<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Python on Abhijith Nagarajan</title><link>https://abhijith-nagarajan.com/tags/python/</link><description>Recent content in Python on Abhijith Nagarajan</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 01 Dec 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://abhijith-nagarajan.com/tags/python/index.xml" rel="self" type="application/rss+xml"/><item><title>Mental Health Chatbot — RAG over PubMed</title><link>https://abhijith-nagarajan.com/projects/mental-health-chatbot/</link><pubDate>Sat, 17 May 2025 00:00:00 +0000</pubDate><guid>https://abhijith-nagarajan.com/projects/mental-health-chatbot/</guid><description>An end-to-end retrieval-augmented generation system that grounds a local LLM in peer-reviewed PubMed abstracts to answer questions on the neurochemistry of mental health, evaluated against the BioASQ-13b biomedical QA benchmark.</description></item><item><title>PII-Aware Sentiment &amp; Topic Pipeline</title><link>https://abhijith-nagarajan.com/projects/pii-aware-sentiment-pipeline/</link><pubDate>Sat, 17 May 2025 00:00:00 +0000</pubDate><guid>https://abhijith-nagarajan.com/projects/pii-aware-sentiment-pipeline/</guid><description>A production-style NLP pipeline that classifies Apple-product feedback by sentiment and product topic, with built-in PII redaction and sarcasm-aware sentiment correction. Served through a FastAPI REST API and a Streamlit UI on a swappable, dependency-injected inference pipeline.</description></item><item><title>SHERPA — Semi-Structured RAG (UIUC CS 546)</title><link>https://abhijith-nagarajan.com/projects/sherpa-semi-structured-rag/</link><pubDate>Thu, 19 Dec 2024 00:00:00 +0000</pubDate><guid>https://abhijith-nagarajan.com/projects/sherpa-semi-structured-rag/</guid><description>A semi-structured, non-parametric memory framework for RAG that combines knowledge graphs with a hierarchical vector store. My contributions: Query Classification (heuristics → LLM-bootstrapped labels → fine-tuned BioLinkBERT) and Entity-Relation Extraction (REBEL fine-tuned on BioRED, with FastCoref preprocessing) — landed on REBEL after a long experimental funnel.</description></item><item><title>Crop Recommendation &amp; Soil Moisture Pipeline</title><link>https://abhijith-nagarajan.com/projects/crop-recommendation-soil-moisture/</link><pubDate>Thu, 15 Feb 2024 00:00:00 +0000</pubDate><guid>https://abhijith-nagarajan.com/projects/crop-recommendation-soil-moisture/</guid><description>An end-to-end agricultural decision-support project pairing a 22-class crop classifier (Naive Bayes + Random Forest on derived agronomic features) with a soil-moisture data pipeline that computes evapotranspiration from a Penman-Monteith equation, fed by WeatherBit + OpenWeather APIs and persisted to SQLite.</description></item><item><title>Loan Defaulter Credit Risk — Imbalanced Classification Study</title><link>https://abhijith-nagarajan.com/projects/loan-defaulter-imbalanced-classification/</link><pubDate>Mon, 22 Jan 2024 00:00:00 +0000</pubDate><guid>https://abhijith-nagarajan.com/projects/loan-defaulter-imbalanced-classification/</guid><description>A systematic study of imbalanced classification techniques on the Home Credit Default Risk dataset (91/9 class split). Final pipeline achieved 0.55 PR-AUC with Logistic Regression and HistGradientBoosting, combining class weighting and threshold tuning. Compared five approaches × three classifiers; Optuna for hyperparameter search; F2 and PR-AUC as the evaluation lens.</description></item><item><title>IPL 2022 Analysis with Plotly</title><link>https://abhijith-nagarajan.com/projects/ipl-2022-plotly-analysis/</link><pubDate>Wed, 15 Jun 2022 00:00:00 +0000</pubDate><guid>https://abhijith-nagarajan.com/projects/ipl-2022-plotly-analysis/</guid><description>A storytelling EDA of the 2022 Indian Premier League season — visualizing toss-decision impact, powerplay performance per team, and batsmen / bowler effectiveness across the three phases of a T20 innings. Built entirely in Plotly (subplots, box plots, scatter quadrants) and published as a Medium article.</description></item><item><title>CompFly AI</title><link>https://abhijith-nagarajan.com/experience/compfly-ai/</link><pubDate>Mon, 01 Dec 2025 00:00:00 +0000</pubDate><guid>https://abhijith-nagarajan.com/experience/compfly-ai/</guid><description>Developed AI evaluation frameworks, red-teaming workflows, and inference systems to improve the reliability, safety, and robustness of agentic AI applications.</description></item><item><title>Bayer - Internship</title><link>https://abhijith-nagarajan.com/experience/bayer-intern/</link><pubDate>Wed, 01 May 2024 00:00:00 +0000</pubDate><guid>https://abhijith-nagarajan.com/experience/bayer-intern/</guid><description>Implemented predictive maintenance analytics and failure-analysis workflows to improve field equipment reliability across global sites.</description></item><item><title>University of Illinois Urbana-Champaign</title><link>https://abhijith-nagarajan.com/experience/uiuc-masters/</link><pubDate>Tue, 01 Aug 2023 00:00:00 +0000</pubDate><guid>https://abhijith-nagarajan.com/experience/uiuc-masters/</guid><description>LLM research on Information Retrieval focused on entity relation extraction.</description></item><item><title>Hewlett-Packard Inc.</title><link>https://abhijith-nagarajan.com/experience/hp-inc/</link><pubDate>Wed, 01 Sep 2021 00:00:00 +0000</pubDate><guid>https://abhijith-nagarajan.com/experience/hp-inc/</guid><description>Built UiPath and OCR-based automation workflows across supply chain, customer support, finance, and marketing operations.</description></item><item><title>SASTRA University</title><link>https://abhijith-nagarajan.com/experience/sastra-bachelors/</link><pubDate>Sat, 01 Jul 2017 00:00:00 +0000</pubDate><guid>https://abhijith-nagarajan.com/experience/sastra-bachelors/</guid><description>Computer Vision research on video captioning for assistive devices.</description></item></channel></rss>