Electronic-Music-Features---201802-BeatportTop100

Context
Electronic dance music (EDM) is a genre where thousands of new songs are released every week. The list of EDM subgenres considered is long, but it also evolves according to trends and musical tastes.
With this in view, we have retrieved two sets of over 2,000 songs separated by more than a year. Songs belong to the top 100 list of an EDM website taxonomy of more than 20 subgenres that changed in the period considered.
Content
Each row is an electronic music song. The dataset contains 100 song for each genre among Beatport electronic music genres, they were the top (100) songs of their genres on November 2018. Columns are audio features extracted of a two random minutes sample of the file audio. These features have been extracted using pyAudioAnalysis (https://github.com/tyiannak/pyAudioAnalysis).
Acknowledgements
Special thanks to the people who made this possible. Javier Arroyo, Laura Prez-Molina y Jaime Snchez-Hernndez.
Inspiration
These datasets are used in this publication "Automatic subgenre classication in an electronic dance music taxonomy
" where we test the effectiveness of automatic classification on these sets and delve into the results.

### 背景
电子舞曲（Electronic Dance Music, EDM）是一类每周都会发行数千首新曲的音乐风格。本次研究涉及的电子舞曲子流派数量繁多，且会随着潮流趋势与大众音乐审美不断演变。
基于此背景，我们收集了两组间隔超过一年的数据集，每组包含超2000首歌曲。这些歌曲均选自某电子舞曲网站的分类榜单前100名，该分类体系涵盖20余个子流派，且在本次统计周期内发生了更新。

### 数据内容
每一行代表一首电子音乐作品。本数据集覆盖Beatport电子音乐分类下的全部子流派，每类风格各收录2018年11月的该风格榜单前100首歌曲。数据集中的每一列均为从音频文件中随机截取2分钟片段后提取的音频特征，所有特征均通过pyAudioAnalysis（https://github.com/tyiannak/pyAudioAnalysis）工具提取得到。

### 致谢
特别感谢为本数据集完成提供支持的人员：Javier Arroyo、Laura Prez-Molina 与 Jaime Snchez-Hernndez。

### 应用场景
本数据集已被用于论文《"Automatic subgenre classification in an electronic dance music taxonomy"》，该研究针对本数据集验证了自动分类任务的有效性，并对分类结果展开了深入分析。