README.md

# Music Classification Dataset

<!--
/**
* Project: Music Classification Dataset
* Author: Molla Samser
* Company: RSK World
* Designer & Tester: Rima Khatun
* Website: https://rskworld.in
* Email: help@rskworld.in, support@rskworld.in
* Phone: +91 93305 39277
* Description: Music genre classification dataset with audio samples
* License: Educational Purpose Only
*/
-->

## 📖 Overview

This dataset includes audio samples from multiple music genres with genre labels. Perfect for music information retrieval, genre classification, audio feature extraction, and music analysis applications.

## 🎵 Features

- **Multiple music genres** - Classical, Jazz, Rock, Pop, Hip-Hop, Electronic, Country, Blues
- **Labeled audio samples** - Each audio file is properly labeled with its genre
- **Training and test sets** - Pre-split datasets for easy model training
- **Audio features extracted** - MFCC, Spectral Centroid, Chroma, and more
- **Ready for classification models** - Compatible with popular ML frameworks

## 📊 Dataset Structure

```
music-classification/
├── data/
│ ├── audio/
│ │ ├── classical/
│ │ ├── jazz/
│ │ ├── rock/
│ │ ├── pop/
│ │ ├── hiphop/
│ │ ├── electronic/
│ │ ├── country/
│ │ └── blues/
│ ├── train_data.csv
│ ├── test_data.csv
│ └── features.csv
├── models/
│ ├── train_model.py
│ ├── predict.py
│ └── saved_models/
├── notebooks/
│ ├── exploratory_analysis.ipynb
│ └── audio_visualization.ipynb
├── utils/
│ ├── audio_processor.py
│ └── feature_extractor.py
└── requirements.txt
```

## 🎯 Genre Categories

1. **Classical** - Orchestral, Chamber, Symphony
2. **Jazz** - Swing, Bebop, Fusion
3. **Rock** - Classic Rock, Hard Rock, Alternative
4. **Pop** - Contemporary Pop, Dance Pop
5. **Hip-Hop** - Rap, Trap, Old School
6. **Electronic** - House, Techno, Ambient
7. **Country** - Traditional, Modern Country
8. **Blues** - Delta Blues, Electric Blues

## 🚀 Getting Started

### Prerequisites

- Python 3.8 or higher
- pip package manager
- Virtual environment (recommended)

### Installation

1. Clone or download this repository
2. Navigate to the project directory
3. Install required packages:

```bash
pip install -r requirements.txt
```

### Quick Start

```python
# Load and analyze audio files
from utils.audio_processor import AudioProcessor
from utils.feature_extractor import FeatureExtractor

# Initialize processors
processor = AudioProcessor()
extractor = FeatureExtractor()

# Load audio file
audio_path = 'data/audio/rock/sample01.wav'
audio_data = processor.load_audio(audio_path)

# Extract features
features = extractor.extract_mfcc(audio_data)
print(f"MFCC Features: {features.shape}")
```

## 🔧 Technologies Used

- **Audio Formats**: WAV, MP3
- **Python Libraries**: Librosa, NumPy, Pandas, Scikit-learn
- **Processing**: Audio Feature Extraction, Signal Processing
- **ML Models**: Random Forest, SVM, Neural Networks

## 📈 Usage Examples

### 1. Train a Classification Model

```bash
python models/train_model.py --model random_forest --epochs 100
```

### 2. Make Predictions

```bash
python models/predict.py --audio sample_music.wav
```

### 3. Extract Audio Features

```bash
python utils/feature_extractor.py --input data/audio/jazz/ --output features/
```

## 📊 Dataset Statistics

- **Total Samples**: 1000+ audio files
- **Duration**: 30 seconds per sample
- **Sample Rate**: 22050 Hz
- **Format**: WAV (lossless), MP3 (compressed)
- **Split Ratio**: 80% Training, 20% Testing

## 🎓 Difficulty Level

**Intermediate** - Requires basic understanding of:
- Python programming
- Audio signal processing
- Machine learning concepts
- Library usage (Librosa, Scikit-learn)

## 📄 File Descriptions

### Data Files

- `train_data.csv` - Training dataset with file paths and labels
- `test_data.csv` - Testing dataset for model evaluation
- `features.csv` - Extracted audio features for all samples

### Scripts

- `audio_processor.py` - Audio loading and preprocessing utilities
- `feature_extractor.py` - Feature extraction functions
- `train_model.py` - Model training pipeline
- `predict.py` - Prediction and inference script

## 🎯 Applications

- Music genre classification
- Music recommendation systems
- Audio content analysis
- Music information retrieval
- Playlist generation
- Audio tagging and categorization

## 📚 Resources

- [Librosa Documentation](https://librosa.org/)
- [Audio Signal Processing Tutorial](https://www.audiocontentanalysis.org/)
- [Music Information Retrieval](https://musicinformationretrieval.com/)

## 👤 Author Information

**Name**: Molla Samser
**Company**: RSK World
**Designer & Tester**: Rima Khatun
**Website**: [https://rskworld.in](https://rskworld.in)
**Email**: help@rskworld.in, support@rskworld.in
**Phone**: +91 93305 39277

## 📝 License

This dataset is provided for **educational purposes only**. Please refer to the [disclaimer](https://rskworld.in/disclaimer.php) for more information.

## 🤝 Contributing

For questions, suggestions, or contributions, please contact us through our website or email.

## ⚠️ Disclaimer

Content used for educational purposes only. View full [disclaimer](https://rskworld.in/disclaimer.php).

---

**© 2026 RSK World - Free Programming Resources & Source Code**

*Founded by Molla Samser with Designer & Tester Rima Khatun*