Name: Spotify Tracks Genre
Creator: Kaggle
License: https://creativecommons.org/publicdomain/zero/1.0/

About this Dataset

Spotify Tracks Genre

Audio features of tracks across diverse genres

By maharshipandya (From Huggingface) [source]

About this dataset

This dataset provides comprehensive information about Spotify tracks encompassing a diverse collection of 125 genres. It has been compiled and cleaned using Spotify's Web API and Python. Presented in CSV format, this dataset is easily accessible and amenable to analysis. The dataset comprises multiple columns, each representing distinctive audio features associated with individual tracks.

The columns include: artists (the name of the artist or artists who performed the track), album_name (the title of the album to which the track belongs), track_name (the specific name of each track), popularity (a numerical score indicating the popularity of a song on Spotify ranging from 0 to 100), duration_ms (the duration of each track measured in milliseconds), explicit (a boolean value denoting whether a song contains explicit content or not).

Furthermore, there are various audio features that provide deep insights into the musical characteristics of each track. These features include danceability, energy, key, loudness, mode, speechiness (indicating whether spoken words are present in a song), acousticness (measuring how much a song leans towards acoustic sounds rather than electric ones), instrumentalness (indicating how likely it is for a song to be instrumental rather than vocal-oriented).

Additional audio attributes encompass liveness, reflecting the presence or absence of live audience elements within tracks; valence quantifying musical positiveness conveyed by a song; tempo denoting beats per minute; and time_signature revealing details about bar structures within tracks.

The dataset enables users to discern patterns across multiple genres while also facilitating genre prediction based on perceptible audio nuances derived through machine learning models.

Aspiring audiophiles, music enthusiasts,and data scientists can effectively harness this repository for research purposes—fostering extensive exploration into genre dynamics and comprehending nuanced relationships between various musical attributes featured in these Spotify masterpieces

How to use the dataset

Introduction:

Download and Load the Dataset:
Start by downloading the dataset from Kaggle in CSV format. Once downloaded, load the dataset into your preferred programming environment or tool such as Python, R, or Excel.

Familiarize Yourself with the Columns:
Take some time to understand the meaning of each column in the dataset:

artists: The name of the artist(s) who performed the track.

album_name: The name of at album that contains a given track.

track_name: The name of a specific track.

popularity: A score indicating how popular a track is on Spotify (ranging from 0 to 100).

duration_ms: The duration of a track in milliseconds.

explicit: Indicates whether a track contains explicit content (True or False).

Explore Audio Features:
This dataset includes various audio features associated with each track. Here are some notable ones:

A. Danceability:
Danceability measures how suitable a track is for dancing, ranging from 0 to 1. Tracks with high danceability scores are more energetic and rhythmic, making them ideal for dancing.

B. Energy:
Energy represents intensity and activity within a song on a scale from 0 to 1. Tracks with high energy tend to be more fast-paced and intense.

C.Loudness:
Loudness indicates how loud or quiet an entire song is in decibels (dB). Positive values represent louder songs while negative values suggest quieter ones.

D.Key:
Key refers to different musical keys assigned integers ranging from 0-11,
with each number representing a different key. Knowing the key can provide insights into the mood and tone of a song.

E.Valence:
Valence measures the musical positiveness conveyed by a track, ranging from 0 to 1. High valence values indicate more positive or happy tracks, while lower values suggest more negative or sad ones.

F.Tempo:
Tempo is the speed or pace of a song in beats per minute (BPM). It gives an idea about how fast or slow a track is.

Data Analysis and Visualization:
Utilize various data analysis techniques and visualization tools to gain insights into the

Research Ideas

Music Recommendation System: With multiple audio features such as danceability, energy, and valence, this dataset can be used to build a music recommendation system. By analyzing the preferences of users for certain genres and characteristics of tracks, the system can suggest similar tracks or even recommend new genres that users might enjoy.

Genre Classification: The dataset provides a wide range of genres across different musical characteristics. By training a machine learning model using the audio features as predictors and the genre as the target variable, it is possible to accurately classify tracks into their respective genres. This classification can be further used for organizing large music libraries or creating playlists based on specific genres.

Studying Genre Evolution: By analyzing trends in various audio features like tempo, danceability, and energy over time, researchers can gain insights into how different music genres have evolved over decades. This analysis could help in understanding cultural shifts and changes within specific musical styles and may shed light on the influence of different factors on genre development

Acknowledgements

If you use this dataset in your research, please credit the original authors.
Data Source

License

License: CC0 1.0 Universal (CC0 1.0) - Public Domain Dedication
No Copyright - You can copy, modify, distribute and perform the work, even for commercial purposes, all without asking permission. See Other Information.

Columns

File: train.csv

Column name	Description
artists	The name(s) of the artist(s) associated with the track. (String)
album_name	The name of the album that the track belongs to. (String)
track_name	The name of the track. (String)
popularity	The popularity score of the track on Spotify, ranging from 0 to 100. (Integer)
duration_ms	The duration of the track in milliseconds. (Integer)
explicit	A boolean value indicating whether the track contains explicit content. (Boolean)
danceability	A score ranging from 0 to 1 that represents how suitable a track is for dancing based on various musical elements. (Float)
energy	A measure of the intensity and activity of a track, ranging from 0 to 1. (Float)
key	The key of the track represented by an integer value. (Integer)
loudness	The loudness of the track in decibels (dB). (Float)
mode	The tonal mode of the track, represented by an integer value (0 for minor, 1 for major). (Integer)
speechiness	A score ranging from 0 to 1 that represents the presence of spoken words in a track. (Float)
acousticness	A score ranging from 0 to 1 that represents the extent to which a track possesses an acoustic quality. (Float)
instrumentalness	A score ranging from 0 to 1 that represents the likelihood of a track being instrumental. (Float)
liveness	A score ranging from 0 to 1 that represents the presence of an audience during the recording or performance of a track. (Float)
valence	A score ranging from 0 to 1 that represents the musical positiveness conveyed by a track. (Float)
tempo	The tempo of the track in beats per minute (BPM). (Float)
time_signature	The number of beats within each bar of the track. (Integer)
track_genre	The genre of the track. (String)

Acknowledgements

If you use this dataset in your research, please credit the original authors.
If you use this dataset in your research, please credit maharshipandya (From Huggingface).

Tables

Train

@kaggle.thedevastator_spotify_tracks_genre_dataset.train

9.01 MB
114000 rows
21 columns


CREATE TABLE train (
  "unnamed_0" BIGINT,
  "track_id" VARCHAR,
  "artists" VARCHAR,
  "album_name" VARCHAR,
  "track_name" VARCHAR,
  "popularity" BIGINT,
  "duration_ms" BIGINT,
  "explicit" BOOLEAN,
  "danceability" DOUBLE,
  "energy" DOUBLE,
  "key" BIGINT,
  "loudness" DOUBLE,
  "mode" BIGINT,
  "speechiness" DOUBLE,
  "acousticness" DOUBLE,
  "instrumentalness" DOUBLE,
  "liveness" DOUBLE,
  "valence" DOUBLE,
  "tempo" DOUBLE,
  "time_signature" BIGINT,
  "track_genre" VARCHAR
);