Mining Frequent Item Sets Using Map Reduce Paradigm

In Text categorization techniques like Text classification or clustering, finding frequent item sets is an acquainted method in the current research trends. Even though finding frequent item sets using Apriori algorithm is a widespread method, later DHP, partitioning, sampling, DIC, Eclat, FP-growth, H-mine algorithms were shown better performance than Apriori in standalone systems. In real scenario, as the data over the internet is expanding regularly, the unstructured data documents are scaling up and the existing computing resources in a single machine may not be sufficient to support the big data in text mining process. In order to handle big data, we need to parallelize the execution of the text mining process. Recently, Hadoop implements a computational paradigm named MapReduce, where the application is divided into many small fragments of work, each of which may be executed or re-executed on any node in the cluster. In addition, it provides a distributed file system that stores data on the compute nodes, providing very high aggregate bandwidth across the cluster and enables the applications to work with thousands of computation-independent computers and petabytes of data. In this paper, we present about the characteristics of map reduce paradigm and shows the experimental results of finding frequent items using map reduce paradigm.