Summary  
This chapter explains the main data types used in feature engineering—numerical, categorical (ordinal vs. nominal), and date/time—and describes how to convert non-numerical types into numerical values by extracting date components or encoding categories.  

General domain of usage  
Machine learning data preprocessing

Each column(feature) in a training set has a datatype associated with it. Those datatypes can be grouped into **numerical**, **categorical**, and **date and(or) time**.

Most ML algorithms perform well only with **numerical data**, so categorical and datetime values need to be converted into numbers.

For date and time, features such as `'year'`, `'month'`, and similar can be extracted, depending on the task. These are already **numerical values**, so they can be used directly.


Categorical data is a little more challenging to deal with.

## Types of Categorical Data

Categorical data is classified into two types:

- **Ordinal data** is a type of categorical data in which categories follow a natural order. For example, level of education (from elementary school to Ph.D.) or rates (from very bad to very well), etc.;

- **Nominal data** is a type of categorical data that follows no natural order. For example, name, gender, country of origin, etc.

Converting ordinal and nominal data types into numerical values requires different approaches, so they must be handled separately.


There are better ways to convert dates to numerical values that are beyond the scope of this introductory course. For example, if we only use the `'month'` feature, it fails to consider that the **12th** month is actually closer to the **1st** than to the **9th**.

Study More

Machine learning is now used everywhere. Want to learn it yourself? This course is an introduction to the world of Machine learning for you to learn basic concepts, work with Scikit-learn – the most popular library for ML and build your first Machine Learning project.
This course is intended for students with a basic knowledge of Python, Pandas, and Numpy.

Learn the Machine Learning concepts and the ML project workflow.

Preprocessing is probably the most important stage of an ML project. This chapter covers the preprocessing steps needed for almost any dataset.

A pipeline is a neat way to combine all the preprocessing steps as well as a model. Pipelines make it much easier to train and use a model.

Modeling is the most fun stage of an ML project. Let's learn to build, fine-tune and evaluate the model!

Types of Data

Types of Categorical Data

Awesome!

Types of Data

Types of Categorical Data