Course : Data science with Cognos Analytics V11 and Python

Practical course - 3d - 21h00 - Ref. CGR
Price : 1930 € E.T.

Data science with Cognos Analytics V11 and Python




Cognos v11 enables data scientists to incorporate languages such as Python as standard. Cognos extends its scope to include all data users. This course will also be of interest to business intelligence (BI) consultants who want to get started in data science and/or in-memory.


INTER
IN-HOUSE
CUSTOM

Practical course in person or remote class
Disponible en anglais, à la demande

Ref. CGR
  3d - 21h00
1930 € E.T.




Cognos v11 enables data scientists to incorporate languages such as Python as standard. Cognos extends its scope to include all data users. This course will also be of interest to business intelligence (BI) consultants who want to get started in data science and/or in-memory.


Teaching objectives
At the end of the training, the participant will be able to:
Understanding the challenges of machine learning in the enterprise
How to use machine learning features in IBM Cognos Analytics CA 11
Handling machine learning algorithms

Intended audience
Machine learning beginners, Python beginners, Cognos beginners, intermediates or experts.

Prerequisites
Some basic knowledge of statistical mathematics.

Practical details
Teaching methods
Active pedagogy, numerous exchanges and feedback. Exercises provide an overview of Python and machine learning concepts in Cognos Analytics 11.

Course schedule

1
Configuring Jupyter Notebooks Server for Cognos Analytics

  • Introduction.
  • Architecture and concepts.
Hands-on work
Installation de la machine virtuelle. Paramétrages pour Cognos.

2
Data manipulation in Jupyter Notebooks from Cognos Analytics

  • Insert data to and from Cognos.
  • Insert data from a CSV file.
  • Inserting data from other data sources. Panda versus Numpy.
  • Data cleansing. Joins, merges, concatenation.
  • Grouping, filtering and other functions.
Hands-on work
Data manipulation exercises in Python from Cognos.

3
Machine learning: general concepts

  • Loss functions, outliers, model evaluation.
  • Linear regression.
  • Linear regression: multiple.
  • Logistic regression. K-means. Decision tree and Random forest.
  • SVM. Clustering. PCA.
Hands-on work
MCQS. Template creation exercises.

4
Visualization in IBM Cognos Analytics 11

  • Overview of data visualization in Cognos.
  • Chart types and uses.
Hands-on work
Création d’un tableau de bord Cognos depuis les données de Jupyter Notebooks. Mutualisation avec d’autres rapports Cognos.

5
Jupyter Notebooks administration from IBM Cognos Analytics

  • Planning.
  • Safety.