Obinna Iheanachor

Empowering the next generation of data professionals 🚀 • AI/Data Engineer • Building @wisabiHQ

[Obinna Iheanachor @DataSenseiObi]

Do you want to become a world-class data analyst in just 6 months?

I’ve been there, and I know how overwhelming it can be to learn data analysis from scratch.

That’s why I’ve created a 6-month roadmap of free high-quality resources that will teach you everything you need to know, from statistics and Excel to Python and cloud computing.

In this thread, I’ll share with you my ultimate roadmap and how you can download it for free.

Let’s get started! 👇

[Obinna Iheanachor @DataSenseiObi]

Spoke at Leeds Data Science meetup last night - From £8,000 to £40: What I Learned Shipping AI in a UK Engineering Company.

4,700 engineering drawings. 4 weeks of manual work → 45 minutes. The model was the least interesting part.

Sharp room, great questions. Thanks @jumping_uk for the invite

[Obinna Iheanachor @DataSenseiObi]

Spoke at Leeds Data Science meetup last night - From £8,000 to £40: What I Learned Shipping AI in a UK Engineering Company.

4,700 engineering drawings. 4 weeks of manual work → 45 minutes. The model was the least interesting part.

Sharp room, great questions. Thanks @jumping_uk for the invite

[Towards Data Science @TDataScience]

Interested in the intersection of data science, electoral politics, and scenario analysis? Don't miss @DataSenseiObi's latest exploration, written just ahead of the May 7 UK elections. https://t.co/g5dPDrmTvF

[Obinna Iheanachor @DataSenseiObi]

Hey #datafam

UK local elections today. Just published in @TDataScience

Across 64 English authorities and six modelled scenarios, the strongest shock is only 13% of the calibrated uncertainty band.

Scenarios sit inside the noise.

https://t.co/LibEFMTnmV

[Towards Data Science @TDataScience]

Ahead of the May 7 elections in the UK, @DataSenseiObi continues his analysis and scenario modeling series, focusing on calibrated uncertainty, historical error, and why some models are most useful when they refuse to forecast. https://t.co/g5dPDrmTvF

[Obinna Iheanachor @DataSenseiObi]

Hey #datafam

Ahead of the UK local elections tomorrow, I just published a Tableau scenario dashboard for the 2026 cycle.

Finding: the strongest modelled shock is only 13% of the median uncertainty band. Scenarios sit inside the noise.

https://t.co/TWg77P2gFA

[Obinna Iheanachor @DataSenseiObi]

Hey #datafam

Ahead of the UK local elections tomorrow, I just published a Tableau scenario dashboard for the 2026 cycle.

Finding: the strongest modelled shock is only 13% of the median uncertainty band. Scenarios sit inside the noise.

https://t.co/TWg77P2gFA

[Towards Data Science @TDataScience]

For his latest deep dive, @DataSenseiObi presents a data-quality case study on English local elections, covering categorical normalisation, metric validation, and why raw labels should never define analytical groups. https://t.co/xN0YcbBJpb

[Obinna Iheanachor @DataSenseiObi]

I got it wrong.

A bug flipped my entire result: fragmentation didn’t rise in 66/67 councils. It rose in just 18.

What actually changed? Voter churn doubled. The party system didn’t fragment.

@TDataScience https://t.co/JDCS8eVj54

@tableau https://t.co/0qplL03M9P

[Obinna Iheanachor @DataSenseiObi]

I got it wrong.

A bug flipped my entire result: fragmentation didn’t rise in 66/67 councils. It rose in just 18.

What actually changed? Voter churn doubled. The party system didn’t fragment.

@TDataScience https://t.co/JDCS8eVj54

@tableau https://t.co/0qplL03M9P

[Towards Data Science @TDataScience]

Whether you're interested in British politics or in smart data-analysis techniques, @DataSenseiObi's data quality case study is a must-read. https://t.co/xN0YcbBJpb

[Obinna Iheanachor @DataSenseiObi]

Quick survey for UK data professionals:

How is AI actually impacting your work? (not the hype)

2 mins. Anonymous.

👉 https://t.co/NNAx0W9bV3

[Towards Data Science @TDataScience]

Follow along @DataSenseiObi's thorough project walkthrough to learn how a hybrid PyMuPDF + GPT-4 Vision pipeline replaced £8,000 in manual engineering effort, and why the latest models weren’t the answer. https://t.co/D31qMtWVNz

[Towards Data Science @TDataScience]

We're thrilled to welcome @DataSenseiObi to TDS! Click below to explore his comprehensive walkthrough on designing a streamlined, rapid document-extraction system. https://t.co/D31qMtWVNz

[Obinna Iheanachor @DataSenseiObi]

I replaced £8,000 of manual work with ~$15 in API calls.

4,700 PDFs. 45 minutes. 96% accuracy.

Published on @TDataScience 👇

https://t.co/ujAFYYgDvc

Here’s the architecture (and why GPT-5 wasn’t the answer) 🧵

[Obinna Iheanachor @DataSenseiObi]

@FNakabugo Glad you found the article insightful Faridah!

[Obinna Iheanachor @DataSenseiObi]

I replaced £8,000 of manual work with ~$15 in API calls.

4,700 PDFs. 45 minutes. 96% accuracy.

Published on @TDataScience 👇

https://t.co/ujAFYYgDvc

Here’s the architecture (and why GPT-5 wasn’t the answer) 🧵

[Faridah Nakabugo @FNakabugo]

@DataSenseiObi This article is very well explained. As someone new to the field, I was able to clearly understand the problem the approach solves. I especially appreciated the discussion around why different approaches were chosen and how they align with stakeholder needs.

[Obinna Iheanachor @DataSenseiObi]

If you’ve built extraction pipelines:

What edge case broke yours at scale?

[Obinna Iheanachor @DataSenseiObi]

What actually broke the system:

→ revision tables mistaken for current values
→ grid letters (A, B, C) read as revisions
→ PDFs rotated with incorrect metadata

None of this showed up in small tests.