🔷 Data Cleaning and Insight Generation from Survey Data 🔷 Cleaned and preprocessed Kaggle’s Data Science Survey data, handling missing values, duplicates, and categorical responses. Applied label encoding and normalization to prepare the dataset for analysis. Built 12+ visualizations (pie, scatter, box, line, heatmap, etc.)

A new package designed to analyze and structure user-submitted text, specifically focusing on community feedback and moderation. The package leverages the capabilities of llmatch-messages to process a

A new package that helps extract and structure insights from discussions about AI system design challenges. Users can input text from forums, articles, or discussions, and the package will use llmatch

A new package that leverages pattern matching with language models to generate structured summaries or insights from user-submitted texts about topics like train maps or other transportation issues. I

This repository provides the official implementation for the EMNLP 2025 Findings paper: KAHAN: Knowledge-Augmented Hierarchical Analysis and Narration for Financial Data Narration

📊 Clean and analyze survey data to extract insights about data science professionals' preferences and behaviors from Kaggle's global survey.