Hi, I'm Pu5hk4r — a passionate developer who loves crafting code, solving problems, and building cool projects.
This is my coding playground where I experiment, learn, and share my work with the world. 🌍
- 💻 Full-Stack Developer with a knack for creating seamless user experiences
- 🌱 Currently working on AI/ML and exploring Web3 technologies
- 🎯 Goal: Build impactful projects that make a difference
- ⚡ Fun Fact: I can debug code faster than I can brew coffee! ☕
| Category | Technologies |
|---|---|
| Languages | Python, JavaScript, TypeScript, C++ |
| AI-Framework | Tensorflow, Keras, Pytorch, Langchain, Spacy, LLM's, Transformers |
| Libraries | Numpy, Pandas, Matplotlib, Seaborn, Scikit-Learn |
| Frameworks | Flask, FastAPI, React, Node.js, Express, Django |
| Tools | Git, Docker, Postman, VS Code |
| Databases | MongoDB, MySQL, Firebase, Faiss, Pinecone |
🟢 Kafka Producer streams data.
🔶 Spark Streaming consumes and processes it.
🧮 Feature Engineering on Spark.
🤖 ML Model predicts demand.
📣 Predictions go to Kafka topic.
📊 Dash shows demand.
🗃️ PostgreSQL stores for analysis.
🧮 Airflow Scheduled ML Training.
A full-stack real-time data pipeline for predicting taxi demand across NYC neighborhoods.
Designed for live ingestion and historical replay, it helps visualize traffic hot zones and optimize fleet allocation. Automatic scheduled job of ML_model train at particular time interval. 🖼️ Preview:
A full-stack application for bank loan applications, risk prediction using ML, and admin management.
User registration/login with JWT auth and roles (user/admin).
Loan application form with real-time installment/interest calculation.
Admin dashboard for approving/rejecting loans, viewing stats and risk !.
🖼️ Preview:
The PDF Chatbot is an AI-powered application that allows users to interact with PDF documents using natural language. It processes PDF files, extracts their content, and leverages a language model to provide context-aware responses to user queries about the document. Built with Python, Langchain, and vector database.
🖼️ Preview:
This is a deep learning-based Flask web application for detecting brain tumors in MRI images. It uses a pre-trained CNN model (braintumor_binary.h5) to classify images as either Tumor Detected or No Tumor Detected, and stores patient records and predictions in MongoDB Atlas.
🖼️ Preview:
This project uses the Florence-2 transformer model to generate captions for uploaded images. With an intuitive Gradio web interface, users can upload images and receive contextually accurate captions in real time.
🖼️ Preview:
This project uses SQL, Pandas, Tableau, Pyspark and AWS.
🖼️ Preview:
This project uses SQL, Pandas, Tableau, Pyspark and MachineLearningModel. This project aims to forecast renewable energy generation using time series data from wind turbines. Leveraging machine learning techniques, it provides accurate predictions based on 30 days of historical wind turbine data.
🖼️ Preview:
Let's chat about code, projects, or just geek out!
- 🥇 Hackathon Winner @ TechFest 2024
- 🏅 Published an Open Source NPM Package
- 🧠 Built a chatbot using OpenAI API and Flask
“Code is like poetry; it’s all about finding the right rhythm.”
Thanks for stopping by! Feel free to explore my repositories and drop a ⭐ if you like what you see! 😄
