Personality Space Explorer visualizes 50k+ celebrity personalities in an interactive 3D map. Built with React, Vite, Three.js, and react-three-fiber, it lets you fly through clustered personality space, search by name, filter by MBTI and Enneagram, and inspect detailed profiles. A Python pipeline (Pandas, scikit-learn, UMAP, HDBSCAN) was used to reduce high‑dimensional traits into 3D coordinates and labels clusters via the Claude API, exported as Parquet file for fast loading.see more
Founder
Screenshots
About
The magic behind this stunning visualization lies in a robust data science pipeline. We took complex, high-dimensional personality data and, using sophisticated tools like Python, Pandas, scikit-learn, and UMAP, we successfully reduced that complexity down into meaningful three-dimensional coordinates. Furthermore, we leveraged the intelligence of the Claude API to analyze and label the resulting clusters, ensuring that the groups you see aren't just random groupings, but meaningful constellations of shared traits. This processed, optimized data is then served up via a fast Parquet file, ensuring that your exploration through this massive personality map is instantaneous, without any frustrating load times. This fusion of advanced machine learning for data reduction and modern front-end frameworks for rendering creates an unparalleled tool for researchers, enthusiasts, or anyone curious about the structure of fame and personality.