--- tags: - bertopic library_name: bertopic pipeline_tag: text-classification --- # transformers_amazon_reviews_topics 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("inesbattah/transformers_amazon_reviews_topics") topic_model.get_topic_info() ``` ## Topic overview * Number of topics: 30 * Number of training documents: 9000
Click here for an overview of all topics. | Topic ID | Topic Keywords | Topic Frequency | Label | |----------|----------------|-----------------|-------| | -1 | amazon - quality - product - cheap - seller | 10 | -1_amazon_quality_product_cheap | | 0 | refund - ordered - order - delivered - return | 3105 | 0_refund_ordered_order_delivered | | 1 | charging - charger - charge - iphone - headphones | 1556 | 1_charging_charger_charge_iphone | | 2 | wear - shoe - shoes - zipper - fit | 655 | 2_wear_shoe_shoes_zipper | | 3 | shampoo - conditioner - scent - flavor - hair | 635 | 3_shampoo_conditioner_scent_flavor | | 4 | protector - protectors - screen - case - cases | 452 | 4_protector_protectors_screen_case | | 5 | color - colors - colored - blue - black | 293 | 5_color_colors_colored_blue | | 6 | bottle - leak - leaking - bottles - leaks | 234 | 6_bottle_leak_leaking_bottles | | 7 | lights - light - bulbs - flashlight - led | 209 | 7_lights_light_bulbs_flashlight | | 8 | dog - toy - dogs - puppy - chewed | 205 | 8_dog_toy_dogs_puppy | | 9 | chairs - chair - assemble - screws - assembling | 192 | 9_chairs_chair_assemble_screws | | 10 | cheap - cheaply - material - quality - cost | 181 | 10_cheap_cheaply_material_quality | | 11 | book - books - chapters - chapter - author | 180 | 11_book_books_chapters_chapter | | 12 | hose - faucet - pump - valve - leak | 167 | 12_hose_faucet_pump_valve | | 13 | pan - pans - pancakes - griddle - cook | 127 | 13_pan_pans_pancakes_griddle | | 14 | dvd - dvds - disc - discs - cd | 114 | 14_dvd_dvds_disc_discs | | 15 | fit - fitting - didnt - galaxy - samsung | 109 | 15_fit_fitting_didnt_galaxy | | 16 | razor - shave - razors - reviews - blades | 97 | 16_razor_shave_razors_reviews | | 17 | cartridges - cartridge - ink - printer - printing | 97 | 17_cartridges_cartridge_ink_printer | | 18 | watches - watch - clocks - clock - battery | 88 | 18_watches_watch_clocks_clock | | 19 | remote - remotes - buttons - button - programmed | 78 | 19_remote_remotes_buttons_button | | 20 | seeds - seed - planted - planting - germinated | 43 | 20_seeds_seed_planted_planting | | 21 | thermometer - temperature - temperatureoff - temps - temp | 36 | 21_thermometer_temperature_temperatureoff_temps | | 22 | instructions - directions - how - installation - cheap | 34 | 22_instructions_directions_how_installation | | 23 | pistol - holster - gun - glock19 - glock | 29 | 23_pistol_holster_gun_glock19 | | 24 | tire - tires - tube - bike - wheel | 20 | 24_tire_tires_tube_bike | | 25 | snoring - snorkeling - snore - snorkel - snores | 17 | 25_snoring_snorkeling_snore_snorkel | | 26 | rugs - carpets - carpet - rug - floors | 13 | 26_rugs_carpets_carpet_rug | | 27 | waterproof - wet - swimming - bathing - raining | 12 | 27_waterproof_wet_swimming_bathing | | 28 | fan - squealing - noise - fans - quiet | 12 | 28_fan_squealing_noise_fans |
## Training hyperparameters * calculate_probabilities: False * language: english * low_memory: False * min_topic_size: 10 * n_gram_range: (1, 1) * nr_topics: 30 * seed_topic_list: None * top_n_words: 10 * verbose: True * zeroshot_min_similarity: 0.7 * zeroshot_topic_list: None ## Framework versions * Numpy: 1.26.4 * HDBSCAN: 0.8.39 * UMAP: 0.5.7 * Pandas: 2.2.2 * Scikit-Learn: 1.5.2 * Sentence-transformers: 3.2.1 * Transformers: 4.44.2 * Numba: 0.60.0 * Plotly: 5.24.1 * Python: 3.10.12