- Team members:
- Contact person: [email protected]
- [email protected]
- [email protected]
- [email protected]
The data science problem addressed in this project is the exploration and understanding of the evolution of music over time using a curated dataset from the Interdisciplinary Contest in Modeling (ICM) for Problem D in 2021. The dataset encompasses various characteristics of music, such as acousticness, energy, instrumentalness, loudness, tempo, explicitness, and frequency of musical keys, among others. The objective is to gain insights into music trends, artist characteristics, and the influence of past music on new compositions.
The Streamlit application developed for this purpose consists of four main sections: Data by Year, Data by Artist, Data by Song, and Music Influence. In the Data by Year section, informative visualizations are presented to highlight trends and changes in music characteristics over different decades, accompanied by explanations of significant events influencing these trends. The Data by Artists section provides a characteristic overview of each artist, allows comparison between artists, and ranks artists by greatest and smallest popularity. The Data by Song section allows users to explore the dataset comprehensively through three tabs, offering an overview of the dataset, ranking songs based on popularity, and comparing individual songs across various attributes. The Music Influence section delves into influencer-follower relationships among artists, employing innovative techniques such as the "pivot-melt" approach for constructing stacked distribution charts and incorporating interactive network visualizations.
Our solution effectively addresses the problem by providing a user-friendly interface that facilitates in-depth exploration of the dataset, enabling users to uncover patterns, correlations, and influential factors in the realm of music. The incorporation of diverse visualizations and interactivity enhances the user experience and contributes to a comprehensive understanding of the multifaceted aspects of music over time.
- Python environment with 3.8 or above
- Package manager such as pip or conda that allows you to download dependencies
- Clone this repo using:
git clone [email protected]:CMU-IDS-Fall-2023/final-project-musicmagicians.git - In your local environment:
- If you use conda, run
conda install --file requirements.txt; - If you use pip, run
pip install -r requirements.txt
- If you use conda, run
- To run the application:
- Run
streamlit run Spotify_Music_Data_Overview.py - If the above does not work, try
python -m streamlit run Spotify_Music_Data_Overview.py
- Run
- Intro page : Equal contributions
- Data by Year : Emily Guo [email protected]
- Data by Artist : Nivedhitha Dhanasekaran [email protected]
- Data by Songs : Mingxin Li [email protected]
- Artist Influence: Yitian Xu [email protected]
- Video: Demonstration
- Report: Project report Markdown
- Proposal: Project proposal Markdown
- Proposal: Project Proposal Google Drive
The team regularly met to discuss, plan, and develop the design for the application. After splitting the workload, each member independently developed their components. Lastly, bugs were collaboratively fixed, and documentation was collectively prepared.
- The URL at the top of this readme needs to point to your application online. It should also list the names of the team members.
- A completed proposal. Each student should submit the URL that points to this file in their GitHub repo on Canvas.
- Develop sketches/prototype of your project.
- All code for the project should be in the repo.
-
Update the Online URL above to point to your deployed project. - A detailed project report. Each student should submit the URL that points to this file in their github repo on Canvas.
- A 5 minute video demonstration. Upload the video to this github repo and link to it from your report.