Class Data Mining

The Data Mining course aims to provide the student with essential skills in data analysis, in a multidisciplinary perspective, as is Data Science. Through the presentation of methodologies and fundamental techniques to treat, transform, construct and analyze data, the objective of this curricular unit is to give the student the ability to translate this analysis into knowledge and value in a sustainable way for decision making.   The practical component is one of the fundamental aspects of the discipline, so the ability to translate knowledge into practical actions and analysis decisions is particularly valued. The close connection with the business world to answer business questions will be portrayed in this course.

Not applicable

1. Introduction to Data Mining Importance and applications of Data and Data Mining Project workflow: practical examples Data types: structured, semi-structured and unstructured Main challenges in Data Mining   2. Tools and Foundations for Data Mining Python: Jupyter Notebook, NumPy, Pandas and Matplotlib SAS Viya for Data Mining and Machine Learning Statistical foundations for Machine Learning   3. Data Preprocessing and Exploratory Analysis Data cleaning, transformation and preparation Missing values, imputation, duplicates and outliers Exploratory data analysis and visualization Unstructured data - Text (lemmatization, stemming)   4. Machine Learning: Supervised and Unsupervised Models Basic concepts Linear and Logistic Regression KNN Dimensionality Reduction (PCA) Clustering Model performance evaluation metrics Implementation in Python and SAS Viya

In classes, theoretical concepts are introduced and complemented with real practical examples. Students are encouraged to solve exercises and to raise any questions they may have. For each topic, a set of exercises applying the theoretical concepts is presented, with guidance provided throughout their resolution and the final solution subsequently presented. Supporting materials and exercises with suggested solutions will be made available on Moodle.   Continuous assessment, adapted according to students' progress, is considered good practice. Individual support and availability to clarify questions, whenever necessary, are essential for students and their performance.

Slides e apontamentos das aulas.   Grus, J. (2019). Dafa science from scratch: first princples with Python . O'ReiIIy Media. Provost, F., Fawcett T. (2013) Data Science for Business: What you need to know about data mining and data-analytic thinking , O'Reilly Media Inc SAS Institute Inc. Statistics You Need to Know for Machine Learning. SAS e-Learning. SAS Institute Inc. Machine Learning Using SAS Viya. SAS e-Learning.