GraceRotich/Condition-of-Water-well-predictor

Predicting which water pumps are faulty to promote access to clean, potable water across Tanzania # **PREDICTING OPERATING CONDITION OF WATER WELLS IN TANZANIA** This is a machine learning project with models that predict the condition of water wells in Tanzania. ## Business Understanding According to Water.org(2024), Tanzania faces a significant water and sanitation crisis, out of its population of 65 million people, 58 million people (88% of the population) lack access to safe water. People living under these circumstances, particularly women and girls, spend a significant amount of time traveling long distances to collect water. And other challenges like underfunding of planned government projects, population growth, and extreme weather events due to climate change create challenges for those living in poverty. Now more than ever access to safe water at home is critical to families in Tanzania The project's main goal is to create a model for forecasting operational conditions of water points in Tanzania. With accurate predictions showing whether a water point will be working, broken, or under repair, the Tanzanian government will improve maintenance decision-making procedures, thereby making sure that communities have sustainable access to drinking water. ## Data Understanding The data was sourced from from Taarifa (taarifa.org) and the Tanzanian Ministry of Water(maji.go.tz). The data had 59400 indvidual data points and 41 columns ### The following are the column names * 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 - Organization that installed the well * longitude - GPS coordinate * latitude - GPS coordinate * wpt_name - Name of the waterpoint if there is one * num_private - * basin - Geographic water basin * subvillage - Geographic location * region - Geographic location * region_code - Geographic location (coded) * district_code - Geographic location (coded) * lga …