public abstract class PwsimEnvironment extends Configured
Modifier and Type | Field and Description |
---|---|
static int |
batchIndexKeyLength |
static int |
chunkOverlapSize |
static boolean |
cluster |
static int |
dfCut |
static boolean |
isCrossLingual |
static int |
maxHammingDistance |
static String |
mode |
static int |
numBatchFiles |
static int |
numChunksPerPermTable |
static int |
numOfBits |
static int |
numOfPermutations |
static int |
numResults |
static boolean |
pairwiseWithinChunk |
static String |
permutationType |
static int |
sampleSize |
static float |
scoreThreshold |
static String |
signatureType |
static int |
slidingWindowSize |
static boolean |
withBoundaries |
Constructor and Description |
---|
PwsimEnvironment() |
Modifier and Type | Method and Description |
---|---|
static String |
getFilteredPwsimDir(String dir,
String signatureType,
int maxHammingDistance,
int numOfBits,
int numOfPermutations,
int slidingWindowSize,
String docnos,
int numResults) |
static String |
getIntDocvectorsFile(String dir,
FileSystem fs) |
static String |
getIntDocvectorsFile(String dir,
FileSystem fs,
int sampleSize) |
static String |
getPermutationsFile(String dir,
FileSystem fs,
int numOfBits,
int numOfPermutations) |
static String |
getPwsimDir(String dir,
String signatureType,
int maxHammingDistance,
int numOfBits,
int numOfPermutations,
int slidingWindowSize) |
static String |
getRandomVectorsDir(String dir,
int numOfBits) |
static String |
getSignaturesDir(String dir,
int numOfBits,
String type) |
static String |
getSignaturesDir(String dir,
int numOfBits,
String type,
int numBatch) |
static String |
getTablesDir(String dir,
FileSystem fs,
String signatureType,
int numOfBits,
int chunkOverlapSize,
int numOfPermutations) |
static String |
getTermDocvectorsFile(String dir,
FileSystem fs) |
static String |
getTermDocvectorsFile(String dir,
FileSystem fs,
int sampleSize) |
static JobConf |
setBitextPaths(JobConf conf,
String dataDir,
String eLang,
String fLang,
String bitextName,
String eDir,
String fDir) |
static JobConf |
setBitextPaths(JobConf conf,
String dataDir,
String eLang,
String fLang,
String bitextName,
String eDir,
String fDir,
float classifierThreshold,
int classifierId,
String pwsimPairsPath,
String classifierType) |
static void |
setClassTypes(String signatureType,
Configuration config) |
getConf, setConf
public static int batchIndexKeyLength
public static int chunkOverlapSize
public static final boolean cluster
public static int dfCut
public static boolean isCrossLingual
public static int maxHammingDistance
public static String mode
public static int numBatchFiles
public static int numChunksPerPermTable
public static int numOfBits
public static int numOfPermutations
public static int numResults
public static boolean pairwiseWithinChunk
public static String permutationType
public static int sampleSize
public static float scoreThreshold
public static String signatureType
public static int slidingWindowSize
public static boolean withBoundaries
public static String getFilteredPwsimDir(String dir, String signatureType, int maxHammingDistance, int numOfBits, int numOfPermutations, int slidingWindowSize, String docnos, int numResults) throws IOException
IOException
public static String getIntDocvectorsFile(String dir, FileSystem fs) throws IOException
IOException
public static String getIntDocvectorsFile(String dir, FileSystem fs, int sampleSize) throws IOException
IOException
public static String getPermutationsFile(String dir, FileSystem fs, int numOfBits, int numOfPermutations) throws IOException
IOException
public static String getPwsimDir(String dir, String signatureType, int maxHammingDistance, int numOfBits, int numOfPermutations, int slidingWindowSize) throws IOException
IOException
public static String getSignaturesDir(String dir, int numOfBits, String type, int numBatch)
public static String getTablesDir(String dir, FileSystem fs, String signatureType, int numOfBits, int chunkOverlapSize, int numOfPermutations) throws IOException
IOException
public static String getTermDocvectorsFile(String dir, FileSystem fs) throws IOException
IOException
public static String getTermDocvectorsFile(String dir, FileSystem fs, int sampleSize) throws IOException
IOException
public static JobConf setBitextPaths(JobConf conf, String dataDir, String eLang, String fLang, String bitextName, String eDir, String fDir) throws IOException, URISyntaxException
IOException
URISyntaxException
public static JobConf setBitextPaths(JobConf conf, String dataDir, String eLang, String fLang, String bitextName, String eDir, String fDir, float classifierThreshold, int classifierId, String pwsimPairsPath, String classifierType) throws IOException, URISyntaxException
IOException
URISyntaxException
public static void setClassTypes(String signatureType, Configuration config)