Faster Learning Tutorials

What is Data Science? The Factors for Success.

Here we have a short session in nano and start to define data science.
  1. Data Science - Define Data Science with a 'skills triangle'.
  2. Who am I? - Learn about your instructor.
  3. Terminal - Introduce the nano text editor and summarize prerequisites.
  4. Our stack - Detail our software stack.
Paul Alan Davis, CFA, January 18, 2017
Updated: August 9, 2018
Now let's see how we can succeed at Data Science.

Outline Back Next

~/ home  / tech  / full stack  / what is data science

What is Data Science?


Video Tutorial

What is Data Science? Factors for success (4:42)

Videos can also be accessed from our Full Stack Playlist 1 on YouTube.

Code Examples and Video Script

Welcome. Today's question is: what is Data Science and what are the factors for success?

I'm Paul, and I wake up every day, thinking about how to convey scientific topics to those who may not have a scientific training.

Here I'll define Data Science and any definition really depends on who's delivering it, so I'll say something about my perspective.

Next, we'll switch to the Terminal to expand on the second part of the question on keys to success, including prerequisites.

Then we'll return for the question newcomers are quick to ask: "what is your software stack?" It will be a quick 4-minutes, so let's get going.

Step 1 - Data Science

Okay, Data Science. I often begin new topics with Wikipedia because it's collaborative, less biased and certainly ad-free, which is nice. There is a link to that and other resources in this video's Description on YouTube. The Data Science Association also has a nice succint definition and delineation between Data Science and traditional business analytics that you might find helpful.

So building on that, this is how I'd "explain it to my grandmother", as they say, using what I'll call a 'skills triangle' and in the middle, the purpose is to make decisions, data-driven decisions of course.

The Three Points of a Skills Triangle
  • Subject Matter Expertise
  • Statistics
  • Cloud

The first requirement, to me, is Subject Matter Expertise. In which field are you trying to make decisions? What are you passionate about? Healthcare, finance, advertising, technology, or basically, which industry do you know a lot about?

Second, Statistics, and here is where the procedures come in: data mining, machine learning, regression analysis, modeling, and note these aren't new. They've been used in academia for decades.

But what is new, in just the last 5 years, or so, which I label Cloud, is the mastery of open-source software and particularly cloud offerings.

Okay, so that's my view of the skills required in Data Science, and as covered in Tutorial 1, we're starting here (Beginner) and heading here (Advanced).

Step 2 - Who am I?

So you've seen my perspective, but who am I? Please see the link for more, but my training is in economics, so the social sciences. With a specialty in investments, MBA, CFA Charterholder and most of my I've managed stocks using a quantitative approach.

Step 3 - Terminal

Now let's jump to Linux, connecting it with what it takes to succeed.

First of all, why are we here? Well, the best way I can say it is, here things don't change unless we want them to.

paul@fullstack:~$ mkdir notes paul@fullstack:~$ cd notes paul@fullstack:~$ nano video0002.txt

As you know, especially on the technology side, things change often. And, depending on who you're working with, your tools, or your stack as some call it. Service providers may change the user interface of an App, or a website as often as weekly. Meaning you have to take the time to reacquaint yourself with their changes. Here at the command line, that isn't the case. So this is our safe place.

GNU nano 2.2.6 File: video0002.txt Modified Prerequisites include experience with, or a strong desire to learn: - Linux operating system - databases - programming - statistics - presentation tools - subject matter expertise It also helps if you don't mind being humbled :) ^G Get Help ^O WriteOut ^R Read File ^Y Prev Page ^K Cut Text ^C Cur Pos ^X Exit ^J Justify ^W Where Is ^V Next Page ^U UnCut Text ^T To Spell

And what I'm doing here is using a text editor called nano located on the server, and creating a directory and a text document summarizing this video.

We'll do a lot of work in nano, so I wanted you to see it early.

I'm connecting from my local machine, or client, using the SSH Protocol in a program called PuTTY because currently I'm using Microsoft, but we will also use an Apple client later in the series.

paul@fullstack:~$ exit

And if you are new to this don't worry, the point of this Full Stack exercise is to take you through the whole thing and I'll explain it all in due time.

Step 4 - Our Stack

Okay, so this is the picture of our stack which we will be adding to, and for an orientation, I suggest watching video (tutorial) 1.

  • Client : HTML, CSS, JavaScript
  • Software : Python Scientific Stack
  • Data : PostgreSQL, MySQL
  • OS : Linux (command line), Debian


So there's a definition of Data Science and a little extra. Join us for the answer to "Is programming required for Data Science? The pros and cons of spreadsheets" in tutorial 3.

Have a nice day.

What's Next?

You will learn faster by combining this text with videos. Subscribe to our YouTube Channel from here.

  • To access all tutorials, click Outline.
  • To see the fastest way to learn Data Science, click Back.
  • To compare spreadsheets with programming, click Next.

Outline Back Next

~/ home  / tech  / full stack  / what is data science

what is data science
learn to code
code the full stack
learn programming
coding classes
data science course
data science prerequisites
nano text editor
data science definition
data science association
data science skills triangle
learn data science