Skip to content
View aasthathakkar's full-sized avatar
💭
poetries and messy codes🌸
💭
poetries and messy codes🌸
2 followers · 3 following

Achievements

Achievement: Pair ExtraordinaireAchievement: Quickdraw

Achievements

Achievement: Pair ExtraordinaireAchievement: Quickdraw

Block or report aasthathakkar

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
aasthathakkar/README.md
aastha thakkar typing

LinkedIn Email GitHub

hi, i'm aastha 🌸

she/her · cs student at iiit vadodara · 2024–2028, building at the intersection of ml, backend & medical imaging. i'm meticulous and a little proud of it - i once wrote 18 unit tests for a single PR. zero regrets.

currently

things i obsess over

clean code & tests ml + debugging medical imaging backend & apis open source

tech i work with

ml & data

Python PyTorch TensorFlow scikit-learn NumPy pandas OpenCV

backend & infra

FastAPI Flask Node.js PostgreSQL MongoDB Docker

languages & tools

C++ C Java Git Jupyter

projects

🩺 MedScan

AI medicine advisor — symptom checker, OCR expiry scanner, drug-safety warnings & a personal medicine cabinet.

React FastAPI scikit-learn

✉️ Spam Email Detector

Hybrid ML + rule-based classifier — Flask API + Chrome extension that flags spam live inside Gmail. ~98.5% accuracy.

Python scikit-learn Flask JavaScript

🔐 MedVault  building now

Secure store + retrieval for medical records, built on a clean backend.

Node.js PostgreSQL Docker

🌐 Diomede  open source · PR #132

Open-source contribution - fork I'm exploring + contributing to.

experience

  • Vounteered ML problem design and judging - HackIIITV'25, IIIT Vadodara, Collaborated in organising HackIIITV'25 and helped in Designing the ML problem statement and judging across 200+ participants & 50+ teams.
  • Technical Committee Member, IIIT Vadodara.
footer

Pinned Loading

  1. MedScan MedScan Public

    AI-powered medicine advisor: symptom checker, OCR expiry scanner, safety warnings, and personal medicine cabinet.

    JavaScript

  2. spam-email-detector spam-email-detector Public

    NLP-based spam email classifier using TF-IDF and Machine Learning

    Jupyter Notebook

  3. MedVault MedVault Public

    A smart DICOM medical image research assistant — ML-powered auto-albuming, anomaly detection, and in-browser image viewing

    Python

  4. aasthathakkar aasthathakkar Public

    CSE student at IIIT Vadodara | Python • Flask • SQLAlchemy | Exploring ML & MLOPs

  5. Diomede Diomede Public

    Forked from KathiraveluLab/Diomede

    DICOM Telemedicine Toolkit

    Python