Add BERTopic model

README.md

@@ -0,0 +1,193 @@
+
+---
+tags:
+- bertopic
+library_name: bertopic
+pipeline_tag: text-classification
+---
+
+# cnn_dailymail_108_50000_25000_test
+
+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("KingKazma/cnn_dailymail_108_50000_25000_test")
+
+topic_model.get_topic_info()
+```
+
+## Topic overview
+
+* Number of topics: 126
+* Number of training documents: 11490
+
+<details>
+  <summary>Click here for an overview of all topics.</summary>
+  
+  | Topic ID | Topic Keywords | Topic Frequency | Label | 
+|----------|----------------|-----------------|-------| 
+| -1 | said - one - year - also - would | 5 | -1_said_one_year_also | 
+| 0 | madrid - real - barcelona - atletico - ronaldo | 6198 | 0_madrid_real_barcelona_atletico | 
+| 1 | isis - syria - islamic - group - iraqi | 263 | 1_isis_syria_islamic_group | 
+| 2 | baby - cancer - hospital - birth - mother | 189 | 2_baby_cancer_hospital_birth | 
+| 3 | fight - mayweather - pacquiao - manny - floyd | 177 | 3_fight_mayweather_pacquiao_manny | 
+| 4 | driver - car - vehicle - road - crash | 163 | 4_driver_car_vehicle_road | 
+| 5 | united - van - manchester - gaal - city | 156 | 5_united_van_manchester_gaal | 
+| 6 | labour - ukip - party - mr - miliband | 129 | 6_labour_ukip_party_mr | 
+| 7 | masters - woods - augusta - mcilroy - spieth | 117 | 7_masters_woods_augusta_mcilroy | 
+| 8 | england - test - wicket - cricket - anderson | 115 | 8_england_test_wicket_cricket | 
+| 9 | fashion - dress - model - collection - designer | 107 | 9_fashion_dress_model_collection | 
+| 10 | school - student - teacher - sexual - sex | 105 | 10_school_student_teacher_sexual | 
+| 11 | minute - wigan - goal - watford - league | 99 | 11_minute_wigan_goal_watford | 
+| 12 | chocolate - food - sugar - egg - chicken | 97 | 12_chocolate_food_sugar_egg | 
+| 13 | liverpool - sterling - rodgers - gerrard - raheem | 93 | 13_liverpool_sterling_rodgers_gerrard | 
+| 14 | celtic - rangers - scottish - inverness - mccall | 91 | 14_celtic_rangers_scottish_inverness | 
+| 15 | clinton - hillary - clintons - president - campaign | 90 | 15_clinton_hillary_clintons_president | 
+| 16 | lion - animal - zoo - elephant - bear | 89 | 16_lion_animal_zoo_elephant | 
+| 17 | dog - cat - animal - pet - owner | 89 | 17_dog_cat_animal_pet | 
+| 18 | saracens - rugby - clermont - wasps - toulon | 75 | 18_saracens_rugby_clermont_wasps | 
+| 19 | murray - djokovic - open - berdych - miami | 74 | 19_murray_djokovic_open_berdych | 
+| 20 | chelsea - mourinho - chelseas - hazard - league | 70 | 20_chelsea_mourinho_chelseas_hazard | 
+| 21 | villa - sherwood - benteke - ramsey - aston | 68 | 21_villa_sherwood_benteke_ramsey | 
+| 22 | property - home - house - room - estate | 68 | 22_property_home_house_room | 
+| 23 | arsenal - wenger - gunners - arsene - sanchez | 66 | 23_arsenal_wenger_gunners_arsene | 
+| 24 | planet - earth - solar - surface - moon | 66 | 24_planet_earth_solar_surface | 
+| 25 | hamilton - rosberg - race - mercedes - prix | 66 | 25_hamilton_rosberg_race_mercedes | 
+| 26 | bayern - guardiola - porto - munich - pep | 64 | 26_bayern_guardiola_porto_munich | 
+| 27 | wars - film - star - movie - trailer | 62 | 27_wars_film_star_movie | 
+| 28 | hughes - capitol - security - snowden - gyrocopter | 60 | 28_hughes_capitol_security_snowden | 
+| 29 | newcastle - sunderland - carver - game - fan | 58 | 29_newcastle_sunderland_carver_game | 
+| 30 | gray - police - baltimore - officer - grays | 56 | 30_gray_police_baltimore_officer | 
+| 31 | shot - shooting - police - gun - said | 56 | 31_shot_shooting_police_gun | 
+| 32 | flight - plane - passenger - airport - airline | 53 | 32_flight_plane_passenger_airport | 
+| 33 | nepal - earthquake - kathmandu - everest - quake | 53 | 33_nepal_earthquake_kathmandu_everest | 
+| 34 | prince - royal - duchess - princess - queen | 51 | 34_prince_royal_duchess_princess | 
+| 35 | hotel - island - resort - sea - room | 49 | 35_hotel_island_resort_sea | 
+| 36 | fire - blaze - flame - smoke - firefighter | 48 | 36_fire_blaze_flame_smoke | 
+| 37 | ship - vessel - boat - crew - titanic | 48 | 37_ship_vessel_boat_crew | 
+| 38 | mccoy - jockey - race - ride - ap | 47 | 38_mccoy_jockey_race_ride | 
+| 39 | chan - sukumaran - execution - bali - indonesian | 46 | 39_chan_sukumaran_execution_bali | 
+| 40 | anzac - gallipoli - war - australian - sbs | 45 | 40_anzac_gallipoli_war_australian | 
+| 41 | weight - size - stone - eating - food | 44 | 41_weight_size_stone_eating | 
+| 42 | migrant - boat - libya - mediterranean - italian | 42 | 42_migrant_boat_libya_mediterranean | 
+| 43 | iran - nuclear - deal - agreement - irans | 41 | 43_iran_nuclear_deal_agreement | 
+| 44 | shark - whale - fish - seal - dolphin | 41 | 44_shark_whale_fish_seal | 
+| 45 | manziel - nfl - game - sox - quarterback | 41 | 45_manziel_nfl_game_sox | 
+| 46 | yemen - saudi - houthi - houthis - rebel | 40 | 46_yemen_saudi_houthi_houthis | 
+| 47 | money - fraud - court - bank - account | 39 | 47_money_fraud_court_bank | 
+| 48 | cave - dinosaur - neanderthals - bone - researcher | 35 | 48_cave_dinosaur_neanderthals_bone | 
+| 49 | bruce - bobbi - bobby - jenner - kris | 35 | 49_bruce_bobbi_bobby_jenner | 
+| 50 | pardew - premier - ham - league - palace | 34 | 50_pardew_premier_ham_league | 
+| 51 | hernandez - lloyd - hernandezs - odin - murder | 34 | 51_hernandez_lloyd_hernandezs_odin | 
+| 52 | apple - watch - battery - iphone - samsung | 33 | 52_apple_watch_battery_iphone | 
+| 53 | law - marriage - religious - samesex - gay | 32 | 53_law_marriage_religious_samesex | 
+| 54 | tsarnaev - boston - dzhokhar - marathon - tamerlan | 32 | 54_tsarnaev_boston_dzhokhar_marathon | 
+| 55 | buckley - police - glasgow - murder - miss | 32 | 55_buckley_police_glasgow_murder | 
+| 56 | slager - scott - officer - charleston - taser | 31 | 56_slager_scott_officer_charleston | 
+| 57 | alshabaab - garissa - kenya - kenyan - somalia | 31 | 57_alshabaab_garissa_kenya_kenyan | 
+| 58 | marathon - running - race - runner - run | 29 | 58_marathon_running_race_runner | 
+| 59 | tax - labour - osborne - economy - balls | 29 | 59_tax_labour_osborne_economy | 
+| 60 | aldi - phone - per - tesco - app | 29 | 60_aldi_phone_per_tesco | 
+| 61 | dellinger - langlais - murder - fradeneck - body | 29 | 61_dellinger_langlais_murder_fradeneck | 
+| 62 | vault - gang - raid - thief - hatton | 28 | 62_vault_gang_raid_thief | 
+| 63 | lubitz - germanwings - flight - crash - plane | 27 | 63_lubitz_germanwings_flight_crash | 
+| 64 | janner - lord - saunders - abuse - public | 27 | 64_janner_lord_saunders_abuse | 
+| 65 | point - nba - playoff - scored - rebound | 27 | 65_point_nba_playoff_scored | 
+| 66 | kane - tottenham - pochettino - townsend - spurs | 27 | 66_kane_tottenham_pochettino_townsend | 
+| 67 | groening - camp - auschwitz - nazi - kor | 26 | 67_groening_camp_auschwitz_nazi | 
+| 68 | crucible - osullivan - selby - frame - doherty | 25 | 68_crucible_osullivan_selby_frame | 
+| 69 | korea - kim - korean - north - seoul | 25 | 69_korea_kim_korean_north | 
+| 70 | melbourne - australia - islamic - rally - australian | 25 | 70_melbourne_australia_islamic_rally | 
+| 71 | nhs - patient - gp - gps - ae | 25 | 71_nhs_patient_gp_gps | 
+| 72 | bates - harris - tulsa - deputy - taser | 25 | 72_bates_harris_tulsa_deputy | 
+| 73 | artist - art - paint - painting - colouring | 25 | 73_artist_art_paint_painting | 
+| 74 | south - johannesburg - africa - african - violence | 24 | 74_south_johannesburg_africa_african | 
+| 75 | phelps - ennishill - olympic - bolt - championships | 24 | 75_phelps_ennishill_olympic_bolt | 
+| 76 | scott - leeton - stephanie - ms - scotts | 23 | 76_scott_leeton_stephanie_ms | 
+| 77 | cancer - breast - prostate - gene - treatment | 23 | 77_cancer_breast_prostate_gene | 
+| 78 | clarkson - gear - bbc - hammond - top | 21 | 78_clarkson_gear_bbc_hammond | 
+| 79 | russian - putin - russia - ukraine - moscow | 21 | 79_russian_putin_russia_ukraine | 
+| 80 | marijuana - cannabis - drug - hemp - medical | 21 | 80_marijuana_cannabis_drug_hemp | 
+| 81 | emoji - app - user - facebook - instagram | 21 | 81_emoji_app_user_facebook | 
+| 82 | brain - memory - dementia - study - rat | 20 | 82_brain_memory_dementia_study | 
+| 83 | vaccine - vaccination - cough - whooping - autism | 19 | 83_vaccine_vaccination_cough_whooping | 
+| 84 | boko - haram - nigeria - buhari - nigerian | 19 | 84_boko_haram_nigeria_buhari | 
+| 85 | housing - tenant - buy - association - property | 19 | 85_housing_tenant_buy_association | 
+| 86 | benaud - cricket - richie - test - commentator | 18 | 86_benaud_cricket_richie_test | 
+| 87 | space - rocket - spacex - launch - astronaut | 18 | 87_space_rocket_spacex_launch | 
+| 88 | cuba - castro - obama - cuban - president | 18 | 88_cuba_castro_obama_cuban | 
+| 89 | kun - pingan - xie - baby - china | 18 | 89_kun_pingan_xie_baby | 
+| 90 | song - music - studio - abbey - manuscript | 17 | 90_song_music_studio_abbey | 
+| 91 | holpin - funeral - care - child - older | 17 | 91_holpin_funeral_care_child | 
+| 92 | diamond - underground - rock - cave - garnet | 17 | 92_diamond_underground_rock_cave | 
+| 93 | sydney - storm - ses - flooding - weather | 17 | 93_sydney_storm_ses_flooding | 
+| 94 | china - chinese - chinas - gao - organ | 17 | 94_china_chinese_chinas_gao | 
+| 95 | genocide - armenians - armenian - pope - ottoman | 16 | 95_genocide_armenians_armenian_pope | 
+| 96 | dunblane - murray - andy - cathedral - wedding | 16 | 96_dunblane_murray_andy_cathedral | 
+| 97 | weather - temperature - warm - sunshine - yesterday | 15 | 97_weather_temperature_warm_sunshine | 
+| 98 | crash - died - manyang - accident - guode | 15 | 98_crash_died_manyang_accident | 
+| 99 | brandt - dr - kimmy - franff - fredric | 14 | 99_brandt_dr_kimmy_franff | 
+| 100 | mchenry - britt - towing - espn - battilana | 14 | 100_mchenry_britt_towing_espn | 
+| 101 | population - cent - per - immigrant - country | 14 | 101_population_cent_per_immigrant | 
+| 102 | tornado - storm - weather - hail - severe | 13 | 102_tornado_storm_weather_hail | 
+| 103 | school - exam - pupil - math - english | 13 | 103_school_exam_pupil_math | 
+| 104 | klopp - dortmund - tuchel - borussia - bundesliga | 13 | 104_klopp_dortmund_tuchel_borussia | 
+| 105 | water - drought - california - state - snow | 12 | 105_water_drought_california_state | 
+| 106 | fifa - blatter - uefa - chess - football | 12 | 106_fifa_blatter_uefa_chess | 
+| 107 | koeman - southampton - saints - fuchs - season | 12 | 107_koeman_southampton_saints_fuchs | 
+| 108 | nuclear - reactor - radiation - plant - fukushima | 12 | 108_nuclear_reactor_radiation_plant | 
+| 109 | car - audi - electric - vehicle - motor | 11 | 109_car_audi_electric_vehicle | 
+| 110 | glitter - sex - nauru - sexual - mee | 11 | 110_glitter_sex_nauru_sexual | 
+| 111 | luke - search - eildon - shambrook - missing | 11 | 111_luke_search_eildon_shambrook | 
+| 112 | music - spotify - radio - streaming - service | 11 | 112_music_spotify_radio_streaming | 
+| 113 | pusok - deputy - officer - mcmahon - bernardino | 9 | 113_pusok_deputy_officer_mcmahon | 
+| 114 | valle - hilbert - gilberto - dmx - whittington | 8 | 114_valle_hilbert_gilberto_dmx | 
+| 115 | alcohol - oak - wine - drinking - bottle | 7 | 115_alcohol_oak_wine_drinking | 
+| 116 | dollar - g650 - jesus - catholic - god | 7 | 116_dollar_g650_jesus_catholic | 
+| 117 | hair - labium - cheryl - finn - woman | 7 | 117_hair_labium_cheryl_finn | 
+| 118 | okawa - oldest - guinness - weber - weaver | 7 | 118_okawa_oldest_guinness_weber | 
+| 119 | martinez - everton - mirallas - lennon - roberto | 6 | 119_martinez_everton_mirallas_lennon | 
+| 120 | karmel - diet - paleo - vitamin - health | 6 | 120_karmel_diet_paleo_vitamin | 
+| 121 | redman - wisconsin - badgers - basketball - wildcats | 5 | 121_redman_wisconsin_badgers_basketball | 
+| 122 | singh - india - jyoti - indian - protest | 5 | 122_singh_india_jyoti_indian | 
+| 123 | volcano - eruption - dune - linear - ash | 5 | 123_volcano_eruption_dune_linear | 
+| 124 | tahir - castner - mascitelli - easy - restraining | 5 | 124_tahir_castner_mascitelli_easy |
+  
+</details>
+
+## Training hyperparameters
+
+* calculate_probabilities: True
+* language: english
+* 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
+
+## Framework versions
+
+* Numpy: 1.22.4
+* HDBSCAN: 0.8.33
+* UMAP: 0.5.3
+* Pandas: 1.5.3
+* Scikit-Learn: 1.2.2
+* Sentence-transformers: 2.2.2
+* Transformers: 4.31.0
+* Numba: 0.57.1
+* Plotly: 5.13.1
+* Python: 3.10.12

config.json

@@ -0,0 +1,15 @@
+{
+  "calculate_probabilities": true,
+  "language": "english",
+  "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,
+  "embedding_model": "sentence-transformers/all-MiniLM-L6-v2"
+}

topic_embeddings.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae8403b0a69922d827e4c40a392ddf770eb2d9b083cedc73b310daa85dcec093
+size 193624