Current App Link: Productive Employment Prediction Application Running on Amazon ECS
Results are according to input dataset, as compared to training dataset
This project is aimed at providing actionable insights to support SDG Number 8, by allowing users/stakeholders to do a Predictive Analysis of Productive Employment in Kenya based on Economic Growth. The project uses machine learning algorithms for the regression problem: Given the economic growth metrics (Contribution to GDP, Growth by GDP) according to Industry, predict the number of people in non-productive employment (working poor) and the total number in employment; per Industry. The two models are deployed using Docker and Amazon EC2 for accessibility of the application
- Build Tools
- Pre-requisites
- Installation
- Container Creation with Docker
- Push to Docker Hub
- Deploy on Amazon ECS
- Contributions
- Bug / Feature Request
- Authors
- Python 3.11.5 - The programming language used.
- SciKit Learn - The machine learning library used.
- Docker & Docker Hub
- Amazon Elastic Container Service (ECS)
- Anaconda from Anaconda Organization Installed on Local System
- Model files from earlier project: https://github.com/IsaacMwendwa/productive-employment-prediction
- Docker Desktop Installed with WSL 2 Integration (Ubuntu 20.04)
- AWS Account (AWS Management Console)
- Create a directory called "Deployment" in your system, and download/clone this repo to the folder
Fire up an Anaconda Prompt or terminal, andcd
to the directory - Create a Python virtual environment using conda. Specify the Python version == 3.6.9:
conda create -n productive_employment_prediction python=3.6.9 anaconda
- Activate conda environment
conda activate productive_employment_prediction
- Install requirements as follows:
pip install -r requirements.txt
- To execute the application, r