A Map Reduce Based Parallel Algorithm

Authors

Priyanka Gupta
Computer Engineering Dwarkadas J Sanghvi College of Engineering Mumbai, Marashtra, India.
Dr. Vinaya Sawant
Head of Information Technology Dwarkadas J Sanghvi College of Engineering Mumbai, Marashtra, India.

Abstract

In Today’s world, Big Data became a vital role in our way of life. Growing rapidly and logical algorithms that will handle large datasets becoming a challenging task. This paper aim is to explain the Hadoop- Map Reduce Framework with Association rule Mining. One of the famous algorithm of ARM is that the Apriori algorithm, which is implemented in MapReduce artificial language, which is executed on the Hadoop framework. These rules are tradition to observe facts that always occur along with datasets. Using association rule, an issue arises when data becomes enormous. To beat this situation they used Hadoop. This paper provides an outline of the Hadoop – MapReduce framework. Our big challenge of this paper are to resolve the matter of scalability, apart from the other problems are execution time and communication overhead. This paper will solve the matter of reliable, scalable and distributed computing.