Research Article
Gaussian Naïve Bayes Algorithm: A Reliable Technique Involved in the Assortment of the Segregation in Cancer
| Input: dataset | | S//dataset attributes involved | | Output: class name | | Start | (1) | To train the date splitting the dataset into 70%, the remaining 30% is used for testing. | (2) | Training phase | (2.1) | | | is class in the dataset of training. | (2.2) | Probability of every single class is calculating | | = frequency ()/total | (2.3) | Calculate the mean () as well as the standard deviation () values of each of the training dataset class attributes. Note down the result. | (3) | Testing phase | (3.1) | In testing DSX is an instance. | (3.2) | By applying equation (1), the probability density function (PDF) value of X is calculated at for values of X attributes remain in S, p (). | (3.3) | By using the equation, P (X| ) = P (), for the values, resulting from step of 3.2, the conditional probability value of X is calculated at , | (3.4) | By using an equation, , here, p () represents the probability value of instance at , and then, the posterior probability of X can be calculated. | (3.5) | By selecting maximization , assign a X class label. | (4) | Return the class name | | End of the process |
|