Skip to content

flexs2n/Forest-Fire-Prediction-

Repository files navigation

Forest-Fire-Prediction

This project is an implementation of classification using linear Regression and Neural Network Classifier.

Data Source

UCI Machine Learning Repository

Forest Fires Data Set - License: --- - Author: Paulo Cortez, Aníbal Morais, Department of Information Systems, University of Minho, Portugal. - Source Link: https://archive.ics.uci.edu/ml/datasets/Forest+Fires - Download: https://archive.ics.uci.edu/ml/machine-learning-databases/forest-fires/ - Citation: --- [Cortez and Morais, 2007] P. Cortez and A. Morais. A Data Mining Approach to Predict Forest Fires using Meteorological Data. In J. Neves, M. F. Santos and J. Machado Eds., New Trends in Artificial Intelligence, Proceedings of the 13th EPIA 2007 - Portuguese Conference on Artificial Intelligence, December, Guimarães, Portugal, pp. 512-523, 2007. APPIA, ISBN-13 978-989-95618-0-9. - Citation: Dua, D. and Graff, C. (2019). UCI Machine Learning Repository [http://archive.ics.uci.edu/ml]. Irvine, CA: University of California, School of Information and Computer Science.

Requirements

The following packages are required to run the code:

scikit-learn numpy pandas matplotlib seaborn tensorflow

You can install these packages using pip.

Usage

To run the code, open the "Forest-Fire_prediction.ipynb" notebook and execute the cells. The notebook contains two sections:

Linear Regression: This section implements logistic regression for linear classification and reports the accuracy score.

Neural Network Classifier: This section implements a neural network classifier using Keras and reports the accuracy score.

Results

The linear regression model achieved an accuracy of 33.33% on the test set, while the neural network classifier achieved an accuracy of 83.33% on the same dataset.

Conclusion

The neural network classifier outperformed logistic regression in terms of accuracy, highlighting the usefulness of deep learning for classification tasks and the neural network has higher levels of randomness.

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published