Add BERTopic model

README.md

@@ -0,0 +1,214 @@
+
+---
+tags:
+- bertopic
+library_name: bertopic
+pipeline_tag: text-classification
+---
+
+# MARTINI_enrich_BERTopic_candlesinthenight
+
+This is a [BERTopic](https://github.com/MaartenGr/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:
+
+```python
+from bertopic import BERTopic
+topic_model = BERTopic.load("AIDA-UPM/MARTINI_enrich_BERTopic_candlesinthenight")
+
+topic_model.get_topic_info()
+```
+
+## Topic overview
+
+* Number of topics: 145
+* Number of training documents: 22892
+
+<details>
+  <summary>Click here for an overview of all topics.</summary>
+  
+  | Topic ID | Topic Keywords | Topic Frequency | Label | 
+|----------|----------------|-----------------|-------| 
+| -1 | donald - patriots - tweet - ballots - 2020 | 20 | -1_donald_patriots_tweet_ballots | 
+| 0 | desantis - romney - governors - desanctimonious - voted | 14610 | 0_desantis_romney_governors_desanctimonious | 
+| 1 | bodycam - shootings - antifa - officers - taser | 261 | 1_bodycam_shootings_antifa_officers | 
+| 2 | ukraine - donetsk - mariupol - zelenskyy - volodymyr | 244 | 2_ukraine_donetsk_mariupol_zelenskyy | 
+| 3 | faith - miracles - satan - bible - always | 226 | 3_faith_miracles_satan_bible | 
+| 4 | fbi - insurrectionists - pelosi - carlson - informant | 195 | 4_fbi_insurrectionists_pelosi_carlson | 
+| 5 | jpmorgan - epstein - billionaire - 290million - ghislaine | 170 | 5_jpmorgan_epstein_billionaire_290million | 
+| 6 | prayers - clots - healed - brother - icu | 166 | 6_prayers_clots_healed_brother | 
+| 7 | republicans - impeachment - mccarthy - committees - newhouse | 154 | 7_republicans_impeachment_mccarthy_committees | 
+| 8 | biden - joey - inauguration - donmeswitwomenofmericalessuwannagetthebenefit - dammmmm | 149 | 8_biden_joey_inauguration_donmeswitwomenofmericalessuwannagetthebenefit | 
+| 9 | georgia - lawyers - whistleblower - dismissed - freekyleusa | 145 | 9_georgia_lawyers_whistleblower_dismissed | 
+| 10 | flynn - prayer - archangel - michael - redstatetalkradio | 142 | 10_flynn_prayer_archangel_michael | 
+| 11 | hannity - newsmax - interviewed - president - klowdtv | 129 | 11_hannity_newsmax_interviewed_president | 
+| 12 | trumpo - mnuchin - lunatics - kristie - ahhhhhhhhh | 117 | 12_trumpo_mnuchin_lunatics_kristie | 
+| 13 | cnn - carlson - murdoch - timewarner - shareholder | 116 | 13_cnn_carlson_murdoch_timewarner | 
+| 14 | taiwan - pompeo - apec - xiaoping - weibo | 116 | 14_taiwan_pompeo_apec_xiaoping | 
+| 15 | tweets - fbi - misinformation - blacklists - slack | 112 | 15_tweets_fbi_misinformation_blacklists | 
+| 16 | georgenews - zoomgov - 2021 - teleprompter - 45pm | 109 | 16_georgenews_zoomgov_2021_teleprompter | 
+| 17 | illegals - deportation - migrant - reynosa - border | 101 | 17_illegals_deportation_migrant_reynosa | 
+| 18 | dan - scavino - retweeted - 17am - booooooooooooooooom | 96 | 18_dan_scavino_retweeted_17am | 
+| 19 | maricopa - ballots - auditors - subpoenaed - counties | 95 | 19_maricopa_ballots_auditors_subpoenaed | 
+| 20 | pfizer - vaccinate - cdc - 125742_s1_m5_crf_c4591001 - pages | 92 | 20_pfizer_vaccinate_cdc_125742_s1_m5_crf_c4591001 | 
+| 21 | clinton - mueller - spygate - dossier - danchenko | 89 | 21_clinton_mueller_spygate_dossier | 
+| 22 | lindelltv - mike - videolink - frankspeech - netstumbler | 88 | 22_lindelltv_mike_videolink_frankspeech | 
+| 23 | fauci - bioterrorism - coronaviruses - darpa - usaid | 87 | 23_fauci_bioterrorism_coronaviruses_darpa | 
+| 24 | unvaxed - nsw - lockdown - frederiksen - mandatory | 86 | 24_unvaxed_nsw_lockdown_frederiksen | 
+| 25 | trumps - prosecutors - indicted - travesty - manhattan | 84 | 25_trumps_prosecutors_indicted_travesty | 
+| 26 | arrests - polk - grady - pornography - abused | 83 | 26_arrests_polk_grady_pornography | 
+| 27 | qanon - qr - greatawakening - posts - decoding | 77 | 27_qanon_qr_greatawakening_posts | 
+| 28 | davos - climate - alarmist - dictatorships - globalized | 76 | 28_davos_climate_alarmist_dictatorships | 
+| 29 | night - blessed - everything - unshakable - hey | 74 | 29_night_blessed_everything_unshakable | 
+| 30 | chats - 10pm - voice - friday - live | 74 | 30_chats_10pm_voice_friday | 
+| 31 | freedom - allegiance - fightback - traitors - reagan | 73 | 31_freedom_allegiance_fightback_traitors | 
+| 32 | psalm - nebuchadnezzar - shadrach - isaiah - righteous | 71 | 32_psalm_nebuchadnezzar_shadrach_isaiah | 
+| 33 | republican - votes - mccormick - fetterman - leads | 71 | 33_republican_votes_mccormick_fetterman | 
+| 34 | donald - staten - 2021 - 45th - july | 71 | 34_donald_staten_2021_45th | 
+| 35 | qanon - traffickers - ballard - rescued - sound | 71 | 35_qanon_traffickers_ballard_rescued | 
+| 36 | georgia - ballots - falsified - raffensperger - scanned | 70 | 36_georgia_ballots_falsified_raffensperger | 
+| 37 | followers - mjtruth - retweets - hahahahahhah - rejoin | 69 | 37_followers_mjtruth_retweets_hahahahahhah | 
+| 38 | prayer - satan - heavenly - amen - forgive | 68 | 38_prayer_satan_heavenly_amen | 
+| 39 | vaers - myocarditis - unvaccinated - strokes - miscarriages | 68 | 39_vaers_myocarditis_unvaccinated_strokes | 
+| 40 | jamesokeefe - whistleblower - americanmuckraker - veritastips - peoject | 67 | 40_jamesokeefe_whistleblower_americanmuckraker_veritastips | 
+| 41 | fbi - melania - raided - documents - unsealed | 67 | 41_fbi_melania_raided_documents | 
+| 42 | gasoline - bidenflation - prices - utah - mile | 66 | 42_gasoline_bidenflation_prices_utah | 
+| 43 | ukraine - appropriations - billion - taxpayers - yellen | 65 | 43_ukraine_appropriations_billion_taxpayers | 
+| 44 | trudeau - tucker - thegatewaypundit - convoy - protesters | 64 | 44_trudeau_tucker_thegatewaypundit_convoy | 
+| 45 | derailment - spills - ohio - hazardous - propylene | 63 | 45_derailment_spills_ohio_hazardous | 
+| 46 | afghanistan - terrorists - amrullah - donald - surrender | 62 | 46_afghanistan_terrorists_amrullah_donald | 
+| 47 | musk - twitterverse - omega - shadowbanned - shatner | 62 | 47_musk_twitterverse_omega_shadowbanned | 
+| 48 | fetterman - oprah - impeaching - democrat - candidates | 62 | 48_fetterman_oprah_impeaching_democrat | 
+| 49 | ivermectin - hydroxychloroquine - remdesivir - antidote - fenbendazole | 61 | 49_ivermectin_hydroxychloroquine_remdesivir_antidote | 
+| 50 | blackpilling - everyone - channel - welcome - maqeveli | 61 | 50_blackpilling_everyone_channel_welcome | 
+| 51 | republicans - scgop - carolina - mckissick - chairman | 61 | 51_republicans_scgop_carolina_mckissick | 
+| 52 | bidenlaptopemails - clancy - hooker - scandal - kgb | 61 | 52_bidenlaptopemails_clancy_hooker_scandal | 
+| 53 | plandemic - unvaccinated - ivermectin - indoctrinating - audited | 60 | 53_plandemic_unvaccinated_ivermectin_indoctrinating | 
+| 54 | truthsocial - update - bots - wtaf - app | 60 | 54_truthsocial_update_bots_wtaf | 
+| 55 | vaccine - pfizer - lockdowns - pepematters - poisoned | 58 | 55_vaccine_pfizer_lockdowns_pepematters | 
+| 56 | vaccinated - fauci - scammers - diphtheria - whaaaaaaaaaaaaaaaaaaat | 57 | 56_vaccinated_fauci_scammers_diphtheria | 
+| 57 | spammers - banned - channel - replies - sorrrryyy | 57 | 57_spammers_banned_channel_replies | 
+| 58 | auditthevotepa - senators - harrisburg - petition - fax | 55 | 58_auditthevotepa_senators_harrisburg_petition | 
+| 59 | pelosi - sfpd - sleezeball - drunk - nudist | 55 | 59_pelosi_sfpd_sleezeball_drunk | 
+| 60 | wildfires - fema - evacuated - kelowna - hawaii | 53 | 60_wildfires_fema_evacuated_kelowna | 
+| 61 | rally - newsmax - 7pm - airing - rewatch | 52 | 61_rally_newsmax_7pm_airing | 
+| 62 | comey - snowden - federalized - nsa - soros | 52 | 62_comey_snowden_federalized_nsa | 
+| 63 | trumper - vivek - candidates - rnc - goviralfg | 50 | 63_trumper_vivek_candidates_rnc | 
+| 64 | arizona - gubernatorial - kelli - recount - judge | 48 | 64_arizona_gubernatorial_kelli_recount | 
+| 65 | hurricanes - rain - cirrus - manipulating - sarasota | 47 | 65_hurricanes_rain_cirrus_manipulating | 
+| 66 | night - faith - unshakeable - little - brightly | 45 | 66_night_faith_unshakeable_little | 
+| 67 | wisvote - ballots - milwaukee - tabulators - zuckerberg | 44 | 67_wisvote_ballots_milwaukee_tabulators | 
+| 68 | queen - diana - raven - sandringham - mi6 | 44 | 68_queen_diana_raven_sandringham | 
+| 69 | deltas - qdrop - july - dday - 2378713 | 44 | 69_deltas_qdrop_july_dday | 
+| 70 | sexualize - blowjobs - teachers - lgbtq - pornstache | 43 | 70_sexualize_blowjobs_teachers_lgbtq | 
+| 71 | voting - california - newsom - cheated - welllll | 41 | 71_voting_california_newsom_cheated | 
+| 72 | congressman - nebraska - endorsed - steve - carey | 40 | 72_congressman_nebraska_endorsed_steve | 
+| 73 | soooooo - reposting - normies - tried - tineye | 40 | 73_soooooo_reposting_normies_tried | 
+| 74 | mobilized - ng - preparedness - marines - fema | 40 | 74_mobilized_ng_preparedness_marines | 
+| 75 | vid - youtube - rewatched - posted - click | 39 | 75_vid_youtube_rewatched_posted | 
+| 76 | cryptocurrencies - hodl - officialsatoshi - bny - rupee | 39 | 76_cryptocurrencies_hodl_officialsatoshi_bny | 
+| 77 | jokingly - sjokeyjoke - laughed - fartwell - tickled | 39 | 77_jokingly_sjokeyjoke_laughed_fartwell | 
+| 78 | resigns - chancellor - parliamentary - brexit - javid | 39 | 78_resigns_chancellor_parliamentary_brexit | 
+| 79 | transgender - minors - wyoming - obamacare - vetoed | 38 | 79_transgender_minors_wyoming_obamacare | 
+| 80 | vaccine - mandate - scotusblog - employers - louisiana | 38 | 80_vaccine_mandate_scotusblog_employers | 
+| 81 | bolsonaro - brasilia - janeiro - moraes - peruvian | 37 | 81_bolsonaro_brasilia_janeiro_moraes | 
+| 82 | republicans - manchin - voted - earmarks - billion | 36 | 82_republicans_manchin_voted_earmarks | 
+| 83 | 1111 - synchronicity - uhhhhhhh - vibration - __hz | 35 | 83_1111_synchronicity_uhhhhhhh_vibration | 
+| 84 | george - posted - graphica - 15pm - 2022 | 35 | 84_george_posted_graphica_15pm | 
+| 85 | fluoridated - cadmium - doritos - microplastics - unhealthy | 35 | 85_fluoridated_cadmium_doritos_microplastics | 
+| 86 | hillary - comeback - evidently - 2016 - tweets | 34 | 86_hillary_comeback_evidently_2016 | 
+| 87 | vaccinations - eeoc - mandatory - exempt - hipaa | 34 | 87_vaccinations_eeoc_mandatory_exempt | 
+| 88 | georgia - kemp - vernon - deputy - audit | 33 | 88_georgia_kemp_vernon_deputy | 
+| 89 | mjtruthhomefront - covfefe - plandemic - 2022 - zelensky | 33 | 89_mjtruthhomefront_covfefe_plandemic_2022 | 
+| 90 | kanye - mkultra - celebrities - ricky - jews | 33 | 90_kanye_mkultra_celebrities_ricky | 
+| 91 | george - headlines - chats - wwg - 55pm | 33 | 91_george_headlines_chats_wwg | 
+| 92 | pandemics - h5n1 - deadlier - brussels - hopkins | 33 | 92_pandemics_h5n1_deadlier_brussels | 
+| 93 | stocked - kroger - status - shortage - farmers | 33 | 93_stocked_kroger_status_shortage | 
+| 94 | mcafee - deadman - countdown - killswitch - activated | 32 | 94_mcafee_deadman_countdown_killswitch | 
+| 95 | texas - illegals - governor - federalizes - standoff | 32 | 95_texas_illegals_governor_federalizes | 
+| 96 | stol - deleted - covfefe - impeached - 2023 | 31 | 96_stol_deleted_covfefe_impeached | 
+| 97 | hamas - gaza - israelis - ashkelon - missiles | 31 | 97_hamas_gaza_israelis_ashkelon | 
+| 98 | telegram - messaged - signal - deactivated - unsubscribe | 31 | 98_telegram_messaged_signal_deactivated | 
+| 99 | abortions - banning - mccorvey - enacted - ab2223 | 31 | 99_abortions_banning_mccorvey_enacted | 
+| 100 | gunmakers - militia - maryland - rulings - unconstitutional | 30 | 100_gunmakers_militia_maryland_rulings | 
+| 101 | pontiff - vatican - benedict - basilica - vigano | 30 | 101_pontiff_vatican_benedict_basilica | 
+| 102 | reelection - republican - wins - rubio - alabama | 29 | 102_reelection_republican_wins_rubio | 
+| 103 | norad - airship - drones - balloon - hypersonic | 29 | 103_norad_airship_drones_balloon | 
+| 104 | zuckerberg - whatapp - surveil - darpa - fakebook | 29 | 104_zuckerberg_whatapp_surveil_darpa | 
+| 105 | musk - shareholders - twatter - acquisition - vanguard | 29 | 105_musk_shareholders_twatter_acquisition | 
+| 106 | republicans - mcconnell - filibuster - senators - trillion | 29 | 106_republicans_mcconnell_filibuster_senators | 
+| 107 | borders - tijuana - immigrant - smuggling - criminals | 28 | 107_borders_tijuana_immigrant_smuggling | 
+| 108 | memorial - veterans - honor - blessings - liberty | 28 | 108_memorial_veterans_honor_blessings | 
+| 109 | mj - illegals - netanyahu - 2023 - happenings | 28 | 109_mj_illegals_netanyahu_2023 | 
+| 110 | trafficked - whistleblower - adoptions - maltreatment - bama | 28 | 110_trafficked_whistleblower_adoptions_maltreatment | 
+| 111 | lewinsky - whore - donna - carrol - defamed | 27 | 111_lewinsky_whore_donna_carrol | 
+| 112 | pelosi - unconstitutionally - subpoena - january - newsflash | 27 | 112_pelosi_unconstitutionally_subpoena_january | 
+| 113 | bidens - 40million - laundered - deposited - llc | 27 | 113_bidens_40million_laundered_deposited | 
+| 114 | communist - khrushchev - goals - disarmament - infiltrate | 27 | 114_communist_khrushchev_goals_disarmament | 
+| 115 | walmart - boycotting - businesses - blackrock - dunkin | 27 | 115_walmart_boycotting_businesses_blackrock | 
+| 116 | hindenburg - hitler - brainwashing - wolff - lifeboat | 26 | 116_hindenburg_hitler_brainwashing_wolff | 
+| 117 | bullion - dollar - rubles - sterling - revalued | 26 | 117_bullion_dollar_rubles_sterling | 
+| 118 | goodnight - blessed - 4am - sunday - birthday | 26 | 118_goodnight_blessed_4am_sunday | 
+| 119 | hey - tomorrow - busy - missed - hopefully | 26 | 119_hey_tomorrow_busy_missed | 
+| 120 | suez - maersk - tugboats - blockade - container | 25 | 120_suez_maersk_tugboats_blockade | 
+| 121 | swimmers - transgender - athlete - ncaa - disqualified | 25 | 121_swimmers_transgender_athlete_ncaa | 
+| 122 | actblue - donations - earmarks - laundering - schwarzman | 25 | 122_actblue_donations_earmarks_laundering | 
+| 123 | planecrash - flightradar - bomber - northrop - f35 | 25 | 123_planecrash_flightradar_bomber_northrop | 
+| 124 | vibes - good - cutest - gif - smiling | 25 | 124_vibes_good_cutest_gif | 
+| 125 | night - faith - alright - unshakable - woooooooooo | 24 | 125_night_faith_alright_unshakable | 
+| 126 | maricopa - auditors - tampered - cyber - password | 24 | 126_maricopa_auditors_tampered_cyber | 
+| 127 | linwoodspeakstruth - redeemed - pastor - david - caroline | 24 | 127_linwoodspeakstruth_redeemed_pastor_david | 
+| 128 | lockdowns - beijing - sichuan - luzhou - urumqi | 24 | 128_lockdowns_beijing_sichuan_luzhou | 
+| 129 | blessings - prayer - thankful - verses - sunday | 24 | 129_blessings_prayer_thankful_verses | 
+| 130 | spacex - satellites - missile - huntsville - cyberattacks | 24 | 130_spacex_satellites_missile_huntsville | 
+| 131 | defcon - arrest - inauguration - broadcast - resignations | 23 | 131_defcon_arrest_inauguration_broadcast | 
+| 132 | george - chats - posted - unshakable - 2022 | 23 | 132_george_chats_posted_unshakable | 
+| 133 | speaker - gop - livestream - delegates - 5pm | 23 | 133_speaker_gop_livestream_delegates | 
+| 134 | trumpers - gabbard - mike - nominee - overturned | 23 | 134_trumpers_gabbard_mike_nominee | 
+| 135 | georgetb - today - images - 48pm - 2094 | 22 | 135_georgetb_today_images_48pm | 
+| 136 | ufos - alienleaks - mothership - nordstream - reconnaissance | 22 | 136_ufos_alienleaks_mothership_nordstream | 
+| 137 | handsome - loves - wooooo - husband - patriot | 21 | 137_handsome_loves_wooooo_husband | 
+| 138 | ncov - swabs - test - contagious - diagnosed | 21 | 138_ncov_swabs_test_contagious | 
+| 139 | explosion - refinery - pemex - louisiana - hazmat | 21 | 139_explosion_refinery_pemex_louisiana | 
+| 140 | died - myocarditis - vaccinated - stroke - moussa | 21 | 140_died_myocarditis_vaccinated_stroke | 
+| 141 | ballots - pennsylvania - countywide - scanned - undelivered | 21 | 141_ballots_pennsylvania_countywide_scanned | 
+| 142 | wikileaks - pompeo - extradited - julian - assassinate | 20 | 142_wikileaks_pompeo_extradited_julian | 
+| 143 | milley - mattis - repdonaldspress - soleimani - treasonous | 20 | 143_milley_mattis_repdonaldspress_soleimani |
+  
+</details>
+
+## Training hyperparameters
+
+* calculate_probabilities: True
+* 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: False
+* zeroshot_min_similarity: 0.7
+* zeroshot_topic_list: None
+
+## Framework versions
+
+* Numpy: 1.26.4
+* HDBSCAN: 0.8.40
+* UMAP: 0.5.7
+* Pandas: 2.2.3
+* Scikit-Learn: 1.5.2
+* Sentence-transformers: 3.3.1
+* Transformers: 4.46.3
+* Numba: 0.60.0
+* Plotly: 5.24.1
+* Python: 3.10.12

config.json

@@ -0,0 +1,16 @@
+{
+  "calculate_probabilities": true,
+  "language": null,
+  "low_memory": false,
+  "min_topic_size": 10,
+  "n_gram_range": [
+    1,
+    1
+  ],
+  "nr_topics": null,
+  "seed_topic_list": null,
+  "top_n_words": 10,
+  "verbose": false,
+  "zeroshot_min_similarity": 0.7,
+  "zeroshot_topic_list": null
+}

ctfidf.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1370e9a5bff54be83fa077ddb0e2da01d2a52762f4b24758144747c0b0c3baf
+size 2277740

topic_embeddings.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:545da3ecaad39207cc3d481366f31cf8ccb7a0f496ace4132a13e25e4225eedf
+size 594016