Add BERTopic model
Browse files- README.md +358 -0
- config.json +15 -0
- topic_embeddings.safetensors +3 -0
- topics.json +0 -0
README.md
ADDED
@@ -0,0 +1,358 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- bertopic
|
5 |
+
library_name: bertopic
|
6 |
+
pipeline_tag: text-classification
|
7 |
+
---
|
8 |
+
|
9 |
+
# bertopic_before_tuning
|
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("vidric/bertopic_before_tuning")
|
27 |
+
|
28 |
+
topic_model.get_topic_info()
|
29 |
+
```
|
30 |
+
|
31 |
+
## Topic overview
|
32 |
+
|
33 |
+
* Number of topics: 291
|
34 |
+
* Number of training documents: 20977
|
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 |
+
| -1 | parfum - tidak - untuk - beli - kirim | 10 | -1_parfum_tidak_untuk_beli |
|
42 |
+
| 0 | orgasm - eos - farhampton - lebih - aku | 6133 | 0_orgasm_eos_farhampton_lebih |
|
43 |
+
| 1 | mantap - smel - legit - lanjutken - goid | 894 | 1_mantap_smel_legit_lanjutken |
|
44 |
+
| 2 | parfum - seperti - pertama - mirip - tidak | 648 | 2_parfum_seperti_pertama_mirip |
|
45 |
+
| 3 | cowok - cewek - feminim - pacar - cocok | 395 | 3_cowok_cewek_feminim_pacar |
|
46 |
+
| 4 | packing - aman - rapi - mewah - keren | 333 | 4_packing_aman_rapi_mewah |
|
47 |
+
| 5 | botol - bocor - tumpah - tutup - pecah | 297 | 5_botol_bocor_tumpah_tutup |
|
48 |
+
| 6 | terlalu - kurang - tidak - nyengat - kuat | 268 | 6_terlalu_kurang_tidak_nyengat |
|
49 |
+
| 7 | terimakasih - bonus - hmns - kasih - wangi | 263 | 7_terimakasih_bonus_hmns_kasih |
|
50 |
+
| 8 | vanilla - dominan - floral - manis - jasmine | 254 | 8_vanilla_dominan_floral_manis |
|
51 |
+
| 9 | seller - respon - rekomendasi - deskripsi - cepat | 236 | 9_seller_respon_rekomendasi_deskripsi |
|
52 |
+
| 10 | jam - indoor - tahan - ac - kulit | 215 | 10_jam_indoor_tahan_ac |
|
53 |
+
| 11 | packing - rapi - bagus - keren - barang | 202 | 11_packing_rapi_bagus_keren |
|
54 |
+
| 12 | cepat - kirim - rapi - packing - aman | 196 | 12_cepat_kirim_rapi_packing |
|
55 |
+
| 13 | terimakasih - parfum - hmns - tester - bonus | 160 | 13_terimakasih_parfum_hmns_tester |
|
56 |
+
| 14 | bubble - wrap - tebal - kardus - kotak | 153 | 14_bubble_wrap_tebal_kardus |
|
57 |
+
| 15 | alpha - tetha - paling - perfection - lebih | 151 | 15_alpha_tetha_paling_perfection |
|
58 |
+
| 16 | packing - parfum - rapi - aman - kirim | 140 | 16_packing_parfum_rapi_aman |
|
59 |
+
| 17 | anime - wangi - gas - gailang - wangjnya | 136 | 17_anime_wangi_gas_gailang |
|
60 |
+
| 18 | alpha - theta - beta - tetha - ha | 135 | 18_alpha_theta_beta_tetha |
|
61 |
+
| 19 | terimakasih - aman - packing - rapi - mewah | 132 | 19_terimakasih_aman_packing_rapi |
|
62 |
+
| 20 | lokal - brand - terbaik - internasional - parfum | 129 | 20_lokal_brand_terbaik_internasional |
|
63 |
+
| 21 | voucher - dapat - 50rb - berlaku - 50k | 127 | 21_voucher_dapat_50rb_berlaku |
|
64 |
+
| 22 | farhampton - paling - sample - bonus - berikutnya | 121 | 22_farhampton_paling_sample_bonus |
|
65 |
+
| 23 | terimakasih - selamat - bang - terima - min | 121 | 23_terimakasih_selamat_bang_terima |
|
66 |
+
| 24 | mawar - rose - bunga - floral - unrosed | 118 | 24_mawar_rose_bunga_floral |
|
67 |
+
| 25 | oke - oké - bos - barang - | 117 | 25_oke_oké_bos_barang |
|
68 |
+
| 26 | sepadan - paten - isimewa - bes - gwp | 115 | 26_sepadan_paten_isimewa_bes |
|
69 |
+
| 27 | terbaik - prestasi - best - biasa - eos | 114 | 27_terbaik_prestasi_best_biasa |
|
70 |
+
| 28 | segar - manis - sia - bersaman - spicy | 111 | 28_segar_manis_sia_bersaman |
|
71 |
+
| 29 | enak - wangi - bagus - - | 97 | 29_enak_wangi_bagus_ |
|
72 |
+
| 30 | good - vry - fuckin - al - smel | 94 | 30_good_vry_fuckin_al |
|
73 |
+
| 31 | hadiah - ulangtahun - hadiahnya - ulang - dia | 93 | 31_hadiah_ulangtahun_hadiahnya_ulang |
|
74 |
+
| 32 | abiez - pokoknya - mantap - foto - serpisnya | 92 | 32_abiez_pokoknya_mantap_foto |
|
75 |
+
| 33 | produk - kualitas - penawaran - amron - naibaho | 90 | 33_produk_kualitas_penawaran_amron |
|
76 |
+
| 34 | pernah - kecewa - fail - gagal - tidak | 85 | 34_pernah_kecewa_fail_gagal |
|
77 |
+
| 35 | magnet - tutup - botol - kemasan - cap | 84 | 35_magnet_tutup_botol_kemasan |
|
78 |
+
| 36 | aman - packing - barang - tujuan - gems | 83 | 36_aman_packing_barang_tujuan |
|
79 |
+
| 37 | debat - no - nget - ngomong - dcb | 83 | 37_debat_no_nget_ngomong |
|
80 |
+
| 38 | terimakasih - pesan - cepat - sampai - kirim | 83 | 38_terimakasih_pesan_cepat_sampai |
|
81 |
+
| 39 | parfum - dipanggil - much - jatuh - namanya | 83 | 39_parfum_dipanggil_much_jatuh |
|
82 |
+
| 40 | terimakasih - packing - aman - rapi - barang | 83 | 40_terimakasih_packing_aman_rapi |
|
83 |
+
| 41 | admin - ramah - respon - informatif - cepat | 82 | 41_admin_ramah_respon_informatif |
|
84 |
+
| 42 | pokok - wnginya - perhatian - entar - terluv | 78 | 42_pokok_wnginya_perhatian_entar |
|
85 |
+
| 43 | love - cinta - jatuh - in - sama | 78 | 43_love_cinta_jatuh_in |
|
86 |
+
| 44 | kedua - beli - dua - kali - 2nd | 78 | 44_kedua_beli_dua_kali |
|
87 |
+
| 45 | indonesia - bangga - harumkan - buatan - produk | 73 | 45_indonesia_bangga_harumkan_buatan |
|
88 |
+
| 46 | love - cinta - jatuh - kasih - secepat | 71 | 46_love_cinta_jatuh_kasih |
|
89 |
+
| 47 | terimakasih - sdah - karin - request - bantu | 71 | 47_terimakasih_sdah_karin_request |
|
90 |
+
| 48 | starterpacking - starterpack - dulu - mana - horas | 70 | 48_starterpacking_starterpack_dulu_mana |
|
91 |
+
| 49 | delta - theta - team - alpha - tetha | 70 | 49_delta_theta_team_alpha |
|
92 |
+
| 50 | repeat - order - kesekian - kali - selalu | 69 | 50_repeat_order_kesekian_kali |
|
93 |
+
| 51 | tahan - lama - enak - flu - pengemasany | 69 | 51_tahan_lama_enak_flu |
|
94 |
+
| 52 | hari - minggu - pre - sabtu - po | 69 | 52_hari_minggu_pre_sabtu |
|
95 |
+
| 53 | parfum - bum - fans - klepek - favorit | 68 | 53_parfum_bum_fans_klepek |
|
96 |
+
| 54 | lembut - gentle - deskripi - sksksk - mendekat | 67 | 54_lembut_gentle_deskripi_sksksk |
|
97 |
+
| 55 | bagus - excelent - pokoknya - good - kedua | 64 | 55_bagus_excelent_pokoknya_good |
|
98 |
+
| 56 | mantap - ubun - tulang - bed - sangar | 63 | 56_mantap_ubun_tulang_bed |
|
99 |
+
| 57 | seller - respon - produk - cepat - ramah | 63 | 57_seller_respon_produk_cepat |
|
100 |
+
| 58 | ketiga - tiga - cny - berupa - 4x | 63 | 58_ketiga_tiga_cny_berupa |
|
101 |
+
| 59 | kesempurnan - perfection - mr - kecil2 - pergi2 | 61 | 59_kesempurnan_perfection_mr_kecil2 |
|
102 |
+
| 60 | enak - banget - wangi - benar - | 61 | 60_enak_banget_wangi_benar |
|
103 |
+
| 61 | enak - sopan - mag - aslilah - sumpah | 61 | 61_enak_sopan_mag_aslilah |
|
104 |
+
| 62 | citrus - citrusnya - fruity - buah - fruit | 60 | 62_citrus_citrusnya_fruity_buah |
|
105 |
+
| 63 | cepat - sampai - sorenya - ih - sampainya | 59 | 63_cepat_sampai_sorenya_ih |
|
106 |
+
| 64 | belum - unboxing - isi - pecah - pekejing | 59 | 64_belum_unboxing_isi_pecah |
|
107 |
+
| 65 | tester - test - sample - diksh - bonus | 58 | 65_tester_test_sample_diksh |
|
108 |
+
| 66 | istri - karir - belin - alhamdulilah - suka | 57 | 66_istri_karir_belin_alhamdulilah |
|
109 |
+
| 67 | seller - tokopedia - terimakasih - produk - mei | 57 | 67_seller_tokopedia_terimakasih_produk |
|
110 |
+
| 68 | voucher - dapat - diskon - 50rb - 50k | 56 | 68_voucher_dapat_diskon_50rb |
|
111 |
+
| 69 | boleh - bolehlah - suka - bolehla - nak | 56 | 69_boleh_bolehlah_suka_bolehla |
|
112 |
+
| 70 | selamat - barang - mendarat - aman - sampai | 55 | 70_selamat_barang_mendarat_aman |
|
113 |
+
| 71 | eos - dos - nada - botom - mid | 55 | 71_eos_dos_nada_botom |
|
114 |
+
| 72 | farhampton - sebelumnya - perfection - parfum - digunain | 54 | 72_farhampton_sebelumnya_perfection_parfum |
|
115 |
+
| 73 | kualitas - ragu - soal - baik - membangun | 54 | 73_kualitas_ragu_soal_baik |
|
116 |
+
| 74 | bad - lumayan - enak - cok - yes | 53 | 74_bad_lumayan_enak_cok |
|
117 |
+
| 75 | respon - quick - cepat - disin - mimin | 53 | 75_respon_quick_cepat_disin |
|
118 |
+
| 76 | banget - wangi - demi - sekali - apapun | 52 | 76_banget_wangi_demi_sekali |
|
119 |
+
| 77 | mantap - senang - inded - sekali - keangunan | 51 | 77_mantap_senang_inded_sekali |
|
120 |
+
| 78 | keren - tebqiklah - wan - gotcha - pelapak | 50 | 78_keren_tebqiklah_wan_gotcha |
|
121 |
+
| 79 | starterpacking - starterpack - ful - beli - team | 49 | 79_starterpacking_starterpack_ful_beli |
|
122 |
+
| 80 | cos - kasus - parfum - rekomendasi - sambil | 49 | 80_cos_kasus_parfum_rekomendasi |
|
123 |
+
| 81 | kirim - cepat - sabtu - pesan - rumah | 48 | 81_kirim_cepat_sabtu_pesan |
|
124 |
+
| 82 | vetiver - mahal - parfum - spice - siap | 47 | 82_vetiver_mahal_parfum_spice |
|
125 |
+
| 83 | lokal - internasional - produk - brand - suport | 47 | 83_lokal_internasional_produk_brand |
|
126 |
+
| 84 | kemasan - paket - kotak - presentation - menawan | 47 | 84_kemasan_paket_kotak_presentation |
|
127 |
+
| 85 | selalu - always - puas - as - memuaskan | 47 | 85_selalu_always_puas_as |
|
128 |
+
| 86 | terbaik - deal - nimbun - salut - canda | 47 | 86_terbaik_deal_nimbun_salut |
|
129 |
+
| 87 | ekspektasi - sesuai - cocok - bayangkan - hugable | 47 | 87_ekspektasi_sesuai_cocok_bayangkan |
|
130 |
+
| 88 | kalem - pangling - undescribable - pernen - sarmento | 46 | 88_kalem_pangling_undescribable_pernen |
|
131 |
+
| 89 | spray - rusak - macet - empuk - berfungsi | 46 | 89_spray_rusak_macet_empuk |
|
132 |
+
| 90 | farhampton - perfection - alpha - sama² - masing | 46 | 90_farhampton_perfection_alpha_sama² |
|
133 |
+
| 91 | admin - bos - ramah - senayan - respon | 46 | 91_admin_bos_ramah_senayan |
|
134 |
+
| 92 | mantap - mangi - wangi - jarak - alhamdulilah | 45 | 92_mantap_mangi_wangi_jarak |
|
135 |
+
| 93 | wajib - beli - ragu - mana - usah | 44 | 93_wajib_beli_ragu_mana |
|
136 |
+
| 94 | cepat - aman - proses - surprised - packing | 44 | 94_cepat_aman_proses_surprised |
|
137 |
+
| 95 | farhampton - banding - lebih - prefer - paling | 44 | 95_farhampton_banding_lebih_prefer |
|
138 |
+
| 96 | ketiga - tiga - mana - masing - rata | 43 | 96_ketiga_tiga_mana_masing |
|
139 |
+
| 97 | rekomendasi - pesta - netizen - kesepakatan - berharga | 43 | 97_rekomendasi_pesta_netizen_kesepakatan |
|
140 |
+
| 98 | worth - it - harga - apakah - amazing | 43 | 98_worth_it_harga_apakah |
|
141 |
+
| 99 | suka - menyukainya - sekali - banget - menyukai | 42 | 99_suka_menyukainya_sekali_banget |
|
142 |
+
| 100 | cepat - sampainya - tolonglah - mengairahkan - dibilangin | 41 | 100_cepat_sampainya_tolonglah_mengairahkan |
|
143 |
+
| 101 | alpha - 10 - theta - paling - cita | 41 | 101_alpha_10_theta_paling |
|
144 |
+
| 102 | kirim - cepat - barang - barangmya - ongkirnya | 41 | 102_kirim_cepat_barang_barangmya |
|
145 |
+
| 103 | lama - legend - tahan - mkin - layak | 41 | 103_lama_legend_tahan_mkin |
|
146 |
+
| 104 | tahan - lama - kalm - anytime - anywhere | 40 | 104_tahan_lama_kalm_anytime |
|
147 |
+
| 105 | longevity - projection - jam - notes - silage | 40 | 105_longevity_projection_jam_notes |
|
148 |
+
| 106 | spray - rusak - macet - susah - agak | 40 | 106_spray_rusak_macet_susah |
|
149 |
+
| 107 | puas - kebahagian - autentik - syekli - sumber | 40 | 107_puas_kebahagian_autentik_syekli |
|
150 |
+
| 108 | perfect - sempurna - uno - numero - | 39 | 108_perfect_sempurna_uno_numero |
|
151 |
+
| 109 | admin - pouch - ramah - respon - plastiknya | 39 | 109_admin_pouch_ramah_respon |
|
152 |
+
| 110 | perfection - kesempurnan - sempurna - diri - bold | 38 | 110_perfection_kesempurnan_sempurna_diri |
|
153 |
+
| 111 | layanan - prima - pelangan - service - performa | 38 | 111_layanan_prima_pelangan_service |
|
154 |
+
| 112 | suka - mertua - adict - wangi - original | 38 | 112_suka_mertua_adict_wangi |
|
155 |
+
| 113 | kedua - kali - beli - rilis - meal | 37 | 113_kedua_kali_beli_rilis |
|
156 |
+
| 114 | tester - test - bonus - unrosed - yesternya | 37 | 114_tester_test_bonus_unrosed |
|
157 |
+
| 115 | botol - perbaiki - cairan - ditaro - mobil | 37 | 115_botol_perbaiki_cairan_ditaro |
|
158 |
+
| 116 | lagi - pasti - depan - nanti - beli | 36 | 116_lagi_pasti_depan_nanti |
|
159 |
+
| 117 | lokal - brand - produk - maju - dua | 36 | 117_lokal_brand_produk_maju |
|
160 |
+
| 118 | kartu - card - greting - ucap - personalized | 36 | 118_kartu_card_greting_ucap |
|
161 |
+
| 119 | enak - tenan - taste - good - ori | 36 | 119_enak_tenan_taste_good |
|
162 |
+
| 120 | sama - suka - banget - dewasa - menyukainya | 36 | 120_sama_suka_banget_dewasa |
|
163 |
+
| 121 | hebat - bagus - kuliatas - good - nicely | 36 | 121_hebat_bagus_kuliatas_good |
|
164 |
+
| 122 | semoga - harap - sempurna - bung - holyshesh | 35 | 122_semoga_harap_sempurna_bung |
|
165 |
+
| 123 | bonus - dapat - ha - bonusan - jiwa | 35 | 123_bonus_dapat_ha_bonusan |
|
166 |
+
| 124 | parah - hotel - bau - gacor - crayzay | 35 | 124_parah_hotel_bau_gacor |
|
167 |
+
| 125 | puas - tergocek - thetat_t - menghibur - terdebest | 35 | 125_puas_tergocek_thetat_t_menghibur |
|
168 |
+
| 126 | barang - terima - terimakasih - lanyard - berproduksi | 34 | 126_barang_terima_terimakasih_lanyard |
|
169 |
+
| 127 | kane - mbak - cept - apanih - kokbisa | 34 | 127_kane_mbak_cept_apanih |
|
170 |
+
| 128 | suami - anda - cowok - neko - jatah | 33 | 128_suami_anda_cowok_neko |
|
171 |
+
| 129 | cewek - pacar - klepek - miminya - manis | 33 | 129_cewek_pacar_klepek_miminya |
|
172 |
+
| 130 | segar - pepernya - basic - liburan - patut | 33 | 130_segar_pepernya_basic_liburan |
|
173 |
+
| 131 | hair - mist - body - rambut - badan | 32 | 131_hair_mist_body_rambut |
|
174 |
+
| 132 | enak - banget - adict - wangi - sumpah | 32 | 132_enak_banget_adict_wangi |
|
175 |
+
| 133 | love - just - swet - cinta - admin | 32 | 133_love_just_swet_cinta |
|
176 |
+
| 134 | langganan - woeh - dikasihnya - tonky - winky | 32 | 134_langganan_woeh_dikasihnya_tonky |
|
177 |
+
| 135 | rekomendasi - gela - ank - terpercaya - bangsa | 32 | 135_rekomendasi_gela_ank_terpercaya |
|
178 |
+
| 136 | semua - bagus - screw - los - hal | 31 | 136_semua_bagus_screw_los |
|
179 |
+
| 137 | istri - hadiah - menyukainya - ulangtahun - alhamdulilah | 31 | 137_istri_hadiah_menyukainya_ulangtahun |
|
180 |
+
| 138 | ibu - awet - tante - itung - mikir | 30 | 138_ibu_awet_tante_itung |
|
181 |
+
| 139 | mewah - seksi - elegan - kemasanua - pokoknha | 29 | 139_mewah_seksi_elegan_kemasanua |
|
182 |
+
| 140 | 10ml - 50ml - ml - 5ml - kaleng2an | 29 | 140_10ml_50ml_ml_5ml |
|
183 |
+
| 141 | ketiga - ofkors - timing - diangkat - cafe | 29 | 141_ketiga_ofkors_timing_diangkat |
|
184 |
+
| 142 | harum - sue - hua - tagih - unik | 29 | 142_harum_sue_hua_tagih |
|
185 |
+
| 143 | pagi - sore - besok - pulang - kerja | 29 | 143_pagi_sore_besok_pulang |
|
186 |
+
| 144 | rekomendasi - layak - releasenya - direkomendasi - prtma | 29 | 144_rekomendasi_layak_releasenya_direkomendasi |
|
187 |
+
| 145 | blind - muantep - beli - kepikiran - nekat | 28 | 145_blind_muantep_beli_kepikiran |
|
188 |
+
| 146 | worth - it - layak - sepadan - harga | 28 | 146_worth_it_layak_sepadan |
|
189 |
+
| 147 | pokok - tpt - mumet - jon - sealu | 28 | 147_pokok_tpt_mumet_jon |
|
190 |
+
| 148 | mantap - menyeruak - berpetualangan - imagi - experimen | 28 | 148_mantap_menyeruak_berpetualangan_imagi |
|
191 |
+
| 149 | layanan - service - percuma - quick - servis | 28 | 149_layanan_service_percuma_quick |
|
192 |
+
| 150 | barang - selamat - aman - trkesan - pintu | 28 | 150_barang_selamat_aman_trkesan |
|
193 |
+
| 151 | esence - matahari - sun - sari - ber | 28 | 151_esence_matahari_sun_sari |
|
194 |
+
| 152 | pernah - salah - selalu - kecewa - gdjob | 28 | 152_pernah_salah_selalu_kecewa |
|
195 |
+
| 153 | bicara - bintang - biar - alasanya - nyang | 27 | 153_bicara_bintang_biar_alasanya |
|
196 |
+
| 154 | sempurna - perfect - namanya - mendarat - dieksekusi | 27 | 154_sempurna_perfect_namanya_mendarat |
|
197 |
+
| 155 | ekspektasi - sesuai - etc - por - insha | 27 | 155_ekspektasi_sesuai_etc_por |
|
198 |
+
| 156 | mahal - harga - murah - segini - ampau | 26 | 156_mahal_harga_murah_segini |
|
199 |
+
| 157 | tahan - lama - harum - manstav - disinj | 26 | 157_tahan_lama_harum_manstav |
|
200 |
+
| 158 | tahan - lama - kurang - ekpetasiku - dragukan | 26 | 158_tahan_lama_kurang_ekpetasiku |
|
201 |
+
| 159 | respon - cepat - penjual - tambahanya - dkulit | 26 | 159_respon_cepat_penjual_tambahanya |
|
202 |
+
| 160 | ahaha - tahan - lama - muali - mentong | 26 | 160_ahaha_tahan_lama_muali |
|
203 |
+
| 161 | bintang - 10 - lima - dimengerti - sebab | 25 | 161_bintang_10_lima_dimengerti |
|
204 |
+
| 162 | bau - seru - enak - alah - banget | 25 | 162_bau_seru_enak_alah |
|
205 |
+
| 163 | paket - terimakasih - terima - segalanya - mengganti | 25 | 163_paket_terimakasih_terima_segalanya |
|
206 |
+
| 164 | jam - sekitar - area - baju - nadi | 25 | 164_jam_sekitar_area_baju |
|
207 |
+
| 165 | sedap - grecep - nangis - midlenya - dipakeny | 25 | 165_sedap_grecep_nangis_midlenya |
|
208 |
+
| 166 | asli - nit - enak - hebat - banget | 24 | 166_asli_nit_enak_hebat |
|
209 |
+
| 167 | eos - dilayerin - gakpapa - nyabeh - matihi | 24 | 167_eos_dilayerin_gakpapa_nyabeh |
|
210 |
+
| 168 | swet - enek - profile - recom - kubaru | 24 | 168_swet_enek_profile_recom |
|
211 |
+
| 169 | manis - merasakan - aple - permen - sesuatu | 24 | 169_manis_merasakan_aple_permen |
|
212 |
+
| 170 | repeat - order - mangep - lahir - konsistensi | 24 | 170_repeat_order_mangep_lahir |
|
213 |
+
| 171 | love - aku - like - menyukai - suka | 23 | 171_love_aku_like_menyukai |
|
214 |
+
| 172 | cowok - unisex - cewek - milion - menye | 23 | 172_cowok_unisex_cewek_milion |
|
215 |
+
| 173 | terbaik - uw - timpa - aseli - keranjang | 23 | 173_terbaik_uw_timpa_aseli |
|
216 |
+
| 174 | asoy - aroma - simpul - grande - malaikat | 22 | 174_asoy_aroma_simpul_grande |
|
217 |
+
| 175 | pengiriman - pingiriman - cepat - kemasa - rapi | 22 | 175_pengiriman_pingiriman_cepat_kemasa |
|
218 |
+
| 176 | hidung - sopan - sensitif - tusuk - enek | 22 | 176_hidung_sopan_sensitif_tusuk |
|
219 |
+
| 177 | amazing - istimewa - luar - biasa - briliant | 22 | 177_amazing_istimewa_luar_biasa |
|
220 |
+
| 178 | segar - harum - ambune - ciamik - bersaman | 22 | 178_segar_harum_ambune_ciamik |
|
221 |
+
| 179 | kantor - ngechat - bosku - kake2 - buaik | 22 | 179_kantor_ngechat_bosku_kake2 |
|
222 |
+
| 180 | indoor - malam - kegiatan - outdor - segala | 22 | 180_indoor_malam_kegiatan_outdor |
|
223 |
+
| 181 | begitu - tahan - lama - disayangkanya - wlpun | 22 | 181_begitu_tahan_lama_disayangkanya |
|
224 |
+
| 182 | bau - sedap - solid - enak - betul | 22 | 182_bau_sedap_solid_enak |
|
225 |
+
| 183 | pakboi - ajip - ajib - pati - rispek | 22 | 183_pakboi_ajip_ajib_pati |
|
226 |
+
| 184 | layanan - service - ingetin - parahsih - ngebut | 22 | 184_layanan_service_ingetin_parahsih |
|
227 |
+
| 185 | layanan - service - produk - servicesnya - langananan | 22 | 185_layanan_service_produk_servicesnya |
|
228 |
+
| 186 | hadiah - memberinya - buka - tahu - bulan | 21 | 186_hadiah_memberinya_buka_tahu |
|
229 |
+
| 187 | pesan - sesuai - kond - psb - alamat | 21 | 187_pesan_sesuai_kond_psb |
|
230 |
+
| 188 | hm - wangik - asyik - hem - suka | 21 | 188_hm_wangik_asyik_hem |
|
231 |
+
| 189 | pengemasab - sesuai - beter - note - nyaman | 20 | 189_pengemasab_sesuai_beter_note |
|
232 |
+
| 190 | memuaskan - dianjurkan - sangat - biasanya - memang | 20 | 190_memuaskan_dianjurkan_sangat_biasanya |
|
233 |
+
| 191 | jajaran - lintas - bks - provinsi - cew2 | 20 | 191_jajaran_lintas_bks_provinsi |
|
234 |
+
| 192 | daily - sehari - use - hari - cudles | 20 | 192_daily_sehari_use_hari |
|
235 |
+
| 193 | kelas - ornamen - visual - bahasa - kerenya | 20 | 193_kelas_ornamen_visual_bahasa |
|
236 |
+
| 194 | hight - clas - kep - paket - up | 20 | 194_hight_clas_kep_paket |
|
237 |
+
| 195 | sel - gwperfume - fragrance - perfum - rec | 20 | 195_sel_gwperfume_fragrance_perfum |
|
238 |
+
| 196 | deskripsi - sesuai - barang - tulis - dengan | 20 | 196_deskripsi_sesuai_barang_tulis |
|
239 |
+
| 197 | job - good - mudah2 - selama - cari | 20 | 197_job_good_mudah2_selama |
|
240 |
+
| 198 | layanan - puas - obsesi - customernya - kiding | 20 | 198_layanan_puas_obsesi_customernya |
|
241 |
+
| 199 | atomizer - praktis - tokopedia - 10ml - dispensernya | 19 | 199_atomizer_praktis_tokopedia_10ml |
|
242 |
+
| 200 | favorit - ceritanya - tep - sepanjang - masa | 19 | 200_favorit_ceritanya_tep_sepanjang |
|
243 |
+
| 201 | travel - frhmptn - ukuran - kecil - botle | 19 | 201_travel_frhmptn_ukuran_kecil |
|
244 |
+
| 202 | keren - idenya - tampan - mengagumkan - cantik | 19 | 202_keren_idenya_tampan_mengagumkan |
|
245 |
+
| 203 | suami - endul - brti - tngan - uwuwuw | 19 | 203_suami_endul_brti_tngan |
|
246 |
+
| 204 | terima - kasih - - - | 19 | 204_terima_kasih__ |
|
247 |
+
| 205 | perlu - ragu - kecewa - dihebohkan - tak | 19 | 205_perlu_ragu_kecewa_dihebohkan |
|
248 |
+
| 206 | akhirnya - taiwan - finaly - bagi - hoki | 19 | 206_akhirnya_taiwan_finaly_bagi |
|
249 |
+
| 207 | segar - tahan - lama - anteng - ekonomis | 19 | 207_segar_tahan_lama_anteng |
|
250 |
+
| 208 | rapi - trusted - akurat - made - packing | 19 | 208_rapi_trusted_akurat_made |
|
251 |
+
| 209 | admin - ramah - pertimbanganya - menghadapi - dipuji2 | 18 | 209_admin_ramah_pertimbanganya_menghadapi |
|
252 |
+
| 210 | ngeri - bau - rd - vanilynya - handuk | 18 | 210_ngeri_bau_rd_vanilynya |
|
253 |
+
| 211 | kirim - cepat - inginkan - sesuai - sekali | 18 | 211_kirim_cepat_inginkan_sesuai |
|
254 |
+
| 212 | minst - double - 2nd - pocketnya - bad | 18 | 212_minst_double_2nd_pocketnya |
|
255 |
+
| 213 | pokok - mantap - sampai - cepat - suka | 18 | 213_pokok_mantap_sampai_cepat |
|
256 |
+
| 214 | sama - suka - semua - wangi - awet | 18 | 214_sama_suka_semua_wangi |
|
257 |
+
| 215 | semua - gilasih - pede - ever - enak | 18 | 215_semua_gilasih_pede_ever |
|
258 |
+
| 216 | kembali - sekian - membelinya - berulang - formulanya | 17 | 216_kembali_sekian_membelinya_berulang |
|
259 |
+
| 217 | bangga - pride - lokal - cakeup - kualitas | 17 | 217_bangga_pride_lokal_cakeup |
|
260 |
+
| 218 | cowok - eons - mantwp - dimainkan - spesial | 17 | 218_cowok_eons_mantwp_dimainkan |
|
261 |
+
| 219 | sukses - inovasi - lapaknya - terus - polisi | 17 | 219_sukses_inovasi_lapaknya_terus |
|
262 |
+
| 220 | produk - dikolom - dinas - diretur - away | 17 | 220_produk_dikolom_dinas_diretur |
|
263 |
+
| 221 | pesan - oekayanan - nemuaskab - sesuai - cepat | 17 | 221_pesan_oekayanan_nemuaskab_sesuai |
|
264 |
+
| 222 | luvs - terimakasih - hmns - fre - dapat | 17 | 222_luvs_terimakasih_hmns_fre |
|
265 |
+
| 223 | ulasin - slur - produqe - magantagap - lebenslangerschicksalschatz | 17 | 223_ulasin_slur_produqe_magantagap |
|
266 |
+
| 224 | tim - percancelan - discus - mrk - tepuk | 17 | 224_tim_percancelan_discus_mrk |
|
267 |
+
| 225 | suka - banget - benar - wangi - favorit | 17 | 225_suka_banget_benar_wangi |
|
268 |
+
| 226 | cowok - pacar - pour - hadiahin - huminya | 17 | 226_cowok_pacar_pour_hadiahin |
|
269 |
+
| 227 | menyesal - keskian - barter - brgnya - pernsh | 16 | 227_menyesal_keskian_barter_brgnya |
|
270 |
+
| 228 | twitter - tws - sosial - review - media | 16 | 228_twitter_tws_sosial_review |
|
271 |
+
| 229 | pesan - ulang - item - setitikomanya - sebesarkecilnya | 16 | 229_pesan_ulang_item_setitikomanya |
|
272 |
+
| 230 | terima - baik - barang - sementara - apik | 16 | 230_terima_baik_barang_sementara |
|
273 |
+
| 231 | gagal - pernah - kecewa - mnecewakan - pekayanan | 16 | 231_gagal_pernah_kecewa_mnecewakan |
|
274 |
+
| 232 | urang - recomened - mintip - teu - mantops | 16 | 232_urang_recomened_mintip_teu |
|
275 |
+
| 233 | pengiriman - komitmen - pekinganya - bugus - thd | 16 | 233_pengiriman_komitmen_pekinganya_bugus |
|
276 |
+
| 234 | eos - trial - sia - re - named | 16 | 234_eos_trial_sia_re |
|
277 |
+
| 235 | alkohol - 5an - k3nceng - kadar - pedas2 | 15 | 235_alkohol_5an_k3nceng_kadar |
|
278 |
+
| 236 | berjuang - suke - setidaknya - kesukan - invalid | 15 | 236_berjuang_suke_setidaknya_kesukan |
|
279 |
+
| 237 | pengiriman - sicepatnya - shipment - besokny - kurir | 15 | 237_pengiriman_sicepatnya_shipment_besokny |
|
280 |
+
| 238 | sukses - semwriwing - rempah2nya - selalu - hasil | 15 | 238_sukses_semwriwing_rempah2nya_selalu |
|
281 |
+
| 239 | puas - waduh - hawanya - sejuk - bahagia | 15 | 239_puas_waduh_hawanya_sejuk |
|
282 |
+
| 240 | coconut - kelapa - pasion - vs - coco | 15 | 240_coconut_kelapa_pasion_vs |
|
283 |
+
| 241 | buka - kotak - pwngirimanya - divideoin - nyangkanya | 14 | 241_buka_kotak_pwngirimanya_divideoin |
|
284 |
+
| 242 | tunggu - akhirnya - datang - ye - pewangi | 14 | 242_tunggu_akhirnya_datang_ye |
|
285 |
+
| 243 | oke - siap - semua - banget - baik | 14 | 243_oke_siap_semua_banget |
|
286 |
+
| 244 | obat - bets - develop - ada - mature | 14 | 244_obat_bets_develop_ada |
|
287 |
+
| 245 | pertama - mengoda - pengatur - kesan - liked | 14 | 245_pertama_mengoda_pengatur_kesan |
|
288 |
+
| 246 | telah - pesan - terima - ndan - sesuai | 13 | 246_telah_pesan_terima_ndan |
|
289 |
+
| 247 | paket - mudik - maf - selali - josh | 13 | 247_paket_mudik_maf_selali |
|
290 |
+
| 248 | ganteng - ajojing - ksowkwk - penampakan - arahnya | 13 | 248_ganteng_ajojing_ksowkwk_penampakan |
|
291 |
+
| 249 | mandi - habis - yha - dikata - syurgah | 13 | 249_mandi_habis_yha_dikata |
|
292 |
+
| 250 | awet - divine - tanteku - folow - up | 13 | 250_awet_divine_tanteku_folow |
|
293 |
+
| 251 | priduk - kirim - keterangan - reorder - original | 13 | 251_priduk_kirim_keterangan_reorder |
|
294 |
+
| 252 | rekomendasi - wajib - foto - langganan - disini | 13 | 252_rekomendasi_wajib_foto_langganan |
|
295 |
+
| 253 | projection - menyerang - kurang - meter - gau | 13 | 253_projection_menyerang_kurang_meter |
|
296 |
+
| 254 | undertone - serbaguna - satset - direkomendasi - volumenya | 13 | 254_undertone_serbaguna_satset_direkomendasi |
|
297 |
+
| 255 | sunguh - mempesona - luar - biasa - amazing | 13 | 255_sunguh_mempesona_luar_biasa |
|
298 |
+
| 256 | bau - suka - senak - awet - banget | 13 | 256_bau_suka_senak_awet |
|
299 |
+
| 257 | suka - banget - wangi - bau - sama | 13 | 257_suka_banget_wangi_bau |
|
300 |
+
| 258 | ulang - tahun - dia - ulangtahun - hadiah | 12 | 258_ulang_tahun_dia_ulangtahun |
|
301 |
+
| 259 | hilang - lamanya - pasaran - ketingal - dispil | 12 | 259_hilang_lamanya_pasaran_ketingal |
|
302 |
+
| 260 | khayangan - chewy - votolnya - kerajan - garis | 12 | 260_khayangan_chewy_votolnya_kerajan |
|
303 |
+
| 261 | bonus - terimaksih - mini - adict - terimakasih | 12 | 261_bonus_terimaksih_mini_adict |
|
304 |
+
| 262 | deskripsi - lancar - tulisanya - sesuai - pulak | 12 | 262_deskripsi_lancar_tulisanya_sesuai |
|
305 |
+
| 263 | calm - tenang - perkirakan - sopan - akhir | 12 | 263_calm_tenang_perkirakan_sopan |
|
306 |
+
| 264 | jiwa - kesegaran - mantap - - | 12 | 264_jiwa_kesegaran_mantap_ |
|
307 |
+
| 265 | keren - parah - anjay - damn - praktis | 12 | 265_keren_parah_anjay_damn |
|
308 |
+
| 266 | mewah - limo - seksi - lux - murah | 12 | 266_mewah_limo_seksi_lux |
|
309 |
+
| 267 | nunguin - penguna - nyala - beralih - 150rb | 12 | 267_nunguin_penguna_nyala_beralih |
|
310 |
+
| 268 | batch - oker - kelewatan - final - cancel | 11 | 268_batch_oker_kelewatan_final |
|
311 |
+
| 269 | astha - terbaeq - smr - arfoi - heuheu | 11 | 269_astha_terbaeq_smr_arfoi |
|
312 |
+
| 270 | winginya - tomat - hiu - dimix - combo | 11 | 270_winginya_tomat_hiu_dimix |
|
313 |
+
| 271 | unik - karene - menyejukan - aromao - clingi | 11 | 271_unik_karene_menyejukan_aromao |
|
314 |
+
| 272 | vubes - muchas - puckboy - begitupun - gracias | 11 | 272_vubes_muchas_puckboy_begitupun |
|
315 |
+
| 273 | mevah - laik - wuhu - kepribadian - karakter | 11 | 273_mevah_laik_wuhu_kepribadian |
|
316 |
+
| 274 | notes - printilan - midlle - base - mbak | 11 | 274_notes_printilan_midlle_base |
|
317 |
+
| 275 | wekend - dicuekin - first - tunangan - again | 11 | 275_wekend_dicuekin_first_tunangan |
|
318 |
+
| 276 | premium - packinya - perbedan - packinganya - beut | 11 | 276_premium_packinya_perbedan_packinganya |
|
319 |
+
| 277 | alien - hade - cirebon - wae - descent | 11 | 277_alien_hade_cirebon_wae |
|
320 |
+
| 278 | respon - bnrn - ckup - disekitar - kilat | 11 | 278_respon_bnrn_ckup_disekitar |
|
321 |
+
| 279 | useful - barang - standar - item - sesuai | 11 | 279_useful_barang_standar_item |
|
322 |
+
| 280 | bonus - sedap - betul - yeay - terimakasih | 11 | 280_bonus_sedap_betul_yeay |
|
323 |
+
| 281 | ekspedisi - lambat - expedisi - hub - tertaham | 11 | 281_ekspedisi_lambat_expedisi_hub |
|
324 |
+
| 282 | favorit - salah - satu - al - menjadi | 11 | 282_favorit_salah_satu_al |
|
325 |
+
| 283 | bonus - dengen - gantengs - nembak - setetes | 11 | 283_bonus_dengen_gantengs_nembak |
|
326 |
+
| 284 | dou - menyukainya - katanya - suka - theta | 10 | 284_dou_menyukainya_katanya_suka |
|
327 |
+
| 285 | lari - kembangin - puch - mesjid - malaikat | 10 | 285_lari_kembangin_puch_mesjid |
|
328 |
+
| 286 | selamalamanya - farfumnya - puasnya - skor - farfum | 10 | 286_selamalamanya_farfumnya_puasnya_skor |
|
329 |
+
| 287 | pengirinan - beginu - yh - spicynya - babget | 10 | 287_pengirinan_beginu_yh_spicynya |
|
330 |
+
| 288 | suami - keman - kenapasi - thankyoh - dijdin | 10 | 288_suami_keman_kenapasi_thankyoh |
|
331 |
+
| 289 | bonus - terkhusus - menghargai - atas - min | 10 | 289_bonus_terkhusus_menghargai_atas |
|
332 |
+
|
333 |
+
</details>
|
334 |
+
|
335 |
+
## Training hyperparameters
|
336 |
+
|
337 |
+
* calculate_probabilities: False
|
338 |
+
* language: indonesian
|
339 |
+
* low_memory: False
|
340 |
+
* min_topic_size: 10
|
341 |
+
* n_gram_range: (1, 1)
|
342 |
+
* nr_topics: None
|
343 |
+
* seed_topic_list: None
|
344 |
+
* top_n_words: 10
|
345 |
+
* verbose: False
|
346 |
+
|
347 |
+
## Framework versions
|
348 |
+
|
349 |
+
* Numpy: 1.23.5
|
350 |
+
* HDBSCAN: 0.8.29
|
351 |
+
* UMAP: 0.5.3
|
352 |
+
* Pandas: 1.5.3
|
353 |
+
* Scikit-Learn: 1.2.1
|
354 |
+
* Sentence-transformers: 2.2.2
|
355 |
+
* Transformers: 4.24.0
|
356 |
+
* Numba: 0.56.4
|
357 |
+
* Plotly: 5.9.0
|
358 |
+
* Python: 3.10.9
|
config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"calculate_probabilities": false,
|
3 |
+
"language": "indonesian",
|
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": false,
|
14 |
+
"embedding_model": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2"
|
15 |
+
}
|
topic_embeddings.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57c9a2126b16d362ec1ef27d577e2ac5ad9a15bf30ecb9c22890d955e1da76d3
|
3 |
+
size 447064
|
topics.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|