Description

 Dataset Consists of Document to be clustered together.  By using CPI (Correlation Preserving Indexing) algorithm to Cluster the document.  Documents in the dataset are converted to term frequency vector  The CPI is performed in Correlation similarity measure which uses the TF/IDF (Term Frequency/Inverse Document Frequency) calculate the weight of the term frequency vector.  Using weighted terms we get the distance between documents.  Documents are grouped together with minimum distance in local patches