cnn_dailymail_6789_200000_100000_v1_50topics_train

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("KingKazma/cnn_dailymail_6789_200000_100000_v1_50topics_train")

topic_model.get_topic_info()

Topic overview

• Number of topics: 50
• Number of training documents: 200000

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	said - one - year - people - would	5	-1_said_one_year_people
0	league - player - game - team - cup	104194	0_league_player_game_team
1	said - police - told - court - family	27178	1_said_police_told_court
2	said - government - us - military - president	16379	2_said_government_us_military
3	car - said - flight - fire - plane	12476	3_car_said_flight_fire
4	per - cent - said - year - school	6776	4_per_cent_said_year
5	obama - president - said - state - republican	4128	5_obama_president_said_state
6	film - show - movie - cosby - the	3747	6_film_show_movie_cosby
7	said - mexico - mexican - government - border	2967	7_said_mexico_mexican_government
8	dog - animal - cat - zoo - pet	2258	8_dog_animal_cat_zoo
9	fashion - weight - art - painting - dress	2176	9_fashion_weight_art_painting
10	apple - user - iphone - google - facebook	2139	10_apple_user_iphone_google
11	food - energy - climate - per - gas	1861	11_food_energy_climate_per
12	ebola - virus - health - disease - outbreak	1846	12_ebola_virus_health_disease
13	war - soldier - british - mr - said	1693	13_war_soldier_british_mr
14	shark - whale - ship - oil - water	1686	14_shark_whale_ship_oil
15	cancer - drug - marijuana - smoking - study	1576	15_cancer_drug_marijuana_smoking
16	space - earth - planet - mars - nasa	1361	16_space_earth_planet_mars
17	prince - royal - queen - duchess - princess	1230	17_prince_royal_queen_duchess
18	ancient - found - site - archaeologist - discovered	769	18_ancient_found_site_archaeologist
19	pope - vatican - church - francis - cardinal	605	19_pope_vatican_church_francis
20	lottery - ticket - jackpot - million - winning	604	20_lottery_ticket_jackpot_million
21	game - robot - console - xbox - 3d	494	21_game_robot_console_xbox
22	park - hotel - island - beach - resort	428	22_park_hotel_island_beach
23	hollande - sarkozy - trierweiler - french - francois	354	23_hollande_sarkozy_trierweiler_french
24	teeth - eye - hand - ear - surgery	180	24_teeth_eye_hand_ear
25	kyle - routh - sniper - littlefield - gun	137	25_kyle_routh_sniper_littlefield
26	country - population - corruption - per - city	121	26_country_population_corruption_per
27	dubai - hajj - pilgrim - mecca - mme	88	27_dubai_hajj_pilgrim_mecca
28	ballet - filin - bolshoi - dancer - dmitrichenko	66	28_ballet_filin_bolshoi_dancer
29	oldest - age - guinness - worlds - dangi	50	29_oldest_age_guinness_worlds
30	fragrance - scent - perfume - smell - bottle	45	30_fragrance_scent_perfume_smell
31	dna - cell - graphene - genome - synthetic	44	31_dna_cell_graphene_genome
32	accent - favourite - fan - language - top	35	32_accent_favourite_fan_language
33	nobel - prize - peace - award - committee	33	33_nobel_prize_peace_award
34	violin - orchestra - stradivarius - instrument - symphony	31	34_violin_orchestra_stradivarius_instrument
35	turing - bletchley - enigma - code - machine	30	35_turing_bletchley_enigma_code
36	gandolfini - sopranos - gandolfinis - soprano - actor	26	36_gandolfini_sopranos_gandolfinis_soprano
37	nelson - napoleon - battle - trafalgar - hms	26	37_nelson_napoleon_battle_trafalgar
38	redskins - name - native - snyder - washington	25	38_redskins_name_native_snyder
39	eurovision - contest - song - conchita - country	25	39_eurovision_contest_song_conchita
40	evolution - creationism - scientific - intelligent - believe	21	40_evolution_creationism_scientific_intelligent
41	prabowo - indonesia - jakarta - widodo - jokowi	17	41_prabowo_indonesia_jakarta_widodo
42	dmlaterbundle - twittervia - lanza - zann - ilfracombe	15	42_dmlaterbundle_twittervia_lanza_zann
43	clock - time - hour - daylight - westworth	13	43_clock_time_hour_daylight
44	ikea - furniture - ikeas - kamprad - refugee	12	44_ikea_furniture_ikeas_kamprad
45	vick - vicks - nfl - dog - virginia	10	45_vick_vicks_nfl_dog
46	bulb - light - leds - paddle - bulbs	8	46_bulb_light_leds_paddle
47	port - cairo - ministry - egypt - fan	7	47_port_cairo_ministry_egypt
48	sanford - sanfords - jenny - carolina - mark	5	48_sanford_sanfords_jenny_carolina

Training hyperparameters

• calculate_probabilities: False
• language: english
• low_memory: False
• min_topic_size: 10
• n_gram_range: (1, 1)
• nr_topics: 50
• 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