Short Coding Course — South Africa
scikit-learn, NumPy, Pandas & OpenAI API
Move beyond writing scripts and start building intelligent systems. This 40-hour course takes you from the fundamentals of supervised and unsupervised learning through to deploying real AI-powered applications — using the same tools as South Africa's leading data science teams.
Types of machine learning (supervised, unsupervised, reinforcement), when to use each, and a complete end-to-end project walkthrough. Environment setup: Python, Jupyter, scikit-learn, pandas.
Arrays, DataFrames, data cleaning, handling missing values and outliers, feature encoding, scaling, and building robust scikit-learn Pipelines.
Linear regression, polynomial regression, and regularisation techniques (Ridge and Lasso). Understanding bias–variance tradeoff and choosing the right model complexity.
Logistic regression and decision boundaries, evaluation metrics (accuracy, precision, recall, F1, ROC-AUC), confusion matrices, and multi-class classification strategies.
Maximum-margin classification, the kernel trick, linear and non-linear SVMs — and when SVMs outperform simpler models.
Building and visualising decision trees, controlling overfitting with pruning, bagging, random forests and gradient boosting — with feature importance analysis.
Cross-validation, grid search and randomised search, learning curves, and strategies for avoiding data leakage — ensuring your model performs on real data, not just training data.
PCA for feature reduction and visualisation, K-Means and DBSCAN clustering — with practical use cases in customer segmentation and anomaly detection.
How perceptrons and activation functions work, building a simple neural network with Keras/TensorFlow, understanding when deep learning adds value over classical ML.
Calling the OpenAI and Anthropic APIs from Python, prompt engineering fundamentals, embeddings and retrieval basics. Build a complete AI-powered Python application as your capstone project.
Machine learning builds on solid Python skills. Make sure you're ready before enrolling.
Comfortable writing Python functions and loops, working with lists and dictionaries, and reading and writing files.
Basic algebra and an understanding of averages and percentages. No calculus or linear algebra is needed — the course applies ML with Python libraries.
A 64-bit laptop with at least 8 GB RAM (16 GB recommended) and Python installed. All libraries used are free and open-source.
Pandas & NumPy: Some experience loading and cleaning data with Pandas will let you focus on the machine learning itself.
API keys: OpenAI and Anthropic API accounts with a small amount of credit for the AI & LLM capstone module.
If you're new to Python: data types, functions, OOP, files and modules.
Recommended: Pandas, NumPy and visualisation — the data skills every ML project starts with.
Ready to take this course! Build, evaluate and deploy machine learning models and AI-powered apps.
You already write Python and want to build machine learning models and AI-powered applications.
Move from analysing data to predicting with it — regression, classification, clustering and model evaluation.
Learn how machine learning and LLM APIs work so you can add intelligent features to your products.
Build a practical AI and machine learning portfolio project to show employers.
Taught by Code College's senior development trainers — practitioners with real-world AI and data science experience, backed by over 20 years of professional developer training since 2004.
Every module includes working code. You train models, analyse results and debug predictions — building a portfolio of Jupyter notebooks you can show employers.
Join 100% live online from anywhere in South Africa, or hybrid — one or two days a week at our Midrand campus and the rest live online. Full-time face-to-face attendance can be requested, and is possible when an onsite group class is running.
Receive a Code College certificate on completion — recognised by employers across South Africa.
No. Matric-level mathematics — basic algebra and an understanding of averages — is sufficient. The course focuses on applying machine learning with Python libraries rather than deriving algorithms from scratch. No calculus or linear algebra is required.
You should be comfortable writing Python functions, loops and working with files before attending. Our Python Fundamentals short course is the recommended prerequisite if you are new to Python.
The Python Data Analysis course focuses on data cleaning, exploration and visualisation with Pandas and Matplotlib. This course builds on those skills and goes further — machine learning models with scikit-learn, model evaluation, neural network basics, and integrating real AI APIs.
Yes. The final module covers calling the OpenAI and Anthropic (Claude) APIs from Python, prompt engineering fundamentals, and using embeddings for retrieval. You build a complete AI-powered Python application as your capstone project. To go much deeper — RAG, agents, MCP servers and evals — continue with Building with LLMs.
Individuals join live online from anywhere, or hybrid — one or two days a week at our Midrand campus and the rest live online. Group courses run live online or hybrid, with fully onsite delivery at our Midrand campus optional, on request. Teams of 2–4 save 10% and teams of 5 or more save 20% per person (same class dates, paid in full upfront). Contact us for a group quote.
Yes. Code College is a B-BBEE Level 4 contributor and training spend qualifies as skills development under the B-BBEE scorecard. The course fee also counts toward your SDL (Skills Development Levy) spend.
Book the Python for AI & Machine Learning course — full-time (5 days) or part-time. Johannesburg and online.