B3992 - Laboratory of Computational Statistics

Learning outcomes

This course aims to equip students with the skills necessary to use Python and Tableau for statistical computation and data visualization. By the end of the course, students will have acquired basic programming skills in Python and will be familiar with the main libraries for scientific and statistical computation. They will be able to manipulate vectors, matrices, and arrays, as well as build numerical simulations and analyze their results. Moreover, students will be able to manipulate complex data and create graphs, advanced visualizations, and interactive dashboards. The course takes an applied approach, introducing different concepts through examples and case studies.

Course contents

Module 1:

• Introduction to Python: development environments for Python; Python language structure; basic data types: int, float, string; lists and tuples; mutable and immutable objects; if-then-else, for loops and function definitions.
  
• Scientific and Statistical Computing with Numpy and Scipy: extended floating point algebra; array creation and manipulation; arrays as objects and their properties; matrix products; code vectorialization; object distributions in Scipy, their properties and methods ; implementing a Monte Carlo simulation.
• matplotlib visualization.

Module 2:

• Introduction to Tableau: Tableau's tools (Desktop, Server, Public e Prep); tableau desktop interface overview; data import and connection from different data sources; dimensions and metrics; introduction to the data model (relations).
• Creation of simple visualizations: dispersion and bar plots; adding colors, shapes and labels; geographic maps, an introduction.
• Computed fields and other tools: personalized computations and computed fields (LOD?); hierarchies; sets; using filters and actions to add interactivity.
• Dashboard creation: fundamental concepts on data visualization and visual analysis; design and implementation of dashboards for presentations with multiple visualizations; adding global filters and interactivity between visualizations; optimization of visual aspect and dashboard arrangement.
• Dasboard Optimization and analysis distributon: exporting visualizations and dashboards to different formats; interactive dashboard publication on Tableau Server or Tableau Online.

Readings/Bibliography

* Transcript of the live tutorial

* Online:

• Introduction to Python: https://docs.python.org/3/tutorial/index.html
• Numpy Quickstart Guide: https://numpy.org/devdocs/user/quickstart.html

Teaching methods

Interactive laboratory tutorial lessons.

From 19/9 to 17/10 lessos are face-to-face at Rimini Campus (GREEN LAB and RED LAB) with online streaming on Teams platform.

Assessment methods

OnlineTest on EOL (esami online) Unibo's platform

Teaching tools

* Laboratorio informatico

* Colab di Google

* Ambiente di sviluppo Spyder

Office hours

See the website of Paolo Foschi

See the website of Giulia Martielli