Data Science vs. Data Analytics: The In-between
In between the terms Data Science and Data Analytics
We have all heard about the terminologies data science, data analytics to some extent that both are used interchangeably even though statistically one tends to be wrong if a specific term is used to apply to the other.
So what is ‘Data Science’ and what is ‘Data Analytics’ and what separates the two from the other?
Well, without much explanation, data science can be interpreted as say, a journalist looking for questions to ask concerning specific topics or issues, whereas data analytics looks into the established questions while proffering answers to them.
Data science can be seen as that broad space which data analytics is a part of but its main purpose is to look into alternative outcomes or issues asking the questions to which it is the duty of data analytics to find its answers.
Quite a lot of people have tried defining what data science is all about in specific terms agreeable to all, but nothing comes closer to a Venn diagram created by Hugh Conway in 2010 in explaining what data science truly is about.
In it there are 3 circles indicating: math and statistics, subject expertise and hacking skills, which means knowing all 3 makes one very much knowledgeable in the field of data science in itself.
When it comes to ‘data analytics’, a data analyst focuses on the descriptive statistics, data visualization and the fact they have to communicate data points in order to arrive at conclusions. Thus, a data analyst needs to have a broad understanding of statistics and a perfect grasp of databases.
In the space of data science, data analytics is basically the necessary level within it.
A data scientist on his end gathers data from multiple sources and applies machine learning, predictive analytics and sentient analysis to carve out relevant information from the established data sets.
On their end they understand data from a business point of view which helps them to raise questions or make accurate predictions that can power business decisions.
Becoming a Data Scientist
In building a career in data science, it is inherent that a student focuses on 3 departments which are analytics, programming and domain knowledge.
There is also the point in fact that the student needs to be knowledgeable in Python, SAS, R, Scala programming languages alongside a hands-on experience in SQL database coding.
The fact that during the process of data collation, a student will somehow have to collate non-numerical data shouldn’t be left out, hence the need for a student to be able to work with unstructured data as well.
Becoming a Data Analyst
Obviously, it’s no longer strange that data analytics deals with proffering answers to asked questions, so an analyst has to be able to take specific question or topic to discuss the facts around it to end users. So if anyone is looking to build a career as an analyst, they need to have knowledge in the right places.
There is the need to be knowledgeable of mathematical statistics, be able to question and dispute data presented to them, have an understanding of PIG/HIVE and of course possess an understanding of R and Python.