Computergestützte Datenanalyse mit Python

What it is about

You learn to formulate data-analytic questions as computational problems and implement complete analysis workflows in Python. In the end you will be able to clean and prepare datasets, apply basic models (regression, classification, dimensionality reduction), interpret results, and communicate decision-relevant statements under uncertainty.

What you will be able to do

• Formulate data-analytic tasks as inputs/outputs, assumptions, metrics and decision context
• Implement and debug end-to-end analyses in Python
• Create analysable datasets through cleaning, joining, reshaping and validation
• Rationale for handling missing values, outliers and data quality issues
• Characterize uncertainty in data (measurement noise, variability, model error)
• Choose, estimate and interpret models (regression, classification)
• Validate models, assess generalizability and control overfitting
• Present results as an evidence-based story for technical and design stakeholders
• Learn foundations of Foundation Models

What the module consists of

• Flipped Classroom / SelbststudiumPreparation through short micro-lectures, guided Python notebooks and reading with reflection tasks
• In-Person Sessions / praktische SitzungenLive tutorials and supervised hack-sprints applying methods to real datasets
• ProjektarbeitThree-phase project work (data analysis, model development, interpretation and communication) as the central assessment

Teaching method

• Flipped, project-oriented formatenables independent work on fundamentals before the session and focused practice in presence
• Guided Python notebooks and micro-lessonsprepare the practical implementation and programming tasks
• Supervised Hack-Sprints in small groupstrain applied problem solving on real datasets and promote peer learning
• Short presentations and feedbacksupport reflection and the connection of technical approach with decision context