wachekeg/Tanzanian-Water-Wells

This repository contains a project whose goal is to predict the operating condition of a waterpoint for each record in the dataset, in order to promote access to clean, potable water across Tanzania. # Tanzania Water Well Project ## Introduction This project aims to utilize machine learning and data visualization to predict the operating condition of a waterpoint for each record in the dataset, and to identify potential issues with existing water well projects, in order to promote access to clean, potable water across Tanzania. ## Problem Statement While recognizing Tanzania's recent efforts to enhance clean water accessibility, the UN-Habitat acknowledges that a significant portion of the population still lacks safe water access. To address this, an initiative is being proposed to evaluate the distribution of wells in Tanzania and assess the functionality of water pumps in existing wells. The wells in Tanzania can be categorized as functional, non-functional, or in need of repair. ## Objectives ### Primary Objective: - Deliver accurate predictions regarding the operational status of wells. ### Specific Objectives: - Identify installers resulting in the most nonfunctional waterpoint pumps. - Determine how extraction type influences operational status of a water pump - Identify where most non-functional water pumps are located in Tanzania. - Identify the proportions of functional, non-functional and pumps in need of repair ## Data Source The data used in this analysis was provided by Taarifa Tanzania, and downloaded from *Driven Data* Website. The target Variable is **status_group**, which is a categorical class indicating whether a well is functional, non-functional or in need of repair: - functional: The waterpoint is operational, and no repairs are needed. - functional needs repair: The waterpoint is operational but needs repairs. - non-functional: The waterpoint is not operational. ## Data Understanding The following set of information was provided about the waterpoints: - amount_tsh - Total static head (amount water available to waterpoint) - date_recorded - The date the row was entered - funder - Who funded the well - gps_height - Altitude of the w …