Add BERTopic model

README.md

@@ -0,0 +1,185 @@
+
+---
+tags:
+- bertopic
+library_name: bertopic
+pipeline_tag: text-classification
+---
+
+# cnn_dailymail_6789_50000_25000_validation
+
+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_6789_50000_25000_validation")
+
+topic_model.get_topic_info()
+```
+
+## Topic overview
+
+* Number of topics: 118
+* Number of training documents: 13368
+
+<details>
+  <summary>Click here for an overview of all topics.</summary>
+  
+  | Topic ID | Topic Keywords | Topic Frequency | Label | 
+|----------|----------------|-----------------|-------| 
+| -1 | said - one - year - also - time | 5 | -1_said_one_year_also | 
+| 0 | isis - syria - islamic - attack - group | 6535 | 0_isis_syria_islamic_attack | 
+| 1 | police - officer - shooting - ferguson - said | 452 | 1_police_officer_shooting_ferguson | 
+| 2 | labour - mr - party - election - tax | 415 | 2_labour_mr_party_election | 
+| 3 | flight - plane - pilot - aircraft - lubitz | 268 | 3_flight_plane_pilot_aircraft | 
+| 4 | car - driver - driving - road - crash | 224 | 4_car_driver_driving_road | 
+| 5 | hair - fashion - dress - model - look | 223 | 5_hair_fashion_dress_model | 
+| 6 | cricket - england - cup - world - pietersen | 205 | 6_cricket_england_cup_world | 
+| 7 | food - sugar - per - cent - product | 189 | 7_food_sugar_per_cent | 
+| 8 | clinton - email - obama - president - clintons | 188 | 8_clinton_email_obama_president | 
+| 9 | property - house - home - price - room | 186 | 9_property_house_home_price | 
+| 10 | rangers - celtic - scotland - ibrox - game | 165 | 10_rangers_celtic_scotland_ibrox | 
+| 11 | fight - pacquiao - mayweather - manny - floyd | 151 | 11_fight_pacquiao_mayweather_manny | 
+| 12 | england - nations - wales - ireland - six | 143 | 12_england_nations_wales_ireland | 
+| 13 | hamilton - mercedes - prix - race - rosberg | 135 | 13_hamilton_mercedes_prix_race | 
+| 14 | baby - birth - cancer - hospital - born | 126 | 14_baby_birth_cancer_hospital | 
+| 15 | fa - league - game - villa - bradford | 116 | 15_fa_league_game_villa | 
+| 16 | dog - animal - dogs - owner - pet | 114 | 16_dog_animal_dogs_owner | 
+| 17 | police - abuse - sexual - sex - child | 112 | 17_police_abuse_sexual_sex | 
+| 18 | madrid - ronaldo - barcelona - real - messi | 111 | 18_madrid_ronaldo_barcelona_real | 
+| 19 | chelsea - mourinho - terry - league - jose | 106 | 19_chelsea_mourinho_terry_league | 
+| 20 | eclipse - earth - mars - solar - sun | 101 | 20_eclipse_earth_mars_solar | 
+| 21 | kane - england - hodgson - lithuania - rooney | 100 | 21_kane_england_hodgson_lithuania | 
+| 22 | show - film - corden - host - noah | 95 | 22_show_film_corden_host | 
+| 23 | prince - royal - duchess - charles - queen | 92 | 23_prince_royal_duchess_charles | 
+| 24 | murray - wells - tennis - andy - 64 | 88 | 24_murray_wells_tennis_andy | 
+| 25 | putin - russian - nemtsov - moscow - russia | 82 | 25_putin_russian_nemtsov_moscow | 
+| 26 | netanyahu - iran - nuclear - israel - israeli | 80 | 26_netanyahu_iran_nuclear_israel | 
+| 27 | court - money - bank - fraud - stiviano | 80 | 27_court_money_bank_fraud | 
+| 28 | weight - size - fat - stone - diet | 76 | 28_weight_size_fat_stone | 
+| 29 | armstrong - race - olympic - uci - championships | 74 | 29_armstrong_race_olympic_uci | 
+| 30 | cheltenham - hurdle - horse - jockey - festival | 73 | 30_cheltenham_hurdle_horse_jockey | 
+| 31 | arsenal - wenger - monaco - giroud - arsenals | 73 | 31_arsenal_wenger_monaco_giroud | 
+| 32 | mcilroy - golf - masters - woods - round | 72 | 32_mcilroy_golf_masters_woods | 
+| 33 | watch - apple - device - google - user | 66 | 33_watch_apple_device_google | 
+| 34 | fraternity - university - sae - oklahoma - chapter | 65 | 34_fraternity_university_sae_oklahoma | 
+| 35 | united - van - gaal - manchester - arsenal | 62 | 35_united_van_gaal_manchester | 
+| 36 | chan - sukumaran - indonesian - bali - myuran | 61 | 36_chan_sukumaran_indonesian_bali | 
+| 37 | school - teacher - student - district - sexual | 58 | 37_school_teacher_student_district | 
+| 38 | sunderland - poyet - advocaat - johnson - april | 55 | 38_sunderland_poyet_advocaat_johnson | 
+| 39 | clarkson - bbc - gear - top - jeremy | 55 | 39_clarkson_bbc_gear_top | 
+| 40 | fire - building - blaze - explosion - firefighter | 48 | 40_fire_building_blaze_explosion | 
+| 41 | liverpool - gerrard - rodgers - steven - anfield | 46 | 41_liverpool_gerrard_rodgers_steven | 
+| 42 | patient - nhs - ae - cancer - care | 44 | 42_patient_nhs_ae_cancer | 
+| 43 | song - zayn - thicke - gayes - pharrell | 43 | 43_song_zayn_thicke_gayes | 
+| 44 | wedding - married - couple - jaclyn - love | 41 | 44_wedding_married_couple_jaclyn | 
+| 45 | car - vehicle - electric - model - jaguar | 41 | 45_car_vehicle_electric_model | 
+| 46 | nfl - borland - bowl - brady - super | 40 | 46_nfl_borland_bowl_brady | 
+| 47 | pellegrini - city - league - manchester - barcelona | 40 | 47_pellegrini_city_league_manchester | 
+| 48 | school - education - porn - sex - child | 39 | 48_school_education_porn_sex | 
+| 49 | bear - cub - tiger - deer - wildlife | 39 | 49_bear_cub_tiger_deer | 
+| 50 | gay - law - indiana - marriage - religious | 38 | 50_gay_law_indiana_marriage | 
+| 51 | india - rape - indian - documentary - singh | 37 | 51_india_rape_indian_documentary | 
+| 52 | boko - haram - nigeria - nigerian - nigerias | 36 | 52_boko_haram_nigeria_nigerian | 
+| 53 | ebola - sierra - leone - virus - liberia | 35 | 53_ebola_sierra_leone_virus | 
+| 54 | tsarnaev - dzhokhar - boston - tamerlan - tsarnaevs | 35 | 54_tsarnaev_dzhokhar_boston_tamerlan | 
+| 55 | ski - mountain - skier - rock - lift | 32 | 55_ski_mountain_skier_rock | 
+| 56 | robbery - armed - store - police - bank | 31 | 56_robbery_armed_store_police | 
+| 57 | roma - inter - juventus - serie - fiorentina | 30 | 57_roma_inter_juventus_serie | 
+| 58 | fifa - blatter - fa - qatar - cup | 29 | 58_fifa_blatter_fa_qatar | 
+| 59 | marijuana - drug - cannabis - colorado - lsd | 29 | 59_marijuana_drug_cannabis_colorado | 
+| 60 | everton - martinez - lukaku - dynamo - evertons | 27 | 60_everton_martinez_lukaku_dynamo | 
+| 61 | chelsea - racist - paris - train - football | 27 | 61_chelsea_racist_paris_train | 
+| 62 | durst - dursts - berman - orleans - robert | 27 | 62_durst_dursts_berman_orleans | 
+| 63 | basketball - ncaa - coach - tournament - game | 25 | 63_basketball_ncaa_coach_tournament | 
+| 64 | bayern - goal - muller - shakhtar - robben | 25 | 64_bayern_goal_muller_shakhtar | 
+| 65 | hotel - beach - cruise - ship - resort | 25 | 65_hotel_beach_cruise_ship | 
+| 66 | sherwood - villa - aston - tim - brom | 25 | 66_sherwood_villa_aston_tim | 
+| 67 | snow - inch - winter - weather - ice | 24 | 67_snow_inch_winter_weather | 
+| 68 | weather - temperature - rain - snow - expected | 24 | 68_weather_temperature_rain_snow | 
+| 69 | korean - korea - kim - north - lippert | 23 | 69_korean_korea_kim_north | 
+| 70 | hospital - doctor - mrs - fracture - patient | 23 | 70_hospital_doctor_mrs_fracture | 
+| 71 | rail - calais - parking - transport - train | 22 | 71_rail_calais_parking_transport | 
+| 72 | mls - lampard - orlando - city - york | 22 | 72_mls_lampard_orlando_city | 
+| 73 | jesus - stone - circle - ancient - stonehenge | 22 | 73_jesus_stone_circle_ancient | 
+| 74 | hernandez - lloyd - jenkins - hernandezs - lloyds | 21 | 74_hernandez_lloyd_jenkins_hernandezs | 
+| 75 | drug - cocaine - jailed - steroid - cannabis | 20 | 75_drug_cocaine_jailed_steroid | 
+| 76 | secret - clancy - service - agent - white | 20 | 76_secret_clancy_service_agent | 
+| 77 | homo - fossil - specie - ago - human | 20 | 77_homo_fossil_specie_ago | 
+| 78 | image - photographer - photograph - photo - landscape | 19 | 78_image_photographer_photograph_photo | 
+| 79 | parade - patricks - irish - st - green | 19 | 79_parade_patricks_irish_st | 
+| 80 | bale - wales - israel - coleman - gareth | 19 | 80_bale_wales_israel_coleman | 
+| 81 | di - maria - angel - united - manchester | 19 | 81_di_maria_angel_united | 
+| 82 | defence - greece - spending - greek - budget | 19 | 82_defence_greece_spending_greek | 
+| 83 | sleep - store - cent - per - kraft | 18 | 83_sleep_store_cent_per | 
+| 84 | student - johnson - virginia - charlottesville - university | 18 | 84_student_johnson_virginia_charlottesville | 
+| 85 | vanuatu - cyclone - vila - pam - port | 18 | 85_vanuatu_cyclone_vila_pam | 
+| 86 | cnn - transcript - student - news - roll | 18 | 86_cnn_transcript_student_news | 
+| 87 | nazi - anne - nazis - war - camp | 18 | 87_nazi_anne_nazis_war | 
+| 88 | attack - synagogue - hebdo - paris - charlie | 17 | 88_attack_synagogue_hebdo_paris | 
+| 89 | ham - west - tomkins - reid - kouyate | 16 | 89_ham_west_tomkins_reid | 
+| 90 | balotelli - mario - liverpool - italian - striker | 16 | 90_balotelli_mario_liverpool_italian | 
+| 91 | chinese - monk - buddhist - thailand - tourist | 15 | 91_chinese_monk_buddhist_thailand | 
+| 92 | snowden - gchq - intelligence - security - agency | 15 | 92_snowden_gchq_intelligence_security | 
+| 93 | pope - francis - naples - vatican - pontiff | 14 | 93_pope_francis_naples_vatican | 
+| 94 | starbucks - schultz - race - racial - campaign | 14 | 94_starbucks_schultz_race_racial | 
+| 95 | point - rebound - sweeney - playoff - scored | 14 | 95_point_rebound_sweeney_playoff | 
+| 96 | poldark - turner - demelza - aidan - drama | 13 | 96_poldark_turner_demelza_aidan | 
+| 97 | cuba - havana - cuban - us - castro | 13 | 97_cuba_havana_cuban_us | 
+| 98 | italy - conte - italian - eder - juventus | 13 | 98_italy_conte_italian_eder | 
+| 99 | richard - iii - leicester - king - iiis | 13 | 99_richard_iii_leicester_king | 
+| 100 | sena - hartman - child - shaday - sexual | 13 | 100_sena_hartman_child_shaday | 
+| 101 | gordon - bobbi - kristina - phil - dr | 12 | 101_gordon_bobbi_kristina_phil | 
+| 102 | jobs - lu - naomi - cook - business | 12 | 102_jobs_lu_naomi_cook | 
+| 103 | duckenfield - mr - gate - hillsborough - greaney | 11 | 103_duckenfield_mr_gate_hillsborough | 
+| 104 | huang - wang - chen - wife - china | 10 | 104_huang_wang_chen_wife | 
+| 105 | coin - coins - silver - cave - gold | 10 | 105_coin_coins_silver_cave | 
+| 106 | shark - whale - mola - crab - barbero | 10 | 106_shark_whale_mola_crab | 
+| 107 | gissendaner - execution - lethal - death - injection | 10 | 107_gissendaner_execution_lethal_death | 
+| 108 | book - handshake - word - author - app | 9 | 108_book_handshake_word_author | 
+| 109 | cosby - cosbys - thompson - welles - bill | 9 | 109_cosby_cosbys_thompson_welles | 
+| 110 | school - pupil - student - parent - computer | 9 | 110_school_pupil_student_parent | 
+| 111 | china - stopera - li - orange - chinese | 8 | 111_china_stopera_li_orange | 
+| 112 | tb - vaccine - disease - measles - meningitis | 8 | 112_tb_vaccine_disease_measles | 
+| 113 | neymar - brazil - willian - dunga - france | 8 | 113_neymar_brazil_willian_dunga | 
+| 114 | gomis - swansea - muamba - fabrice - bafetimbi | 7 | 114_gomis_swansea_muamba_fabrice | 
+| 115 | netflix - tv - content - screen - definition | 6 | 115_netflix_tv_content_screen | 
+| 116 | snake - eastern - redback - postlethwaite - woolworths | 6 | 116_snake_eastern_redback_postlethwaite |
+  
+</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: 1.23.5
+* 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: 5.15.0
+* 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 sha256:1073d33bcc89cf9c86265355d9d499e319cef4dfdd8c992e8ad69ea46565f731
+size 181336