Apriori算法在卫生标准问卷调查数据挖掘中的应用及R语言实现

Application of Apriori Algorithm in Data Mining of Health Standard Questionnaire and its Implementation in R Programming Language

目的归纳Apriori算法在卫生健康标准问卷调查数据中的应用方法、注意事项及R语言实现方法。方法2019年5—9月,利用arules包(版本号:1.6-4)的Apriori函数进行关联规则计算,设定最小支持度和最小置信度分别为0.3和0.8。以提升度排名前10名的规则作为有效强关联规则。结果问卷调查数据整理成以调查对象为行、以标准名称为列的二维表格,利用library()命令调用readxl包导入数据,利用arules、arulesViz和grid包挖掘关联规则,并实现数据结果可视化。还可以利用shinythemes包进行交互式关联规则挖掘。结论Apriori算法挖掘的关联信息可以为完善标准管理提供技术线索,但是也存在算法效率偏低,不适用于数据量较大的问卷调查数据。

Objective To summarize the application,precautions and R programming language implementation of Apriori algorithm in health standard questionnaire survey data.Methods From May to September 2019,the Apriori function of arules package(version1.6-4)was used to calculate association rules,and the minimum support and minimum confidence were set as 0.3 and 0.8,respectively.The rules with top 10 lift degree were taken as effective strong association rules.Results The questionnaire data was sorted into a two-dimensional table with the survey object as the row and the health standard as the column.The library()command was used to call the readxl package to import the data.The arules,arulesViz and grid packages were used to mine association rules and visualize of data results.The shinythemes package could also be used for interactive association rule mining.Conclusion The association information mined by Apriori algorithm can provide technical clues for improving the standard management,but the algorithm efficiency is low,and it is not suitable for questionnaire data with large amount of data.