Add BERTopic model

README.md

@@ -0,0 +1,75 @@
+
+---
+tags:
+- bertopic
+library_name: bertopic
+pipeline_tag: text-classification
+---
+
+# BERTopic-Indonesia-Finance-News
+
+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("ZhafranR/BERTopic-Indonesia-Finance-News")
+
+topic_model.get_topic_info()
+```
+
+## Topic overview
+
+* Number of topics: 8
+* Number of training documents: 74933
+
+<details>
+  <summary>Click here for an overview of all topics.</summary>
+  
+  | Topic ID | Topic Keywords | Topic Frequency | Label | 
+|----------|----------------|-----------------|-------| 
+| 0 | penguatan - menguat - ihsg - acuan - kamis | 28336 | 0_penguatan_menguat_ihsg_acuan | 
+| 1 | perseroan - keterbukaan - sepekan - kepemilikan - hmetd | 12504 | 1_perseroan_keterbukaan_sepekan_kepemilikan | 
+| 2 | perseroan - penyaluran - restrukturisasi - otoritas - transformasi | 11737 | 2_perseroan_penyaluran_restrukturisasi_otoritas | 
+| 3 | sekuritas - ihsg - squawk - saksikan - cnbcindonesia | 9410 | 3_sekuritas_ihsg_squawk_saksikan | 
+| 4 | menguat - penguatan - sekuritas - terpantau - jakarta | 8680 | 4_menguat_penguatan_sekuritas_terpantau | 
+| 5 | penyidikan - diperiksa - kejagung - penyidik - persidangan | 2616 | 5_penyidikan_diperiksa_kejagung_penyidik | 
+| 6 | iurannya - ketenagakerjaan - kepesertaan - pemberi - dibayarkan | 1317 | 6_iurannya_ketenagakerjaan_kepesertaan_pemberi | 
+| 7 | likuiditas - pencatatan - berkelanjutan - sukuk - cyclicals | 333 | 7_likuiditas_pencatatan_berkelanjutan_sukuk |
+  
+</details>
+
+## Training hyperparameters
+
+* calculate_probabilities: False
+* language: None
+* low_memory: False
+* min_topic_size: 100
+* n_gram_range: (1, 2)
+* nr_topics: None
+* seed_topic_list: None
+* top_n_words: 20
+* verbose: True
+
+## Framework versions
+
+* Numpy: 1.24.1
+* HDBSCAN: 0.8.33
+* UMAP: 0.5.4
+* Pandas: 1.5.3
+* Scikit-Learn: 1.3.2
+* Sentence-transformers: 2.2.2
+* Transformers: 4.35.0
+* Numba: 0.57.1
+* Plotly: 5.18.0
+* Python: 3.10.6

config.json

@@ -0,0 +1,15 @@
+{
+  "calculate_probabilities": false,
+  "language": null,
+  "low_memory": false,
+  "min_topic_size": 100,
+  "n_gram_range": [
+    1,
+    2
+  ],
+  "nr_topics": null,
+  "seed_topic_list": null,
+  "top_n_words": 20,
+  "verbose": true,
+  "embedding_model": "ZhafranR/XLM-RoBERTa-Large-FineTuned-CCIDNews"
+}

ctfidf.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4e1359fc7c583b419299a9a69be4bd108c3a03cec36d3e9eed69067b965d9d4
+size 3660004

topic_embeddings.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07e953fda427e63231596f37535a6cc1a507e3e159273e66ae2d30cfd866c898
+size 32856