A Survey on Data Mining and Analysis in Hadoop and MongoDb

Abstract

Data  Mining is a process to generate pattern and rules from various types of data marts and data warehouses ,in this process there are several steps which contains data cleaning data anomaly detection then clean data is mined with various approaches .In this research we have discussed data mining on large datasets ( Big Data) with this large data set major issues are scalability and security ,Hadoop is the tool to mine the data and Mongo db provides input for it, which is a key-value paradigm for parsing the data ,Other approaches are discussed with this report and their capability for data storage ,Map reduce is method which can be  used to reduce the data set to reduce query processing time and improve system throughput, In the Proposed system we are going to mine the big data this  Hadoop and Mongo db and we will try to mine the data with sorted or double sorted key value pair ,for and analyze the outcome of system.

Keywords- DataMIning , Hadoop, MapReduce, HDFS, MongoDb.