potloc-topic-model

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("joshEm/potloc-topic-model")

topic_model.get_topic_info()

Topic overview

• Number of topics: 132
• Number of training documents: 10000

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	the - in - and - of - to	10	-1_the_in_and_of
0	computer - yahoo - windows - click - can	3344	0_computer_yahoo_windows_click
1	god - jesus - bible - of - believe	958	1_god_jesus_bible_of
2	bush - president - war - iraq - us	487	2_bush_president_war_iraq
3	court - job - to - for - jail	387	3_court_job_to_for
4	equation - solve - number - answer - numbers	208	4_equation_solve_number_answer
5	foreheadnheadon - directly - apply - skin - ear	162	5_foreheadnheadon_directly_apply_skin
6	song - lyrics - me - oh - music	130	6_song_lyrics_me_oh
7	degree - school - university - college - courses	123	7_degree_school_university_college
8	credit - account - mortgage - bank - loan	122	8_credit_account_mortgage_bank
9	music - song - songs - rock - favorite	111	9_music_song_songs_rock
10	friends - meet - friend - looking - woman	109	10_friends_meet_friend_looking
11	sex - orgasm - sexual - ejaculation - men	95	11_sex_orgasm_sexual_ejaculation
12	where - ebay - buy - shirt - find	94	12_where_ebay_buy_shirt
13	usa - cup - world - win - team	90	13_usa_cup_world_win
14	illegal - immigrants - mexico - illegals - immigration	81	14_illegal_immigrants_mexico_illegals
15	ball - sport - bowling - play - tennis	80	15_ball_sport_bowling_play
16	plants - plant - whales - species - seals	78	16_plants_plant_whales_species
17	man - joke - said - he - she	77	17_man_joke_said_he
18	him - he - me - guy - but	72	18_him_he_me_guy
19	period - doctor - periods - pregnant - pregnancy	65	19_period_doctor_periods_pregnant
20	study - math - test - sat - practice	64	20_study_math_test_sat
21	water - solution - moles - reaction - grams	64	21_water_solution_moles_reaction
22	flag - 1918 - of - was - the	63	22_flag_1918_of_was
23	means - french - mi - word - mean	63	23_means_french_mi_word
24	baseball - player - he - sox - pitcher	62	24_baseball_player_he_sox
25	girls - guys - men - girl - women	60	25_girls_guys_men_girl
26	questions - points - question - bored - answers	60	26_questions_points_question_bored
27	sleep - feel - hours - depression - you	57	27_sleep_feel_hours_depression
28	dna - genetic - blood - gene - cells	54	28_dna_genetic_blood_gene
29	english - language - french - learn - spanish	54	29_english_language_french_learn
30	search - find - name - looking - address	53	30_search_find_name_looking
31	word - winter - words - letters - letter	53	31_word_winter_words_letters
32	weight - calories - fat - diet - eat	52	32_weight_calories_fat_diet
33	bowl - game - qb - team - usc	47	33_bowl_game_qb_team
34	moon - time - horizon - day - sun	47	34_moon_time_horizon_day
35	wwe - guerrero - tna - diva - cena	45	35_wwe_guerrero_tna_diva
36	her - mom - gift - she - ideas	44	36_her_mom_gift_she
37	him - he - sister - my - his	44	37_him_he_sister_my
38	book - books - read - harlem - beard	43	38_book_books_read_harlem
39	color - blue - sky - light - colors	43	39_color_blue_sky_light
40	tax - taxes - unemployment - state - income	42	40_tax_taxes_unemployment_state
41	alamo - movie - movies - trilogy - aka	42	41_alamo_movie_movies_trilogy
42	show - watch - anime - episodes - tv	42	42_show_watch_anime_episodes
43	insurance - health - disability - help - for	42	43_insurance_health_disability_help
44	girl - her - she - likes - ask	42	44_girl_her_she_likes
45	navy - military - army - marine - marines	41	45_navy_military_army_marine
46	white - black - racist - blacks - racism	40	46_white_black_racist_blacks
47	cheat - spouse - wife - her - she	40	47_cheat_spouse_wife_her
48	he - him - likes - guy - me	39	48_he_him_likes_guy
49	visa - passport - birth - us - citizen	38	49_visa_passport_birth_us
50	marijuana - drug - weed - opium - test	37	50_marijuana_drug_weed_opium
51	velocity - force - angle - cm - triangle	37	51_velocity_force_angle_cm
52	cup - championship - world - player - euro	36	52_cup_championship_world_player
53	nascar - racing - fight - gordon - sport	33	53_nascar_racing_fight_gordon
54	celebrities - tom - celebrity - her - jolie	32	54_celebrities_tom_celebrity_her
55	cricket - india - batsman - dravid - indian	31	55_cricket_india_batsman_dravid
56	weight - eat - skinny - fat - healthy	30	56_weight_eat_skinny_fat
57	eye - lenses - astigmatism - eyes - glasses	30	57_eye_lenses_astigmatism_eyes
58	people - yourself - person - others - confidence	29	58_people_yourself_person_others
59	stock - fund - shares - mutual - market	29	59_stock_fund_shares_mutual
60	arsenal - liverpool - league - fans - celtic	29	60_arsenal_liverpool_league_fans
61	warming - global - climate - ice - snow	29	61_warming_global_climate_ice
62	her - she - friend - friends - me	28	62_her_she_friend_friends
63	wave - frequency - electromagnetic - radar - antenna	28	63_wave_frequency_electromagnetic_radar
64	dream - dreams - my - elevator - was	27	64_dream_dreams_my_elevator
65	gauge - bullet - caliber - gun - barrel	27	65_gauge_bullet_caliber_gun
66	pain - knee - elbow - tennis - shoulder	27	66_pain_knee_elbow_tennis
67	beach - trail - resort - appalachian - shaw	26	67_beach_trail_resort_appalachian
68	scam - home - quixtar - money - survey	25	68_scam_home_quixtar_money
69	business - sell - idea - start - money	25	69_business_sell_idea_start
70	tv - watch - channels - espn - cup	25	70_tv_watch_channels_espn
71	abs - muscles - exercises - reps - muscle	25	71_abs_muscles_exercises_reps
72	hair - shave - cut - pubic - trim	25	72_hair_shave_cut_pubic
73	psychic - divination - astrology - cards - tarot	25	73_psychic_divination_astrology_cards
74	number - phone - code - address - area	24	74_number_phone_code_address
75	was - my - hit - ever - freezer	24	75_was_my_hit_ever
76	trailers - trailer - dvd - media - wmp	24	76_trailers_trailer_dvd_media
77	penis - condom - size - sex - inches	24	77_penis_condom_size_sex
78	love - person - beloved - live - we	24	78_love_person_beloved_live
79	war - world - countries - soviet - were	24	79_war_world_countries_soviet
80	de - le - la - et - les	24	80_de_le_la_et
81	job - jobs - guard - where - work	24	81_job_jobs_guard_where
82	christmas - thanksgiving - holidays - celebrate - tree	24	82_christmas_thanksgiving_holidays_celebrate
83	hepatitis - pneumonia - infections - vaccination - link	23	83_hepatitis_pneumonia_infections_vaccination
84	peanuts - ibs - may - heartburn - bowel	22	84_peanuts_ibs_may_heartburn
85	name - sarah - named - pronounced - my	21	85_name_sarah_named_pronounced
86	kids - he - husband - him - cheated	20	86_kids_he_husband_him
87	gas - oil - energy - kingdom - 2006	19	87_gas_oil_energy_kingdom
88	taller - tall - height - grow - short	19	88_taller_tall_height_grow
89	estate - property - heirs - lien - damages	19	89_estate_property_heirs_lien
90	aluminum - 68 - element - 212 - metal	18	90_aluminum_68_element_212
91	organization - management - organizational - behavior - leadership	18	91_organization_management_organizational_behavior
92	melatonin - medication - effects - dosage - zofran	18	92_melatonin_medication_effects_dosage
93	smoking - quit - smoke - smoked - session	17	93_smoking_quit_smoke_smoked
94	nba - referees - game - heat - win	17	94_nba_referees_game_heat
95	superman - doom - hero - vs - super	17	95_superman_doom_hero_vs
96	skateboarding - skateboard - snowboard - snowboarding - gymnastics	17	96_skateboarding_skateboard_snowboard_snowboarding
97	electron - quarks - neutrons - antimatter - particle	16	97_electron_quarks_neutrons_antimatter
98	happy - happiness - life - rushhour - secret	16	98_happy_happiness_life_rushhour
99	fart - farting - gas - embarrassing - flatus	16	99_fart_farting_gas_embarrassing
100	teeth - tooth - dentist - gums - braces	16	100_teeth_tooth_dentist_gums
101	scorpio - zodiac - libra - signs - cancers	16	101_scorpio_zodiac_libra_signs
102	dog - wolf - sheep - horse - animal	16	102_dog_wolf_sheep_horse
103	hiv - aids - virus - infected - blood	16	103_hiv_aids_virus_infected
104	thanked - poem - poetry - she - were	15	104_thanked_poem_poetry_she
105	force - motion - mass - momentum - rocket	15	105_force_motion_mass_momentum
106	minister - president - kagame - prime - natchaba	15	106_minister_president_kagame_prime
107	kiss - kissing - lips - gently - tongue	15	107_kiss_kissing_lips_gently
108	pictures - photos - google - site - find	15	108_pictures_photos_google_site
109	dating - age - old - young - 19	14	109_dating_age_old_young
110	ebay - sell - smc - selling - products	14	110_ebay_sell_smc_selling
111	planets - sun - stars - star - earth	14	111_planets_sun_stars_star
112	imports - trade - importing - oil - mobil	14	112_imports_trade_importing_oil
113	questions - question - politics - reported - answers	14	113_questions_question_politics_reported
114	gay - crackle - snap - girlfriend - marry	14	114_gay_crackle_snap_girlfriend
115	gravity - sun - earth - rotating - force	13	115_gravity_sun_earth_rotating
116	weaknesses - abt - strengths - interview - job	13	116_weaknesses_abt_strengths_interview
117	love - eachother - fall - forget - deeply	13	117_love_eachother_fall_forget
118	animals - pets - tv - cage - communicate	13	118_animals_pets_tv_cage
119	flax - yogurt - nonfat - health - healthy	13	119_flax_yogurt_nonfat_health
120	grants - grant - business - federal - entrepreneurs	13	120_grants_grant_business_federal
121	idol - american - chris - win - favorite	12	121_idol_american_chris_win
122	clubs - golf - hit - irons - iron	12	122_clubs_golf_hit_irons
123	lottery - scam - scammer - money - international	12	123_lottery_scam_scammer_money
124	address - email - presale - bart - michaels	12	124_address_email_presale_bart
125	jones - her - she - stargate - reynolds	11	125_jones_her_she_stargate
126	data - product - analysis - regression - marketing	11	126_data_product_analysis_regression
127	cancer - cure - tumor - parasite - cancers	11	127_cancer_cure_tumor_parasite
128	nba - paul - team - redick - kobe	11	128_nba_paul_team_redick
129	autism - autistic - homeschooling - child - she	10	129_autism_autistic_homeschooling_child
130	seller - nike - soccer - jersey - dynamo	10	130_seller_nike_soccer_jersey

Training hyperparameters

• calculate_probabilities: False
• 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
• zeroshot_min_similarity: 0.7
• zeroshot_topic_list: None

Framework versions

• Numpy: 1.23.5
• HDBSCAN: 0.8.33
• UMAP: 0.5.5
• Pandas: 1.5.3
• Scikit-Learn: 1.2.2
• Sentence-transformers: 2.2.2
• Transformers: 4.35.2
• Numba: 0.58.1
• Plotly: 5.15.0
• Python: 3.10.12