Data Science 2

Course "Data Science 1"

The course teaches the classic tools of machine learning (aka data analytics, AI). The methodological basics are explained and the tools are applied in a programming environment using examples.

• Data structures (samples, features, targets) and data visualisations
• Statistical basics: correlation, statistical correlation vs. causality
• Supervised learning: regression vs. classification, k-nearest neighbours, linear and logistic regression, linear support vector machines, (ensembles of) decision trees
• Unsupervised learning: clustering, scaling
• Cross-validation and Monte Carlo analysis: learning and test data sets, fit and prediction
• Simple time series forecasts (autoregressive models and time dummies)
• Additional methods: Data transformations (principal component analysis), dummies, feature selection, regularisation, grid search

Students acquire basic knowledge and application expertise in the classic tools of machine learning. The students

• can distinguish between statistical correlation and causality.
• are able to find correlations in data, visualise them graphically and evaluate them quantitatively.
• can model correlations in data on the basis of various algorithms.
• can distinguish between supervised and unsupervised learning and know the classical methods of the respective categories.
• understand the classical models for regression and classification and can interpret the results.
• can create and evaluate fits and forecasts based on different models.
• understand the influence of the choice of their data set and model complexity and know methods for tuning and evaluating their models.
• can use cross-validation to assess the quality and robustness of their model statements.

Students acquire the following future skills:

• Critical thinking: interpretation of models and results
• Digital Literacy: Implementing on the computer with Python
• Communication Skills: Communicating analysis methods and results
• Environmental and Sustainability Awareness: Application to energy data

Integrated course with lectures, exercises, coaching and project work.

• Written intermediate exam (30%)
• Oral exam and assessment of project work (65%)
• Compulsory project pitch (5%)

For a positive grade, a minimum of 50% of the possible points must be achieved across all parts of the examination.

None

• Guido, Sarah; Müller, Andreas C. (2016): Introduction to Machine Learning with Python: A Guide for Data Scientists. Sebastopol, CA: O’Reilly UK Ltd.
• VanderPlas, Jake (2016): Python Data Science Handbook: Essential Tools for working with Data. Sebastopol, CA: O’Reilly UK Ltd.
• Géron, Aurélien (2019): Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems. 2nd ed. O’Reilly UK Ltd.
• McKinney, Wes (2017): Python for Data Analysis: Data Wrangling with Pandas, NumPy, and IPython. 2nd edition. Sebastopol, California: O’Reilly UK Ltd.
• Provost, Foster; Fawcett, Tom (2013): Data Science for Business: What you need to know about data mining and data-analytic thinking. O’Reilly and Associates

Presence Course