Add BERTopic model
Browse files- README.md +289 -0
- config.json +16 -0
- ctfidf.safetensors +3 -0
- ctfidf_config.json +0 -0
- topic_embeddings.safetensors +3 -0
- topics.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,289 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- bertopic
|
| 5 |
+
library_name: bertopic
|
| 6 |
+
pipeline_tag: text-classification
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
# BERTopic_ver1.0
|
| 10 |
+
|
| 11 |
+
This is a [BERTopic](https://github.com/MaartenGr/BERTopic) model.
|
| 12 |
+
BERTopic is a flexible and modular topic modeling framework that allows for the generation of easily interpretable topics from large datasets.
|
| 13 |
+
|
| 14 |
+
## Usage
|
| 15 |
+
|
| 16 |
+
To use this model, please install BERTopic:
|
| 17 |
+
|
| 18 |
+
```
|
| 19 |
+
pip install -U bertopic
|
| 20 |
+
```
|
| 21 |
+
|
| 22 |
+
You can use the model as follows:
|
| 23 |
+
|
| 24 |
+
```python
|
| 25 |
+
from bertopic import BERTopic
|
| 26 |
+
topic_model = BERTopic.load("hts98/BERTopic_ver1.0")
|
| 27 |
+
|
| 28 |
+
topic_model.get_topic_info()
|
| 29 |
+
```
|
| 30 |
+
|
| 31 |
+
## Topic overview
|
| 32 |
+
|
| 33 |
+
* Number of topics: 220
|
| 34 |
+
* Number of training documents: 529579
|
| 35 |
+
|
| 36 |
+
<details>
|
| 37 |
+
<summary>Click here for an overview of all topics.</summary>
|
| 38 |
+
|
| 39 |
+
| Topic ID | Topic Keywords | Topic Frequency | Label |
|
| 40 |
+
|----------|----------------|-----------------|-------|
|
| 41 |
+
| 0 | vietnam - vietnamese - in - we - the | 53744 | 0_vietnam_vietnamese_in_we |
|
| 42 |
+
| 1 | hoi - an - homestay - town - and | 20530 | 1_hoi_an_homestay_town |
|
| 43 |
+
| 2 | room - not - no - that - they | 21674 | 2_room_not_no_that |
|
| 44 |
+
| 3 | hostel - dorm - beds - dorms - you | 11859 | 3_hostel_dorm_beds_dorms |
|
| 45 |
+
| 4 | minh - ho - chi - city - in | 9284 | 4_minh_ho_chi_city |
|
| 46 |
+
| 5 | saigon - hotel - in - of - is | 11401 | 5_saigon_hotel_in_of |
|
| 47 |
+
| 6 | bikes - free - bike - town - bicycles | 9413 | 6_bikes_free_bike_town |
|
| 48 |
+
| 7 | hanoi - staff - stay - here - in | 14656 | 7_hanoi_staff_stay_here |
|
| 49 |
+
| 8 | noise - noisy - loud - room - hear | 7392 | 8_noise_noisy_loud_room |
|
| 50 |
+
| 9 | hue - citadel - hotel - in - and | 5076 | 9_hue_citadel_hotel_in |
|
| 51 |
+
| 10 | villa - villas - pool - beach - resort | 5879 | 10_villa_villas_pool_beach |
|
| 52 |
+
| 11 | hanoi - quarter - hotel - old - in | 17910 | 11_hanoi_quarter_hotel_old |
|
| 53 |
+
| 12 | beach - sea - view - hotel - is | 8826 | 12_beach_sea_view_hotel |
|
| 54 |
+
| 13 | massage - spa - massages - was - treatment | 5163 | 13_massage_spa_massages_was |
|
| 55 |
+
| 14 | hcmc - in - is - district - hotel | 3851 | 14_hcmc_in_is_district |
|
| 56 |
+
| 15 | resort - beach - pool - beautiful - is | 7510 | 15_resort_beach_pool_beautiful |
|
| 57 |
+
| 16 | nha - trang - beach - nhi - hotel | 4085 | 16_nha_trang_beach_nhi |
|
| 58 |
+
| 17 | pool - hotel - swimming - is - nice | 11201 | 17_pool_hotel_swimming_is |
|
| 59 |
+
| 18 | quarter - old - location - staff - located | 4437 | 18_quarter_old_location_staff |
|
| 60 |
+
| 19 | nang - da - beach - hotel - to | 3677 | 19_nang_da_beach_hotel |
|
| 61 |
+
| 20 | hostel - hanoi - hostels - tour - dorm | 3237 | 20_hostel_hanoi_hostels_tour |
|
| 62 |
+
| 21 | mekong - delta - tour - river - boat | 2828 | 21_mekong_delta_tour_river |
|
| 63 |
+
| 22 | hotel - good - very - location - is | 15993 | 22_hotel_good_very_location |
|
| 64 |
+
| 23 | staff - helpful - very - friendly - they | 9720 | 23_staff_helpful_very_friendly |
|
| 65 |
+
| 24 | phu - quoc - resort - island - beach | 2774 | 24_phu_quoc_resort_island |
|
| 66 |
+
| 25 | here - stayed - nights - stay - was | 12545 | 25_here_stayed_nights_stay |
|
| 67 |
+
| 26 | danang - sanouva - beach - hotel - is | 2526 | 26_danang_sanouva_beach_hotel |
|
| 68 |
+
| 27 | asia - asian - chinese - hotel - se | 3539 | 27_asia_asian_chinese_hotel |
|
| 69 |
+
| 28 | halong - bay - cruise - tour - our | 3438 | 28_halong_bay_cruise_tour |
|
| 70 |
+
| 29 | lake - quarter - location - old - walk | 3284 | 29_lake_quarter_location_old |
|
| 71 |
+
| 30 | river - view - town - the - views | 3504 | 30_river_view_town_the |
|
| 72 |
+
| 31 | kiem - hoan - lake - quarter - old | 2299 | 31_kiem_hoan_lake_quarter |
|
| 73 |
+
| 32 | hostel - vietnam - hostels - dorm - best | 2403 | 32_hostel_vietnam_hostels_dorm |
|
| 74 |
+
| 33 | siesta - la - hanoi - trendy - our | 2241 | 33_siesta_la_hanoi_trendy |
|
| 75 |
+
| 34 | star - stars - hotel - five - not | 3399 | 34_star_stars_hotel_five |
|
| 76 |
+
| 35 | stayed - nights - hotel - was - night | 10954 | 35_stayed_nights_hotel_was |
|
| 77 |
+
| 36 | lounge - club - executive - floor - service | 3454 | 36_lounge_club_executive_floor |
|
| 78 |
+
| 37 | phong - nha - cave - farmstay - caves | 1940 | 37_phong_nha_cave_farmstay |
|
| 79 |
+
| 38 | birthday - cake - honeymoon - our - we | 4252 | 38_birthday_cake_honeymoon_our |
|
| 80 |
+
| 39 | ninh - binh - coc - tam - us | 1828 | 39_ninh_binh_coc_tam |
|
| 81 |
+
| 40 | ben - thanh - market - walk - walking | 1957 | 40_ben_thanh_market_walk |
|
| 82 |
+
| 41 | mui - ne - hills - beach - resort | 1694 | 41_mui_ne_hills_beach |
|
| 83 |
+
| 42 | sapa - bay - halong - train - us | 1919 | 42_sapa_bay_halong_train |
|
| 84 |
+
| 43 | district - location - in - is - located | 1811 | 43_district_location_in_is |
|
| 85 |
+
| 44 | hcm - city - in - hotel - is | 1499 | 44_hcm_city_in_hotel |
|
| 86 |
+
| 45 | lodge - bamboo - park - national - tien | 2214 | 45_lodge_bamboo_park_national |
|
| 87 |
+
| 46 | hanoi - vietnam - in - hotel - our | 6611 | 46_hanoi_vietnam_in_hotel |
|
| 88 |
+
| 47 | location - good - place - nice - great | 8629 | 47_location_good_place_nice |
|
| 89 |
+
| 48 | hanoi - us - our - we - to | 4330 | 48_hanoi_us_our_we |
|
| 90 |
+
| 49 | villa - hoi - an - villas - town | 1997 | 49_villa_hoi_an_villas |
|
| 91 |
+
| 50 | english - speak - good - spoke - hotel | 3246 | 50_english_speak_good_spoke |
|
| 92 |
+
| 51 | kiem - hoan - lake - hanoi - quarter | 2147 | 51_kiem_hoan_lake_hanoi |
|
| 93 |
+
| 52 | cat - ba - island - catba - bay | 1302 | 52_cat_ba_island_catba |
|
| 94 |
+
| 53 | ha - long - bay - cruise - trip | 1767 | 53_ha_long_bay_cruise |
|
| 95 |
+
| 54 | hue - vietnam - in - hotel - vietnamese | 1361 | 54_hue_vietnam_in_hotel |
|
| 96 |
+
| 55 | airport - taxi - hotel - flight - from | 4310 | 55_airport_taxi_hotel_flight |
|
| 97 |
+
| 56 | japanese - yen - bridge - japan - is | 1455 | 56_japanese_yen_bridge_japan |
|
| 98 |
+
| 57 | siesta - la - trendy - our - at | 1179 | 57_siesta_la_trendy_our |
|
| 99 |
+
| 58 | tau - vung - beach - pullman - imperial | 1046 | 58_tau_vung_beach_pullman |
|
| 100 |
+
| 59 | pool - swimming - staff - nice - great | 4683 | 59_pool_swimming_staff_nice |
|
| 101 |
+
| 60 | loop - giang - ha - tour - bong | 1557 | 60_loop_giang_ha_tour |
|
| 102 |
+
| 61 | dalat - is - center - lake - in | 1113 | 61_dalat_is_center_lake |
|
| 103 |
+
| 62 | beach - place - nice - good - great | 4310 | 62_beach_place_nice_good |
|
| 104 |
+
| 63 | anantara - hoi - resort - an - river | 902 | 63_anantara_hoi_resort_an |
|
| 105 |
+
| 64 | thank - staff - hotel - service - us | 13044 | 64_thank_staff_hotel_service |
|
| 106 |
+
| 65 | naman - retreat - ambassador - resort - hay | 1051 | 65_naman_retreat_ambassador_resort |
|
| 107 |
+
| 66 | food - restaurant - buffet - vegetarian - dinner | 4595 | 66_food_restaurant_buffet_vegetarian |
|
| 108 |
+
| 67 | room - clean - bathroom - bed - was | 10694 | 67_room_clean_bathroom_bed |
|
| 109 |
+
| 68 | french - colonial - style - quarter - hotel | 1375 | 68_french_colonial_style_quarter |
|
| 110 |
+
| 69 | vinpearl - resort - vin - luxury - pearl | 1012 | 69_vinpearl_resort_vin_luxury |
|
| 111 |
+
| 70 | hanoi - noise - room - in - street | 3048 | 70_hanoi_noise_room_in |
|
| 112 |
+
| 71 | dao - senses - six - con - resort | 749 | 71_dao_senses_six_con |
|
| 113 |
+
| 72 | salinda - resort - quoc - phu - beach | 720 | 72_salinda_resort_quoc_phu |
|
| 114 |
+
| 73 | spa - hanoi - massage - hotel - service | 2630 | 73_spa_hanoi_massage_hotel |
|
| 115 |
+
| 74 | dragon - bridge - han - river - view | 973 | 74_dragon_bridge_han_river |
|
| 116 |
+
| 75 | host - hosts - family - us - she | 2397 | 75_host_hosts_family_us |
|
| 117 |
+
| 76 | metropole - sofitel - wing - hanoi - legend | 775 | 76_metropole_sofitel_wing_hanoi |
|
| 118 |
+
| 77 | noi - ha - hotel - in - old | 862 | 77_noi_ha_hotel_in |
|
| 119 |
+
| 78 | opera - house - wing - the - hotel | 838 | 78_opera_house_wing_the |
|
| 120 |
+
| 79 | tam - coc - family - homestay - place | 728 | 79_tam_coc_family_homestay |
|
| 121 |
+
| 80 | la - residencia - residence - hoi - an | 853 | 80_la_residencia_residence_hoi |
|
| 122 |
+
| 81 | citadel - walk - river - restaurants - tombs | 715 | 81_citadel_walk_river_restaurants |
|
| 123 |
+
| 82 | island - beach - resort - on - you | 1697 | 82_island_beach_resort_on |
|
| 124 |
+
| 83 | pros - cons - room - pro - not | 769 | 83_pros_cons_room_pro |
|
| 125 |
+
| 84 | marriott - jw - quoc - phu - university | 624 | 84_marriott_jw_quoc_phu |
|
| 126 |
+
| 85 | fusion - resort - fusionista - spa - quoc | 675 | 85_fusion_resort_fusionista_spa |
|
| 127 |
+
| 86 | mia - resort - trang - nha - sandals | 540 | 86_mia_resort_trang_nha |
|
| 128 |
+
| 87 | oriental - hanoi - suites - central - quarter | 882 | 87_oriental_hanoi_suites_central |
|
| 129 |
+
| 88 | chi - ho - min - city - ming | 680 | 88_chi_ho_min_city |
|
| 130 |
+
| 89 | kim - kiman - she - her - an | 668 | 89_kim_kiman_she_her |
|
| 131 |
+
| 90 | rex - rooftop - bar - suite - history | 492 | 90_rex_rooftop_bar_suite |
|
| 132 |
+
| 91 | nang - da - vietnam - vietnamese - beach | 647 | 91_nang_da_vietnam_vietnamese |
|
| 133 |
+
| 92 | mango - bay - resort - beach - bungalow | 617 | 92_mango_bay_resort_beach |
|
| 134 |
+
| 93 | chau - mai - rice - fields - valley | 747 | 93_chau_mai_rice_fields |
|
| 135 |
+
| 94 | veranda - la - quoc - phu - beach | 476 | 94_veranda_la_quoc_phu |
|
| 136 |
+
| 95 | lat - da - place - is - you | 672 | 95_lat_da_place_is |
|
| 137 |
+
| 96 | ancient - town - walk - very - good | 968 | 96_ancient_town_walk_very |
|
| 138 |
+
| 97 | hyatt - park - saigon - opera - at | 491 | 97_hyatt_park_saigon_opera |
|
| 139 |
+
| 98 | old - town - hotel - walk - very | 2147 | 98_old_town_hotel_walk |
|
| 140 |
+
| 99 | golden - moon - hanoi - legend - hotel | 879 | 99_golden_moon_hanoi_legend |
|
| 141 |
+
| 100 | serene - palace - hue - shining - hotel | 549 | 100_serene_palace_hue_shining |
|
| 142 |
+
| 101 | selva - la - hanoi - us - our | 510 | 101_selva_la_hanoi_us |
|
| 143 |
+
| 102 | marriott - jw - hanoi - lounge - executive | 517 | 102_marriott_jw_hanoi_lounge |
|
| 144 |
+
| 103 | golden - sun - suites - hanoi - palace | 560 | 103_golden_sun_suites_hanoi |
|
| 145 |
+
| 104 | christina - christinas - team - an - hoi | 441 | 104_christina_christinas_team_an |
|
| 146 |
+
| 105 | korean - korea - koreans - kind - good | 502 | 105_korean_korea_koreans_kind |
|
| 147 |
+
| 106 | hcmc - vietnam - hcm - in - vietnamese | 657 | 106_hcmc_vietnam_hcm_in |
|
| 148 |
+
| 107 | metropole - sofitel - wing - club - legend | 460 | 107_metropole_sofitel_wing_club |
|
| 149 |
+
| 108 | hostel - saigon - dorm - backpackers - place | 523 | 108_hostel_saigon_dorm_backpackers |
|
| 150 |
+
| 109 | riverside - royal - river - town - pool | 708 | 109_riverside_royal_river_town |
|
| 151 |
+
| 110 | dong - hoi - caves - khoi - duong | 761 | 110_dong_hoi_caves_khoi |
|
| 152 |
+
| 111 | lao - ngu - pham - street - vien | 544 | 111_lao_ngu_pham_street |
|
| 153 |
+
| 112 | gym - fitness - equipment - pool - is | 1282 | 112_gym_fitness_equipment_pool |
|
| 154 |
+
| 113 | nhon - quy - avani - resort - beach | 469 | 113_nhon_quy_avani_resort |
|
| 155 |
+
| 114 | lotus - royal - danang - boutique - at | 446 | 114_lotus_royal_danang_boutique |
|
| 156 |
+
| 115 | jade - hue - fruit - hotel - juice | 380 | 115_jade_hue_fruit_hotel |
|
| 157 |
+
| 116 | halong - bay - hanoi - cruise - trip | 2120 | 116_halong_bay_hanoi_cruise |
|
| 158 |
+
| 117 | moon - alisa - ms - she - us | 548 | 117_moon_alisa_ms_she |
|
| 159 |
+
| 118 | oriental - suites - central - hotel - our | 439 | 118_oriental_suites_central_hotel |
|
| 160 |
+
| 119 | window - windows - room - no - not | 1599 | 119_window_windows_room_no |
|
| 161 |
+
| 120 | ha - bay - long - hanoi - cruise | 1173 | 120_ha_bay_long_hanoi |
|
| 162 |
+
| 121 | liberty - central - saigon - citypoint - riverside | 446 | 121_liberty_central_saigon_citypoint |
|
| 163 |
+
| 122 | wifi - wi - fi - room - not | 2295 | 122_wifi_wi_fi_room |
|
| 164 |
+
| 123 | palm - garden - resort - beach - gardens | 480 | 123_palm_garden_resort_beach |
|
| 165 |
+
| 124 | bar - rooftop - drinks - cocktails - drink | 1653 | 124_bar_rooftop_drinks_cocktails |
|
| 166 |
+
| 125 | russian - russians - beach - russia - english | 406 | 125_russian_russians_beach_russia |
|
| 167 |
+
| 126 | moon - homestay - luna - her - hoi | 400 | 126_moon_homestay_luna_her |
|
| 168 |
+
| 127 | essence - hanoi - palace - quarter - our | 378 | 127_essence_hanoi_palace_quarter |
|
| 169 |
+
| 128 | boutique - hotel - is - and - with | 1641 | 128_boutique_hotel_is_and |
|
| 170 |
+
| 129 | silverland - jolie - sakyo - afternoon - tea | 463 | 129_silverland_jolie_sakyo_afternoon |
|
| 171 |
+
| 130 | pullman - saigon - executive - lounge - accor | 407 | 130_pullman_saigon_executive_lounge |
|
| 172 |
+
| 131 | lotte - hanoi - club - dennis - dat | 375 | 131_lotte_hanoi_club_dennis |
|
| 173 |
+
| 132 | orchid - orchids - garden - hue - flower | 371 | 132_orchid_orchids_garden_hue |
|
| 174 |
+
| 133 | hcmc - saigon - hcm - city - hotel | 622 | 133_hcmc_saigon_hcm_city |
|
| 175 |
+
| 134 | alagon - antique - hotels - rooftop - spa | 368 | 134_alagon_antique_hotels_rooftop |
|
| 176 |
+
| 135 | dalat - hostel - family - canyoning - dinner | 375 | 135_dalat_hostel_family_canyoning |
|
| 177 |
+
| 136 | golden - sun - suites - palace - at | 386 | 136_golden_sun_suites_palace |
|
| 178 |
+
| 137 | jacuzzi - sauna - bath - tub - rooftop | 710 | 137_jacuzzi_sauna_bath_tub |
|
| 179 |
+
| 138 | peppercorn - pepper - farm - resort - beach | 295 | 138_peppercorn_pepper_farm_resort |
|
| 180 |
+
| 139 | maia - fusion - treatments - spa - resort | 293 | 139_maia_fusion_treatments_spa |
|
| 181 |
+
| 140 | nikko - saigon - japanese - hotel - buffet | 367 | 140_nikko_saigon_japanese_hotel |
|
| 182 |
+
| 141 | hai - phong - haiphong - huong - hotel | 526 | 141_hai_phong_haiphong_huong |
|
| 183 |
+
| 142 | buffet - breakfast - hotel - is - the | 5261 | 142_buffet_breakfast_hotel_is |
|
| 184 |
+
| 143 | amiana - resort - nha - trang - pools | 286 | 143_amiana_resort_nha_trang |
|
| 185 |
+
| 144 | hoian - town - cozy - ancient - stay | 392 | 144_hoian_town_cozy_ancient |
|
| 186 |
+
| 145 | pullman - accor - quoc - phu - at | 303 | 145_pullman_accor_quoc_phu |
|
| 187 |
+
| 146 | hilton - opera - hanoi - executive - house | 548 | 146_hilton_opera_hanoi_executive |
|
| 188 |
+
| 147 | homestay - hanoi - family - home - 3b | 602 | 147_homestay_hanoi_family_home |
|
| 189 |
+
| 148 | rooftop - bar - roof - top - views | 2055 | 148_rooftop_bar_roof_top |
|
| 190 |
+
| 149 | anam - resort - pools - beach - beautiful | 307 | 149_anam_resort_pools_beach |
|
| 191 |
+
| 150 | gia - pham - giang - homestay - thy | 409 | 150_gia_pham_giang_homestay |
|
| 192 |
+
| 151 | indochine - palace - hue - hotel - at | 271 | 151_indochine_palace_hue_hotel |
|
| 193 |
+
| 152 | english - speak - good - staff - spoke | 1392 | 152_english_speak_good_staff |
|
| 194 |
+
| 153 | australia - australian - au - aussie - lac | 629 | 153_australia_australian_au_aussie |
|
| 195 |
+
| 154 | notre - dame - cathedral - post - office | 372 | 154_notre_dame_cathedral_post |
|
| 196 |
+
| 155 | sofia - nang - da - boutique - suite | 269 | 155_sofia_nang_da_boutique |
|
| 197 |
+
| 156 | bungalow - bungalows - beach - garden - you | 1752 | 156_bungalow_bungalows_beach_garden |
|
| 198 |
+
| 157 | hoang - trinh - mr - le - hotel | 503 | 157_hoang_trinh_mr_le |
|
| 199 |
+
| 158 | apricot - lake - hanoi - lobby - rooftop | 246 | 158_apricot_lake_hanoi_lobby |
|
| 200 |
+
| 159 | sapa - hanoi - train - bay - halong | 1293 | 159_sapa_hanoi_train_bay |
|
| 201 |
+
| 160 | thai - bangkok - thailand - very - good | 459 | 160_thai_bangkok_thailand_very |
|
| 202 |
+
| 161 | sheraton - nha - trang - lounge - club | 298 | 161_sheraton_nha_trang_lounge |
|
| 203 |
+
| 162 | gallery - premier - hanoi - our - hotel | 340 | 162_gallery_premier_hanoi_our |
|
| 204 |
+
| 163 | review - reviews - write - advisor - this | 814 | 163_review_reviews_write_advisor |
|
| 205 |
+
| 164 | pool - stayed - here - nights - was | 4365 | 164_pool_stayed_here_nights |
|
| 206 |
+
| 165 | ruby - gem - pearl - diamond - hotel | 588 | 165_ruby_gem_pearl_diamond |
|
| 207 |
+
| 166 | golden - legend - gold - art - bell | 467 | 166_golden_legend_gold_art |
|
| 208 |
+
| 167 | sheraton - club - lounge - service - at | 308 | 167_sheraton_club_lounge_service |
|
| 209 |
+
| 168 | royal - palace - king - queen - hotel | 584 | 168_royal_palace_king_queen |
|
| 210 |
+
| 169 | nam - hai - seasons - four - resort | 324 | 169_nam_hai_seasons_four |
|
| 211 |
+
| 170 | halal - muslim - ben - market - malaysian | 452 | 170_halal_muslim_ben_market |
|
| 212 |
+
| 171 | green - heaven - apple - hoi - town | 414 | 171_green_heaven_apple_hoi |
|
| 213 |
+
| 172 | sherwood - residence - apartment - suites - bedroom | 237 | 172_sherwood_residence_apartment_suites |
|
| 214 |
+
| 173 | omelette - omelettes - breakfast - omelet - fresh | 659 | 173_omelette_omelettes_breakfast_omelet |
|
| 215 |
+
| 174 | marvel - jm - peridot - us - our | 281 | 174_marvel_jm_peridot_us |
|
| 216 |
+
| 175 | vien - bui - street - is - located | 386 | 175_vien_bui_street_is |
|
| 217 |
+
| 176 | hyatt - park - opera - service - at | 274 | 176_hyatt_park_opera_service |
|
| 218 |
+
| 177 | liberty - central - riverside - citypoint - bar | 261 | 177_liberty_central_riverside_citypoint |
|
| 219 |
+
| 178 | hano - han - hanh - hanio - hani | 324 | 178_hano_han_hanh_hanio |
|
| 220 |
+
| 179 | pearl - hanoi - junie - lake - quarter | 412 | 179_pearl_hanoi_junie_lake |
|
| 221 |
+
| 180 | meridien - le - saigon - lounge - club | 369 | 180_meridien_le_saigon_lounge |
|
| 222 |
+
| 181 | leo - tigers - tiger - tiny - hostel | 234 | 181_leo_tigers_tiger_tiny |
|
| 223 |
+
| 182 | nikko - club - japanese - buffet - hotel | 252 | 182_nikko_club_japanese_buffet |
|
| 224 |
+
| 183 | hostel - hoi - an - hien - she | 402 | 183_hostel_hoi_an_hien |
|
| 225 |
+
| 184 | song - villa - saigon - river - boat | 344 | 184_song_villa_saigon_river |
|
| 226 |
+
| 185 | lasenta - rice - fields - town - hoi | 205 | 185_lasenta_rice_fields_town |
|
| 227 |
+
| 186 | essence - aira - palace - christine - tom | 244 | 186_essence_aira_palace_christine |
|
| 228 |
+
| 187 | 1010 - would - 910 - recommend - amazing | 329 | 187_1010_would_910_recommend |
|
| 229 |
+
| 188 | lat - da - hostel - canyoning - family | 273 | 188_lat_da_hostel_canyoning |
|
| 230 |
+
| 189 | deluxe - room - double - bed - suite | 1012 | 189_deluxe_room_double_bed |
|
| 231 |
+
| 190 | bonsella - hanoi - jason - lake - prestige | 248 | 190_bonsella_hanoi_jason_lake |
|
| 232 |
+
| 191 | imperial - city - ibis - palace - river | 315 | 191_imperial_city_ibis_palace |
|
| 233 |
+
| 192 | jm - marvel - hanoi - spa - anna | 222 | 192_jm_marvel_hanoi_spa |
|
| 234 |
+
| 193 | infinity - pool - beach - view - ocean | 534 | 193_infinity_pool_beach_view |
|
| 235 |
+
| 194 | asia - hostel - hostels - se - east | 349 | 194_asia_hostel_hostels_se |
|
| 236 |
+
| 195 | siesta - la - vietnam - our - trendy | 280 | 195_siesta_la_vietnam_our |
|
| 237 |
+
| 196 | alba - wellness - onsen - spa - resort | 223 | 196_alba_wellness_onsen_spa |
|
| 238 |
+
| 197 | cherish - hue - cherry - hotel - breakfast | 220 | 197_cherish_hue_cherry_hotel |
|
| 239 |
+
| 198 | selva - la - eldora - our - at | 315 | 198_selva_la_eldora_our |
|
| 240 |
+
| 199 | melia - hanoi - solaria - in - hotel | 252 | 199_melia_hanoi_solaria_in |
|
| 241 |
+
| 200 | rosaleen - rosaka - rosa - bella - hue | 304 | 200_rosaleen_rosaka_rosa_bella |
|
| 242 |
+
| 201 | grand - splendid - hotel - suite - the | 467 | 201_grand_splendid_hotel_suite |
|
| 243 |
+
| 202 | venus - hoi - spa - hotel - an | 201 | 202_venus_hoi_spa_hotel |
|
| 244 |
+
| 203 | muong - thanh - hotel - cuong - ms | 260 | 203_muong_thanh_hotel_cuong |
|
| 245 |
+
| 204 | novotel - nha - trang - beach - at | 264 | 204_novotel_nha_trang_beach |
|
| 246 |
+
| 205 | pilgrimage - village - hue - miwa - resort | 226 | 205_pilgrimage_village_hue_miwa |
|
| 247 |
+
| 206 | guesthouse - house - guest - owner - family | 1118 | 206_guesthouse_house_guest_owner |
|
| 248 |
+
| 207 | somerset - apartment - chancellor - apartments - bedroom | 248 | 207_somerset_apartment_chancellor_apartments |
|
| 249 |
+
| 208 | tho - can - kieu - ninh - floating | 276 | 208_tho_can_kieu_ninh |
|
| 250 |
+
| 209 | vy - maison - hoi - her - vui | 313 | 209_vy_maison_hoi_her |
|
| 251 |
+
| 210 | sheraton - saigon - lounge - towers - club | 284 | 210_sheraton_saigon_lounge_towers |
|
| 252 |
+
| 211 | vinh - hung - riverside - resort - emerald | 285 | 211_vinh_hung_riverside_resort |
|
| 253 |
+
| 212 | museum - war - remnants - palace - reunification | 362 | 212_museum_war_remnants_palace |
|
| 254 |
+
| 213 | gallery - majestic - ogallery - premier - art | 273 | 213_gallery_majestic_ogallery_premier |
|
| 255 |
+
| 214 | emerald - waters - hanoi - trendy - elegance | 359 | 214_emerald_waters_hanoi_trendy |
|
| 256 |
+
| 215 | dalat - vietnam - hostel - vietnamese - family | 265 | 215_dalat_vietnam_hostel_vietnamese |
|
| 257 |
+
| 216 | hoi - hanoi - an - from - after | 680 | 216_hoi_hanoi_an_from |
|
| 258 |
+
| 217 | sofitel - saigon - plaza - lounge - club | 320 | 217_sofitel_saigon_plaza_lounge |
|
| 259 |
+
| 218 | storia - ruby - la - hanoi - isabella | 156 | 218_storia_ruby_la_hanoi |
|
| 260 |
+
| 219 | melia - vi - solaria - ba - mountain | 219 | 219_melia_vi_solaria_ba |
|
| 261 |
+
|
| 262 |
+
</details>
|
| 263 |
+
|
| 264 |
+
## Training hyperparameters
|
| 265 |
+
|
| 266 |
+
* calculate_probabilities: False
|
| 267 |
+
* language: None
|
| 268 |
+
* low_memory: False
|
| 269 |
+
* min_topic_size: 10
|
| 270 |
+
* n_gram_range: (1, 1)
|
| 271 |
+
* nr_topics: None
|
| 272 |
+
* seed_topic_list: None
|
| 273 |
+
* top_n_words: 10
|
| 274 |
+
* verbose: True
|
| 275 |
+
* zeroshot_min_similarity: 0.7
|
| 276 |
+
* zeroshot_topic_list: None
|
| 277 |
+
|
| 278 |
+
## Framework versions
|
| 279 |
+
|
| 280 |
+
* Numpy: 1.24.3
|
| 281 |
+
* HDBSCAN: 0.8.33
|
| 282 |
+
* UMAP: 0.5.4
|
| 283 |
+
* Pandas: 2.1.3
|
| 284 |
+
* Scikit-Learn: 1.2.2
|
| 285 |
+
* Sentence-transformers: 2.2.2
|
| 286 |
+
* Transformers: 4.35.0
|
| 287 |
+
* Numba: 0.58.1
|
| 288 |
+
* Plotly: 5.16.1
|
| 289 |
+
* Python: 3.10.12
|
config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"calculate_probabilities": false,
|
| 3 |
+
"language": null,
|
| 4 |
+
"low_memory": false,
|
| 5 |
+
"min_topic_size": 10,
|
| 6 |
+
"n_gram_range": [
|
| 7 |
+
1,
|
| 8 |
+
1
|
| 9 |
+
],
|
| 10 |
+
"nr_topics": null,
|
| 11 |
+
"seed_topic_list": null,
|
| 12 |
+
"top_n_words": 10,
|
| 13 |
+
"verbose": true,
|
| 14 |
+
"zeroshot_min_similarity": 0.7,
|
| 15 |
+
"zeroshot_topic_list": null
|
| 16 |
+
}
|
ctfidf.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48d9ad803c60ace35507482000e2fe8c6318420a2b98d9ba111faf55d0b02ba7
|
| 3 |
+
size 17924188
|
ctfidf_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
topic_embeddings.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfaddc81420f79c56475ab402b3b4935819ae4ed2d16296805b2c125eaa52ad1
|
| 3 |
+
size 338008
|
topics.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|