Predicting the Condition of Tanzania Water Wells
# Predicting-Water-Well-Conditions-in-Tanzania
## 1. Business Understanding
### Problem Statement
Lack of clean and potable water is a major issue in many communities across Tanzania. To address this issue, the Tanzanian Ministry of Water has installed several water wells across the country.
However, not all of these wells are functioning as intended, which results in a lack of access to clean water for communities.
The goal of this project is to build a predictive model that can accurately predict the condition of water wells in Tanzania based on data from Taarifa and the Tanzanian Ministry of Water to predict which pumps are functional, which need some repairs, and which don't work at all.
By doing so, the aim is to improve maintenance operations and ensure that clean and potable water is available to communities across Tanzania.
### Research Question
Which classifier model can accurately predict the condition of water wells in Tanzania?
### Objectives
#### Main Objective
To predict the condition of water wells in Tanzania to ensure that clean and potable water is available to communities across Tanzania.
#### Specific Objectives
To understand the problem statement and the goal of the project
To identify the variables that can impact the functionality of water wells
To determine the target variable (functional, need repairs, or non-functional)
### Metric of Success
The model will be considered a success when both accuracy and f1 score are between 0.8 to 1.
## 2. Data Understanding
### Data Source
Data is downloaded from "Pump it Up: Data Mining the Water Table" competition hosted by DrivenData
### Data Description
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 well
installer - The organization that installed the well
longitude - GPS coordinate
latitude - GPS coordinate
wpt_name - Name of the waterpoint if ther …