Machine Learning- Frequency Distributions and Graphs - Organizing Data Frequency Distribution

In this video we are going to discuss organizing data and frequency distribution

So, frequency distribution is the organization of raw data in table form using classes

and frequencies. So here we are having a set of data. So at first we are trying to find out the minimum data out of them

So intentionally I have marked the minimum one here. And then we should have to find out the maximum data in this range

So intentionally I have marked this 90 because 90 is the maximum data here

Now we have decided that we shall go on representing this data in this tabular form in eight

different classes. So 35 to 41, 40 to 48 in this way we are having 84 to 91

So here we have defined eight different classes are there. So, now these are known as the lower class limit, this is upper class limit, lower class

limit, upper class limit. Also you can convert it to the lower class boundary and upper class boundary in this way, deducting

point five from here, so it will become 34.5 and adding 0.5 here, so it will become 40.5

so here deducing 0.5 from here, so it will become 41.5 and adding 0.5 here, so it will become

48.5. So, in this way, we are having the respective class limits we are having

So now this is our raw set of data and here we are having the respective class limits and also you can express this one using class boundaries as I discussed and then we shall find out that which data is falling in which class

limits so accordingly the telemark has been produced and from this telemark we

have written the respective integer values of this against this telemarks in the

frequency column so how many number of data we are having we're having here 50

number of data so obviously the frequency sum will be total is equal to 50

next one we are going for the categorical frequency distribution the categorical frequency

distribution is used for data that can be placed in a specific category such as nominal

or ordinal level data so let us consider the following distribution of blood types so here

we are having 25 army inductees so their respective blood blood types we have listed here

So, now here we are having these classes, that means distinct blood types

So A, B, O, and AB, so they are belonging here. So distinct set we have made

So, respective telemark, so how many times this A is appearing, how many times B is appearing

here, then the respective frequencies we have expressed in the form of integers and that

is a percentage frequency we are calculating. So this 25 is a total frequency because we are having 25 army inductees

So, this 5 is out of 25 is 20%. So, in this way, the respective percentage frequency also you have calculated, and obviously

the sum of the percentage frequency will be 100 here. So in this way, we can organize our data and we have explained this one with some examples

Thanks for watching this video