Add BERTopic model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+ctfidf_config.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,167 @@
+
+---
+tags:
+- bertopic
+library_name: bertopic
+pipeline_tag: text-classification
+---
+
+# yelpreview_base
+
+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("Ayomidedeji/yelpreview_base")
+
+topic_model.get_topic_info()
+```
+
+## Topic overview
+
+* Number of topics: 98
+* Number of training documents: 10000
+
+<details>
+  <summary>Click here for an overview of all topics.</summary>
+  
+  | Topic ID | Topic Keywords | Topic Frequency | Label | 
+|----------|----------------|-----------------|-------| 
+| -1 | food - good - place - great - like | 10 | -1_food_good_place_great | 
+| 0 | mexican - tacos - salsa - burrito - food | 3827 | 0_mexican_tacos_salsa_burrito | 
+| 1 | pizza - crust - pizzas - good - wait | 705 | 1_pizza_crust_pizzas_good | 
+| 2 | bar - music - drinks - night - place | 393 | 2_bar_music_drinks_night | 
+| 3 | burger - fries - burgers - good - like | 288 | 3_burger_fries_burgers_good | 
+| 4 | ordered - just - bread - good - chicken | 275 | 4_ordered_just_bread_good | 
+| 5 | sushi - roll - rolls - happy hour - happy | 261 | 5_sushi_roll_rolls_happy hour | 
+| 6 | scottsdale - place - great - bar - food | 191 | 6_scottsdale_place_great_bar | 
+| 7 | coffee - starbucks - coffee shop - shop - espresso | 190 | 7_coffee_starbucks_coffee shop_shop | 
+| 8 | hotel - pool - room - stay - resort | 186 | 8_hotel_pool_room_stay | 
+| 9 | minutes - table - server - asked - came | 183 | 9_minutes_table_server_asked | 
+| 10 | chinese - chinese food - food - asian - china | 145 | 10_chinese_chinese food_food_asian | 
+| 11 | thai - pad - curry - pad thai - thai food | 131 | 11_thai_pad_curry_pad thai | 
+| 12 | beer - beers - peaks - brewery - craft | 131 | 12_beer_beers_peaks_brewery | 
+| 13 | breakfast - eggs - pancakes - toast - french toast | 115 | 13_breakfast_eggs_pancakes_toast | 
+| 14 | pho - vietnamese - spring rolls - spring - broth | 104 | 14_pho_vietnamese_spring rolls_spring | 
+| 15 | bbq - brisket - ribs - sauce - pork | 94 | 15_bbq_brisket_ribs_sauce | 
+| 16 | theater - movie - seats - movies - theaters | 84 | 16_theater_movie_seats_movies | 
+| 17 | food - place - great - lunch - love | 82 | 17_food_place_great_lunch | 
+| 18 | hair - cut - salon - haircut - barber | 81 | 18_hair_cut_salon_haircut | 
+| 19 | great - valentine - food - patio - valentine day | 78 | 19_great_valentine_food_patio | 
+| 20 | service - food - server - servers - food service | 71 | 20_service_food_server_servers | 
+| 21 | clothes - shoes - store - nordstrom - pair | 69 | 21_clothes_shoes_store_nordstrom | 
+| 22 | gym - classes - yoga - fitness - workout | 67 | 22_gym_classes_yoga_fitness | 
+| 23 | phoenix - food - durant - restaurant - good | 66 | 23_phoenix_food_durant_restaurant | 
+| 24 | italian - pasta - italian food - restaurant - best | 65 | 24_italian_pasta_italian food_restaurant | 
+| 25 | sandwich - sandwiches - bread - sacks - al | 64 | 25_sandwich_sandwiches_bread_sacks | 
+| 26 | airport - flight - terminal - sky harbor - harbor | 64 | 26_airport_flight_terminal_sky harbor | 
+| 27 | yogurt - frozen yogurt - flavors - frozen - toppings | 64 | 27_yogurt_frozen yogurt_flavors_frozen | 
+| 28 | nails - nail - manicure - pedicure - gel | 62 | 28_nails_nail_manicure_pedicure | 
+| 29 | car - auto - warranty - repair - new | 61 | 29_car_auto_warranty_repair | 
+| 30 | trail - hike - park - mountain - view | 60 | 30_trail_hike_park_mountain | 
+| 31 | dr - doctor - office - care - doctors | 58 | 31_dr_doctor_office_care | 
+| 32 | ice - ice cream - cream - flavors - custard | 56 | 32_ice_ice cream_cream_flavors | 
+| 33 | cupcakes - cupcake - cake - frosting - sprinkles | 54 | 33_cupcakes_cupcake_cake_frosting | 
+| 34 | wine - wines - total wine - daniel - bottle | 51 | 34_wine_wines_total wine_daniel | 
+| 35 | vegan - vegetarian - meat - mock - green | 45 | 35_vegan_vegetarian_meat_mock | 
+| 36 | stars - christopher - star - reason - pat | 45 | 36_stars_christopher_star_reason | 
+| 37 | staff - love place - food - great - friendly | 45 | 37_staff_love place_food_great | 
+| 38 | stadium - game - spring training - parking - spring | 44 | 38_stadium_game_spring training_parking | 
+| 39 | sub - subway - subs - jimmy - sandwich | 44 | 39_sub_subway_subs_jimmy | 
+| 40 | indian - indian food - buffet - india - masala | 43 | 40_indian_indian food_buffet_india | 
+| 41 | museum - kids - art - exhibits - exhibit | 40 | 41_museum_kids_art_exhibits | 
+| 42 | donuts - donut - dunkin - bosa - dunkin donuts | 40 | 42_donuts_donut_dunkin_bosa | 
+| 43 | fez - yelp - yelp event - event - yoli | 39 | 43_fez_yelp_yelp event_event | 
+| 44 | vet - dog - animals - pet - dogs | 35 | 44_vet_dog_animals_pet | 
+| 45 | happy hour - happy - hour - great happy - great | 35 | 45_happy hour_happy_hour_great happy | 
+| 46 | steak - steaks - steakhouse - good steak - sides | 34 | 46_steak_steaks_steakhouse_good steak | 
+| 47 | mall - stores - malls - shopping - food court | 33 | 47_mall_stores_malls_shopping | 
+| 48 | phone - store - iphone - camera - customer | 33 | 48_phone_store_iphone_camera | 
+| 49 | massage - spa - therapist - room - massages | 33 | 49_massage_spa_therapist_room | 
+| 50 | dog - dogs - hot dog - hot - beef | 33 | 50_dog_dogs_hot dog_hot | 
+| 51 | dog - pet - dog food - treats - pets | 32 | 51_dog_pet_dog food_treats | 
+| 52 | closed - location closed - open - closed good - business closed | 29 | 52_closed_location closed_open_closed good | 
+| 53 | dentist - dr - dental - teeth - office | 29 | 53_dentist_dr_dental_teeth | 
+| 54 | salad - lunch - sandwich - chicken - dressing | 29 | 54_salad_lunch_sandwich_chicken | 
+| 55 | greek - greek food - pita - gyro - greek restaurant | 27 | 55_greek_greek food_pita_gyro | 
+| 56 | waffles - lo - chicken waffles - chicken - lolo | 27 | 56_waffles_lo_chicken waffles_chicken | 
+| 57 | car - wash - car wash - job - exterior | 27 | 57_car_wash_car wash_job | 
+| 58 | gelato - angel sweet - angel - italy - flavors | 27 | 58_gelato_angel sweet_angel_italy | 
+| 59 | wings - wing - love wings - wild wings - buffalo | 26 | 59_wings_wing_love wings_wild wings | 
+| 60 | tea - boba - teas - drink - milk tea | 25 | 60_tea_boba_teas_drink | 
+| 61 | food - service - great food - great - awesome food | 25 | 61_food_service_great food_great | 
+| 62 | bagel - bagels - cream cheese - lox - cream | 25 | 62_bagel_bagels_cream cheese_lox | 
+| 63 | bruschetta - postino - wine - postinos - bottle | 24 | 63_bruschetta_postino_wine_postinos | 
+| 64 | review - stars - reviews - hotdog - mold | 24 | 64_review_stars_reviews_hotdog | 
+| 65 | foods - fresh easy - trader - easy - grocery | 22 | 65_foods_fresh easy_trader_easy | 
+| 66 | mongolian - mongolian bbq - yc - bowl - bbq | 22 | 66_mongolian_mongolian bbq_yc_bowl | 
+| 67 | service - food - time - horrible - ordered | 22 | 67_service_food_time_horrible | 
+| 68 | course - holes - courses - played - tee | 21 | 68_course_holes_courses_played | 
+| 69 | dog - dogs - park - dog park - active | 21 | 69_dog_dogs_park_dog park | 
+| 70 | books - book - library - bookstore - used books | 21 | 70_books_book_library_bookstore | 
+| 71 | pita - pita jungle - jungle - hummus - lentil | 20 | 71_pita_pita jungle_jungle_hummus | 
+| 72 | pasta - spaghetti - sauce - italian - bread | 20 | 72_pasta_spaghetti_sauce_italian | 
+| 73 | store - office max - prices - max - office | 20 | 73_store_office max_prices_max | 
+| 74 | expensive - good price - food - price - good food | 19 | 74_expensive_good price_food_price | 
+| 75 | thrift - store - goodwill - thrift store - vintage | 19 | 75_thrift_store_goodwill_thrift store | 
+| 76 | safeway - store - grocery - shopping - winco | 19 | 76_safeway_store_grocery_shopping | 
+| 77 | beer - bar - asked - minutes - trout | 18 | 77_beer_bar_asked_minutes | 
+| 78 | japanese - tokyo - japanese food - knife - knives | 18 | 78_japanese_tokyo_japanese food_knife | 
+| 79 | irish - pub - irish pub - fish chips - guinness | 16 | 79_irish_pub_irish pub_fish chips | 
+| 80 | works meh - friendly awesome - ing great - awesome intense - job super | 16 | 80_works meh_friendly awesome_ing great_awesome intense | 
+| 81 | zia - record - cd - stinkweeds - music | 15 | 81_zia_record_cd_stinkweeds | 
+| 82 | tires - tire - discount tire - discount - new tires | 14 | 82_tires_tire_discount tire_discount | 
+| 83 | cheesesteak - wiz - cheesesteaks - forefathers - philly | 14 | 83_cheesesteak_wiz_cheesesteaks_forefathers | 
+| 84 | korean - korean food - kimchi - bbq - dishes | 14 | 84_korean_korean food_kimchi_bbq | 
+| 85 | buffet - buffets - sushi - hong - hong kong | 13 | 85_buffet_buffets_sushi_hong | 
+| 86 | gyro - tzatziki - pita - gyros - meat | 13 | 86_gyro_tzatziki_pita_gyros | 
+| 87 | classes - campus - school - teacher - students | 13 | 87_classes_campus_school_teacher | 
+| 88 | romantic - love love - whinings excellent - whinings - live amazing | 13 | 88_romantic_love love_whinings excellent_whinings | 
+| 89 | patio - service - excellent service - excellent - great service | 12 | 89_patio_service_excellent service_excellent | 
+| 90 | staff - clean staff - clean - selection awesome - friendly | 12 | 90_staff_clean staff_clean_selection awesome | 
+| 91 | lux - coffee - espresso - love space - surfing | 12 | 91_lux_coffee_espresso_love space | 
+| 92 | wine - bottle - glass - bar - maybe | 12 | 92_wine_bottle_glass_bar | 
+| 93 | sushi - roll - ra - sushi bar - seated | 12 | 93_sushi_roll_ra_sushi bar | 
+| 94 | german - schnitzel - murphy - german food - haus | 12 | 94_german_schnitzel_murphy_german food | 
+| 95 | ethiopian - lalibela - injera - watt - lentils | 11 | 95_ethiopian_lalibela_injera_watt | 
+| 96 | store - items - michaels - susan - employee | 11 | 96_store_items_michaels_susan |
+  
+</details>
+
+## Training hyperparameters
+
+* calculate_probabilities: True
+* 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: True
+* zeroshot_min_similarity: 0.7
+* zeroshot_topic_list: None
+
+## Framework versions
+
+* Numpy: 1.25.2
+* HDBSCAN: 0.8.36
+* UMAP: 0.5.6
+* Pandas: 2.0.3
+* Scikit-Learn: 1.2.2
+* Sentence-transformers: 3.0.0
+* Transformers: 4.41.1
+* Numba: 0.58.1
+* Plotly: 5.15.0
+* Python: 3.10.12

config.json

@@ -0,0 +1,17 @@
+{
+  "calculate_probabilities": true,
+  "language": "english",
+  "low_memory": false,
+  "min_topic_size": 10,
+  "n_gram_range": [
+    1,
+    1
+  ],
+  "nr_topics": null,
+  "seed_topic_list": null,
+  "top_n_words": 10,
+  "verbose": true,
+  "zeroshot_min_similarity": 0.7,
+  "zeroshot_topic_list": null,
+  "embedding_model": "sentence-transformers/all-MiniLM-L6-v2"
+}

ctfidf.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11cd12440a8b1bd90cfd6da02223cd3a7071fda0b7edd634e6eef782ffc27228
+size 11094659

ctfidf_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54843059e15d369db36fdfc0d49e147e9d647c00ca6fb248f5bcc7c65e2f4a22
+size 12824606

topic_embeddings.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35863e7b3319e8ab6682d25bd19ee2249e5bdb3c3940a0c717a463a2f96534c2
+size 151817