Naive Bayes classification model improvement method based on attribute weighting

Abstract

The invention discloses a naive Bayes classification model improvement method based on attribute weighting, and relates to the field of data processing and classification. The method comprises the following steps of S1, preprocessing the data; S2, calculating a grouping Spearman coefficient, removing the redundant attributes, and updating the data set; S3, solving the prior probability and the class condition probability of each class; S4, calculating a weighting coefficient of each attribute of the updated training set; and S5, performing classification according to the weighted improved model, and performing statistics on a classification result. According to the method, the conditional independence assumption of the naive Bayes classification model is effectively weakened through an attribute weighting mode, the redundant attributes are removed through the Spearman coefficient, and the accuracy and efficiency of the naive Bayes model are obviously improved through the improved model.

Description

technical field [0001] The invention belongs to the field of data processing and classification, in particular to a method for improving a naive Bayesian classification model based on attribute weighting. Background technique [0002] Naive Bayesian classification algorithm is the most classic classification method. However, due to the conditional independence of the algorithm itself and the fact that all attributes have the same impact on the results, the accuracy of the algorithm is low in actual use. At present, the improvement methods of Naive Bayesian algorithm mainly include: improving based on the algorithm itself, such as Bayesian network classification algorithm, double Bayesian classification algorithm, lazy Bayesian network classification algorithm, etc. These methods make Bayesian The accuracy rate and application scope of the classification algorithm have been improved; combined with other methods to improve the Naive Bayesian classification algorithm, there ar...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a method for improving the Naive Bayesian classification model based on attribute weighting, which effectively weakens the conditional independence assumption of the Naive Bayesian classification model through attribute weighting, and eliminates the Redundant attributes, the improved model significantly improves the accuracy and efficiency of the Naive Bayesian model, and solves the problem that the existing Naive Bayesian classification attributes are not always independent of each other, and the classification accuracy and efficiency are low

Images