Curious about Data Science? Learn Data Types first!

We all are curious about Data Science and Machine Learning now a days. Its true that due to rapid increase in data generation, probably after 5-10 years from now every industry will be using data science to optimize their business. And it is important for all of us who are working in IT industry to keep our self upgraded with all the latest technologies and new concepts.

People who are interested in learning data science or machine learning concepts, it is important for them to understand the basic concepts like Statistics, Probability, Linear Algebra, Data Manipulation with Plots etc.

Even before brushing up all above concepts, one should learn about the types of data they may deal with when working on Data Science or ML projects.

Here is a quick guide on Types of Data:

Data Types: Qualitative & Quantitative

A. Qualitative [Categorical Data]: In lay man language we can say that Categorical Data represents the group labels. It can take fixed number of possible values. Each label describes some specific characteristics and quality of the data set.

Usually it is non-numeric in nature but sometimes it can be binary [0, 1] as well.

It can be divided into 2 types: Nominal & Ordinal

1.Nominal Data: A categorical data where no natural ordering is present, it is called Nominal Data. For Example: Genders (Male/Female).

2.Ordinal Data: A categorical data with natural ordering is called Ordinal Data. For Example: Like Scale (Strongly Disagree/ Disagree/ Neutral/ Agree/ Strongly Agree).

B. Quantitative [Numeric Data]: A data set which is derived from some calculations, measurements or observations and describes the quantity/counts, is called Quantitative Data.

It can be either Discrete or Continuous.

Discrete: Usually integers and rounded values. For Example: Age of students in a class.

Continuous: Usually decimals or fixed range numbers which can take any values within a given range. For Example: Height of students in a class.

1.Interval: A data set which is in the form of numbers or numerical values where the distance between the two points is standardized and equal. Interval data cannot be multiplied or divided, however, it can be added or subtracted.

Interval data doesn’t have a defined absolute zero point which is present in ratio data. For Example: Temperature, Credit Score (CIBIL Score).

2.Ratio: A ratio data set, has all the properties of an interval variable, and also has absolute zero point. When the variable equals 0, that means none of that variable is present. For Example: Reaction Rate, Liquid Flow Rate, Dose Amount.

0 Reaction Rate means, reaction is not happening.

I hope this article helped you!

Kindly excuse me for any kind of typos.

Thanks and Regards

Rohit Thareja