Justin

Command Palette

Search for a command to run...

Back to project archive
Prototype2026information-system

Lyrics Cultural Analytics Lab

Copyright-safe lyrics culture analytics and explainable ML platform

A bilingual data product built with React, FastAPI, DuckDB, and scikit-learn for analyzing music culture through metadata, BoW features, TF-IDF, topic modeling, similarity, and classification outputs without publishing full lyrics.

Live DemoGitHubDemo RecordingProject Docs

Verified Demo Recording 1

Copied by the portfolio quality pass from existing project demo media.

33 screenshots3 demo videos

Media overview

Browse the project screenshots and recorded walkthroughs.

Project links and demo readiness

live

Live Demo

Open the verified live demo when available, or use the internal run guide for manual demo preparation.

github

GitHub

Open the public repository when available, or review the source-access status captured by this case study.

video

Demo Recording

Open the demo recording when available, or use this section as the recording checklist for the project.

documentation

Project Docs

Open the project README when available, or use this case study as the documentation baseline.

Project overview

Lyrics Cultural Analytics Lab is a copyright-safe lyrics culture analytics data product. It is not a standalone notebook: it combines a FastAPI backend, DuckDB feature store, scikit-learn modeling workflow, and React TypeScript dashboard into a usable platform. The product focuses on exploring music culture without publishing complete lyrics. The demo works with metadata, BoW features, TF-IDF, topic labels, sentiment scores, similarity outputs, classification metrics, and aggregate charts, with safety checks that keep raw lyric fields out of API responses, sample data, and rendered UI. The frontend includes an overview dashboard, dataset workflow, topic explorer, sentiment timeline, similar songs, artist style, ML lab, evaluation, explainability center, and report workspace. The portfolio entry includes overview, workflow, ML lab screenshots, and a guided-tour recording, so the all-projects page can show what the project actually looks like.

My role

Independent Developer / Full-stack Data Product Developer

Problem

Lyrics analytics demos can easily become either notebook-only charts or unsafe showcases that expose full lyric text. This project turns derived song metadata, features, model outputs, and visual workflows into a runnable product while keeping a copyright-safe boundary.

Solution

I built a FastAPI backend, DuckDB feature store, scikit-learn analysis pipeline, and React TypeScript dashboard so users can inspect data, clean fields, compare models, explore topics and sentiment trends, and follow the full workflow through a guided tour.

Highlights

  • Uses metadata, BoW, TF-IDF, topics, model outputs, and aggregate charts instead of displaying complete lyrics.
  • Includes overview, dataset workflow, ML lab, evaluation, similarity, artist style, and reporting dashboards.
  • Backend covers data validation, safety checks, DuckDB ETL, classification, similarity, topic modeling, and evaluation endpoints.
  • Playwright captures guided-tour screenshots and video so the portfolio card shows real product screens.

Engineering challenges

  • Designing a demo experience that remains useful without exposing raw lyrics.
  • Connecting ingestion, model training, evaluation, and frontend exploration into one coherent workflow.

Target users

  • Portfolio reviewers and interviewers
  • Technical readers who need a quick view of purpose, stack, and maturity

Technical highlights

  • Detected technical signals: React, TypeScript, FastAPI, Python, DuckDB, scikit-learn, Playwright
  • README evidence exists and can support a fuller reviewed case study
  • A public GitHub repository is not verified yet; the portfolio marks it as pending

Architecture

This case study is generated from the portfolio catalog pipeline using README, Git metadata, package/build configuration, and media signals. The final architecture narrative still needs source-level review. Current detected technology signals include: React, TypeScript, FastAPI, Python, DuckDB, scikit-learn, Playwright.

Data flow

A public data-flow narrative is not fully reviewed yet. If the project includes data processing, AI pipelines, or backend APIs, the next pass should document input, processing, storage, and UI/output flow end to end.

Project structure

lyrics-cultural-analytics-lab/
  README.md              # project documentation, when available
  source files           # implementation reviewed by local audit
  package/build config   # detected capability signals

Setup / Run guide

This project does not expose a verified runnable web command yet. Review the README/source tree and add exact install, run, test, and build commands before interview use.
No verified build command was detected. Treat the current portfolio page as a case-study placeholder until build steps are reviewed.

Future improvements

  • Complete the production-quality README, screenshots, and demo recording
  • Add architecture diagrams, data-flow notes, and key technical decisions
  • Verify build/test status and update the portfolio release report

Interview notes

  • State the current maturity and demonstrable scope first
  • Focus on verified stack, source structure, and completed behavior
  • Do not claim unverified deployment, video, or test coverage as finished

Next steps

  • Expand derived-feature imports for more licensed datasets.
  • Deepen model comparison and cultural-trend report generation.

Related projects