基于大数据视角的肉类食品安全抽检数据分析

目的 基于大数据视角分析肉类食品安全抽检数据。方法 在大数据技术支持下以国家肉类食品抽检监测数据源为基础, 通过Python语言编程设计分类与预测实验, 并利用数据挖掘预测集实验结果与真实食品检验结果进行对比研究, 以验证该方法的可行性。结果 基于决策树+典型相关系数和二次指数平滑法相结合的数据挖掘方法分类效果较好, 预测准确性达到98.26%。结论 通过预判不合格肉类食品的出现数量和分布情况, 可指导其安全抽检监测工作, 提高管理的效率和准确率, 有效预防肉类食品安全事故的发生。

Study on meat food safety sampling data under the perspective of big data

Objective To analyze meat food safety sampling data under the perspective of big data. Methods With the support of big data technology and based on the national meat food sampling inspection and monitoring data source, the classification and prediction experiment was designed by Python language programming, and the experimental results of the prediction set were compared with the real food inspection results to verify the feasibility of this method. Results The data mining method based on decision tree+typical correlation coefficient and quadratic exponential smoothing method had better classification effect, and the prediction accuracy reached 98.26%. Conclusion By predicting the quantity and distribution of unqualified meat foods, it can guide its safety sampling inspection and monitoring, improve the efficiency and accuracy of management, and effectively prevent the occurrence of meat food safety accidents.