Skip to content

Spotify song popularity analysis based on various audio features. Analysis was done in python using pandas and matplotlib.

Notifications You must be signed in to change notification settings

juliemcbaker/Spotify-Popularity-Project

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

14 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

project-1

This project explores relationships between factors of a data set of spotify popularity ratings.

The project branches contain the following:

breckin_branch

  1. Presentation.pptx -- powerpoint with our major findings
  2. spotify_popularityBS.ipynb -- contains code related to initial data cleaning and the following regression analyses:
  • accousticness vs popularity (outputted as acousticvspop.png)
  • dancability vs popularity (outputted as dancevspop.png)
  • enegery vs popularity (outputted as energyvspop.png)
  • instrumentation vs popularity (outputted as instrumentvspop.png)
  • liveness versus popularity (outputted as livevspop.png)
  • loudness vs popularity (outputted as loudvspop.png)
  • speechiness vs popularity (outputted as speechvspop.png)
  • tempo vs popularity (outputted as tempovspop.png)
  • valence (i.e., happiness) vs popularity (outputted as valancevspop.png)
  1. output_data folder -- contains the image files mentioned previously

lydia_branch

  1. Project 1 Writeup Final.docx -- a brief write-up of our major findings
  2. spotify_popularity_LD.ipynb -- contains code related to analysis of the following:
  • correlation heatmap between acoustic factors (outputted also as CorrelationHeatMap.png)
  • popularity of explicit vs non-explicit songs (outputted as PopvsExplicit.png)
  • popularity based on genre (outputted as PopvsGenre.png)
  1. resources folder that contains the second dataset that focused on genres (genres_v2 2.csv)

julie_branch

  1. investigating_dfs.ipynb -- notebook used for initial exploration and planning for artist-track analyses
  2. artist_tracks.ipynb -- notebook with code and analyses related to the following analyses & generates the accompanying image files:
  • box plot of the number of tracks artists have (Artist_Tracks_BoxPlot.png)
  • number of tracks an artist has compared the the mean popularity of their tracks (01_Tracks_by_Mean_Pop_Post-1950.png, 02_Tracks_by_Mean_Pop_Non-Outliers.png, 03_Tracks_by_Mean_Pop_Outliers.png)
  • number of tracks an artist has compared to the maximum popularity of their tracks (04_Tracks_by_Max_Pop_Post-1950.png, 05_Tracks_by_Max_Pop_Non-Outliers.png, 06_Tracks_by_Max_Pop_Outliers.png)
  • relative release order of artists' releases vs popularity (07_Tracks_by_Max_Pop_Outliers.png, 08_Relative_Release_by_Max_Pop.png)
  • release year by popularity for full dataset (popbyrelease.png)

About

Spotify song popularity analysis based on various audio features. Analysis was done in python using pandas and matplotlib.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 100.0%