Data Science & AI Project-Based Learning Hub

Build a solid Python foundation tailored to data work, from syntax to clean, reusable code.

• play_circlePython syntax, data types and control flow
• play_circleFunctions, modules and error handling
• play_circleLists, dictionaries and comprehensions
• play_circleObject-oriented programming essentials
• play_circleLab: Jupyter notebooks and a first data script

Learn the statistics that power every model and every business decision backed by data.

• play_circleDescriptive statistics and distributions
• play_circleProbability theory and Bayes' theorem
• play_circleSampling and the central limit theorem
• play_circleHypothesis testing and A/B testing
• play_circleCorrelation, covariance and regression basics

Clean, reshape and transform messy real-world datasets into analysis-ready data.

• play_circleNumPy arrays and vectorised computing
• play_circlePandas Series and DataFrames
• play_circleHandling missing values, duplicates and outliers
• play_circleMerging, grouping and pivoting data
• play_circleLab: cleaning a real-world business dataset

Uncover patterns and tell compelling stories with charts and structured exploration.

• play_circleThe EDA workflow and asking the right questions
• play_circleVisualisation with Matplotlib and Seaborn
• play_circleInteractive charts with Plotly
• play_circleFeature relationships and data storytelling
• play_circleLab: EDA report on a retail dataset

Query, join and aggregate data at scale using the language every data team speaks.

• play_circleRelational databases and data modelling
• play_circleSELECT, filtering, sorting and aggregations
• play_circleJoins, subqueries and CTEs
• play_circleWindow functions for analytics
• play_circleLab: connecting Python to SQL databases

Build predictive models for regression and classification problems end-to-end.

• play_circleThe machine learning workflow with scikit-learn
• play_circleLinear and logistic regression
• play_circleDecision trees and random forests
• play_circleGradient boosting with XGBoost and LightGBM
• play_circleLab: customer churn prediction model

Discover hidden structure in data and make your models robust and production-worthy.

• play_circleClustering with K-Means and DBSCAN
• play_circleDimensionality reduction with PCA
• play_circleFeature engineering and pipelines
• play_circleCross-validation and hyperparameter tuning
• play_circleModel evaluation metrics and explainability (SHAP)

Understand and build neural networks for images, sequences and tabular data.

• play_circleNeural network fundamentals and backpropagation
• play_circleBuilding models with PyTorch and TensorFlow
• play_circleConvolutional neural networks for computer vision
• play_circleRecurrent networks and sequence modelling
• play_circleLab: image classification with transfer learning

Process text and harness transformer-based language models for real applications.

• play_circleText preprocessing, tokenisation and embeddings
• play_circleSentiment analysis and text classification
• play_circleTransformers and the attention mechanism
• play_circleWorking with LLMs through APIs and Hugging Face
• play_circleLab: building a document Q&A assistant

Create intelligent assistants using prompt engineering, retrieval and agentic workflows.

• play_circlePrompt engineering techniques
• play_circleRetrieval-augmented generation (RAG) with vector databases
• play_circleConversational AI and chatbot design
• play_circleIntroduction to AI agents and tool use
• play_circleLab: deploying a domain-specific AI chatbot

Turn models and data into dashboards, pipelines and deployed services the business can use.

• play_circleDashboards with Power BI and Looker Studio
• play_circleBig data processing with Apache Spark
• play_circleETL pipelines and workflow orchestration
• play_circleServing models with FastAPI and Docker
• play_circleMLOps: experiment tracking and monitoring with MLflow

Deliver an industry-grade capstone and prepare to land your first data science role.

• play_circleCapstone scoping and problem framing
• play_circleEnd-to-end build: data, model and deployment
• play_circlePresenting insights to stakeholders
• play_circlePortfolio, GitHub and resume for data roles
• play_circleMock interviews and final capstone review