wanadzhar913
Follow
-
This repo details code for building a text classifier for predicting Bank Transaction categories. I finetune a base version of a DeBERTaV3 model purely on text data, as well as another version usin…
Jupyter Notebook UpdatedJan 28, 2025 -
This repo details code written as part of the 1st place solution for the AI Tinkerer's Hackathon in Kuala Lumpur for an LLM-as-a-Judge use case.
-
Jupyter Notebook Updated
Dec 25, 2024 -
This is a RAG Microservice Backend built using Redis (to cache conversations), Postgres/pgvector (as the vector store), the Unstructured library (to aid in table/image extraction in PDFs), LangChai…
Jupyter Notebook UpdatedDec 24, 2024 -
This is a simple CRUD app for emails built using FastAPI, Docker and Postgres.
Python UpdatedDec 19, 2024 -
chat-with-PDFs-using-LLMs Public
Simple PDF chatbot using LangChain, OpenAI API, FAISS and Streamlit.
-
research-paper Public
Forked from mesolitica/research-paperPreprint under Mesolitica.
TeX UpdatedOct 31, 2024 -
malaya Public
Forked from mesolitica/malayaNatural Language Toolkit for Malaysian language, https://malaya.readthedocs.io/
Jupyter Notebook MIT License UpdatedOct 31, 2024 -
text-dataset-dedup Public
Forked from malaysia-ai/pretrain-text-datasetDedup and postprocessing for text dataset.
Jupyter Notebook UpdatedOct 15, 2024 -
Repo for RFM (Recency, Frequency & Monetary) analysis and customer segmentation using the Online Retail II dataset from the UCI Machine Learning Repository.
Jupyter Notebook UpdatedSep 29, 2024 -
selenium-twitter-scraper Public
Forked from godkingjay/selenium-twitter-scraperAdapted from @godkingjay's Selenium Twitter Scraper. Each branch is a different scraping project. Projects: a) Scraping NSFW tweets (religion);
Jupyter Notebook Apache License 2.0 UpdatedJun 2, 2024 -
llm-embedding Public
Forked from mesolitica/llm-embeddingFinetune Malaysian LLM for Malaysian context embedding task.
Jupyter Notebook UpdatedApr 27, 2024 -
faiq-scraping-projects Public
This repo collates a list of websites I've scraped. They have either been for open source contributions or for my own personal practice/use.
-
malaysian-dataset Public
Forked from mesolitica/malaysian-datasetText corpus for Malaysia, https://malaya.readthedocs.io/en/latest/Dataset.html
Jupyter Notebook Apache License 2.0 UpdatedNov 13, 2023 -
classification-ml-with-shap Public
Exploratory data analysis & modeling exercise with Logistic Regression, Imbalanced-learn, RobustScaler and SHAP (SHapley Additive exPlanations). The dataset details a set of categorical/continuous …
Jupyter Notebook UpdatedOct 30, 2023 -
-
bbc-world-news-scraper Public
Simple Python webscraper (using BeautifulSoup and Requests) that cleans and consolidates the latest news from https://www.bbc.com/news/world.
Python UpdatedJul 19, 2023 -
This repo details my revised attempt at the capstone project for the Centre of Applied Data Science's (CADS) bootcamp. The initial submission was on the 5th of October 2022.
-
sample-project-Sentiment-Analysis-for-Shopee Public
Forked from gracechia/Sentiment-Analysis-for-ShopeeForked a repo that built a sentiment analysis tool for Shopee based on Google Play reviews
Jupyter Notebook UpdatedMay 1, 2023 -
This is a simple currency exchange converter using Python and the Frankfurter API.
Python UpdatedFeb 22, 2023 -
sample-solution-MoneyLionAssessmentDS Public
Forked from yudhiesh/MoneyLionAssessmentDSJupyter Notebook UpdatedJun 11, 2021