Traditional data analytics tools are designed to deal with the asymmetrical type of data i.e., structured, semi-structured, and unstructured. The diverse behavior of data produced by different sources requires the selection of suitable tools. The restriction of recourses to deal with a huge volume of data is a challenge for these tools, which affects the performances of the tool’s execution time. Therefore, in the present paper, we proposed a time optimization model, shares common HDFS (Hadoop Distributed File System) between three Name-node (Master Node), three Data-node, and one Client-node. These nodes work under the DeMilitarized zone (DMZ) to maintain symmetry. Machine learning jobs are explored from an independent platform to realize this model. In the first node (Name-node 1), Mahout is installed with all machine learning libraries through the maven repositories. The second node (Name-node 2), R connected to Hadoop, is running through the shiny-server. Splunk is configured in the third node (Name-node 3) and is used to analyze the logs. Experiments are performed between the proposed and legacy model to evaluate the response time, execution time, and throughput. K-means clustering, Navies Bayes, and recommender algorithms are run on three different data sets, i.e., movie rating, newsgroup, and Spam SMS data set, representing structured, semi-structured, and unstructured data, respectively. The selection of tools defines data independence, e.g., Newsgroup data set to run on Mahout as others cannot be compatible with this data. It is evident from the outcome of the data that the performance of the proposed model establishes the hypothesis that our model overcomes the limitation of the resources of the legacy model. In addition, the proposed model can process any kind of algorithm on different sets of data, which resides in its native formats.

Today we are living with the extensive volume of information which is developing at a very fast pace. Clustering is the process of group similar kinds of information. The serial k-means clustering method takes a large amount of computational time when it is applied to enormous data sets which are large in size of tera and petabyte. In this paper, we evaluated the performance of the K-means algorithm in different ways like K-mean simple (using java codes on MapReduce), K-means (using java codes on MapReduce) with IEC (Initial Equidistant Centres), K-mean on Mahout (using Machine learning library) and K-mean on Spark (Machine learning library) on static IP address data sets over the MapReduce framework. In addition to this we also compare the K-mean simple and K-mean (IEC) on different iteration level. Outcome shows on the better performance on the basis of time on different infrastructure and it also defines the behaviour of K-means algorithms on the basis of centroids and different iteration levels.