Exploitez des données textuelles

Exploitez des données textuelles

12 h
This content is rated 5 out of 5
  • From openclassrooms.com
  • Self-paced
  • Free Access
  • Fee-based Certificate
More info
  • 3 Sequences
  • Introductive Level

Their employees are learning daily with Edflex

  • Safran
  • Air France
  • TotalEnergies
  • Generali
Learn more

Course details


Partie 1 - Traitez des données textuelles
1. Explorez des données texte
2. Nettoyez et normalisez des données texte
Activité : Effectuez un nettoyage et une analyse exploratoire de données texte
Partie 2 - Transformez des données textuelles
1. Représentez votre corpus en "bag of words"
2. Effectuez des plongements de mots (word embeddings)
3. Modélisez des sujets avec des méthodes non supervisées
Quiz : Partie 2
Partie 3 - Effectuez une classification de données textuelles
1. Opérez une première classification naïve de sentiments
2. Allez plus loin dans la classification de mots
3. Traitez le langage à l'aide de réseaux de neurones
Activité : Classifiez du texte
Certificat de réussite




Yannis Chaouche
Ingénieur Machine Learning - Professeur @ OpenClassrooms


CentraleSupélec is the result of the merger of the Ecole Centrale Paris and the Supélec. The collaboration between the two Colleges of engineering begun in 1969 with the introduction of the joint competitive entrance exam. Since 2009, the Ecole Centrale Paris and Supélec have continually strengthened their partnerships and collaborations with the aim of encompassing the whole of their activities (engineering education, research and post graduate programs) and confirmed their shared values of excellence, innovation, entrepreneurship, internationalization and leadership. Today CentraleSupélec aims to become a reference in the field of engineering and systems sciences and a leading engineering College in the area of higher education and research, ranked amongst the best institutions in the world.


OpenClassrooms (formerly Le site du Zéro or SdZ) is a website that offers courses about computer science and entrepreneurship. Online courses can be made both by site staff, professors of universities or colleges partner as by its members.

Today, courses are available in several formats: MOOC (Massive Open Online Course), web text, e-book, book and video. The company delivers certifications for certain courses, including one recognized by the state in partnership with IESA multimedia.

This content is rated 5 out of 5
(no review)
This content is rated 5 out of 5
(no review)
Complete this resource to write a review