Dataset: Spotify 1Million Tracks

About this Dataset

Spotify 1Million Tracks

This dataset was extracted from the Spotify platform using the Python library "Spotipy", which allows users to access music data provided via APIs. The dataset collected includes about 1 Million tracks with 19 features between 2000 and 2023. Also, there is a total of 61,445 unique artists and 82 genres in the data.

This clean data has been prepared and utilized for research purposes. Its significance lies in its potential to unravel patterns and predict song popularity prior to its release. This dataset could be used to create various predictive models with machine-learning/deep-learning techniques.

Tables

Spotify Data

@kaggle.amitanshjoshi_spotify_1million_tracks.spotify_data

78.98 MB
1159764 rows
20 columns


CREATE TABLE spotify_data (
  "unnamed_0" BIGINT,
  "artist_name" VARCHAR,
  "track_name" VARCHAR,
  "track_id" VARCHAR,
  "popularity" BIGINT,
  "year" BIGINT,
  "genre" VARCHAR,
  "danceability" DOUBLE,
  "energy" DOUBLE,
  "key" BIGINT,
  "loudness" DOUBLE,
  "mode" BIGINT,
  "speechiness" DOUBLE,
  "acousticness" DOUBLE,
  "instrumentalness" DOUBLE,
  "liveness" DOUBLE,
  "valence" DOUBLE,
  "tempo" DOUBLE,
  "duration_ms" BIGINT,
  "time_signature" BIGINT
);