May 25, 2017 by milindjagre
Hello, everyone, we are going to start off learning the concepts of Machine Learning. If you are following my blog posts on Hadoop and Big Data Analytics, then you will come to know I do give more importance on performing the hands-on exercises. Same is going to be the case for these tutorials.
Here, we are going to use both R and Python to demonstrate the concepts of Machine Learning. To use these programming languages, we first need to install those along with their recommended IDEs (Integrated Development Environment).
Just to be clear, I am going to use the WINDOWS 10 OPERATING SYSTEM throughout this tutorial series. So please make sure you also do that so that a lot of time will be saved while performing the troubleshooting operations.
The following infographics show this installation process.
We will first do R installation and then will go on to install Python with Spyder IDE.
Let us start with the installation of R.
- DOWNLOAD and INSTALL R
The first thing to do is to download the execution file of R.
You can download this file by clicking here. This will download R for you. The downloaded file name is going to have a pattern like R-<VERSION>-win.exe and for me, the downloaded file name is R-3.4.0-win.exe since the version is 3.4.0.
You can open this file and start the installation process for R. It is simple windows installation so I think most of us will be able to do it without much help.
- DOWNLOAD and INSTALL RSTUDIO
Once R is installed successfully, it is time to download the RStudio. RStudio is the IDE which is used by almost everyone working on R. You can download the latest version of RStudio by clicking here. For me, version 1.0.143 got downloaded as it was the latest version of RStudio on May 22nd.
Once the file is downloaded successfully, you can install it in the same traditional way as you did install R and other software on windows OS.
Once RStudio is installed correctly, you can open it by clicking on its icon from the Start Menu or Desktop, and the screen looks like this.
This confirms that both R and RStudio are installed successfully.
Now, let us start with Python Installation.
- DOWNLOAD and INSTALL ANACONDA
We do not need to download Python separately like R. In this case, we need to download Anaconda which is an open source free package manager and Python distributor. Python comes built-in with Anaconda.
You can download Anaconda Application by clicking here. The latest version as of on May 22nd is 4.3.1, therefore the downloaded file name is Anaconda3-4.3.1-Windows-x86_64.exe. Once the file is downloaded successfully, you can open it and install it like any other windows software.
Once installed successfully, you can open a program called Anaconda Navigator from the Start Menu. This is a gateway to opening the Python IDE called Spyder. The application window for Anaconda Navigator looks like as follows.
As you can see in the above picture, an application called Spyder is visible on the first line in the third column. Spyder is used as an IDE for application/code development using Python as the programming language.
You can click on the launch button, as shown in the above screenshot, to launch Spyder IDE. Once you click on launch, a new window will pop up asking to grant permission for this application to load. This window looks as follows.
You can click on Allow Access to grant access and load the Spyder IDE.
Once Spyder IDE is up and running, the application window looks like this.
If you are able to view the above application window, it means both Python and Spyder were installed successfully and now we are ready for writing some code.
If you have reached here without any problem, congratulations, you are ready to learn further about the concepts of Machine Learning, and eventually Artificial Intelligence.
You can reach out to me if you are facing any issues while doing the installations. I will be more than happy to help anyone out regarding this.
In the next tutorial, we are going to start off with the DATA PREPROCESSING part of the Machine Learning. I will break down this broad concept of Data Preprocessing in some sub-parts, which will tackle in individual posts.
Hope you guys are liking the content. Your suggestions and feedback are most welcome. Stay tuned for the further updates.