id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_k4dphi7rgzgifgf4jv7luea7gu	Gao Pengfei	Research and Improvement of Apriori Algorithm Based on Hadoop	2019	6	.pdf	application/pdf	2805	258	65	Research and Improvement of Apriori Algorithm Based on Hadoop parallel Apriori algorithms needs much more time in data IO Keywords-Apriori algorithm; Hadoop; Association rules Apriori algorithm, which is a classic association rule transaction database, and the support of this frequent set generate frequent 3-item set L3. 1) When the Apriori algorithm generates the candidate scan the transaction data set again and compare the candidate 2) Apriori algorithm need to rescan transaction datasets A. Reduce frequent item sets self-connection comparison merging processes, some frequent item sets of the data d) Scan transaction data set D minimum support count with the set of transaction items After association rules mine frequent item sets, it is experimental transaction data set. MEC-Apriori algorithm, and then the association rule is The transaction data set for this experiment is stored as a number of transaction item sets, apriori algorithm running on number of transaction item sets increases, the time 	./cache/work_k4dphi7rgzgifgf4jv7luea7gu.pdf	./txt/work_k4dphi7rgzgifgf4jv7luea7gu.txt