This project analyzes Bollywood songs on Spotify, exploring trends in genres, artists, and audio features like danceability and energy. It includes visualizations like bar plots, pie charts, radar charts, and song recommendations to uncover patterns in song popularity and audio characteristics within the Bollywood music scene.
"Bollywood Beats" explores Bollywood music trends through data analysis. Using a synthetic dataset modeled after Spotify’s music metrics, this project investigates various aspects of Bollywood songs, including popularity, genre trends, artist influence, and key audio features like danceability, energy, and tempo.
- Analyze Bollywood songs and artists based on popularity and audio features.
- Visualize trends and patterns in Bollywood music, including genre popularity and song characteristics.
- Provide insights on the relationship between audio features and song success.
- Suggest similar songs based on audio features like tempo, energy, and danceability.
- Top Artists by Average Popularity: Identifies the most popular Bollywood artists based on average song popularity.
- Genre Popularity Over Time: Tracks the growth and decline of different Bollywood genres over the years.
- Popularity vs. Danceability: Analyzes the correlation between song popularity and danceability.
- Audio Feature Correlations: Displays the relationships between key audio features like energy, danceability, and tempo.
- WordCloud: Visualizes the most common words in Bollywood song titles.
- Radar Charts: Compares audio profiles of songs or artists to understand their distinct sound.
- Song Recommendation: Recommends songs similar to a given track based on audio feature similarity.
- Genre Distribution: Shows the distribution of genres through a pie chart.
-
Clone the repository:
git clone https://github.com/yourusername/bollywood-beats.git -
Install required dependencies:
pip install pandas numpy matplotlib seaborn plotly wordcloud scikit-learn -
Upload the dataset: Use the provided script to upload and analyze your Bollywood dataset in CSV format.
- Run the provided Python script in Jupyter Notebook or Google Colab.
- Upload your CSV dataset when prompted.
- The analysis will be displayed with visualizations, including bar plots, line charts, heatmaps, and radar charts.
- Bar Plot: Displays the top 5 artists by average popularity.
- Line Chart: Shows genre popularity over time.
- Box Plot: Compares danceability in popular vs. unpopular songs.
- Heatmap: Shows correlations between audio features.
- WordCloud: Displays common words in song titles.
- Radar Chart: Compares audio features between two songs/artists.
- Pie Chart: Visualizes genre distribution.
This project is licensed under the MIT License - see the LICENSE file for details.
- The dataset used in this project is a synthetic representation of Bollywood songs, inspired by Spotify's data metrics.
- Special thanks to the open-source community for the libraries and resources used in this analysis.