Skip to content

Latest commit

 

History

History
26 lines (14 loc) · 1.76 KB

README.md

File metadata and controls

26 lines (14 loc) · 1.76 KB

Baby-names-data-visualization

Groupe G: Léo BARBERIS, Anaële BAUDANT-COJAN, Florent BRIAND, Edouard DUCLOY, Pety Ialimita RAKOTONIAINA

Master Spécialisé Intelligence Artificielle - Telecom Paris (2023-2024) Visualisation Class (IGR204) - Professor: James EAGAN

A data visualization project that aims at highlighting relevant information from a dataset of baby names in France from 1900 to 2020.

INSTRUCTIONS

In this mini-project, we will be working with a data set of baby names in France. It contains the list of all baby names registered in France, year by year, from 1900 through 2020. There are two data sets: one aggregated to the national level, and another with data by department. Your goal is to create 3 different visualizations around these data, each focussed on answering different kinds of questions about the data:

- Visualization 1:

How do baby names evolve over time? Are there names that have consistently remained popular or unpopular? Are there some that have were suddenly or briefly popular or unpopular? Are there trends in time?

- Visualization 2:

Is there a regional effect in the data? Are some names more popular in some regions? Are popular names generally popular across the whole country?

- Visualization 3:

Are there gender effects in the data? Does popularity of names given to both sexes evolve consistently? (Note: this data set treats sex as binary; this is a simplification that carries into this assignment but does not generally hold.)

The repository is composed of one folder per visualization. In each folder, you will find the preliminary sketch of the visualization and one notebook per implementation (initial and refined). You only have too run the notebooks to display the visualizations and play with it. ENJOY !!