stoves_splitfires_splitfire
102 automotive - backing - lights - corvette - reverse 14 102_automotive_backing_lights_corvette
103 dock - docks - minidocks - portable - minidock 14 103_dock_docks_minidocks_portable
104 cdaudio - stereo - audio - soundbase - speakers 14 104_cdaudio_stereo_audio_soundbase
105 uv - flashlight - houselights - fluorescent - lamps 14 105_uv_flashlight_houselights_fluorescent
106 papal - papacy - pope - popes - schism 14 106_papal_papacy_pope_popes
107 scsi - quadra - quadras - quadraspecific - firmware 14 107_scsi_quadra_quadras_quadraspecific
108 crohns - colitis - dietary - gastroenterology - diet 13 108_crohns_colitis_dietary_gastroenterology
109 crashes - powerbook - plugged - corrupted - duos 13 109_crashes_powerbook_plugged_corrupted
110 eyedness - handedness - righteye - righthandedness - eyes 13 110_eyedness_handedness_righteye_righthandedness
111 wrench - pliers - tool - tools - srb 13 111_wrench_pliers_tool_tools
112 scripture - scriptures - prophecy - revelation - revelations 13 112_scripture_scriptures_prophecy_revelation
113 nikon - lens - lenses - olympus - 35mm 13 113_nikon_lens_lenses_olympus
114 prosecution - suspects - encrypted - defendant - incriminate 13 114_prosecution_suspects_encrypted_defendant
115 wheel - shaftdrives - wheelies - wheelie - shaftdrive 12 115_wheel_shaftdrives_wheelies_wheelie
116 obesity - rebound - dieting - diet - metabolism 12 116_obesity_rebound_dieting_diet
117 adl - adls - spying - fbi - investigation 12 117_adl_adls_spying_fbi
118 lunar - moon - exploration - attend - conference 12 118_lunar_moon_exploration_attend
119 draftees - draft - selective - military - abolished 12 119_draftees_draft_selective_military
120 sunrise - sunset - daylight - algorithm - astronomical 12 120_sunrise_sunset_daylight_algorithm
121 octopus - octopuses - octopi - squid - octapus 12 121_octopus_octopuses_octopi_squid
122 gassing - explosion - gas - explode - explosive 11 122_gassing_explosion_gas_explode
123 tutorial - handbook - chemistry - paperback - books 11 123_tutorial_handbook_chemistry_paperback
124 amp - decibels - current - ampere - db 11 124_amp_decibels_current_ampere
125 uniforms - jerseys - uniform - mets - reds 11 125_uniforms_jerseys_uniform_mets
126 eugenics - eugenic - geneticallyengineered - genetic - genetically 11 126_eugenics_eugenic_geneticallyengineered_genetic
127 fractals - fractal - fractally - compression - pascalfractals 11 127_fractals_fractal_fractally_compression
128 sunview - xputimage - pixmap - pixmaps - ximage 11 128_sunview_xputimage_pixmap_pixmaps
129 waving - wave - waves - bikers - bikes 11 129_waving_wave_waves_bikers
130 vocoder - compressionalgorithms - compression - modems - cryptophones 11 130_vocoder_compressionalgorithms_compression_modems
131 mouse - jumpiness - mousecom - mouseits - jumps 11 131_mouse_jumpiness_mousecom_mouseits
132 netware - lan - workgroup - workgroups - w4wg 10 132_netware_lan_workgroup_workgroups
133 timers - timer - ultralong - clock - oscillator 10 133_timers_timer_ultralong_clock

Training hyperparameters

  • calculate_probabilities: False
  • language: english
  • low_memory: False
  • min_topic_size: 10
  • n_gram_range: (1, 1)
  • 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: 1.23.5
  • HDBSCAN: 0.8.33
  • UMAP: 0.5.5
  • Pandas: 2.2.1
  • Scikit-Learn: 1.3.1
  • Sentence-transformers: 2.5.1
  • Transformers: 4.37.0.dev0
  • Numba: 0.59.1
  • Plotly: 5.20.0
  • Python: 3.10.4
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.