Basic Things You Should Know About Data Science

1
Basic Things You Should Know About Data Science

• Roger Samara

2
Roger Samara

• Around 6 billion and more devices connected to
  the internet at present, as much as 2.5 million
  terabytes of data are produced each day. By 2020,
  a lot more devices are expected to get linked,
  evaluating an estimate of around 30 million
  terabytes of data each day.
• As a tech lover or an IT professional, this
  should make you curious to explore more. So, if
  youre someone who is curious to know more about
  Data Science.

3
Lets explore a few basic things about data
science with Roger Samara.

• What actually is Data Science all about?
• Hadoop's role when you talk about Data Science
• What is R in Data Science?
• What is Apache Mahout?

4
What actually is Data Science all about?

• It has become a hot topic when it comes to new
  technology and trends in the Information
  Technology world. This is common with many
  technologies which individuals start discussing
  as a nonsense without having actual knowledge of
  what is meant by the technology, what comes
  within its scope and so on. Therefore it is
  essential to discuss in a bit of detail.

5

• The confusion arises at the point when you
  consider data science as part of today's
  technical scenario. It comes with its numerous
  components. Every time when people talk about the
  constituents of data science, they actually
  talking about big data. At the same time, they
  are talking about several jobs that form part of
  Data Science - what really is a role of Data
  Scientist's what actually is the Data Curator's
  role, what particularly id the Data Librarian's
  role and so on. At present scenario when you talk
  about it as a field within itself, it mainly
  deals with large chunks of data.

6
Hadoop's role when you talk about Data Science

• It basically alludes to huge information and vast
  amounts of frameworks which are utilized to
  grapple with this large data. There are a
  significant number of structures which are
  existing, and they happen to have their very own
  pros and cons. Hadoop is the most far-reaching
  and mainstream structure. At whatever point you
  talk about data science, you talk about the
  various examination, which you have worked on
  this substantial amount of data - you truly can't
  escape Hadoop.
• Every time when you perform a statistical
  examination, there is no need to care about
  Hadoop or any such structure for big data.
  However, Data Science happens to be an alternate
  creature. Likewise, Hadoop is created in Java, so
  it will truly help on the off chance that you
  comprehend Java too.

7
What is R in Data Science?

• R is really a programming language for figures.
  Avoiding R is not a good idea since when you
  speak of different algorithms you have to apply
  over this large range of data in for you to have
  the capacity to get to the bits of knowledge of
  this information or essentially to empower
  certain machine learning algorithms over its
  highest point, you have to employ the services of
  R.

8
What is Apache Mahout?

• Apache Mahout happens to be a library utilized
  for machine learning. It has been produced by
  Apache. Presently, what are the purposes behind
  getting so much popularity? What decisively are
  the causes behind it? The genuine sauce is that
  it specifically incorporates to science. It is
  truly not just about the sheer volume of
  information. It is extremely about getting
  helpful bits of knowledge from a given set of
  data.

9

• Mahout happens to have an immediate vital
  condition with Hadoop that enables it to utilize
  Hadoop's capacity of preparing in executing its
  algorithm on big data. According to Roger Samara,
  on the off chance that you investigate enormous
  organizations including Facebook and LinkedIn,
  you will experience Mahout Implementations.

10
Roger Samara