This Data Science laboratorial course was designed independently of the data science tool to use, and consider the different tasks in the KDD process. However, given the differences on the methods used to process different kinds of data, we instantiated the process into two distinct modules:

• the first to deal with multidimensional data (tabular format) usually collected from relational databases and data warehouses;
• and the second to process uni and multi-variate time series.

Following each one of the paths you will find the way to mine the corresponding kind of data. The material was prepared using Python, along with its usual packages for applying machine learning. In the following links you are goinf to find:

• auxiliary files including the dslabs_functions.py that contains all the auxiliary functions implemented in the following pages
• and data files used in the examples.