MATLAB is an interactive working environment based on the matrix, the most natural way to express computational mathematics. Moreover, it is a programming language designed for technical computing, mathematical analysis, and system simulation. The integrated graphics make it easy to view and acquire knowledge from the data. Finally, a large library of prebuilt toolboxes allows us to immediately start with programming.

After installing, to start MATLAB, simply double-click on the icon on the desktop; or from the system prompt, type matlab. At first startup, MATLAB will show us a desk of contents with all the necessary items for its proper and smooth operation. Figure 2.1 shows the MATLAB desktop in the R2017a version:

The MATLAB desktop includes the following panels:

• Current Folder...

In data analysis, a fundamental role is assumed by the exchange of such data between the analysis environment and external devices. We start from data collection and importing in MATLAB for whatever analysis we are going to do--always. As well, we will finish our activities by exporting the results. There are several ways to import and export data in the MATLAB environment depending on the different formats in which data is available. In this section, we will cover data import.

We can import files into MATLAB both interactively and programmatically. Interactively, we can import data from a disk file or the system clipboard. From a file, do any one of these three actions:

• On the...

Many of the functions we have used to import data into MATLAB have a corresponding function that allows us to export data. At the beginning of the chapter, we learned to save our data for later use with the save command:

>> save filename.mat

The dlmread() function allows us to handle text files with a specified delimiter. We can use this function to write a matrix to an ASCII-delimited file. To test the function, we start from a matrix of random numbers:

>> MyMatrix = rand(5)
MyMatrix =
    0.7577    0.7060    0.8235    0.4387    0.4898
    0.7431    0.0318    0.6948    0.3816    0.4456
    0.3922    0.2769    0.3171    0.7655    0.6463
    0.6555    0.0462    0.9502    0.7952    0.7094
    0.1712    0.0971...

Images, videos, and audio files nowadays are an integral part of our lives. We use them widely thanks to the capabilities provided by modern devices that enable us to capture, store, and manipulate them. They often represent the input data we use in our machine learning applications, because through such algorithms, it is possible to extract a lot of information that at first glance is not so obvious. In this section, we will learn to deal with such files in the MATLAB environment.

Raster images are made up of a grid of colored pixels. In MATLAB, images can be represented as two-dimensional matrices, where each matrix element corresponds to a single pixel of the displayed image. For...

So far, for data organization, we have mostly used standard arrays that represent useful data structures for storing a large number of objects, but all of the same type, such as a matrix of numbers or characters. However, such arrays cannot be used if you want to memorize both numbers and strings in the same object. This is a problem that can be solved by so-called cell arrays, structure arrays, and more generally all those structures that the MATLAB programming environment provides us.

A cell array is a datatype that has indexed data containers called cells. Each cell can contain any type of data; cell arrays can contain, for example, text strings, combinations of text and numbers, or numeric...

In this chapter, we started to explore the MATLAB desktop and how to easily interact with it. We took a look at MATLAB Toolstrip and how it is organized into a series of tabs. Then we just used MATLAB as a calculator and learned to manipulate matrices.

Next, we discovered the importing capabilities of MATLAB for reading several input types of data resources. We also learned how to import data into MATLAB interactively and programmatically. Afterwards, we understood how to export data from the workspace and working with media files.

Finally, we introduced data organization. We learned how to work with a cell array, structure array, table, and categorical array.

In the next chapter, we will learn the different datatypes in machine learning and how to clean the data and identify missing data. In addition, we will understand how to work with outliers and derived variables...