| 摘要: |
| 对频繁模式增长（FP-Growth）算法进行了改进，用哈希头表代替头表.通过合并频繁模式树（FP-Tree）中支持数相同的结点，压缩了树的规模，有效地节省了空间.实验结果表明，改进后的算法在查找效率上有了大幅度的提高，可以更好地适用于大规模数据集的关联规则挖掘. |
| 关键词: 频繁模式增长(FP-Growth) 关联规则 频繁项集 哈希头表 合并结点 |
| DOI：10.3969/J.ISSN.1000-5137.2018.04.012 |
| 分类号:TP311 |
| 基金项目: |
|
| A new FP-growth based on Hash and merging techniques |
|
He Qing, Lu Liming
|
|
The College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 200234, China
|
| Abstract: |
| In this paper,we improve frequent pattern growth(FP-Growth) algorithm,we replace the header table with Hash-header table.By merging the same frequency nodes in frequent pattern tree(FP-Tree),we compress the scale of the tree.The experimental results show that the proposed algorithm has improved the efficiency of query,and it can be applied in mining large data sets with association rules. |
| Key words: frequent pattern growth (FP-Growth) association rules frequent item sets Hash-header table merging nodes |
