Overview central steps#
Following steps are typical for a machine learning project:
Look at the big picture.
Get the data.
Explore and visualize the data.
Prepare the data for the machine learning algorithm.
Select a model and train it.
Fine-tune your model.
Present your model and make it ready for later usage.
We will go through them in the following using scikit-learn as machine learning library.
Scikit-learn is a Python library providing access to classification, regression, clustering and dimensionality reduction with few lines of code. Furthermore, essential workflows for preprocessing the data or to validate the generated models are available as well. More details on scikit-learn can be found here: Link to website scikit-learn
Within this section, diverse regression models will be trained to introduce the general workflow of a machine learning project and to get familiar with scikit-learn.