Java Text Classification

I require a Java command line program that does a binary classification from a text file using a Support Vector Machine (SVM) and K-Nearest Neighbor. I would like to replicate this but using Java. [login to view URL] [login to view URL] The program should have the following parts (clearly commented in the code): a) Train on 70% of the Data, Test on 30% (random samples). Can also segment Training/Test data by Year column (i.e. Train on years 2000-2010, Test on 2011-2017) b) Clean the Corpus - Remove Punctuation - Strip Whitespace - Convert to Lowercase - Remove Stopwords - Word Stemming c) Create Term Document Matrix - Remove Sparse Terms d) Apply Support Vector Machine (SVM)/K-Nearest Neighbor Algorithm e) Print Results For the SDK, please send me which one you are planning on using (No Weka) when bidding. One suggestion is [login to view URL] The program should have the following parameters: Filename (CSV filename) Algorithm (SVM or KNN) Outcome Column Name Text Column Name Example Command Line: Java -jar TextClassify <filename> <SVM | KNN> <OutcomeColumn> <TextColumn> I have attached a sample CSV file (with 3 outcome columns to test on) and can create more if needed. Final deliverables are: a) Jar file b) Source Code with clean code and basic documentation (i.e. comments in the source code). Preference is IntelliJ with Maven.