Add BERTopic model

README.md

@@ -0,0 +1,135 @@
+
+---
+tags:
+- bertopic
+library_name: bertopic
+pipeline_tag: text-classification
+---
+
+# bertopic_after_tuning
+
+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("vidric/bertopic_after_tuning")
+
+topic_model.get_topic_info()
+```
+
+## Topic overview
+
+* Number of topics: 68
+* Number of training documents: 20977
+
+<details>
+  <summary>Click here for an overview of all topics.</summary>
+  
+  | Topic ID | Topic Keywords | Topic Frequency | Label | 
+|----------|----------------|-----------------|-------| 
+| -1 | parfum - wangi - tidak - banget - tapi | 11 | -1_parfum_wangi_tidak_banget | 
+| 0 | wangi - mantap - enak - banget - suka | 6775 | 0_wangi_mantap_enak_banget | 
+| 1 | orgasm - eos - aku - lebih - farhampton | 10606 | 1_orgasm_eos_aku_lebih | 
+| 2 | terbaik - selalu - always - deal - puas | 886 | 2_terbaik_selalu_always_deal | 
+| 3 | admin - ramah - respon - cepat - kirim | 191 | 3_admin_ramah_respon_cepat | 
+| 4 | bubble - wrap - tebal - aman - kotak | 187 | 4_bubble_wrap_tebal_aman | 
+| 5 | alpha - theta - beli - tim - tetha | 154 | 5_alpha_theta_beli_tim | 
+| 6 | beli - menyesal - kali - lagi - ragu | 125 | 6_beli_menyesal_kali_lagi | 
+| 7 | kedua - beli - dua - kali - 2x | 109 | 7_kedua_beli_dua_kali | 
+| 8 | pernah - kecewa - tidak - selalu - hmns | 98 | 8_pernah_kecewa_tidak_selalu | 
+| 9 | farhampton - coba - beli - terimakasih - bonus | 86 | 9_farhampton_coba_beli_terimakasih | 
+| 10 | delta - theta - alpha - sama - suka | 85 | 10_delta_theta_alpha_sama | 
+| 11 | tidak - debat - ekspektasi - no - nget | 83 | 11_tidak_debat_ekspektasi_no | 
+| 12 | magnet - tutup - botol - ada - kemasan | 80 | 12_magnet_tutup_botol_ada | 
+| 13 | belum - unboxing - buka - tidak - bocor | 79 | 13_belum_unboxing_buka_tidak | 
+| 14 | indonesia - bangga - produk - buatan - terus | 73 | 14_indonesia_bangga_produk_buatan | 
+| 15 | repeat - order - kesekian - kali - selalu | 70 | 15_repeat_order_kesekian_kali | 
+| 16 | tester - test - sample - dapat - bonus | 67 | 16_tester_test_sample_dapat | 
+| 17 | ketiga - tiga - beli - kali - cny | 59 | 17_ketiga_tiga_beli_kali | 
+| 18 | selamat - barang - dengan - mendarat - sampai | 57 | 18_selamat_barang_dengan_mendarat | 
+| 19 | lokal - produk - internasional - brand - kualitas | 53 | 19_lokal_produk_internasional_brand | 
+| 20 | starterpacking - beli - starterpack - coba - varian | 44 | 20_starterpacking_beli_starterpack_coba | 
+| 21 | spray - macet - rusak - keras - berfungsi | 44 | 21_spray_macet_rusak_keras | 
+| 22 | longevity - jam - projection - notes - silage | 42 | 22_longevity_jam_projection_notes | 
+| 23 | kartu - card - greting - ucap - tulis | 39 | 23_kartu_card_greting_ucap | 
+| 24 | tahan - lama - harum - disinj - horny | 32 | 24_tahan_lama_harum_disinj | 
+| 25 | love - just - swet - cinta - lembut | 31 | 25_love_just_swet_cinta | 
+| 26 | rekomendasi - gela - ank - bangsa - karya | 31 | 26_rekomendasi_gela_ank_bangsa | 
+| 27 | proses - chat - lama - kirim - pengiriman | 31 | 27_proses_chat_lama_kirim | 
+| 28 | matahari - esence - sun - sari - ber | 30 | 28_matahari_esence_sun_sari | 
+| 29 | rekomendasi - sangat - super - layak - direkomendasi | 29 | 29_rekomendasi_sangat_super_layak | 
+| 30 | blind - beli - muantep - ekspektasi - sisi | 29 | 30_blind_beli_muantep_ekspektasi | 
+| 31 | istri - hadiah - menyukainya - suami - buat | 28 | 31_istri_hadiah_menyukainya_suami | 
+| 32 | harum - sue - hua - unik - tagih | 28 | 32_harum_sue_hua_unik | 
+| 33 | bicara - bintang - biar - alasanya - nyang | 28 | 33_bicara_bintang_biar_alasanya | 
+| 34 | worth - it - layak - lumayan - harga | 26 | 34_worth_it_layak_lumayan | 
+| 35 | atomizer - dapat - bonus - 10ml - praktis | 25 | 35_atomizer_dapat_bonus_10ml | 
+| 36 | hadiah - tahu - buka - belum - semoga | 25 | 36_hadiah_tahu_buka_belum | 
+| 37 | ragu - perlu - kecewa - tidak - rugi | 24 | 37_ragu_perlu_kecewa_tidak | 
+| 38 | bintang - 10 - lima - kasih - sebab | 23 | 38_bintang_10_lima_kasih | 
+| 39 | segar - harum - ambune - ciamik - memuaskan | 22 | 39_segar_harum_ambune_ciamik | 
+| 40 | tim - hmns - terimakasih - kami - telah | 21 | 40_tim_hmns_terimakasih_kami | 
+| 41 | twitter - review - instagram - tws - decants | 20 | 41_twitter_review_instagram_tws | 
+| 42 | pokok - mantap - sampai - cepat - suka | 20 | 42_pokok_mantap_sampai_cepat | 
+| 43 | travel - ukuran - kecil - botle - frhmptn | 20 | 43_travel_ukuran_kecil_botle | 
+| 44 | eos - sama - suka - adict - zodiak | 20 | 44_eos_sama_suka_adict | 
+| 45 | notes - base - printilan - midlle - note | 20 | 45_notes_base_printilan_midlle | 
+| 46 | bangga - lokal - pride - kualitas - bagus | 20 | 46_bangga_lokal_pride_kualitas | 
+| 47 | cowok - cocok - spesial - masculine - dimainkan | 19 | 47_cowok_cocok_spesial_masculine | 
+| 48 | rapi - packing - trusted - ramah - aman | 18 | 48_rapi_packing_trusted_ramah | 
+| 49 | sukses - terus - lapaknya - inovasi - selalu | 18 | 49_sukses_terus_lapaknya_inovasi | 
+| 50 | mantan - ayah - abang - dia - masjid | 18 | 50_mantan_ayah_abang_dia | 
+| 51 | first - wekend - again - dicuekin - tunangan | 18 | 51_first_wekend_again_dicuekin | 
+| 52 | paket - mudik - maf - buka - selamat | 17 | 52_paket_mudik_maf_buka | 
+| 53 | bonus - dapat - gantengs - dengen - nembak | 15 | 53_bonus_dapat_gantengs_dengen | 
+| 54 | premium - packinya - 30k - perbedan - kemasan | 14 | 54_premium_packinya_30k_perbedan | 
+| 55 | obat - ada - tidak - bets - develop | 14 | 55_obat_ada_tidak_bets | 
+| 56 | projection - kurang - menyerang - meter - palagi | 14 | 56_projection_kurang_menyerang_meter | 
+| 57 | coconut - kelapa - pasion - vs - panas | 14 | 57_coconut_kelapa_pasion_vs | 
+| 58 | cewek - pacar - klepek - senenk - comunikasi | 14 | 58_cewek_pacar_klepek_senenk | 
+| 59 | pertama - mengoda - kesan - kali - pengatur | 13 | 59_pertama_mengoda_kesan_kali | 
+| 60 | ekspedisi - lambat - expedisi - hub - langsung | 13 | 60_ekspedisi_lambat_expedisi_hub | 
+| 61 | tunggu - akhirnya - datang - ye - uh | 13 | 61_tunggu_akhirnya_datang_ye | 
+| 62 | produk - dikolom - tanya - segini - kabari | 13 | 62_produk_dikolom_tanya_segini | 
+| 63 | jiwa - mantap - kesegaran -  -  | 12 | 63_jiwa_mantap_kesegaran_ | 
+| 64 | darker - warna - hitam - kuning - dof | 12 | 64_darker_warna_hitam_kuning | 
+| 65 | mewah - limo - seksi - lux - harum | 11 | 65_mewah_limo_seksi_lux | 
+| 66 | batch - oker - kelewatan - final - bagi | 11 | 66_batch_oker_kelewatan_final |
+  
+</details>
+
+## Training hyperparameters
+
+* calculate_probabilities: False
+* language: indonesian
+* low_memory: False
+* min_topic_size: 10
+* n_gram_range: (1, 1)
+* nr_topics: auto
+* seed_topic_list: None
+* top_n_words: 10
+* verbose: False
+
+## Framework versions
+
+* Numpy: 1.23.5
+* HDBSCAN: 0.8.29
+* UMAP: 0.5.3
+* Pandas: 1.5.3
+* Scikit-Learn: 1.2.1
+* Sentence-transformers: 2.2.2
+* Transformers: 4.24.0
+* Numba: 0.56.4
+* Plotly: 5.9.0
+* Python: 3.10.9

config.json

@@ -0,0 +1,15 @@
+{
+  "calculate_probabilities": false,
+  "language": "indonesian",
+  "low_memory": false,
+  "min_topic_size": 10,
+  "n_gram_range": [
+    1,
+    1
+  ],
+  "nr_topics": "auto",
+  "seed_topic_list": null,
+  "top_n_words": 10,
+  "verbose": false,
+  "embedding_model": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2"
+}

topic_embeddings.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cda72d98128beee7889013059fe04c0f2e905bf458d06bb53f44b0d590ec346
+size 104536