Basics of Data Analysis using Python
From a messy DHIS2 export to a clean indicator and an honest chart, using free tools on any laptop.
What you will learn
- State three things Python does with routine health data that a spreadsheet does slowly or not at all.
- Open a Python notebook in the browser or on a laptop and run a first cell.
- Load a CSV or Excel export into a pandas DataFrame and describe its shape and columns.
- Select columns and filter rows with a condition, and sort the result.
- Convert columns to the right type and handle Ethiopian and Gregorian month labels.
- Find and resolve duplicate rows and inconsistent category spellings.
- Choose between a mean and a median for a health data distribution and justify the choice.
- Summarise a column with count, sum, mean, median and the quartiles.
- Choose between a bar, a line, a scatter and a table for a given question.
- Draw a labelled chart with matplotlib and save it at a resolution a report can use.
Syllabus
5 modules, each with a knowledge check🐍1. Python for people who work with health dataNo budget, no licence, no programming background. One laptop and a data export are enough.4 lessons · 28 min
- 1.1 The Monday morning report7 min
- 1.2 Getting Python running7 min
- 1.3 Numbers, text and lists7 min
- 1.4 Your first indicator7 min
Objectives. State three things Python does with routine health data that a spreadsheet does slowly or not at all. Open a Python notebook in the browser or on a laptop and run a first cell. Use variables, numbers, text and lists to compute a coverage indicator by hand. Read an error message and name the three questions to ask before asking for help. Describe the dataset that carries this course and what each column means.
📊2. Tables with pandasOpen the export, look at it properly, filter it and save the result. The copying by hand stops here.4 lessons · 27 min
- 2.1 The DataFrame7 min
- 2.2 Selecting and filtering7 min
- 2.3 Missing is not zero7 min
- 2.4 Saving work somebody can find6 min
Objectives. Load a CSV or Excel export into a pandas DataFrame and describe its shape and columns. Select columns and filter rows with a condition, and sort the result. Distinguish a missing value from a zero and handle each one correctly. Save a cleaned table with a file name and folder structure that survives the next month. Recognise the three export problems that break a first load and fix them.
🧹3. Cleaning and data qualityMost of the work in any analysis. Do it in code, write down every decision, and the report can be defended.4 lessons · 27 min
- 3.1 Types, months and calendars7 min
- 3.2 Duplicates and untidy categories7 min
- 3.3 The four data quality dimensions7 min
- 3.4 A cleaning script that explains itself6 min
Objectives. Convert columns to the right type and handle Ethiopian and Gregorian month labels. Find and resolve duplicate rows and inconsistent category spellings. Apply the four WHO data quality dimensions to a facility dataset. Flag outliers with a stated rule rather than by eye. Write a cleaning script that records every decision and its effect on the row count.
🧮4. Summarising and computing indicatorsCounts, proportions, medians and group summaries, then one indicator computed the way the national guide defines it.4 lessons · 27 min
- 4.1 Describing a column honestly7 min
- 4.2 Grouping by facility and by month7 min
- 4.3 Computing the indicator for every facility7 min
- 4.4 Answering a management question6 min
Objectives. Choose between a mean and a median for a health data distribution and justify the choice. Summarise a column with count, sum, mean, median and the quartiles. Group a table by facility and by period and produce a summary table. Compute a coverage indicator for every facility and month from the national definition. Compare facilities fairly using rates rather than raw counts.
📈5. Charts that tell the truthChoose the chart for the question, label it so it can stand alone, and never let the axis do the arguing.4 lessons · 28 min
- 5.1 Which chart answers which question7 min
- 5.2 Four ways a chart misleads7 min
- 5.3 Charts that make their point7 min
- 5.4 Capstone, one indicator end to end7 min
Objectives. Choose between a bar, a line, a scatter and a table for a given question. Draw a labelled chart with matplotlib and save it at a resolution a report can use. Identify the four ways a chart misleads and correct each one. Annotate a chart so that it makes its point without a speaker. Produce the capstone, one indicator from raw export to chart with its cleaning log.
How it is taught
Narrated micro lessons
Every screen has recorded narration that adds context and examples from Ethiopian hospitals. Lessons are five to ten minutes and resume where you stopped, on any device.
Decisions, not slides
Branching scenarios, matching, ordering and short written tasks with immediate feedback and the reasoning, whichever way you answer.
Blended option
Five ninety minute laboratory sessions, one per module, each ending with working code on the learner own machine.
Tools for Monday
Printable ward cards, checklists and audit forms are linked from the modules and free to adapt.
Frequently asked
How long do I have?
There is no deadline. Most learners finish in one to three weeks of short sessions. Your progress is saved to your account.
Is there a cost?
No. Enrolment, the course, the certificate and the resources are free.
What if I fail the post-test?
You can retake it. The feedback after each item tells you which module to revisit.
Is the certificate recognised for licence renewal?
The certificate states the CEU value calculated at one CEU per hour of learning in line with the national CPD Guideline, with a verification number. Recognition for licence renewal depends on accreditation by the CPD accreditor, which ERAS Africa and the EAA are pursuing.
Can my hospital run it as a workshop?
Yes. Each module has a facilitated 90 minute session plan. Contact ERAS Africa through the website to arrange a cohort.