Add BERTopic model

README.md

@@ -0,0 +1,160 @@
+
+---
+tags:
+- bertopic
+library_name: bertopic
+pipeline_tag: text-classification
+---
+
+# MARTINI_enrich_BERTopic_SicilianGorillian2
+
+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_SicilianGorillian2")
+
+topic_model.get_topic_info()
+```
+
+## Topic overview
+
+* Number of topics: 91
+* Number of training documents: 13362
+
+<details>
+  <summary>Click here for an overview of all topics.</summary>
+  
+  | Topic ID | Topic Keywords | Topic Frequency | Label | 
+|----------|----------------|-----------------|-------| 
+| -1 | biden - migrants - arrested - hamas - texas | 20 | -1_biden_migrants_arrested_hamas | 
+| 0 | blacks - racists - naacp - whiteness - melanin | 8570 | 0_blacks_racists_naacp_whiteness | 
+| 1 | transgenderism - minors - doctors - detransitioned - hormones | 236 | 1_transgenderism_minors_doctors_detransitioned | 
+| 2 | fbi - insurrection - pelosi - january - footage | 178 | 2_fbi_insurrection_pelosi_january | 
+| 3 | gunshots - swat - arrests - lewiston - killed | 135 | 3_gunshots_swat_arrests_lewiston | 
+| 4 | lampedusa - mussolini - milan - deportations - austria | 130 | 4_lampedusa_mussolini_milan_deportations | 
+| 5 | sinaloa - tamaulipas - cartel - zacatecas - sicario | 128 | 5_sinaloa_tamaulipas_cartel_zacatecas | 
+| 6 | teachers - lgbtqi - superintendent - indoctrinating - blackface | 113 | 6_teachers_lgbtqi_superintendent_indoctrinating | 
+| 7 | epstein - ghislaine - jpmorgan - blackmail - billionaire | 112 | 7_epstein_ghislaine_jpmorgan_blackmail | 
+| 8 | massachusetts - mbta - mayor - sanctuary - 7news | 106 | 8_massachusetts_mbta_mayor_sanctuary | 
+| 9 | unvaxxed - vaccinate - pfizer - ivermectin - injected | 99 | 9_unvaxxed_vaccinate_pfizer_ivermectin | 
+| 10 | petrodollar - currencies - bullion - greenback - yuan | 98 | 10_petrodollar_currencies_bullion_greenback | 
+| 11 | fentanyl - narcotics - sinaloa - smuggling - overdosed | 97 | 11_fentanyl_narcotics_sinaloa_smuggling | 
+| 12 | exploded - derailment - hazmat - flames - richland | 95 | 12_exploded_derailment_hazmat_flames | 
+| 13 | missiles - destroyers - submarine - drone - hormuz | 91 | 13_missiles_destroyers_submarine_drone | 
+| 14 | gaza - airstrikes - israeli - rafah - massacres | 89 | 14_gaza_airstrikes_israeli_rafah | 
+| 15 | viralnewsnyc - migrant - bronx - midtown - shelters | 89 | 15_viralnewsnyc_migrant_bronx_midtown | 
+| 16 | musk - dorsey - tweets - taibbi - shareholders | 82 | 16_musk_dorsey_tweets_taibbi | 
+| 17 | cbp - migrants - smugglers - illegally - fy2011 | 73 | 17_cbp_migrants_smugglers_illegally | 
+| 18 | kanye - chappelle - banned - zombieland - marilyn | 68 | 18_kanye_chappelle_banned_zombieland | 
+| 19 | soros - actblue - philanthropists - donated - fraudulently | 68 | 19_soros_actblue_philanthropists_donated | 
+| 20 | ukraine - kakhovka - sevastopol - zaporozhye - missiles | 68 | 20_ukraine_kakhovka_sevastopol_zaporozhye | 
+| 21 | illegals - naperville - mayor - pritzker - sanctuary | 67 | 21_illegals_naperville_mayor_pritzker | 
+| 22 | greenpeace - methane - junkscience - wheat - hottest | 66 | 22_greenpeace_methane_junkscience_wheat | 
+| 23 | patton - chickamauga - paratroopers - lifeofthecivilwar - 1942 | 66 | 23_patton_chickamauga_paratroopers_lifeofthecivilwar | 
+| 24 | illegals - panama - border - cartel - treason | 65 | 24_illegals_panama_border_cartel | 
+| 25 | migrants - juarez - cbp - crossing - illegally | 65 | 25_migrants_juarez_cbp_crossing | 
+| 26 | tucker - carlson - murdoch - shadowbanning - intellectuals | 65 | 26_tucker_carlson_murdoch_shadowbanning | 
+| 27 | deepfake - chatgpt - palantir - technology - websites | 62 | 27_deepfake_chatgpt_palantir_technology | 
+| 28 | ballots - mandamus - georgia - democrat - tampering | 60 | 28_ballots_mandamus_georgia_democrat | 
+| 29 | smuggled - arrested - hidalgo - deputies - txdps | 59 | 29_smuggled_arrested_hidalgo_deputies | 
+| 30 | texasattorneygeneral - border - brownsville - governor - jorge | 59 | 30_texasattorneygeneral_border_brownsville_governor | 
+| 31 | banks - bailout - blankfein - sivb - insolvent | 57 | 31_banks_bailout_blankfein_sivb | 
+| 32 | illegals - biden - amnesty - border - policies | 57 | 32_illegals_biden_amnesty_border | 
+| 33 | desantis - trumpism - romney - republican - ronna | 55 | 33_desantis_trumpism_romney_republican | 
+| 34 | republicans - pelosi - mccarthy - impeaching - committees | 54 | 34_republicans_pelosi_mccarthy_impeaching | 
+| 35 | trump - judge - indictment - blagojevich - viralnewsnyc | 54 | 35_trump_judge_indictment_blagojevich | 
+| 36 | drag - hookers - lgbt - beastiality - performs | 53 | 36_drag_hookers_lgbt_beastiality | 
+| 37 | biden - teleprompter - gaffe - jokes - gwen | 52 | 37_biden_teleprompter_gaffe_jokes | 
+| 38 | riots - parisians - gendarmes - algerian - cherbourg | 50 | 38_riots_parisians_gendarmes_algerian | 
+| 39 | ireland - finglas - derry - cathaoirleach - clonmel | 50 | 39_ireland_finglas_derry_cathaoirleach | 
+| 40 | pedophiles - pervert - busted - kidnapper - shane | 50 | 40_pedophiles_pervert_busted_kidnapper | 
+| 41 | boeing - airliner - pilots - a320 - hartsfield | 49 | 41_boeing_airliner_pilots_a320 | 
+| 42 | bidenlaptopreport - bribed - whistleblowers - joe - 140million | 47 | 42_bidenlaptopreport_bribed_whistleblowers_joe | 
+| 43 | migrants - border - yuma - smugglers - bisbee | 46 | 43_migrants_border_yuma_smugglers | 
+| 44 | manchin - senators - earmarks - moratorium - gulf | 43 | 44_manchin_senators_earmarks_moratorium | 
+| 45 | followers - myniggle - tweet - clickbait - stewpetersofficial | 39 | 45_followers_myniggle_tweet_clickbait | 
+| 46 | guns - disarmed - albuquerque - governor - rallied | 38 | 46_guns_disarmed_albuquerque_governor | 
+| 47 | trudeau - alberta - cbc - _mackenzie - heckled | 37 | 47_trudeau_alberta_cbc__mackenzie | 
+| 48 | teslas - megawatt - turbines - renewable - coal | 36 | 48_teslas_megawatt_turbines_renewable | 
+| 49 | nypd - robbery - mugger - punched - boardwalk | 36 | 49_nypd_robbery_mugger_punched | 
+| 50 | bolsonaro - brasilia - favelas - paulo - janeiro | 36 | 50_bolsonaro_brasilia_favelas_paulo | 
+| 51 | wikileaks - extradited - julian - journalists - belmarsh | 35 | 51_wikileaks_extradited_julian_journalists | 
+| 52 | gaza - exterminated - instagram - benshapiro - dumbass | 34 | 52_gaza_exterminated_instagram_benshapiro | 
+| 53 | trumpo - rushmore - melania - idiots - iceberg | 32 | 53_trumpo_rushmore_melania_idiots | 
+| 54 | ufc - mayweather - knockouts - backfist - cocksucker | 32 | 54_ufc_mayweather_knockouts_backfist | 
+| 55 | ukrainehumanrightsabuses - zelenskyy - overthrown - dmytro - ww3 | 32 | 55_ukrainehumanrightsabuses_zelenskyy_overthrown_dmytro | 
+| 56 | mosques - islamize - cathedral - christianization - mujahid | 32 | 56_mosques_islamize_cathedral_christianization | 
+| 57 | maui - hawaiians - waihee - wildfires - landowners | 32 | 57_maui_hawaiians_waihee_wildfires | 
+| 58 | afrikaners - ramaphosa - johannesburg - genocide - plaasmoorde | 31 | 58_afrikaners_ramaphosa_johannesburg_genocide | 
+| 59 | arrested - felon - molestation - usbp - laredo | 31 | 59_arrested_felon_molestation_usbp | 
+| 60 | telegram - channels - evans_baked_telegram - redpilldealer4833 - scammers | 31 | 60_telegram_channels_evans_baked_telegram_redpilldealer4833 | 
+| 61 | statues - charlottesville - tubman - defaced - removed | 31 | 61_statues_charlottesville_tubman_defaced | 
+| 62 | disney - bambi - blackwash - mermaid - reimagined | 30 | 62_disney_bambi_blackwash_mermaid | 
+| 63 | antisemite - splc - mossad - greenblatt - blacklisted | 30 | 63_antisemite_splc_mossad_greenblatt | 
+| 64 | migrants - reynosa - expires - haitian - title | 29 | 64_migrants_reynosa_expires_haitian | 
+| 65 | carjackers - stolen - robbers - oakland - kia | 28 | 65_carjackers_stolen_robbers_oakland | 
+| 66 | georgia - prosecutor - fulton - willis - subpoena | 27 | 66_georgia_prosecutor_fulton_willis | 
+| 67 | women - transgender - serena - powerlifters - navratilova | 27 | 67_women_transgender_serena_powerlifters | 
+| 68 | bidenflation - cpi - krugman - deficits - reduction | 27 | 68_bidenflation_cpi_krugman_deficits | 
+| 69 | illegals - taxpayers - billion - bankrupting - dreamers | 27 | 69_illegals_taxpayers_billion_bankrupting | 
+| 70 | mayor - nypd - adams - illegals - tenants | 26 | 70_mayor_nypd_adams_illegals | 
+| 71 | deficits - hyperinflation - treasury - trillion - yellen | 26 | 71_deficits_hyperinflation_treasury_trillion | 
+| 72 | army - enlisting - milley - recruited - rifleman | 26 | 72_army_enlisting_milley_recruited | 
+| 73 | prosecutors - plea - gun - misdemeanors - delaware | 26 | 73_prosecutors_plea_gun_misdemeanors | 
+| 74 | abortions - satanic - lujan - baals - ab2223 | 25 | 74_abortions_satanic_lujan_baals | 
+| 75 | died - stroke - defibrillators - henrique - jaguars | 25 | 75_died_stroke_defibrillators_henrique | 
+| 76 | shootings - transgender - nashville - martyr - aiden | 25 | 76_shootings_transgender_nashville_martyr | 
+| 77 | holocaust - treblinka - hitler - mengele - firebombed | 25 | 77_holocaust_treblinka_hitler_mengele | 
+| 78 | ftx - bankman - zuckerberg - laundering - scandal | 25 | 78_ftx_bankman_zuckerberg_laundering | 
+| 79 | whales - giraffes - alligator - rescued - manasquan | 24 | 79_whales_giraffes_alligator_rescued | 
+| 80 | jesus - freedom - rescuing - starring - traffickers | 24 | 80_jesus_freedom_rescuing_starring | 
+| 81 | antisemite - populism - roseanne - leibowitz - jevvs | 22 | 81_antisemite_populism_roseanne_leibowitz | 
+| 82 | aipac - zionism - netanyahu - mearsheimer - influencing | 22 | 82_aipac_zionism_netanyahu_mearsheimer | 
+| 83 | farmers - vlaardingerbroek - spain - protests - blockade | 22 | 83_farmers_vlaardingerbroek_spain_protests | 
+| 84 | resilience - blackpilled - hopelessness - rebel - rejoice | 21 | 84_resilience_blackpilled_hopelessness_rebel | 
+| 85 | tiktok - banning - chinafication - ceo - totalitarianism | 21 | 85_tiktok_banning_chinafication_ceo | 
+| 86 | blackrock - megacorp - larryfink - trillions - privatized | 21 | 86_blackrock_megacorp_larryfink_trillions | 
+| 87 | censorship - misinformation - reclaimthenet - obama - unconstitutionally | 20 | 87_censorship_misinformation_reclaimthenet_obama | 
+| 88 | budweiser - mulvaney - drinkers - sponsors - boycott | 20 | 88_budweiser_mulvaney_drinkers_sponsors | 
+| 89 | boston - children - firefighters - underreported - corpse | 20 | 89_boston_children_firefighters_underreported |
+  
+</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 sha256:844ad2c71fcee7b9a8ed34abc5bffad24ad7bbba36706fa6fe25d2731bd4aaa9
+size 1299872

topic_embeddings.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de760b05833b62eb4c1bfeabde9e9b5a7d011e32bc2e32b544dae0e4da67f86f
+size 372824