Classification of word2vec using weka - machine-learning

Question

I have trained a word2vec model on a corpus of around 70k sentences. Each sentence contains a unique keyword such as 'abc-2011-100' followed by certain features that describe it. Now, I have to classify for every abc id. like abc-2011-100 belongs to abc_category_1. abc-2999-0000 belongs to abc_category_20 and so on. A category can have multiple abc id's assigned to it. I have around 70000 unique abc Id's. Out of these 70000, 5000 are already classified appropriately. Now I want to check my classification accuracy on the already classified 5000 id's. For that I will take 80% as training data and 20% for checking accuracy. I can describe every abc id as a d-dimensional vector. Using this information, how can I use weka for running this classification task.? Please any input would be highly appreciated.

Answer 1

See here.
First, read in your csv/arff:
import weka.core.Instances;
import java.io.BufferedReader;
import java.io.FileReader;
...
BufferedReader reader = new BufferedReader(new FileReader("yourData.arff"));
Instances data = new Instances(reader);
reader.close();
// setting class attribute
data.setClassIndex(data.numAttributes() - 1); // This is category for you
Then instantiate and train a classifier
import weka.classifiers.trees.J48;
...
String[] options = new String[1];
options[0] = "-U"; // unpruned tree
J48 tree = new J48(); // new instance of tree
tree.setOptions(options); // set the options
tree.buildClassifier(data); // build classifier
Run Cross-validation to evaluate the learner
import weka.classifiers.Evaluation;
import java.util.Random;
...
Evaluation eval = new Evaluation(data);
eval.crossValidateModel(tree, data, 10, new Random(1));
Or do training and testing on separate sets
import weka.core.Instances;
import weka.classifiers.Evaluation;
import weka.classifiers.trees.J48;
...
/* train and test are of type Instances (see above) */
// train classifier
Classifier cls = new J48();
cls.buildClassifier(train);
// evaluate classifier and print some statistics
Evaluation eval = new Evaluation(train);
eval.evaluateModel(cls, test);
System.out.println(eval.toSummaryString("\nResults\n======\n", false));