Infinite values ​​and NaN (Not a Number) in statistics

Infinite values ​​and NaN (Not a Number) in statistics for the management of Big Data They are part of the first instance of big data statistics that aims to identify which are the characteristics of the data you are working withso that the processes, assignments and operations you apply are consistent with the type of information that the data can provide you.

At we recognize the importance of this type of knowledge, so if you want to learn more about it, Stay until the end of this post! Below, we explain everything about infinite values ​​and NaN (Not a Number) in statistics for Big Data management.

How does statistics work for Big Data?

In the first instance, before putting you in context with infinite values ​​and NaN (Not a Number) in statistics for the management of Big Data, we remind you that this type of statistical processes They try to understand the variables of the information and their relationship between them; In this way, they help you understand what your data population is like through estimators, percentiles, variance, mode, operations, statistical tests, assignments, etc.

Besides, Statistics in Big Data requires an open source system (open source) as is Rtherefore, this is the favorite programming language, since It was designed for this purpose and today continues to be oriented towards statistics..

Likewise, statistics is a discipline that is dedicated to analyze the data thoroughly to subsequently identify the coincidences of variables with which the information has.

Infinite values ​​and NaN (Not a Number) in statistics

Infinite values ​​and NaN (Not a Number) in statistics for the management of Big Data They are a type of data that you can find within the large volume of data with which you are working. Therefore, they are part of the first stage of identifying the information that is being used.

First of all, Infinite values ​​refer to the type of data that in basic operations results in infinite or unconventional values. which cannot be schematized because they are a floating point.

Secondly, NaN (Not a Number) are a type of result returned by basic operations that, on the one hand, they may have been poorly developed or, on the other hand, do not make mathematical sense.

Finally, infinite values ​​and NaN (Not a Number) in statistics for the management of Big Data They have Inf and -Inf, which are positive and negative for the first data type, while NaN means “Not a Number” In a second.

For example

Now, we expose you How to write this type of functions of infinite values ​​and NaN (Not a Number) in statistics for the management of Big Data through a practical example:

#x <- 10
#x <- 1/0
x <- 0/0 paste(«The value of x is»,x) is.finite(x) is.infinite(x) is.nan(x)

‘The value of x is NaN’
FALSE
FALSE
TRUE

#NaNValues
is.nan(NaN) is.nan(0/0) is.nan(Info–Info)

TRUE
TRUE
TRUE
Checking whether a number is NaN must be done with the is.nan() function

x<-NaN
x==NaN
is.nan(x)

TRUE

Learn more about Big Data management

In this post, we have explained the basics of infinite values ​​and NaN (Not a Number) in statistics. However, these are only one type of results from the great variety that can occur, So there is still a lot to learn about Big Data management!

For this reason, at we advise you to take a look at the Full Stack Big Data, Artificial Intelligence & Machine Learning Bootcamp if what you want is to continue learning and train yourself as a data scientist professional. Through 11 modules and with the help of great experts in the Big Data worldyou will be able to educate yourself in the most important systems, languages ​​and programs for managing big data. Don’t wait any longer to sign up!