testing_b

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("sneakykilli/testing_b")

topic_model.get_topic_info()

Topic overview

• Number of topics: 20
• Number of training documents: 5134

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	killiair - flight - service - customer - airport	12	-1_killiair_flight_service_customer
0	killiair - flight - airport - time - doha	2257	0_killiair_flight_airport_time
1	bag - luggage - bags - cabin - pay	847	1_bag_luggage_bags_cabin
2	jet - ryan - easy - air - flight	499	2_jet_ryan_easy_air
3	refund - flight - cancelled - customer - service	312	3_refund_flight_cancelled_customer
4	flight - delayed - delay - gatwick - hours	229	4_flight_delayed_delay_gatwick
5	check - change - online - pay - fee	173	5_check_change_online_pay
6	food - seat - meal - flight - plane	151	6_food_seat_meal_flight
7	seats - seat - class - killiair - extra	150	7_seats_seat_class_killiair
8	star - stressstress - stress - stars - zero	149	8_star_stressstress_stress_stars
9	company - customer - worst - service - terrible	74	9_company_customer_worst_service
10	thank - amazing - crew - flight - thanks	73	10_thank_amazing_crew_flight
11	car - hire - rental - insurance - card	62	11_car_hire_rental_insurance
12	stansted - flight - airport - parking - killiair	39	12_stansted_flight_airport_parking
13	passport - date - son - gate - check	33	13_passport_date_son_gate
14	chat - customer - service - reach - ai	20	14_chat_customer_service_reach
15	voucher - rune - residual - booking - refund	15	15_voucher_rune_residual_booking
16	band - word - easy - corporate - sue	14	16_band_word_easy_corporate
17	malaga - page - alicante - taxi - killiair	13	17_malaga_page_alicante_taxi
18	good - friendly - sh - service - late	12	18_good_friendly_sh_service

Training hyperparameters

• calculate_probabilities: False
• language: None
• low_memory: False
• min_topic_size: 10
• n_gram_range: (1, 1)
• nr_topics: 20
• seed_topic_list: None
• top_n_words: 10
• verbose: False
• zeroshot_min_similarity: 0.7
• zeroshot_topic_list: None

Framework versions

• Numpy: 1.24.3
• HDBSCAN: 0.8.33
• UMAP: 0.5.5
• Pandas: 2.0.3
• Scikit-Learn: 1.2.2
• Sentence-transformers: 2.3.1
• Transformers: 4.36.2
• Numba: 0.57.1
• Plotly: 5.16.1
• Python: 3.10.12