Frequency distribution in Machine Learning

The frequency distribution is an arrangement of data according to the number (called frequency) possessing the individual or grouped values of the variable.

In other words, a tabular form the data in which the frequencies fo the values of a variable distribution. 

1. Univariate Frequency Distribution - A frequency distribution that shows the frequency of occurrence of different values of a single variable is called a univariate frequency distribution.
2. Bivariate Frequency Distribution - A frequency distribution based on two variables is known as a variable is known as bivariate frequency distribution.
3. Discrete Frequency Distribution - A frequency distribution which is formed by distinct values of a discrete variable or a continuous variable is called a discrete frequency distribution. 
4. Grouped Frequency Distribution - A frequency distribution which is obtained by dividing the entire range of given observation on a discrete or the continuous variable into groups and distributions the frequencies over these groups is called a grouped frequency distribution. The groups are called the classes and the boundary ends are called class limits. For the class 15-20, say 15 is the lower limit and 20 upper limit. The difference between the upper and lower limits of a class or class interval is called its magnitude or width of the class interval. The number of observations falling e=within a particular class is called its frequency or class frequency.  The value of the variable which lies mid-way between the upper and lower limits is called mid-value or mid-point of that class.