I am data scientist in the Department of Economic Studies at the French national statistical institute, Insee. I use Big Data and computational methods in microeconometric and data science fields.
I work with and sometimes use C++
to improve performance. I also use Spark
and Python
for big data analysis. I am a huge Git
fan. Most of my work is available on my Github page or Gitlab page page. I maintain the utilitR
project which is a collective effort involving many people from French administration to propose a high-quality documentation regarding software.
I currently teach Python for Data Scientists and Economists at ENSAE Paris Tech. You can find the course website here and the underlying Github repository . I used to teach urban economics for Master students at Sciences Po Paris. See teaching section for more details.
Msc Statistics and Data Science, 2017
ENSAE
Msc Econometrics, 2013-2018
ENS Lyon & Paris School of Economics
Msc Applied Mathematics, 2015-2017
Université Pierre et Marie Curie (Jussieu), Paris VI
Python for data scientists and economists
Academic research in the Department of Economic Studies.
I use big data sources and computational methods to improve our knowledge of economic phenomena.
Urban Economics: Master 1 in geography (since 2016)
Past courses:
foodbowl est un package Python visant à simplifier l’utilisation d’ElasticSearch pour effectuer des appariements flous
Le projet utilitR est une documentation opensource sur le logiciel R pour la manipulation de données
A docker container integrating together R and Python (anaconda environment) that can be used in gitlab CI/CD
I use microsimulation as a tool to understand capital accumulation in a life cycle perspective
I explore the evolution of segregation in the three French biggest cities within a typical day using individual mobile phone data combined with traditional data sources. I propose an innovative methodology to build within-day segregation indices and study segregation dynamics at fine spatial granularity
Projet OpenCancer
Participation to the 2017 Insee’s Hackathon
We bring together mobile phone and geocoded tax data on the three biggest French cities to shed a new light on segregation that accounts for population flows. Mobility being a key factor to reduce spatial segregation, we build a gravity model on an unprecedent scale to estimate the heterogeneity in travel costs.
Residential segregation represents the acme of segregation. Low-income people spread more than high-income people during the day. Distance plays a key role to limit population flows. Low-income people live in neighbourhoods where the spatial frictions are strongest.
Les données de mobilité issues de la téléphonie mobile permettent d’analyser la mixité sociale au-delà des seuls lieux de résidence. En …
We bring together mobile phone and geocoded tax data on the three biggest French cities to shed a new light on segregation that …
D’après ses estimations construites à partir de comptages issus de la téléphonie mobile, l’Insee estime que 1,4 million de résidents de …