https://github.com/oguzhantekeli06/datascience_machinelearning_prediction
Data science project
https://github.com/oguzhantekeli06/datascience_machinelearning_prediction
data-visualization datascience-machinelearning numpy python3
Last synced: about 1 month ago
JSON representation
Data science project
- Host: GitHub
- URL: https://github.com/oguzhantekeli06/datascience_machinelearning_prediction
- Owner: OguzhanTekeli06
- License: mit
- Created: 2024-09-28T19:39:11.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-12-18T16:11:17.000Z (over 1 year ago)
- Last Synced: 2025-12-26T21:59:46.960Z (5 months ago)
- Topics: data-visualization, datascience-machinelearning, numpy, python3
- Language: Python
- Homepage:
- Size: 29.3 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Audio Features Mood Classification
This project demonstrates how to build a machine learning model to predict mood based on audio features. Using audio data (valence, energy, danceability, etc.), a Random Forest Classifier is trained to classify moods, and feature importance is visualized.
## Project Structure
data_processing.py: Handles loading and preprocessing the JSON data.
model.py: Contains model training and evaluation functions.
visualization.py: Visualizes feature importance.
How to Use
Load Data
from data_processing import load_data_from_json
X_train, X_test, y_train, y_test = load_data_from_json('data/audio_feature_with_mood.json')
Train Model
from model import train_model
clf = train_model(X_train, y_train)
Evaluate Model
from model import evaluate_model
evaluate_model(clf, X_test, y_test)
Visualize Feature Importance
from visualization import plot_feature_importance
plot_feature_importance(clf)
## Dependencies
Install the required Python libraries:
pip install pandas numpy scikit-learn matplotlib
**File Descriptions**
data_processing.py: Loads and preprocesses audio feature data from a JSON file.
model.py: Contains functions for training and evaluating the Random Forest Classifier.
visualization.py: Visualizes the importance of features used by the classifier.
## Future Work
Improving model accuracy by experimenting with other classifiers.
Adding more features and tuning hyperparameters.
## License
This project is licensed under the MIT License.