Food Security Predictive Models

In an era characterized by rapid global changes, understanding factors impacting food security and safety is paramount. These concerns encompass a wide variety of interconnected variables, from environmental factors to socio-political dynamics. Delving into this complexity requires nuanced analytical approaches that can account for these multifactorial influences.

This project seeks to employ the tool of multiple linear regression to model uncertainties related to food security or safety. Given the vastness of this domain, the approach here is intentionally open-ended, enabling exploration of a plethora of potential predictor variables. The primary aim is to distill a model that is both predictive and illustrative of the intricate relationships between predictors and outcomes.

However, this project ultimately is not only just about producing a model but also about crafting a narrative on food security and safety that is backed by rigorous analysis. Through iterative processes of model creation, evaluation, and refinement, the goal is to shine a light on the intricate relationships that underpin one of humanity's most pressing concerns.

For more information regarding the project, please read more here.

Setup & Execution

1. Clone the Repository

   git clone https://github.com/verneylmavt/regression-food_security-py.git

2. Navigate to the Project Directory

   cd regression-food_security-py

3. Execute The Jupyter Notebook

   PLEASE REFER TO FinalReport/regression_dev_test_docs.ipynb FOR FULL DOCUMENTATION (INCLUDING REPORT)

   jupyter notebook regression_dev_test.ipynb

   ---

   Heads Up: There are no infinite loops in the code, it takes ~5s to execute

Dependencies

Note: Ensure that in your working environment, you have all the required dependencies. If it is not installed, you can get it using:

pip install jupyter
pip install numpy
pip install pandas
pip install seaborn
pip install matplotlib
pip install scikit-learn

Or alternatively:

pip install -r requirements.txt

Contributors

This project was made possible thanks to the hard work and dedication of the following team members:

• Bundhoo Simriti
• Elvern Neylmav Tanny
• Koh Chee Kiat
• Haritha Shraeya Rajasekar
• Mahima Sharma
• Zhang Jianyu

Kudos to all contributors for their invaluable insights and dedication.