The choice of what machine learning algorithm to use always depends on the type of data you have. If you have a labeled dataset, then your obvious choice will be to select one of the supervised machine learning techniques. Moreover, if your labeled dataset contains real values in the target variable, then you will opt for regression algorithms. Finally, if your labeled dataset contains a categorical variable in the target variable, then you will opt for the classification algorithm. In any case, the algorithm you choose always depends on the type of dataset you have. 

In a similar fashion, if your dataset does not contain any target variables, then the obvious choice is unsupervised algorithms. In this section, we are going to look at the unified approach to machine learning.

The machine learning workflow can be divided into several stages:

• Data preprocessing
• Data preparation
• Training sets and corpus creation
• Model creation and training
• Model evaluation
• Best model selection and evaluation
• Model deployment

The entire workflow of the machine learning algorithm can be seen in the following diagram:

As depicted in the preceding diagram, the first step in any machine learning workflow is data preprocessing. We'll briefly explain each stage in the following sections.