Machine learning and data

Machine learning, NLP, OCR and data analysis.

Related work

• Galactic merger-history clustering Key workHDBSCAN clustering pipeline that reconstructs galactic merger histories from large stellar datasets.
• Faint stellar structure detection Key workAutoGluon models that detect faint stellar structures, run on HPC infrastructure.
• Knowledge graph construction from unstructured data Key work Feb 2025Pipeline that builds knowledge graphs from unstructured text: entity and relation extraction with spaCy, graph construction with NetworkX, export to edge lists, adjacency matrices and GraphML.
• OMR exam system Key work Mar 2026Exam management and OMR analytics system: classrooms, question papers, seating, review and reports.
• Mistral OCR to LaTeX Jun 2026Upload a PDF or image of an academic document and get a compilable .tex file back, questions and solutions separated.
• Thai OMR answer sheet generator Mar 2026Generates Thai and English OMR answer sheets; first built so a teacher could grade homework without checking every answer.
• Intro to DBSCAN Mar 2026Learning resource for DBSCAN from the 1996 KDD paper to applications, with derivations, visualisations and notebooks.
• Driving scenario generator Jun 2025LLM-driven generator of driving scenarios (e.g. highway merges) from prompts and past experiences; in development.
• Text preprocessing pipeline Mar 2025Command-line pipeline that cleans raw text CSVs for NLP.
• Graph classification experiments Feb 2025Graph-classification experiments on the MUTAG and PROTEINS datasets with PyTorch Geometric.
• Deep reinforcement learning May 2025Deep reinforcement-learning notebook.
• Language model study Apr 2025Language-model study code.
• Intro to machine learning Dec 2024Machine-learning course notebooks and preprocessing.
• Flask OpenAI chatbot Dec 2024Simple chatbot using GPT-3.5 Turbo and Flask.
• Handwritten digit OCR Oct 2024Notebooks and models for recognising handwritten digits.
• ONNX models in Unity May 2024Converting a Keras model to ONNX and running it inside Unity.
• COVID-19 in US counties Oct 2023Data analysis of COVID-19 in US counties, with code-quality and coverage checks.
• CS203 playground Oct 2023Notebooks and source for a data-science course.
• Kaggle on Colab Sep 2023Tutorial for using Kaggle datasets in Google Colab.

@prefix id: <https://ask.chaipat.cc/id/> .
@prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
@prefix cj: <https://ask.chaipat.cc/ns#> .
@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> .

id:ThemeML
    a cj:Theme ;
    rdfs:label "Machine learning and data" ;
    cj:description "Machine learning, NLP, OCR and data analysis." .