如何将带有tinestamp等的CSV文件输入到mahout中以实现相似功能等？

Question

Currently, I am trying to input my data to try machine learning purpose, the data is like following with three columns (first one is time, the second one is code and the third one is number):

2016-06-05 00:00:00      fd04:bd3:80e8:2:215:8d00:35:ca4b   0

2016-06-05 00:00:00      fd04:bd3:80e8:2:215:8d00:35:f2be   0.12549

2016-06-05 00:00:00      fd04:bd3:80e8:2:215:8d00:35:c8a1   0.14091

2016-06-05 00:00:01      fd04:bd3:80e8:2:215:8d00:35:ca4b   0

2016-06-05 00:00:01      fd04:bd3:80e8:2:215:8d00:35:f2be   0.25098

2016-06-05 00:00:01      fd04:bd3:80e8:2:215:8d00:35:c8a1   0

2016-06-05 00:00:02      fd04:bd3:80e8:2:215:8d00:35:ca4b   0

2016-06-05 00:00:02      fd04:bd3:80e8:2:215:8d00:35:f2be   0.25098

The following is the code to import the data into mahout:

import java.util.List;
import java.io.File;
import org.apache.mahout.cf.taste.model.DataModel;
import org.apache.mahout.cf.taste.impl.model.file.FileDataModel;
import org.apache.mahout.cf.taste.similarity.UserSimilarity;
import     org.apache.mahout.cf.taste.impl.similarity.PearsonCorrelationSimilarity;
import org.apache.mahout.cf.taste.neighborhood.UserNeighborhood;
import org.apache.mahout.cf.taste.impl.neighborhood.NearestNUserNeighborhood;
import org.apache.mahout.cf.taste.recommender.Recommender;
import org.apache.mahout.cf.taste.recommender.RecommendedItem;
import org.apache.mahout.cf.taste.impl.recommender.GenericUserBasedRecommender;
/**
 */
    public class RecommenderIntro {
        public static void main(String[] args) throws Exception {

            // TODO code application logic here
            DataModel model = new FileDataModel (new File("/home/leo/csv_dump11.csv"));
            UserSimilarity similarity = new PearsonCorrelationSimilarity (model);
            UserNeighborhood neighborhood = new NearestNUserNeighborhood (2, similarity, model);
            Recommender recommender = new GenericUserBasedRecommender (model, neighborhood, similarity);
            List<RecommendedItem> recommendations = recommender.recommend(1, 1);
            for (RecommendedItem recommendation : recommendations) {
                System.out.println(recommendation);
            }
        }
    }

How can I achieve the classification function etc.? Please let me know. Thank you very much!

Answer 1

Your input file is in the wrong format for FileDataModel . If you look at the source code you'll see its expecting:

userID,itemID,timestamp

Which is in-line with the java.lang.NumberFormatException error your seeing. Its expecting a userID as a long and you have a formatted date.

Also note the timestamp should be a long . The documentation in the source indicates you can provide your own function to parse the date if you override readTimestampFromString(String) if you don't want to convert all your dates to milliseconds.

So you'll either need to reformat your data to work with this class or extend it and override the relevant methods need to parse it correctly (if possible).