aggie2411/Pump-it-up-Tanzania-Water-Wells

### Set up Instructions To run these notebooks independently, I have provided the environment.yml to clone the new-env environment which contains all dependencies. If you want to create all the models that appear in the Submission notebook, notebooks 1-7 would be need to be run first, the models would automatically be stored in the models folder. # Tanzania Water Pump Classification Project There are over 56,000 water pumps in Tanzania and the challenge is to create a model that can accurately classify them into the one of the following: - Functional - Non Functional - Functional needs repair Why? - Save on money, time and labor. - Ensure potable water is being provided to as many communities as possible It would be much better if the Tanzanian Government was able to focus its time and resources to deliver potable water across all communities in a more efficient manner. Being able to accurately identify pumps in need of repair or broken pumps would improve efficiency in terms of site visits, labor costs, materials and also be a way of informing communities of where they can find their nearest working pump ## Data The data was downloaded directly from the Driven Data A summary of the features was provided: - 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 - Geographic location - ward - Geographic location - population - Population around the well - public_meeting - True/False - recorded_by - Group entering this row of data - scheme_management - Who operates …