A Parallel Apriori Algorithm and FP- Growth Based on SPARK

Frequent Itemset Mining is an important data mining task in real-world applications. Distributed parallel Apriori and FP-Growth algorithm the most that works on for finding frequent itemsets. Originally, Map-Reduce algorithm-based itemsets Hadoop were resolved. For handling big data, comes into picture but implementation of does not reach expectations distributed because its high I/O results transactional disk. According to research, Spark has in-memory computation technique gives faster than Hadoop. It was mainly acceptable algorithms data. The working multiple datasets itemset get accurate time. In this paper, we propose apriori FP-growth using Apache SPARK framework. Our experiment depend support value results.