Final Project for the Coursera Data Science Capstone

Milestone report: cleaning/sampling SwiftKey English data, tokenization + profanity filter, EDA of 1–3-grams with coverage, and a compact n-gram backoff model for next-word prediction.

An interactive presentation showing the distribution of total water points across Somalia’s 18 pre-war regions and total population by region. The data is based on the Population Estimation Survey (PESS) 2014 and official region boundaries.

This interactive presentation visualises the distribution of total water points and population across Somalia’s 18 pre-war regions.Using data from the Population Estimation Survey (PESS) 2014.

This project presents an interactive Leaflet map of Somalia’s regional population and water point distribution, based on the Population Estimation Survey (PESS) 2014 and administrative boundary data from UN OCHA. It visualises: • Total population and breakdowns by urban, rural, nomadic, and IDP groups • Average household size by region and Total number of water points across regions,