Data Mining in Python (PYDM)

Training course goals:

Aim of the course is the application of data mining and machine learning methods with Python. The participants will get an overview of the most important procedures and learn how to set up, train, validate and finally apply models to new data using the Python package "scikit-learn".

Target Audience:

This course is aimed at project managers and qualified specialists in service or industrial companies who want to evaluate large and heterogeneous data sets with modern machine learning methods.

Course Contents:

The course gives an insight into the common machine learning methods and their possible applications for data analysis and forecasting using Python. The topics:

  • General paradigm for the application of machine learning methods (especially in "scikit-learn")
  • Data preprocessing
  • Pre-selection of relevant features (Feature Selection)
  • Explanation and modelling of different machine learning methods (decision tree methods, regressions, support vector machines, artificial neural networks)
  • Model validation, comparison and optimization
  • Model use in practice (deployment)

The training consists of an application-oriented explanation of the mentioned procedures. The participants can deepen the acquired knowledge in exercises. Generally understandable data sets from different application areas serve as examples for the exercises.

Course Requirements:

In order to benefit optimally from the training, participants should have attended the course "Introduction to Data Analysis with Python" (PYE) and have basic knowledge in statistics.

Supplementary Courses:

Methodological Courses

Software Courses:

Deep Learning in Python (PDL)
 

Duration: 2 Days             Time: 9:30 - 17:00 h            Price: EUR 1.600,- (plus VAT) per participant

 

Register

back to overview