ReDI School Data Circle 2026
This repository is our team fork of the ReDI School Data Circle repository.
Our team project investigates the functionality of water pumps across Tanzania using exploratory data analysis, geospatial analysis, and machine learning, with a focus on generating insights that may support water-pump maintenance prioritisation.
Our active project is located here:
The project contains:
- exploratory data analysis;
- data-quality assessment;
- geospatial analysis;
- feature engineering;
- machine-learning classification;
- model interpretation;
- maintenance-oriented insights;
- an optional interactive Streamlit dashboard.
| Role | Responsibility |
|---|---|
| PM-1 | Project coordination, integration, shared technical work |
| PM-2 | Data quality and preprocessing |
| PM-3 | Exploratory and geospatial analysis |
| PM-4 | Modelling, evaluation, and deployment |
Technical responsibilities may rotate between sprints so that all team members gain experience across the complete data-science workflow.
Current phase: Sprint 1: Exploratory Data Analysis
The project follows three main stages:
- Sprint 1: Exploratory Data Analysis
- Sprint 2: Model Development
- Sprint 3: Insights and Deployment
Python | uv | pandas | NumPy | GeoPandas | scikit-learn | Matplotlib | Plotly | Streamlit
The broader repository contains the original ReDI School Data Circle project materials.
Our team's work is contained primarily within:
projects/water_pumps/team-WTM/
Please see the Team WTM project README for the full problem statement, research questions, setup instructions, project structure, and development workflow.
The Data Circle is a project-based learning programme in which students work in small teams on real-world data projects using collaborative development, data analysis, machine learning, and project-based workflows.
Original repository: