dssg_topicmodel_500000

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("sanash43/dssg_topicmodel_500000")

topic_model.get_topic_info()

Topic overview

• Number of topics: 49
• Number of training documents: 500000

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
0	the - of - to - and - in	444110	0_the_of_to_and
1	university - college - student - passed - permit	31380	1_university_college_student_passed
2	001 - 000 - xxxxxxxxxxxx - on9998 - 8703	10678	2_001_000_xxxxxxxxxxxx_on9998
3	ergocentric - inc - or - services - 1231	3124	3_ergocentric_inc_or_services
4	regular - force - labrador - newfoundland - commercial	1590	4_regular_force_labrador_newfoundland
5	seeding - hail - storm - radar - weather	1228	5_seeding_hail_storm_radar
6	000000 - rental - 42012e12 - 5000 - 2170	926	6_000000_rental_42012e12_5000
7	hearing - loss - tinnitus - noise - ear	796	7_hearing_loss_tinnitus_noise
8	the - and - of - in - you	684	8_the_and_of_in
9	traduction - documents - parl - mots - tr03	534	9_traduction_documents_parl_mots
10	mci - 24 - 1943 - 23 - inst	517	10_mci_24_1943_23
11	cbsa - lasfc - dasile - demandeurs - total	467	11_cbsa_lasfc_dasile_demandeurs
12	wwater - burlington - laboratory - eclabbur - testing	424	12_wwater_burlington_laboratory_eclabbur
13	epoll - ou - doffres - elector - 10162	306	13_epoll_ou_doffres_elector
14	heritage - sussex - the - residence - building	249	14_heritage_sussex_the_residence
15	greenough - daycare - wellington - consulting - october	239	15_greenough_daycare_wellington_consulting
16	tage - floor - rue - confirmed - dorchester	228	16_tage_floor_rue_confirmed
17	jeunes - youth - we - de - les	216	17_jeunes_youth_we_de
18	bnp - hartals - violence - the - that	211	18_bnp_hartals_violence_the
19	10aig - i0aig - 10aic - ioaig - i0aic	187	19_10aig_i0aig_10aic_ioaig
20	complaints - files - case - rdims - vs	173	20_complaints_files_case_rdims
21	mckinsey - formatted - font - publishingemail - page	165	21_mckinsey_formatted_font_publishingemail
22	cerb - english - french - xxxxxxxxxxxx - rdprm	151	22_cerb_english_french_xxxxxxxxxxxx
23	aeroplane - pilot - complete - private - passed	132	23_aeroplane_pilot_complete_private
24	blue - bridge - delay - water - edt	130	24_blue_bridge_delay_water
25	dymista - nasal - fluticasone - propionate - spray	123	25_dymista_nasal_fluticasone_propionate
26	individual - wh - pied - dd - tob	113	26_individual_wh_pied_dd
27	holman - financial - 19971101 - services - ar	80	27_holman_financial_19971101_services
28	pch - anthem - c210 - senator - bill	77	28_pch_anthem_c210_senator
29	6299 - r300 - assigned - liabilities - 21111	72	29_6299_r300_assigned_liabilities
30	cad - registered - 000 - eur - 19112015	71	30_cad_registered_000_eur
31	original - single - age - months - commercial	70	31_original_single_age_months
32	biden - trump - votes - wshdc - election	57	32_biden_trump_votes_wshdc
33	link - bellletstalk - mental - farmers - thefirstsixteen	54	33_link_bellletstalk_mental_farmers
34	visits - average - daily - busiest - active	44	34_visits_average_daily_busiest
35	de - laroport - dorval - mirabel - et	41	35_de_laroport_dorval_mirabel
36	undefined - null - owning - created - status	40	36_undefined_null_owning_created
37	20190101 - treasurer - 20191231 - pastor - member	39	37_20190101_treasurer_20191231_pastor
38	1000040908 - protak - consulting - cad - cleared	37	38_1000040908_protak_consulting_cad
39	parental - z5 - 75 - maternity - zq	27	39_parental_z5_75_maternity
40	propane - per - cost - cents - bushel	26	40_propane_per_cost_cents
41	male - haiti - female - minor - colombia	26	41_male_haiti_female_minor
42	tsnrc - tsmrc - sda - standard - option	25	42_tsnrc_tsmrc_sda_standard
43	stakeholders - 10072019 - 0000 - delegation - accredited	25	43_stakeholders_10072019_0000_delegation
44	meop - eoms - multilateral - observation - eom	25	44_meop_eoms_multilateral_observation
45	de - cuves - la - des - anodes	22	45_de_cuves_la_des
46	destroyed - goods - importer - customs - rh	22	46_destroyed_goods_importer_customs
47	pa - mexico - passed - female - male	21	47_pa_mexico_passed_female
48	linda - cheverie - giulia - transcripts - command	18	48_linda_cheverie_giulia_transcripts

Training hyperparameters

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

Framework versions

• Numpy: 1.26.4
• HDBSCAN: 0.8.38.post1
• UMAP: 0.5.6
• Pandas: 2.2.1
• Scikit-Learn: 1.4.0
• Sentence-transformers: 3.0.1
• Transformers: 4.43.4
• Numba: 0.60.0
• Plotly: 5.23.0
• Python: 3.9.19