Always free. For everyone.
Python to AI · Course outline

From your first line of Python to AI research.

20 modules and 60 lessons in 4 stages. Every lesson has real Python practice that runs in your browser and a short quiz. The course is free and open to everyone. Start with no assumed Python knowledge. Learn programming, data science, machine learning, and research through practical examples.

Start the first lesson

Foundations

Modules 01 to 06

MODULE 01

Your first Python program

Turn a reading, a formula, and a real question into working Python.

  1. Make Python say something
  2. Name values and keep the units
  3. Build a useful calculator
3 lessons1h
MODULE 02

Work with everyday data

Use numbers, text, lists, and records to organise useful information.

  1. Clean text and convert numbers
  2. Keep a sequence in a list
  3. Describe a record with a dictionary
3 lessons1h
MODULE 03

Make decisions and repeat work

Turn rules into conditions and process a whole dataset with loops.

  1. Turn a rule into a condition
  2. Process every value with a for loop
  3. Repeat until a target is reached
3 lessons1h
MODULE 04

Write reusable solutions

Build small functions that turn clear inputs into useful outputs.

  1. Put a calculation in a function
  2. Turn a list into an answer
  3. Combine small functions
3 lessons1h
MODULE 05

Read data and catch mistakes

Load CSV data, handle expected failures, and check important results.

  1. Read and write CSV data
  2. Handle a bad value without hiding it
  3. Check results with small tests
3 lessons1h
MODULE 06

Build code people can reuse

Organise small projects with classes, clear functions, and repeatable setup.

  1. Keep data and behaviour together
  2. Make a small project readable
  3. Make an experiment repeatable
3 lessons1h

Data science

Modules 07 to 09

MODULE 07

Think in arrays

Turn sensor readings into fast calculations with NumPy, vectors, and simple linear algebra.

  1. Read and filter sensor arrays
  2. Calculate energy across a grid
  3. Solve a simple engineering model
3 lessons1h 15m
MODULE 08

Make messy data useful

Clean tables, combine records, and answer useful questions with pandas.

  1. Clean a small transaction table
  2. Join meters to sites
  3. Ask better questions of a table
3 lessons1h 15m
MODULE 09

See patterns and uncertainty

Build honest charts, compare summaries, and show how uncertain an estimate can be.

  1. Choose a chart that answers a question
  2. Separate a pattern from a cause
  3. Build an interval with resampling
3 lessons1h 15m

Machine learning

Modules 10 to 15

MODULE 10

Build an honest ML workflow

Define a prediction task, prevent data leakage, and compare your model with a simple baseline.

  1. Split before you learn
  2. Keep preprocessing inside a pipeline
  3. Set a baseline worth beating
3 lessons1h 15m
MODULE 11

Predict a number

Fit regression models, understand loss, and compare models across validation folds.

  1. Fit a line and inspect its errors
  2. Watch a model learn from loss
  3. Compare models across folds
3 lessons1h 15m
MODULE 12

Predict a category

Train classifiers, read confusion matrices, and choose thresholds for meaningful tradeoffs.

  1. Turn a probability into a decision
  2. Read errors when positives are rare
  3. Choose a threshold on validation data
3 lessons1h 15m
MODULE 13

Learn with trees and ensembles

Model nonlinear patterns, compare forests, and tune a model without using test labels.

  1. Control a tree before it memorizes
  2. Combine trees and inspect their signals
  3. Tune, test, and write a model card
3 lessons1h 15m
MODULE 14

Find hidden patterns

Group sensor readings, compress features, and spot unusual activity without labels.

  1. Group machines with k-means
  2. Compress correlated sensors with PCA
  3. Flag unusual payments with a robust score
3 lessons1h 30m
MODULE 15

Forecast what comes next

Build time features, evaluate in date order, and compare honest forecasting baselines.

  1. Build features that respect time
  2. Validate by walking forward
  3. Beat a seasonal baseline
3 lessons1h 30m

AI & research

Modules 16 to 20

MODULE 16

Build a neural network

Follow numbers through a network, learn with gradients, and check backpropagation.

  1. Follow a forward pass
  2. Learn weights with gradient descent
  3. Backpropagate and check a gradient
3 lessons1h 30m
MODULE 17

Turn language into numbers

Represent maintenance text, compare vectors, and inspect a small attention calculation.

  1. Represent maintenance notes
  2. Compare documents with vector similarity
  3. See how attention mixes information
3 lessons1h 30m
MODULE 18

Build grounded AI workflows

Retrieve useful passages, answer with evidence, and evaluate an offline RAG prototype.

  1. Retrieve passages from a small library
  2. Answer with sources or abstain
  3. Evaluate retrieval and grounded answers
3 lessons1h 30m
MODULE 19

Make responsible model decisions

Inspect group errors, challenge explanations, and protect sensitive records.

  1. Compare errors across groups
  2. Challenge a model explanation
  3. Minimise data and validate inputs
3 lessons1h 30m
MODULE 20

Do research that others can trust

Run reproducible experiments, monitor changing data, and assemble a capstone evidence report.

  1. Make an experiment reproducible
  2. Monitor change after deployment
  3. Build a capstone evidence report
3 lessons1h 30m
ABOUT THE LEARNING LAB

Free, open and run by a nonprofit.

This page is part of Python to AI, a free course of 20 modules and 60 lessons in the engineering.fit( ) Learning Lab. The Learning Lab is built and run by engineering.fit( ), a nonprofit founded by Abdullateef Opeyemi Bakare that helps African engineering students gain research experience. You do not need an account or pay a fee to learn.

Course outline · Project lab · Visit engineering-fit.org