mahout

问题 I am trying to run the 2newsgroup classification example in Mahout. I have set MAHOUT_LOCAL=true, the classifier doesn't display the Confusion matrix and gives the following warnings : ok. You chose 1 and we'll use cnaivebayes creating work directory at /tmp/mahout-work-cloudera + echo 'Preparing 20newsgroups data' Preparing 20newsgroups data + rm -rf /tmp/mahout-work-cloudera/20news-all + mkdir /tmp/mahout-work-cloudera/20news-all + cp -R /tmp/mahout-work-cloudera/20news-bydate/20news-bydate

问题 There exists in Mahout a command for create sequence file as bin/mahout seqdirectory -c UTF-8 -i <input address> -o <output address> . I want use this command as code API. 回答1: You can do something like this: import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.FileSystem; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.SequenceFile; import org.apache.hadoop.io.Text; Configuration conf = new Configuration(); FileSystem fs = FileSystem.get(conf); Path

问题 I have to perform a k-means clustering on a really huge matrix (about 300.000x100.000 values which is more than 100Gb). I want to know if I can use R software to perform this or weka. My computer is a multiprocessor with 8Gb of ram and hundreds Gb of free space. I have enough space for calculations but loading such a matrix seems to be a problem with R (I don't think that using the bigmemory package would help me and big matrix use automatically all my RAM then my swap file if not enough

问题 I have a server application implemented using Dropwizard and Gradle as Build System. Now I want to integrate Apache Mahout for some recommender system action. After adding the Mahout dependency and try to run, I get exceptions. My initial dependencies look like dependencies { compile 'io.dropwizard:dropwizard-core:0.9.1' compile 'io.dropwizard:dropwizard-jdbi:0.9.1' compile 'mysql:mysql-connector-java:5.1.37' compile 'redis.clients:jedis:2.8.0' compile 'com.google.guava:guava:18.0' compile

问题 I want to do a sort of user-user collaborative filtering wherein the users in the user-item matrix are a selected part of whole users in the database. These selected users are refreshed regularly with newly selected users preferences. New users shouldn't be added to the matrix. For a new user, based on his preferences we need to recommend items from the user-item matrix (which has only a part of users which are selected). I do not want to add the new anonymous users to the matrix. Explored in

问题 I am trying to cluster a sample dataset which is in csv file format. But when I give the below command, user@ubuntu:/usr/local/mahout/trunk$ bin/mahout kmeans -i /root/Mahout/temp/parsedtext-seqdir-sparse-kmeans/tfidf-vectors/ -c /root/Mahout/temp/parsedtext-kmeans-clusters -o /root/Mahout/reuters21578/root/Mahout/temp/parsedtext-kmeans -dm org.apache.mahout.common.distance.CosineDistanceMeasure -x 2 -k 1 -ow --clustering -cl I am getting the following error, saying there is no input clusters

问题 Where did my code go wrong? When I searched, I found a similar post, but couldn't adapt it to my problem. Exception in thread "main" java.lang.IncompatibleClassChangeError: Found interface org.apache.hadoop.mapreduce.JobContext, but class was expected at org.apache.mahout.common.HadoopUtil.getCustomJobName(HadoopUtil.java:174) at org.apache.mahout.common.AbstractJob.prepareJob(AbstractJob.java:614) at org.apache.mahout.cf.taste.hadoop.preparation.PreparePreferenceMatrixJob.run

问题 I'm having a text file with label and tweets . positive,I love this car negative,I hate this book positive,Good product. I need to convert each line into vector value.If i use seq2sparse command means the whole document gets converted to vector,but i need to convert each line as vector not the whole document. ex : key : positive value : vectorvalue(tweet) How can we achieve this in mahout? /* Here is what i have done */ StringTokenizer str= new StringTokenizer(line,","); String label=str

问题 I have hadoop cluster version 2.2.0 running with mahout 0.8, is it compatible? Because whenever I run this command: bin/mahout recommenditembased --input mydata.dat --usersFile user.dat --numRecommendations 2 --output output/ --similarityClassname SIMILARITY_PEARSON_CORRELATION Give me this error: Exception in thread "main" java.lang.IncompatibleClassChangeError: Found interface org.apache.hadoop.mapreduce.JobContext, but class was expected at org.apache.mahout.common.HadoopUtil

问题 As suggested here, I am running hadoop in pseudodistributed mode with the following mapred-site.xml file. The job is running on a 4 core machine. <configuration> <property> <name>mapred.job.tracker</name> <value>localhost:9001</value> </property> <property> <name>mapred.map.tasks</name> <value>4</value> </property> <property> <name>mapred.reduce.tasks</name> <value>4</value> </property> </configuration> I am getting the following error: The ratio of reported blocks 1.0000 has reached the