Skip to content

kelseyfglenn/rapgeo

Folders and files

NameName
Last commit message
Last commit date

Latest commit

3f0caf4 · Sep 21, 2021

History

8 Commits
Aug 21, 2020
Aug 21, 2020
Aug 21, 2020
Aug 21, 2020
Sep 21, 2021
Aug 21, 2020
Aug 21, 2020
Aug 21, 2020
Aug 21, 2020

Repository files navigation

Objective:

  • Categorize hip-hop songs and artists by lyrical content and prosodic style.

Notebook Order:

  • data_collection -> preprocessing -> topic_modeling -> clustering
  • webapp folder contains files for flask deployment including Tableau dashboard embedding

Data Sources:

Methodology:

  • Data Collection
    • Scrape wikipedia for artist names
    • Genius API requests for top N songs by each artist
    • Genius.com scrape for lyrics to each song
  • Preprocessing
    • Clean and tokenize text
    • Generate TF-IDF matrix
    • Calculate unique word and syllable rates
  • Analysis
    • Topic Modeling
    • NMF Topic Modeling to create semantic categories
    • Combine with unique word and syllabic information and apply KMeans clustering
    • Aggregate artists’ song categorizations to characterize their style
    • Deployment
      • Recommender flask application
      • Tableau visualization

Link to Tableau Public Workbook:

https://public.tableau.com/views/Metis_Proj4_Viz/Dashboard1?:language=en&:display_count=y&publish=yes&:origin=viz_share_link

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages