Last checked
Start with the Kenya National Bureau of Statistics for the census, the Economic Survey and county abstracts, the Central Bank of Kenya for rates and mobile payment totals, the World Bank for CSV downloads, and HDX for humanitarian maps and health data. Each source below was opened on 3 November 2026.
McTaba runs coding and data bootcamps in Kenya. This guide is written to be useful whether or not you ever join one.
A portfolio on the Titanic passenger list tells an employer nothing about you. A chart of county populations, or of mobile payment totals from the central bank, shows you can handle messy public data on a question Kenyans care about. This list is part of our data science career map.
We opened every link below on 3 November 2026 and list only sources that loaded. Government sites move pages often, so expect some paths to change. If a link breaks, search the site by its name.
Check each source's licence or terms before you republish its data. Cite it in your project.
| Source | What is inside | Format | Checked |
|---|---|---|---|
| Kenya National Bureau of Statistics (KNBS) | Economic Survey, statistical abstracts, county statistical abstracts, CPI and inflation, quarterly GDP, gross county product, the 2019 census, labour force and demographic health reports | Mostly PDF reports; portals for survey microdata | 3 November 2026 |
| Kenya Open Data portal | Government datasets, many with maps. The site now runs on the ArcGIS Hub platform | Depends on the dataset, often CSV or map layers | 3 November 2026 |
| Central Bank of Kenya statistics | Exchange rates, the Central Bank Rate, KESONIA, treasury bills and bonds, balance of payments, inflation, mobile payments, diaspora remittances | Web tables and PDF reports | 3 November 2026 |
| Humanitarian Data Exchange (HDX), Kenya | Humanitarian and development datasets: boundaries, population, health, food security. Its search reported 656 datasets matching "kenya" in our check | CSV, Excel, shapefile and others, by dataset | 3 November 2026 |
| World Bank Data, Kenya | World Development Indicators on people, economy, environment and institutions | CSV, XML, Excel and an API | 3 November 2026 |
| World Bank Microdata Library | Household and enterprise survey data from many countries, including Kenya | Survey files, with documentation | 3 November 2026 |
| The DHS Program | Demographic and Health Surveys: births, child health, family planning, household assets | Survey files, with documentation. Read the site for how to request access | 3 November 2026 |
| openAFRICA | A volunteer-run repository of open data from across Africa, searchable for Kenyan sets | Varies by dataset | 3 November 2026 |
Sources: KNBS, Kenya Open Data, CBK, HDX, World Bank Data, DHS, openAFRICA, checked on 3 November 2026.
Our Data Science to AI Engineering programme has you finish 24 weekly projects, so public data like this gets plenty of use.
Get weekly developer tips
Join 25,000+ developers. Practical guides, job tips, and new content — straight to your inbox.
No spam. Unsubscribe anytime.
The World Bank is the easiest start because it has a plain web API. This code pulls Kenya's total population by year. Run it, then plot it.
import json
import urllib.request
import pandas as pd
url = ("https://api.worldbank.org/v2/country/KE/"
"indicator/SP.POP.TOTL?format=json&per_page=100")
with urllib.request.urlopen(url, timeout=30) as r:
rows = json.load(r)[1]
pop = pd.DataFrame(rows)[["date", "value"]].dropna()
pop["year"] = pop["date"].astype(int)
print(pop.sort_values("year").tail(3))
The API answers with two parts: a header, then the rows, which is why the code takes the item at position 1. Swap the indicator code for another from the World Bank site to get a different series.
PDF tables need extra work. The pdfplumber method in analysing your M-Pesa statement applies to them too.
Kaggle hosts competition data and user uploads. For a mobile money practice set, see mobile money fraud detection with machine learning. To learn the platform itself, read Kaggle for beginners.
Pick one question, one source and one chart. Write what you cleaned and what you assumed. Then publish it, since employers ask about projects like this.
If you would like a cohort, mentors and a capstone to go with it, see our Data Science to AI Engineering programme, starting 11 January 2027 at KES 140,000.
KES 140,000
Data Science to AI Engineering: 5 months full time or 8 months part time, hybrid in Nairobi. Fraud, credit and M-Pesa data from Week 1, and every model deployed. Starts 11 January 2027.
See the Data Science programme