Organisations and Digital Societies
A.Y. 2023/2024
Learning objectives
The course is the natural complement and extension of the Digital Technologies for Organizations course and it refers to the general area of Data Analysis for the Social Sciences, as well.
It has three general objectives:
1) Familiarize students with changing technology for data analysis and visualization, and the contextual usage of more than just one (R and Python);
2) Extend the usage of open data: data provided by public organizations and associations both Italian and international, institutes of Statistics both Italian (ISTST) and international (Eurostat, etc.), and other data in the public domain; requiring analysis and transformation operations of medium or medium-high complexity;
3) Improve data visualization practice and theory through an extended graph gallery and the study of theoretical principles and professional examples.
More specific objectives are:
1) Data analysis with Python: lists, arrays, dataframes, multiindex, and pivoting;
2) Adoption of Jupyter Notebook/Lab for documents containing narrative text, executable code, and results (data or plots);
3) Use of Github as a personal repository and versioning system;
4) Data visualization and dynamic maps for georeferenced datasets: Seaborn library and annotated choropleth maps (folium and geopandas libraries)
It has three general objectives:
1) Familiarize students with changing technology for data analysis and visualization, and the contextual usage of more than just one (R and Python);
2) Extend the usage of open data: data provided by public organizations and associations both Italian and international, institutes of Statistics both Italian (ISTST) and international (Eurostat, etc.), and other data in the public domain; requiring analysis and transformation operations of medium or medium-high complexity;
3) Improve data visualization practice and theory through an extended graph gallery and the study of theoretical principles and professional examples.
More specific objectives are:
1) Data analysis with Python: lists, arrays, dataframes, multiindex, and pivoting;
2) Adoption of Jupyter Notebook/Lab for documents containing narrative text, executable code, and results (data or plots);
3) Use of Github as a personal repository and versioning system;
4) Data visualization and dynamic maps for georeferenced datasets: Seaborn library and annotated choropleth maps (folium and geopandas libraries)
Expected learning outcomes
A student should demonstrate to have acquired a good knowledge of analysis methods and to have become familiar with open source tools for data analysis and visualization. Learning outcomes should also demonstrate that the student's preparation is not limited to a sufficient usage of technologies, but she/he has understood critical aspects of a data analysis, the appropriate way of conducting a data analysis, and she/he is able to produce well-motivated evaluations of both open data analyses and the graphical representation of results.
Lesson period: First trimester
Assessment methods: Esame
Assessment result: voto verbalizzato in trentesimi
Single course
This course can be attended as a single course.
Course syllabus and organization
Single session
Responsible
Lesson period
First trimester
Course syllabus
DATA SCIENCE FUNDAMENTALS WITH PYTHON
1. Introduction to Data Science con Python
2. Jupyter Notebook and Markdown language
3. Data Wrangling: data import and e main transformation operations, operations on date, strings, and missing values
4. Operations on groups, aggregations, functions and multicolumn operations, join between data frames and dati as dictionary format
5. Advanced exercises with national and international Open Data: socio-economics data, environmental, mobility, retail and production, energy, cultural events, etc.
DATA VISUALIZATION
6. Introduction to Data Visualization with R and Python: grammar of graphics, graphical elements, types and characteristics
7. Analysis and design of the main types of static graphics with ggplot and seaborn libraries.
8. Elements regarding interactive graphics, dashboards, and maps.
During the course, several exercises with Open Data, of increasing complexity, should be completed in order to acquire the skills necessary to analyze real case studies. For a successful preparation, it is required to also work autonomously on several exercises.
1. Introduction to Data Science con Python
2. Jupyter Notebook and Markdown language
3. Data Wrangling: data import and e main transformation operations, operations on date, strings, and missing values
4. Operations on groups, aggregations, functions and multicolumn operations, join between data frames and dati as dictionary format
5. Advanced exercises with national and international Open Data: socio-economics data, environmental, mobility, retail and production, energy, cultural events, etc.
DATA VISUALIZATION
6. Introduction to Data Visualization with R and Python: grammar of graphics, graphical elements, types and characteristics
7. Analysis and design of the main types of static graphics with ggplot and seaborn libraries.
8. Elements regarding interactive graphics, dashboards, and maps.
During the course, several exercises with Open Data, of increasing complexity, should be completed in order to acquire the skills necessary to analyze real case studies. For a successful preparation, it is required to also work autonomously on several exercises.
Prerequisites for admission
English reading and understanding: basic knowledge.
To be familiar with personal computer usage and with the internet.
Recommended to have attended to the Tecnologie Digitali per le Organizzazioni course.
To be familiar with personal computer usage and with the internet.
Recommended to have attended to the Tecnologie Digitali per le Organizzazioni course.
Teaching methods
Classes are in person and it is recommended to bring a laptop in order to follow examples and exercises discussed during classes.
Some additional exercises will be taught by the course tutor. Note that these are extra hours in addition to 40 hours of the course, they will not include new contents with respect to the official program, and therefore they are not mandatory for the exam preparation. However, they are a useful learning support for several students.
Some additional exercises will be taught by the course tutor. Note that these are extra hours in addition to 40 hours of the course, they will not include new contents with respect to the official program, and therefore they are not mandatory for the exam preparation. However, they are a useful learning support for several students.
Teaching Resources
FONDAMENTI DI DATA SCIENCE - Python, R e OpenData
Marco Cremonini, Egea Editore, Giugno 2023. ISBN/EAN: 9788823823501
https://www.egeaeditore.it/ita/prodotti/ict-e-sistemi-informativi/fondamenti-di-data-science.aspx
Of this book, we will use sections dedicated to the Python language.
DATA VISUALIZATION - Grafici, dashboard e mappe con Python, R e Open Data
Marco Cremonini, Egea Editore, 2023
(to be published, both paperback and digital)
Of this book, we will specifically use Part 1, only few elements of the others.
Additional material will be from online sources, regarding open data or technical documentation.
Marco Cremonini, Egea Editore, Giugno 2023. ISBN/EAN: 9788823823501
https://www.egeaeditore.it/ita/prodotti/ict-e-sistemi-informativi/fondamenti-di-data-science.aspx
Of this book, we will use sections dedicated to the Python language.
DATA VISUALIZATION - Grafici, dashboard e mappe con Python, R e Open Data
Marco Cremonini, Egea Editore, 2023
(to be published, both paperback and digital)
Of this book, we will specifically use Part 1, only few elements of the others.
Additional material will be from online sources, regarding open data or technical documentation.
Assessment methods and Criteria
The exam is exclusively in written form with practical exercises requiring to use a personal computer and softwares employed during the course.
No intermediate exams are provided.
The evaluation will consider to what extent computational logic has been understood, the familiarity achieved with data analysis principles, and usage of software employed during classes.
No intermediate exams are provided.
The evaluation will consider to what extent computational logic has been understood, the familiarity achieved with data analysis principles, and usage of software employed during classes.
Educational website(s)
Professor(s)