Engineered Primary Data & Spatial Analytics
Powered by LIOWANYI Solutions
Spearheaded by Liseteli Mukelabai Ndiyoi — Data Analyst & GIS Specialist in Lusaka, Zambia. Architecting robust survey infrastructures (CSPro, ODK, Survey Solutions), high-frequency data pipelines (R, Python), and geospatial health risk mapping across provinces.
# Zambia Spatial Health Analytics ETL
library(sf)
library(tidyverse)
library(pyodk)
zvac_clean <- fetch_odk_data() %>%
mutate(hfc_status = validate_anthro(weight, height)) %>%
st_as_sf(coords = c("long", "lat"), crs = 4326)
# Status: 0 Outliers Detected. Ready for Mapping.
Expertise & Background
Data Systems Engineered for Precision & Impact
Bridging high-volume field operations with automated statistical workflows and interactive spatial intelligence.
Primary Data Architecture
Specializing in survey development using CSPro, World Bank Survey Solutions, KoboToolbox, and ODK. Creating bulletproof skip-patterns, rosters, logic checks, and dictionary parsers.
Spatial GIS Analytics
Geospatial risk mapping and district-level spatial modeling for nutrition, health infrastructure, and emergency vulnerability assessments across Zambia.
Automated Data Pipelines
Automating raw survey ingestion into clean `.dta` / `.rds` datasets using Python, R (tidyverse), and custom Quarto reporting dashboards deployed on Linux VPS setups.
Portfolio Showcase
Featured Projects & Systems
ZVAC Data Cleaning & Verification Engine
Built end-to-end automated data processing engine for the Zambia Vulnerability Assessment Committee (ZVAC). Standardizes multi-district survey payloads.
EmONC Survey & Quality Assurance System
Architected the Emergency Obstetric & Newborn Care survey instrument for health facilities across priority districts in Zambia with high-frequency check scripts.
Multi-District Health Risk & Spatial Mapping
High-resolution spatial analysis covering Chibombo, Chisamba, Kawambwa, Mazabuka, Monze, Mumbwa, and Chama to map health facility coverage and vulnerability.
CSPro to Stata/R Data Dictionary Conversion
Developed automated script to parse CSPro dictionary specs (`.dcf`) directly into labeled Stata `.dta` and R data frames with value labels preserved.
Quarto Analytics Dashboard Server
Configured self-hosted Linux VPS (Ubuntu) running Apache/Gunicorn to publish automated, real-time Quarto analytical reports for key stakeholders.
High-Frequency Anthropometric Quality Checks
High-frequency data quality checking system enforcing WHO growth standard z-scores, flag detection, and enumerator performance tracking during field collection.
Capabilities & Toolkit
Full-Stack Data Engineering & GIS Stack
R & Tidyverse
dplyr, ggplot2, sf, openxlsx, Quarto, haven, janitor
Python Data Stack
pyodk, pandas, geopandas, numpy, requests ETL
CSPro Logic
Data Dictionaries (.dcf), CAPI logic, Batch Editing, Export
Spatial & Mapping
QGIS, ArcGIS, Vector Analysis, Spatial Joins, Coordinate Verification
ODK / Kobo / SuSo
XLSForm creation, World Bank Survey Solutions Server, REST API Ingestion
Linux Deployment
Ubuntu Server, Apache, Gunicorn, SSL setup, Cron Automation
Get In Touch
Let's Build Reliable Data & GIS Infrastructure
Available for dataset cleaning engines, survey instrument designs, geospatial health mapping, and data system audits across Zambia and internationally.