Sharon-Chebet/Tanzania-Water-Project

### Overview Tanzania, as a developing country, struggles with providing clean water to its population of over 57,000,000. There are many water points already established in the country, but some are in need of repair while others have failed altogether. We are going to build a classifier to predict the condition of a water well, using historical data about well features, such as location, pump type, and installation year, we aim to classify wells into one of three categories: functional, functional but in need of repair, or non-functional.This classification can aid NGOs and the Tanzanian government in identifying wells that require maintenance or replacement, improving water accessibility. To achieve this, we will build a machine learning model that leverages the available features to predict the condition of the wells. By following the full data science process, from data preprocessing to model evaluation, we will iteratively refine the model to improve its accuracy. Ultimately, this project will provide actionable insights for resource allocation, ensuring that the wells in most critical need are prioritized for maintenance or replacement. ## Data Understanding #### Data Source The data for this project comes from the Taarifa waterpoints dashboard, which aggregates data from the Tanzania Ministry of Water. The Ministry of Water describes Taarifa as such "Taarifa is an open source platform for the crowd sourced reporting and triaging of infrastructure related issues. Think of it as a bug tracker for the real world which helps to engage citizens with their local government. We are currently working on an Innovation Project in Tanzania, with various partners." The Taarifa homepage can be found by following this link: taarifa.org To solve classification problem with the Tanzanian Water Wells dataset, we'll primarily work with both Training set values and Training set labels to build and train your model. 1. Training Set Values: - This dataset conta …