class AbhijeetKartikeya:
def __init__(self):
self.name = "Abhijeet Kartikeya"
self.location = "Delhi, India"
self.role = "ML Engineer & Full-Stack Developer"
self.education = "B.Tech (AI/ML)"
self.currently_building = [
"Solar Energy Forecasting Platform (Tata Power)",
"MediVault - AI Medical Report Manager",
"Production Weather Prediction System"
]
self.interests = ["Deep Learning", "Time Series Forecasting",
"Computer Vision", "MLOps", "Agent AI"]
def say_hi(self):
print("Thanks for dropping by! Let's build something amazing together.")
me = AbhijeetKartikeya()
me.say_hi()
|
Full-stack solar energy monitoring for Tata Power assets across India. Interactive Leaflet map, 3-day ML power forecasts, and real-time Grafana dashboards. |
Production ML pipeline with XGBoost models for 5 weather variables at 15-min granularity. 288-step forecasts across 10+ Indian locations. |
|
AI-powered medical report manager. OCR extraction, LLM summaries via Ollama/Mistral, semantic search with ChromaDB, and family-based organization. |
Interactive deep learning demo: digit recognition (CNN, 98%+ acc), image classification (MobileNetV2), sentiment analysis (LSTM), and predictive analytics. |
|
Streamlit dashboard for telecom customer churn prediction. Logistic Regression (~78%) and Random Forest (~82%) with interactive visualizations. |
CLI expense management tool with smart categorization, monthly budget analysis, and pie chart visualizations using Pandas and Matplotlib. |
|
|
|
|
