Mahout algorithm source code analysis: Itembased Collaborative Filtering (3) RowSimilari

Mahout version: 0.7, hadoop version: 1.0.4, jdk: 1.7.0 _ 25 64bit. This article analyzes whether the analysis in the previous article is correct, mainly writing the reading of the output file in the previous article and adding log information to print related variables. First, write the following test file to analyze all the output: [java] package mahout. fansy. item; import java. io. IOException; import java. util. map; import mahout. fansy. utils. read. readArbiKV; import org. apache. hadoop. conf. configuration; import org. apache. hadoop. fs. path; import org. apache. hadoop. io. writable; import org. apache. mahout. math. vector; import org. apache. mahout. math. hadoop. similarity. cooccurrence. vectors; import junit. framework. test Case; public class ReadRowSimilarityJobOut extends TestCase {// test weights output: public void testWeights () throws IOException {String path = "hdfs: // ubuntu: 9000/user/mahout/item/temp/weights/part-r-00000 "; Map <Writable, Writable> map = ReadArbiKV. readFromFile (path); System. out. println ("weights ======================"); System. out. println (map);} // normsPath public void testNormsPath () throws IOException {Str Ing path = "hdfs: // ubuntu: 9000/user/mahout/item/temp/norms. bin "; Vector map = getVector (path); System. out. println ("normsPath ======================"); System. out. println (map);} // maxValues. bin public void testMaxValues () throws IOException {String path = "hdfs: // ubuntu: 9000/user/mahout/item/temp/maxValues. bin "; Vector map = getVector (path); System. out. println ("maxValues ======================"); System. out. println (m Ap);} // numNonZeroEntries. bin public void testNumNonZeroEntries () throws IOException {String path = "hdfs: // ubuntu: 9000/user/mahout/item/temp/numNonZeroEntries. bin "; Vector map = getVector (path); System. out. println ("numNonZeroEntries =================="); System. out. println (map);} // pairwiseSimilarityPath public void testPairwiseSimilarityPath () throws IOException {String path = "hdfs: // ubuntu: 9000/user /Mahout/item/temp/pairwiseSimilarity/part-r-00000 "; Map <Writable, Writable> map = ReadArbiKV. readFromFile (path); System. out. println ("pairwiseSimilarityPath ===================="); System. out. println (map);} // similarityMatrix public void testSimilarityMatrix () throws IOException {String path = "hdfs: // ubuntu: 9000/user/mahout/item/temp/similarityMatrix/part-r-00000 "; Map <Writable, Writable> map = ReadArbiKV. ReadFromFile (path); System. out. println ("similarityMatrix ===================="); System. out. println (map);} // read. binfile public Vector getVector (String path) {Configuration conf = new Configuration (); conf. set ("mapred. job. tracker "," ubuntu: 9001 "); Vector vector = null; try {vector = Vectors. read (new Path (path), conf);} catch (IOException e) {e. printStackTrace () ;}return vector ;}run the above file to get the following output: [plai N] weights ==========================={ 1 = {103:2. 5,102: 3.0. 0}, 2 = {101:2. 0,104: 2.0. 0,102: 2.5}, 3 = {10. 5,107: 5.0. 5,104: 4.0}, 4 = {10. 0,106: 4.0. 5,103: 3.0}, 5 =. 0,105: 3.5. 0,103: 2.0. 0,101: 4.0} normsPath ========================={ 107:25. 0,106: 32.0, 10:32. 5,104: 56.25, 10:44. 25,102: 24.25, 101: 76.25} maxValues ============================{} numNonZeroEntries ====================== {} pairwiseSimila RityPath ==========================={ 102 = {106:0. 14972506706560876,105: 0.14328432723886902. 12789210656028413,103: 0.1975496259559987}, 103 =. 1424339656566283,105: 0.11208890297777215. 14037600977966974}, 101 =. 10275248635596666,106: 0.1424339656566283, 10:0. 1158457425543559,104: 0.16015261286229274. 15548737703860027,102: 0.14201473202245876}, 106 = {}, 107 = {}, 104 =. 13472338607037426, 106:0. 18181818181818182,105: 0.16736577623297264}, 105 =. 2204812092115424,106: 0.14201473202245876 }}similaritymatrix ======================={ 102 = {101:0. 14201473202245876,106: 0.14972506706560876, 10:0. 14328432723886902,104: 0.12789210656028413. 1975496259559987}, 103 = {101:0. 15548737703860027,106: 0.1424339656566283, 10:0. 11208890297777215,104: 0.14037600977966974, 10:0. 1975496259559987}, 101 = {107: 0.10275248635596666. 1424339656566283,105: 0.1158457425543559. 16015261286229274,103: 0.15548737703860027, 10:0. 14201473202245876}, 106 = {101:0. 1424339656566283,105: 0.14201473202245876. 18181818181818182,103: 0.1424339656566283, 10:0. 14972506706560876}, 107 = {105:0. 2204812092115424,104: 0.13472338607037426. 10275248635596666}, 104 =. 13472338607037426,106: 0.18181818181818182, 105: 0.16736577623297264. 14037600977966974,102: 0.12789210656028413. 16015261286229274}, 105 =. 2204812092115424,106: 0.14201473202245876. 16736577623297264,103: 0.11208890297777215, 10:0. 14328432723886902,101: 0.1158457425543559} The first weights is exactly the same as the analysis, so I don't believe it anymore. Then we only analyze pairwiseSimilarityPath and similarityMatrix: