Advanced Technology
Data Science
Collect, clean, and analyze data to support decisions in government, NGOs, and business.
Prerequisites
No prior experience required — open to beginners.
Certificate
Awarded by Rescue Academy on successful completion of the program's assessments and final project.
Learn Online — Live Classes
Register, receive your schedule, and join live instructor-led Data Science classes on Zoom. Assignments, instructor feedback, and a certificate on completion.
Learn In Person
Attend Data Science classes in person in Juba with hands-on labs, instructor mentorship, and a certificate on completion.
What You'll Learn
- The data science life cycle and framing decision-linked questions
- Exploratory analysis, statistics and uncertainty
- Visualisation, storytelling and privacy-protecting outputs
- Survey data, wrangling, inference and regression
- Reproducible reporting, indicators and dashboards
- Causal inference, predictive targeting, spatial and text data
- Data governance and responsible data sharing
Program Objectives
- Turn organisational questions into rigorous, decision-focused analyses
- Collect, clean and combine real-world data, including survey data
- Apply statistical, causal, predictive, spatial and text methods appropriately
- Communicate findings and uncertainty clearly to decision-makers
- Protect people's data and keep analyses reproducible and governed
Who It's For
- M&E, research and data officers in NGOs and government
- Analysts who want to move beyond spreadsheets
- Graduates preparing for data science roles
Where You'll Use It
- Monitoring and evaluation of humanitarian and development programmes
- Public health, education and agriculture analysis
- Business and market analysis
Curriculum
Instructor-led, practical training. Each level is a block of 4, 8 or 12 weeks; every module ends with a practical activity and an assessment, and every level with a project.
Module 1: The Data Science Process 10 h
See how data science turns questions into evidence for decisions, where data comes from and the tools used in this program. 3 lessons
Module 2: Exploratory Data Analysis with pandas 11 h
Summarise, group and visualise data to find patterns, problems and questions worth investigating. 3 lessons
Module 3: Statistics for Decisions 10 h
Describe data with the right summary statistics, understand distributions and sampling, and explain uncertainty in plain language. 3 lessons
Module 4: Visualisation and Data Storytelling 11 h
Choose effective charts, build them in Python and turn analysis into a clear, honest story for decision-makers. 3 lessons
Module 5: Data Privacy and Ethics in Analysis 10 h
Protect the people behind the data when analysing, publishing and sharing results. 3 lessons
Level project: Water Access Snapshot from Survey Data
Module 1: Data Collection and Survey Data 15 h
Design questionnaires and samples, collect data digitally and prepare survey data correctly, including weights. 3 lessons
Module 2: Data Wrangling with pandas and NumPy 16 h
Reshape, merge and transform data from several sources efficiently and reliably. 3 lessons
Module 3: Statistical Inference 16 h
Estimate population values with confidence intervals, test hypotheses and interpret results without common mistakes. 3 lessons
Module 4: Relationships and Regression for Analysis 13 h
Describe relationships with correlation and regression, control for other factors and recognise confounding. 3 lessons
Module 5: Reporting and Dashboards 13 h
Produce reproducible reports and monitoring dashboards that stay correct as data is updated. 3 lessons
Module 6: Intermediate Data Science Project 17 h
Deliver the education programme monitoring analysis end to end, from merged data to report, dashboard and presentation. 3 lessons
Level project: Education Programme Monitoring Analysis
Module 1: Causal Inference and Programme Evaluation 22 h
Move from association to cause with experiments and quasi-experimental designs, and understand their assumptions. 4 lessons
Module 2: Predictive Modelling in Data Science Projects 22 h
Use predictive models where they help a data science project, evaluate them for the decision at hand and communicate their outputs responsibly. 4 lessons
Module 3: Working with Larger and Spatial Data 22 h
Handle data too large for simple workflows, query it with SQL and analyse and map location data. 4 lessons
Module 4: Text Data and Open-Ended Responses 20 h
Analyse open-ended survey answers, feedback and documents with text methods, including careful use of AI tools. 4 lessons
Module 5: Data Governance and Responsible Data Science 24 h
Manage data quality, documentation, reproducibility and responsible sharing so that analyses can be trusted. 4 lessons
Module 6: Data Science Capstone 30 h
Lead the cash assistance impact and targeting analysis from questions to a decision memo, combining causal, spatial, predictive and text methods responsibly. 5 lessons
Level project: Impact and Targeting Analysis for a Cash Assistance Programme
Final practical project
Impact and Targeting Analysis for a Cash Assistance Programme
A multi-method analysis that estimates a programme's effect, maps needs, evaluates targeting, analyses beneficiary feedback and recommends changes in a decision memo.
Deliverables
- A reproducible repository with documented data and analyses
- Causal, spatial, predictive and text analyses
- A decision memo with recommendations and uncertainty
- A technical appendix and a presentation
Assessed on
- Methods suit each question and their assumptions are checked
- Findings are triangulated and clearly communicated
- Privacy and governance requirements are met throughout
- Every number can be regenerated from the raw data
Worked Examples
A selection of the visual, practical examples used in this program's lessons — each teaches a different skill.
- Workflow The data science life cycle in a water project How a committee's question becomes evidence for a decision — and a better question next time. Beginner · Module 1 · Lesson 1
- Worked calculation Why one trader changes the 'average' income Mean versus median for seven household incomes, one of them very high. Beginner · Module 3 · Lesson 1
- Troubleshooting tree Which chart should I use? Choose a chart from what you want the reader to see. Beginner · Module 4 · Lesson 1
- Step-by-step Preparing a survey for safe sharing The steps that turn a household survey into a data set and tables that can be shared without exposing anyone. Beginner · Module 5 · Lesson 2
- Worked calculation How precise is '42% of households lack safe water'? A 95% confidence interval for a survey proportion, worked step by step. Intermediate · Module 3 · Lesson 1
- Data and chart Did school feeding raise attendance? A difference-in-differences estimate Attendance before and after a feeding programme in programme and comparison districts. Advanced · Module 1 · Lesson 3
Free Course: Data Science Starter
A free introduction to data science: the project lifecycle, exploring a dataset, basic statistical reasoning, visual storytelling and handling personal data responsibly. Free, self-study, about 6 hours — no certificate. The full program above is taught live by an instructor, with practical assignments, assessments and a certificate.
- 1Free lesson 1The Data Science Lifecycle
- 2Free lesson 2Exploratory Data Analysis (EDA)
- 3Free lesson 3Statistical Inference & Data Mining
- 4Free lesson 4Data Visualization & Storytelling
- 5Free lesson 5Data Privacy & Security in Analytics
- Final checkQuick Quiz — Data Science Basics
Tools & Technologies
Primary Tools
- Python with Jupyter or Google Colab — The analysis environment for every module Practice: Reproducible notebooks and scripts
- pandas and NumPy — Loading, cleaning, reshaping and summarising data Practice: Data wrangling and exploratory analysis
- matplotlib and seaborn — Charts for exploration and communication Practice: Clear, honest visualisation
Supporting Tools
- SciPy and statsmodels — Statistical tests, confidence intervals and regression Practice: Inference and explanatory modelling
- KoboToolbox or ODK — Digital survey design and collection Practice: Better data at the source
- Git — Version control for analysis projects Practice: Reproducibility and review
Professional / Industry Tools
- scikit-learn — Predictive models used within projects at Advanced level Practice: Targeting models and evaluation
- DuckDB and GeoPandas — Large-file SQL and spatial analysis Practice: Efficient querying and mapping
- A BI tool (e.g. Power BI or Looker Studio) or Streamlit — Dashboards for monitoring Practice: Dashboard design for decision-makers
Career Opportunities
- Data/AI analyst role at a bank, telecom, or NGO
- Research or further-study pathway in AI/ML/Data Science
- Remote/freelance AI or data work
Practical Projects
- Complete a full data analysis: clean, explore, visualize, and report insights from a real dataset
- Build a simple data dashboard summarizing key findings for a non-technical audience
- Take a completed analysis and produce a one-page, non-technical summary with a single clear recommendation for a decision-maker who has two minutes to read it
Problem-Solving Focus
Problem: A real-world dataset (survey responses, sensor logs, program records) has missing, duplicate, or inconsistently formatted entries
Approach: Systematically detect and handle missing or duplicate data — through imputation, removal, or explicit flagging — rather than dropping rows blindly, and document every decision made along the way.
Problem: Two variables are correlated in the data, and someone wants to conclude that one causes the other
Approach: Distinguish correlation from causation explicitly, and design any conclusion or recommendation around what the data can actually prove — not what would make the best headline.
Problem: A non-technical decision-maker — a director, funder, or government official — needs to act on the analysis but won't read a table of statistics
Approach: Translate the findings into a clear visual story and one specific recommendation, not a dump of every chart and number the analysis produced.
Problem: Sensitive personal data (health status, income, location) is required for the analysis, but sharing it directly risks people's privacy
Approach: Anonymize or aggregate the data before analysis or sharing, applying the same privacy practices covered directly in this program's Data Privacy module.
Ready to register for Data Science?
Register — Learn Online Register — Learn In Person WhatsApp: +211926196668 Email: rescueacademy26@gmail.com