// Determines the run-time coefficients of the different parts of the //确定查询算法不同部分的运行时间
// query algorithm. Values that are computed and returned are
// <lshPrecomp>, <uhashOver>, <distComp>. <lshPrecomp> is the time for
// pre-computing one function from the LSH family. <uhashOver> is the
// time for getting a bucket from a hash table (of buckets).<distComp>
// is the time to compute one distance between two points. These times
// are computed by constructing a R-NN DS on a sample data set and
// running a sample query set on it.
void determineRTCoefficients(RealT thresholdR,
RealT successProbability,
BooleanT useUfunctions,
IntT typeHT, //建立hash表的类型
IntT dimension,
Int32T nPoints,
PPointT *realData,
RealT &lshPrecomp,
RealT &uhashOver,
RealT &distComp){
// use a subset of the original data set. 使用原始数据集的一个子集
// there is not much theory behind the formula below. //减小运算规模
IntT n = nPoints / 50; //最多生成n各点，缩小50倍
if (n < 100) { //如果生成的点的个数小于100，则使桶的数量与数据集点的数量一样多
n = nPoints;
}
if (n > 10000) {
n = 10000;
}
// Initialize the data set to use.
PPointT *dataSet;
FAILIF(NULL == (dataSet = (PPointT*)MALLOC(n * sizeof(PPointT))));
for(IntT i = 0; i < n; i++){ //从真实数据集中随机取n个点 （最多10000个）
dataSet[i] = realData[genRandomInt(0, nPoints - 1)];
}
IntT hashTableSize = n; //哈希表大小也初始化为n，是指hashTableSize放的点的个数，还是放的桶的个数？
RNNParametersT algParameters;
algParameters.parameterR = thresholdR; //半径
algParameters.successProbability = successProbability;
algParameters.dimension = dimension;
#ifdef USE_L1_DISTANCE
algParameters.parameterR2 = thresholdR; //使用L1距离，R2=R
#else
algParameters.parameterR2 = SQR(thresholdR); //使用L2 R2=R^2
#endif
algParameters.useUfunctions = useUfunctions;
algParameters.parameterK = 16; //k 设定为16，只是测试，估算运算时间，可能是先随机设置一个时间，之后再在代码中改成16，因为16是bestK.
algParameters.parameterW = PARAMETER_W_DEFAULT; //W=4，manuel中说经过多次测试，4是最好的值
algParameters.parameterT = n; //点的个数
algParameters.typeHT = typeHT; //桶的类型HT_HYBRID_CHAINS，在line405里面定义的。
if (algParameters.useUfunctions){
algParameters.parameterM = computeMForULSH(algParameters.parameterK, algParameters.successProbability); //经过改进的L和M
algParameters.parameterL = algParameters.parameterM * (algParameters.parameterM - 1) / 2;
}else{
algParameters.parameterM = computeLfromKP(algParameters.parameterK, algParameters.successProbability); //论文里面的M=L
algParameters.parameterL = algParameters.parameterM;
}
// FAILIF(NULL == (dataSet = (PPointT*)MALLOC(n * sizeof(PPointT))));
// for(IntT i = 0; i < n; i++){
// FAILIF(NULL == (dataSet[i] = (PPointT)MALLOC(sizeof(PointT))));
// FAILIF(NULL == (dataSet[i]->coordinates = (RealT*)MALLOC(dimension * sizeof(RealT))));
// dataSet[i]->index = i;
// sqrLength = 0;
// for(IntT d = 0; d < dimension; d++){
// if (i == 0) {
// dataSet[i]->coordinates[d] = genUniformRandom(-100, 100);
// }else{
// dataSet[i]->coordinates[d] = dataSet[0]->coordinates[d];
// }
// sqrLength += SQR(dataSet[i]->coordinates[d]);
// }
// dataSet[i]->sqrLength = sqrLength;
// }
// switch on timing
BooleanT tempTimingOn = timingOn; //初始化为True
timingOn = TRUE;
// initialize result arrays
PPointT *result = NULL; //结果集以及其初始化
IntT resultSize = 0;
IntT nNNs;
IntT nSucReps;
do{
// create the test structure
PRNearNeighborStructT nnStruct;
switch(algParameters.typeHT){
case HT_LINKED_LIST:
nnStruct = initLSH(algParameters, n);
// add points to the test structure
for(IntT i = 0; i < n; i++){
addNewPointToPRNearNeighborStruct(nnStruct, realData[i]);
}
break;
case HT_HYBRID_CHAINS:
nnStruct = initLSH_WithDataSet(algParameters, n, dataSet); //初始化数据结构，参数集，点的个数，数据集，对点进行映射转换，桶进行映射转换，点存入桶中
break;
default:
ASSERT(FALSE);
}
// query point
PPointT queryPoint;
// FAILIF(NULL == (queryPoint = (PPointT)MALLOC(sizeof(PointT))));
// FAILIF(NULL == (queryPoint->coordinates = (RealT*)MALLOC(dimension * sizeof(RealT))));
// RealT sqrLength = 0;
// for(IntT i = 0; i < dimension; i++){
// queryPoint->coordinates[i] = dataSet[0]->coordinates[i];
// //queryPoint->coordinates[i] = 0.1;
// sqrLength += SQR(queryPoint->coordinates[i]);
// }
//queryPoint->coordinates[0] = dataPoint->coordinates[0] + 0.0001;
//queryPoint->sqrLength = sqrLength;
// reset the R parameter so that there are no NN neighbors.
setResultReporting(nnStruct, FALSE);
//DPRINTF1("X\n");
lshPrecomp = 0;
uhashOver = 0;
distComp = 0;
IntT nReps = 20;
nSucReps = 0;
for(IntT rep = 0; rep < nReps; rep++){
queryPoint = realData[genRandomInt(0, nPoints - 1)]; //查询点为数据集中随机抽取出来的一个点
timeComputeULSH = 0;
timeGetBucket = 0;
timeCycleBucket = 0;
nOfDistComps = 0; //点与点比较的次数
//返回查找到的近邻点数，并将查询到的近邻点存入result中。
nNNs = getNearNeighborsFromPRNearNeighborStruct(nnStruct, queryPoint, result, resultSize);
//DPRINTF("Time to compute LSH: %0.6lf\n", timeComputeULSH);
//DPRINTF("Time to get bucket: %0.6lf\n", timeGetBucket);
//DPRINTF("Time to cycle through buckets: %0.9lf\n", timeCycleBucket);
//DPRINTF("N of dist comp: %d\n", nOfDistComps);
ASSERT(nNNs == 0); //若一个点都没有找到，将发生中断。
if (nOfDistComps >= MIN(n / 10, 100)){ //与足够的点比较过，才将时间计入
nSucReps++;
lshPrecomp += timeComputeULSH / algParameters.parameterK / algParameters.parameterM; //一个点对一个哈希函数的处理时间。共有k*L个哈希函数
uhashOver += timeGetBucket / algParameters.parameterL; //找到一个链表中桶的时间
distComp += timeCycleBucket / nOfDistComps; //遍历链表中桶，并与桶里面的点比较的时间
}
}
if (nSucReps >= 5){
lshPrecomp /= nSucReps;
uhashOver /= nSucReps;
distComp /= nSucReps;
DPRINTF1("RT coeffs computed.\n");
}else{
algParameters.parameterR *= 2; // double the radius and repeat //比较的点数不够，将半径扩大，重复比较
DPRINTF1("Could not determine the RT coeffs. Repeating.\n");
}
freePRNearNeighborStruct(nnStruct);
}while(nSucReps < 5); //做一个有效值的判断，要获得5次有效值
FREE(dataSet);
FREE(result);
timingOn = tempTimingOn;
}
/*
The main entry to LSH package. Depending on the command line
parameters, the function computes the R-NN data structure optimal
parameters and/or construct the R-NN data structure and runs the
queries on the data structure.
*/
int main_T(int nargs, char **args)
{
//先分析参数
/* 官方lsh文件：10个参数
1000 9 784 0.9 0.6 mnist1k.dts mnist1k.q
bin/LSHMain $nDataSet $nQuerySet $dimension $successProbability "$1" "$2" "$3" $m -c*/
//算参数 bin/LSHMain 1000 9 784 0.9 "0.6" "mnist1k.dts" "mnist1k.q" 1002000000 -c
//bin/LSHMain $nDataSet $nQuerySet $dimension $successProbability 1.0 "$1" "$2" $m -p "$3"
//匹配 bin/LSHMain 1000 9 784 0.9 1.0 "mnist1k.dts" "mnist1k.q" 1002000000 -p "outputparma.txt"
if(nargs < 9)
{
usage(args[0]);
exit(1);
}
//initializeLSHGlobal();
// Parse part of the command-line parameters.
nPoints = atoi(args[1]);
IntT nQueries = atoi(args[2]);
pointsDimension = atoi(args[3]);
successProbability = atof(args[4]);
char* endPtr[1];
RealT thresholdR = strtod(args[5], endPtr);//点相邻的距离阈值
//str-to -double 将字符串转换成浮点数的函数
//endPtr 接收数字结尾后非字符串字母
//这个r阈值是什么呢？
if (thresholdR == 0 || endPtr[1] == args[5])
{//如果阈值为0，或者第一个字符就不是数字，
//表示是用文件保存的
//这大概是用于测试哪个阈值好的
// The value for R is not specified, instead there is a file
// specifying multiple R's.
thresholdR = 0;
// Read in the file
FILE *radiiFile = fopen(args[5], "rt");
FAILIF(radiiFile == NULL);
fscanf(radiiFile, "%d\n", &nRadii);
ASSERT(nRadii > 0);
FAILIF(NULL == (listOfRadii = (RealT*)MALLOC(nRadii * sizeof(RealT))));
FAILIF(NULL == (memRatiosForNNStructs = (RealT*)MALLOC(nRadii * sizeof(RealT))));
for(IntT i = 0; i < nRadii; i++)
{
FSCANF_REAL(radiiFile, &listOfRadii[i]);
ASSERT(listOfRadii[i] > 0);
FSCANF_REAL(radiiFile, &memRatiosForNNStructs[i]);
ASSERT(memRatiosForNNStructs[i] > 0);
}
}
else
{
nRadii = 1;
FAILIF(NULL == (listOfRadii = (RealT*)MALLOC(nRadii * sizeof(RealT))));
FAILIF(NULL == (memRatiosForNNStructs = (RealT*)MALLOC(nRadii * sizeof(RealT))));
listOfRadii[0] = thresholdR;
memRatiosForNNStructs[0] = 1;
}//对阈值R 和Radiii的处理
DPRINTF("No. radii: %d\n", nRadii);
//thresholdR = atof(args[5]);
availableTotalMemory = atoll(args[8]);//$M表示的是内存空间大小
if (nPoints > MAX_N_POINTS)
{
printf("Error: the structure supports at most %d points (%d were specified).\n", MAX_N_POINTS, nPoints);
fprintf(ERROR_OUTPUT, "Error: the structure supports at most %d points (%d were specified).\n", MAX_N_POINTS, nPoints);
exit(1);
}
readDataSetFromFile(args[6]);//点读到dataSetPoints
//这个totalAllocatedMemory初始化为0，但是
//#define MALLOC(amount) ((amount > 0) ? totalAllocatedMemory += amount, malloc(amount) : NULL)
//这样，每次申请内存都会统计到了
DPRINTF("Allocated memory (after reading data set): %lld\n", totalAllocatedMemory);
Int32T nSampleQueries = N_SAMPLE_QUERY_POINTS;
PPointT sampleQueries[N_SAMPLE_QUERY_POINTS];
Int32T sampleQBoundaryIndeces[N_SAMPLE_QUERY_POINTS];
// PPointT sampleQueries[nSampleQueries];
// Int32T sampleQBoundaryIndeces[nSampleQueries];
if ((nargs <= 9) || (strcmp("-c", args[9]) == 0) )
{
// In this cases, we need to generate a sample query set for
// computing the optimal parameters.
// Generate a sample query set.
FILE *queryFile = fopen(args[7], "rt");
if (strcmp(args[7], ".") == 0 || queryFile == NULL || nQueries <= 0)
{//没有查询文件，就用所有点产生随机点
// Choose several data set points for the sample query points.
for(IntT i = 0; i < nSampleQueries; i++){
sampleQueries[i] = dataSetPoints[genRandomInt(0, nPoints - 1)];
}
}
else
{
//从查询文件中选取随机的点，
// Choose several actual query points for the sample query points.
nSampleQueries = MIN(nSampleQueries, nQueries);
Int32T sampleIndeces[N_SAMPLE_QUERY_POINTS];
//Int32T sampleIndeces[nSampleQueries];
for(IntT i = 0; i < nSampleQueries; i++)
{
sampleIndeces[i] = genRandomInt(0, nQueries - 1);
}
qsort(sampleIndeces, nSampleQueries, sizeof(*sampleIndeces), compareInt32T);
//printIntVector("sampleIndeces: ", nSampleQueries, sampleIndeces);
Int32T j = 0;
for(Int32T i = 0; i < nQueries; i++)
{
if (i == sampleIndeces[j])
{
sampleQueries[j] = readPoint(queryFile);
j++;
while (i == sampleIndeces[j])
{
sampleQueries[j] = sampleQueries[j - 1];
j++;
}
}else
{
fscanf(queryFile, "%[^\n]", sBuffer);
fscanf(queryFile, "\n");
}
}
nSampleQueries = j;
fclose(queryFile);
}
//前面那么多，好像就是在申请内存，读文件，读入参数
// Compute the array sampleQBoundaryIndeces that specifies how to
// segregate the sample query points according to their distance
// to NN.
//采用遍历的方法，计算查询点的最近邻（并且距离小于listOfRadii【nRadii】）
sortQueryPointsByRadii(pointsDimension,
nSampleQueries,
sampleQueries,
nPoints,
dataSetPoints,
nRadii,
listOfRadii,
sampleQBoundaryIndeces);
}//if ((nargs < 9) || (strcmp("-c", args[9]) == 0))
RNNParametersT *algParameters = NULL;
PRNearNeighborStructT *nnStructs = NULL;
if (nargs > 9)
{/* 官方lsh文件：10个参数
bin/LSHMain $nDataSet $nQuerySet $dimension $successProbability "$1" "$2" "$3" $m -c
*/
// Additional command-line parameter is specified.
if (strcmp("-c", args[9]) == 0) //-c表示参数优化
{
// Only compute the R-NN DS parameters and output them to stdout.
printf("%d\n", nRadii);
transformMemRatios();
for(IntT i = 0; i < nRadii; i++)
{
// which sample queries to use
Int32T segregatedQStart = (i == 0) ? 0 : sampleQBoundaryIndeces[i - 1];
Int32T segregatedQNumber = nSampleQueries - segregatedQStart;
if (segregatedQNumber == 0)
{
// XXX: not the right answer
segregatedQNumber = nSampleQueries;
segregatedQStart = 0;
}
ASSERT(segregatedQStart < nSampleQueries);
ASSERT(segregatedQStart >= 0);
ASSERT(segregatedQStart + segregatedQNumber <= nSampleQueries);
ASSERT(segregatedQNumber >= 0);
//从文件读取点，然后计算优化后的参数
RNNParametersT optParameters = computeOptimalParameters(listOfRadii[i],
successProbability,
nPoints,
pointsDimension,
dataSetPoints,
segregatedQNumber,
sampleQueries + segregatedQStart,
/*对内存的约束，就体现在这里，
availableTotalMemory总共的内存（传入） - totalAllocatedMemory（使用mallloc分配的）*1=内存上限
然后(L * nPoints > memoryUpperBound / 12 来约束
*/
(MemVarT)((availableTotalMemory - totalAllocatedMemory) * memRatiosForNNStructs[i]));
printRNNParameters(stdout, optParameters);
}
exit(0);
}
else if (strcmp("-p", args[9]) == 0)
{//-p表示从文件读入参数，然后建立结构体
// Read the R-NN DS parameters from the given file and run the
// queries on the constructed data structure.
if (nargs < 10)
{
usage(args[0]);
exit(1);
}
FILE *pFile = fopen(args[10], "rt");
FAILIFWR(pFile == NULL, "Could not open the params file.");
fscanf(pFile, "%d\n", &nRadii);
DPRINTF1("Using the following R-NN DS parameters:\n");
DPRINTF("N radii = %d\n", nRadii);
FAILIF(NULL == (nnStructs = (PRNearNeighborStructT*)MALLOC(nRadii * sizeof(PRNearNeighborStructT))));
FAILIF(NULL == (algParameters = (RNNParametersT*)MALLOC(nRadii * sizeof(RNNParametersT))));
for(IntT i = 0; i < nRadii; i++)
{//默认i=1
algParameters[i] = readRNNParameters(pFile);//从文件读参数
printRNNParameters(stderr, algParameters[i]);
nnStructs[i] = initLSH_WithDataSet(algParameters[i], nPoints, dataSetPoints);
//核心
//初始化整个数据结构 包括整体+l个hash表 +点映射到桶
}
pointsDimension = algParameters[0].dimension;
FREE(listOfRadii);
FAILIF(NULL == (listOfRadii = (RealT*)MALLOC(nRadii * sizeof(RealT))));
for(IntT i = 0; i < nRadii; i++)
{
listOfRadii[i] = algParameters[i].parameterR;
}
}
else
{
// Wrong option.
usage(args[0]);
exit(1);
}
}//if (nargs > 9)
else
{
FAILIF(NULL == (nnStructs = (PRNearNeighborStructT*)MALLOC(nRadii * sizeof(PRNearNeighborStructT))));
// Determine the R-NN DS parameters, construct the DS and run the queries.
transformMemRatios();
for(IntT i = 0; i < nRadii; i++)
{
// XXX: segregate the sample queries...
//建立查询结构，自动优化参数
nnStructs[i] = initSelfTunedRNearNeighborWithDataSet(listOfRadii[i],
successProbability,
nPoints,
pointsDimension,
dataSetPoints,
nSampleQueries,
sampleQueries,
(MemVarT)((availableTotalMemory - totalAllocatedMemory) * memRatiosForNNStructs[i]));
}
} // if (nargs <= 9)
//上面都是根据不同配置，对参数的优化，建立查询结构
DPRINTF1("X\n");
IntT resultSize = nPoints;
PPointT *result = (PPointT*)MALLOC(resultSize * sizeof(*result));
PPointT queryPoint;
FAILIF(NULL == (queryPoint = (PPointT)MALLOC(sizeof(PointT))));
FAILIF(NULL == (queryPoint->coordinates = (RealT*)MALLOC(pointsDimension * sizeof(RealT))));
//读取查询点的文件
FILE *queryFile = fopen(args[7], "rt");
FAILIF(queryFile == NULL);
TimeVarT meanQueryTime = 0;
PPointAndRealTStructT *distToNN = NULL;
for(IntT i = 0; i < nQueries; i++)
{//对于每一个要查询的点
RealT sqrLength = 0;
// read in the query point.
for(IntT d = 0; d < pointsDimension; d++)
{
FSCANF_REAL(queryFile, &(queryPoint->coordinates[d]));
sqrLength += SQR(queryPoint->coordinates[d]);
/*//test
if (d >150 && d<160)
{
printf(" %lf ",queryPoint->coordinates[d]);
}
if ( d==160)
{
printf("原始的文件数据\n");
}
*/
}
queryPoint->sqrLength = sqrLength;
//printRealVector("Query: ", pointsDimension, queryPoint->coordinates);
// get the near neighbors.
IntT nNNs = 0;
for(IntT r = 0; r < nRadii; r++)
{//查询n个近邻点，并计算距离
//查询核心
nNNs = getRNearNeighbors(nnStructs[r], queryPoint, result, resultSize);
printf("Total time for R-NN query at radius %0.6lf (radius no. %d):\t%0.6lf\n", (double)(listOfRadii[r]), r, timeRNNQuery);
meanQueryTime += timeRNNQuery;
if (nNNs > 0)
{
printf("Query point %d: found %d NNs at distance %0.6lf (%dth radius). First %d NNs are:\n",
i, nNNs, (double)(listOfRadii[r]), r, MIN(nNNs, MAX_REPORTED_POINTS));
// compute the distances to the found NN, and sort according to the distance
//计算近邻点和查询点的距离
FAILIF(NULL == (distToNN = (PPointAndRealTStructT*)REALLOC(distToNN, nNNs * sizeof(*distToNN))));
for(IntT p = 0; p < nNNs; p++)
{
distToNN[p].ppoint = result[p];
distToNN[p].real = distance(pointsDimension, queryPoint, result[p]);
}
qsort(distToNN, nNNs, sizeof(*distToNN), comparePPointAndRealTStructT);
// Print the points
for(IntT j = 0; j < MIN(nNNs, MAX_REPORTED_POINTS); j++)
{
ASSERT(distToNN[j].ppoint != NULL);
printf("%09d\tDistance:%0.6lf\n", distToNN[j].ppoint->index, distToNN[j].real);
CR_ASSERT(distToNN[j].real <= listOfRadii[r]);
//DPRINTF("Distance: %lf\n", distance(pointsDimension, queryPoint, result[j]));
//printRealVector("NN: ", pointsDimension, result[j]->coordinates);
}
break;
}
}
if (nNNs == 0)
{
printf("Query point %d: no NNs found.\n", i);
}
}// for(IntT i = 0; i < nQueries; i++)每个点查询
//
if (nQueries > 0)
{
meanQueryTime = meanQueryTime / nQueries;
printf("Mean query time: %0.6lf\n", (double)meanQueryTime);
}
for(IntT i = 0; i < nRadii; i++)
{
freePRNearNeighborStruct(nnStructs[i]);
}
// XXX: should ideally free the other stuff as well.
return 0;
}
/*
The main entry to LSH package. Depending on the command line
parameters, the function computes the R-NN data structure optimal
parameters and/or construct the R-NN data structure and runs the
queries on the data structure.
*/
int main(int nargs, char **args){
if(nargs < 9){
usage(args[0]);
exit(1);
}
//initializeLSHGlobal();
// Parse part of the command-line parameters.
nPoints = atoi(args[1]);
IntT nQueries = atoi(args[2]);
pointsDimension = atoi(args[3]);
successProbability = atof(args[4]);
char* endPtr[1];
RealT thresholdR = strtod(args[5], endPtr); //strtod将字符串转换成浮点数 //r=0.6
//strtod()会扫描参数nptr字符串，跳过前面的空格字符，直到遇上数字或正负符号才开始做转换
//，到出现非数字或字符串结束时('')才结束转换， 并将结果返回。
//若endptr不为NULL，则会将遇到不合条件而终止的nptr中的字符指针由endptr传回。
if (thresholdR == 0 || endPtr[1] == args[5]){ //确保阈值合法
// The value for R is not specified, instead there is a file
// specifying multiple R's.
thresholdR = 0;
// Read in the file
FILE *radiiFile = fopen(args[5], "rt");
FAILIF(radiiFile == NULL);
fscanf(radiiFile, "%d\n", &nRadii);
ASSERT(nRadii > 0);
FAILIF(NULL == (listOfRadii = (RealT*)MALLOC(nRadii * sizeof(RealT))));
FAILIF(NULL == (memRatiosForNNStructs = (RealT*)MALLOC(nRadii * sizeof(RealT))));
for(IntT i = 0; i < nRadii; i++){
FSCANF_REAL(radiiFile, &listOfRadii[i]);
ASSERT(listOfRadii[i] > 0);
FSCANF_REAL(radiiFile, &memRatiosForNNStructs[i]);
ASSERT(memRatiosForNNStructs[i] > 0);
}
}else{
nRadii = 1; //半径的个数为1个
FAILIF(NULL == (listOfRadii = (RealT*)MALLOC(nRadii * sizeof(RealT))));
FAILIF(NULL == (memRatiosForNNStructs = (RealT*)MALLOC(nRadii * sizeof(RealT))));
listOfRadii[0] = thresholdR;
memRatiosForNNStructs[0] = 1;
}
DPRINTF("No. radii: %d\n", nRadii);
//thresholdR = atof(args[5]);
availableTotalMemory = atoll(args[8]);
if (nPoints > MAX_N_POINTS) {
printf("Error: the structure supports at most %d points (%d were specified).\n", MAX_N_POINTS, nPoints);
fprintf(ERROR_OUTPUT, "Error: the structure supports at most %d points (%d were specified).\n", MAX_N_POINTS, nPoints);
exit(1);
}
readDataSetFromFile(args[6]); //数据集的文件名
DPRINTF("Allocated memory (after reading data set): %lld\n", totalAllocatedMemory);
Int32T nSampleQueries = N_SAMPLE_QUERY_POINTS; //样本查询点的个数，100
PPointT sampleQueries[nSampleQueries]; //对查询点编号
Int32T sampleQBoundaryIndeces[nSampleQueries]; //第一个大于半径的点的编号，如果有多个半径的话，就会记录更多
if ((nargs < 9) || (strcmp("-c", args[9]) == 0)){ //计算最优参数
// In this cases, we need to generate a sample query set for
// computing the optimal parameters.
// Generate a sample query set.
FILE *queryFile = fopen(args[7], "rt"); //打开查询集，以只读文本方式打开
if (strcmp(args[7], ".") == 0 || queryFile == NULL || nQueries <= 0){
// Choose several data set points for the sample query points. //如果没有查询点就随机选择几个数据集点作为查询点
for(IntT i = 0; i < nSampleQueries; i++){
sampleQueries[i] = dataSetPoints[genRandomInt(0, nPoints - 1)];
}
}else{
// Choose several actual query points for the sample query points.
nSampleQueries = MIN(nSampleQueries, nQueries); //MIN（100，9）
Int32T sampleIndeces[nSampleQueries]; //定义了一个查询点样本索引数组
for(IntT i = 0; i < nSampleQueries; i++){
////为什么要对查询点索引进行随机变化？ 想把样本查询点控制在一定的范围内，如果查询点过多，则样本点最多取100个查询点。
sampleIndeces[i] = genRandomInt(0, nQueries - 1); //对查询点做了一下顺序的变化，对查询点的索引做随机处理。
}
// 根据你给的比较条件进行快速排序，通过指针的移动实验排序，排序之后的结果仍然放在原数组中，必须自己写一个比较函数
//http://www.slyar.com/blog/stdlib-qsort.html qsort(数组起始地址，数组元素大小，每个元素的大小，函数指针指向比较函数)
qsort(sampleIndeces, nSampleQueries, sizeof(*sampleIndeces), compareInt32T); //qsort，C语言标准库函数，对样本查询点的索引值进行排序
//printIntVector("sampleIndeces: ", nSampleQueries, sampleIndeces);
Int32T j = 0;
for(Int32T i = 0; i < nQueries; i++){
if (i == sampleIndeces[j]){ //如果样本查询点的索引值与实际查询点的索引值一致，读入点
sampleQueries[j] = readPoint(queryFile);
j++;
while (i == sampleIndeces[j]){ //如果样本查询点之后的索引值与实践查询点的索引值一致，则直接将此点的值赋给后面一点的值
sampleQueries[j] = sampleQueries[j - 1]; //覆盖之后索引点的值
j++; //取后面的点
}
}else{
fscanf(queryFile, "%[^\n]", sBuffer);
fscanf(queryFile, "\n");
}
}
nSampleQueries = j;
fclose(queryFile);
}
// Compute the array sampleQBoundaryIndeces that specifies how to
// segregate the sample query points according to their distance
// to NN.
//边界sampleQBoundaryIndeces只会存取一个点的索引，该点的大小为第一个大于半径点的值
sortQueryPointsByRadii(pointsDimension,
nSampleQueries, //查询集的点的个数
sampleQueries, //查询点的集合，函数运行完成后，点的值将以距离数据集合的距离由小到大的顺序排序
nPoints, //数据集点的个数
dataSetPoints, //数据集集合
nRadii, //半径的个数
listOfRadii, //半径的值
sampleQBoundaryIndeces);
}
//之前的东西-c运行的，-p是不会运行的
RNNParametersT *algParameters = NULL;
PRNearNeighborStructT *nnStructs = NULL;
if (nargs > 9) {
// Additional command-line parameter is specified.
if (strcmp("-c", args[9]) == 0) {
// Only compute the R-NN DS parameters and output them to stdout. // 如果是-c，就只计算数据集参数，然后输出
printf("%d\n", nRadii); //打印出半径的个数：1个。 将写入到参数文件中，
transformMemRatios(); //memRatiosForNNstructs,转换内存使用率。假设每个结构为1，每个半径占用的总内存的比率，用于计算内存
for(IntT i = 0; i < nRadii; i++){ //看使用哪个样本查询点
// which sample queries to use
Int32T segregatedQStart = (i == 0) ? 0 : sampleQBoundaryIndeces[i - 1]; //起始点的位置
Int32T segregatedQNumber = nSampleQueries - segregatedQStart; //查询点的个数
if (segregatedQNumber == 0) { //如果计算所得点的个数为0，就查询所有的点，从0到最后
// XXX: not the right answer
segregatedQNumber = nSampleQueries;
segregatedQStart = 0;
}
ASSERT(segregatedQStart < nSampleQueries);
ASSERT(segregatedQStart >= 0);
ASSERT(segregatedQStart + segregatedQNumber <= nSampleQueries);
ASSERT(segregatedQNumber >= 0);
RNNParametersT optParameters = computeOptimalParameters(listOfRadii[i], //计算最优的运行时间，
successProbability,
nPoints,
pointsDimension,
dataSetPoints,
segregatedQNumber,
sampleQueries + segregatedQStart,
(MemVarT)((availableTotalMemory - totalAllocatedMemory) * memRatiosForNNStructs[i])); //比率
////memRatioForNNStructs[i]：近邻结构体每个半径所占用的内存比率，计算能用多少内存
printRNNParameters(stdout, optParameters); //将参数打印出来
}
exit(0);
} else if (strcmp("-p", args[9]) == 0) {
// Read the R-NN DS parameters from the given file and run the
// queries on the constructed data structure.
if (nargs < 10){
usage(args[0]);
exit(1);
}
FILE *pFile = fopen(args[10], "rt"); //读取参数文件，由lsh_computeParas产生
FAILIFWR(pFile == NULL, "Could not open the params file.");
fscanf(pFile, "%d\n", &nRadii); //这里只取了参数文件中的半径，那参数文件中的其他数据怎样被取用的？？
DPRINTF1("Using the following R-NN DS parameters:\n"); //使用R-NN DS(DateSet)参数
DPRINTF("N radii = %d\n", nRadii); //不知道将数据输出到哪里了？？
// printf("Using the following R-NN DS parameters:\n");
// printf("N radii=%d\n",nRadii);
FAILIF(NULL == (nnStructs = (PRNearNeighborStructT*)MALLOC(nRadii * sizeof(PRNearNeighborStructT))));
FAILIF(NULL == (algParameters = (RNNParametersT*)MALLOC(nRadii * sizeof(RNNParametersT))));
for(IntT i = 0; i < nRadii; i++){
algParameters[i] = readRNNParameters(pFile); //将参数信息，输出到屏幕上
// printRNNParameters(stderr, algParameters[i]);@727
//printRNNParameters(stdout,algParameters[i]);
nnStructs[i] = initLSH_WithDataSet(algParameters[i], nPoints, dataSetPoints); //根据用户输入的参数，初始化结构
}
pointsDimension = algParameters[0].dimension;
FREE(listOfRadii);
FAILIF(NULL == (listOfRadii = (RealT*)MALLOC(nRadii * sizeof(RealT))));
for(IntT i = 0; i < nRadii; i++){
listOfRadii[i] = algParameters[i].parameterR;
}
} else{
// Wrong option.
usage(args[0]);
exit(1);
}
} else {
FAILIF(NULL == (nnStructs = (PRNearNeighborStructT*)MALLOC(nRadii * sizeof(PRNearNeighborStructT))));
// Determine the R-NN DS parameters, construct the DS and run the queries.
transformMemRatios();
for(IntT i = 0; i < nRadii; i++){
// XXX: segregate the sample queries...
nnStructs[i] = initSelfTunedRNearNeighborWithDataSet(listOfRadii[i],
successProbability,
nPoints,
pointsDimension,
dataSetPoints,
nSampleQueries,
sampleQueries,
(MemVarT)((availableTotalMemory - totalAllocatedMemory) * memRatiosForNNStructs[i]));
}
}
// DPRINTF1("X\n");@
printf("X\n");
IntT resultSize = nPoints;
PPointT *result = (PPointT*)MALLOC(resultSize * sizeof(*result));
PPointT queryPoint;
FAILIF(NULL == (queryPoint = (PPointT)MALLOC(sizeof(PointT))));
FAILIF(NULL == (queryPoint->coordinates = (RealT*)MALLOC(pointsDimension * sizeof(RealT))));
FILE *queryFile = fopen(args[7], "rt");
FAILIF(queryFile == NULL);
TimeVarT meanQueryTime = 0;
PPointAndRealTStructT *distToNN = NULL;
for(IntT i = 0; i < nQueries; i++){
RealT sqrLength = 0;
// read in the query point.
for(IntT d = 0; d < pointsDimension; d++){
FSCANF_REAL(queryFile, &(queryPoint->coordinates[d]));
sqrLength += SQR(queryPoint->coordinates[d]); //向量到原点的距离
}
queryPoint->sqrLength = sqrLength;
//printRealVector("Query: ", pointsDimension, queryPoint->coordinates);
// get the near neighbors.
IntT nNNs = 0;
for(IntT r = 0; r < nRadii; r++){
nNNs = getRNearNeighbors(nnStructs[r], queryPoint, result, resultSize);
printf("Total time for R-NN query at radius %0.6lf (radius no. %d):\t%0.6lf\n", (double)(listOfRadii[r]), r, timeRNNQuery);
meanQueryTime += timeRNNQuery;
if (nNNs > 0){
printf("Query point %d: found %d NNs at distance %0.6lf (%dth radius). First %d NNs are:\n", i, nNNs, (double)(listOfRadii[r]), r, MIN(nNNs, MAX_REPORTED_POINTS));
// compute the distances to the found NN, and sort according to the distance
FAILIF(NULL == (distToNN = (PPointAndRealTStructT*)REALLOC(distToNN, nNNs * sizeof(*distToNN))));
for(IntT p = 0; p < nNNs; p++){
distToNN[p].ppoint = result[p];
distToNN[p].real = distance(pointsDimension, queryPoint, result[p]);
}
qsort(distToNN, nNNs, sizeof(*distToNN), comparePPointAndRealTStructT); //C语言标准的函数
// Print the points
for(IntT j = 0; j < MIN(nNNs, MAX_REPORTED_POINTS); j++){
ASSERT(distToNN[j].ppoint != NULL);
printf("%09d\tDistance:%0.6lf\n", distToNN[j].ppoint->index, distToNN[j].real); //打印点的坐标
CR_ASSERT(distToNN[j].real <= listOfRadii[r]);
//DPRINTF("Distance: %lf\n", distance(pointsDimension, queryPoint, result[j]));
//printRealVector("NN: ", pointsDimension, result[j]->coordinates);
}
break;
}
}
if (nNNs == 0){
printf("Query point %d: no NNs found.\n", i);
}
}
if (nQueries > 0){
meanQueryTime = meanQueryTime / nQueries;
printf("Mean query time: %0.6lf\n", (double)meanQueryTime);
}
for(IntT i = 0; i < nRadii; i++){
freePRNearNeighborStruct(nnStructs[i]);
}
// XXX: should ideally free the other stuff as well.
return 0;
}
/*
The main entry to LSH package. Depending on the command line
parameters, the function computes the R-NN data structure optimal
parameters and/or construct the R-NN data structure and runs the
queries on the data structure.
*/
int main(int nargs, char **args){
if(nargs < 9){
usage(args[0]);
exit(1);
}
//initializeLSHGlobal();
// Parse part of the command-line parameters.
nPoints = atoi(args[1]);
IntT nQueries = atoi(args[2]);
pointsDimension = atoi(args[3]);
successProbability = atof(args[4]);
char* endPtr[1];
RealT thresholdR = strtod(args[5], endPtr);
if (thresholdR == 0 || endPtr[1] == args[5]){
// The value for R is not specified, instead there is a file
// specifying multiple R's.
thresholdR = 0;
// Read in the file
FILE *radiiFile = fopen(args[5], "rt");
FAILIF(radiiFile == NULL);
fscanf(radiiFile, "%d\n", &nRadii);
ASSERT(nRadii > 0);
FAILIF(NULL == (listOfRadii = (RealT*)MALLOC(nRadii * sizeof(RealT))));
FAILIF(NULL == (memRatiosForNNStructs = (RealT*)MALLOC(nRadii * sizeof(RealT))));
for(IntT i = 0; i < nRadii; i++){
FSCANF_REAL(radiiFile, &listOfRadii[i]);
ASSERT(listOfRadii[i] > 0);
FSCANF_REAL(radiiFile, &memRatiosForNNStructs[i]);
ASSERT(memRatiosForNNStructs[i] > 0);
}
}else{
nRadii = 1;
FAILIF(NULL == (listOfRadii = (RealT*)MALLOC(nRadii * sizeof(RealT))));
FAILIF(NULL == (memRatiosForNNStructs = (RealT*)MALLOC(nRadii * sizeof(RealT))));
listOfRadii[0] = thresholdR;
memRatiosForNNStructs[0] = 1;
}
DPRINTF("No. radii: %d\n", nRadii);
//thresholdR = atof(args[5]);
availableTotalMemory = atoll(args[8]);
if (nPoints > MAX_N_POINTS) { // 104w points
printf("Error: the structure supports at most %d points (%d were specified).\n", MAX_N_POINTS, nPoints);
fprintf(ERROR_OUTPUT, "Error: the structure supports at most %d points (%d were specified).\n", MAX_N_POINTS, nPoints);
exit(1);
}
readDataSetFromFile(args[6]); // read points into data structure
DPRINTF("Allocated memory (after reading data set): %lld\n", totalAllocatedMemory);
Int32T nSampleQueries = N_SAMPLE_QUERY_POINTS;
PPointT sampleQueries[nSampleQueries];
Int32T sampleQBoundaryIndeces[nSampleQueries];
if ((nargs < 9) || (strcmp("-c", args[9]) == 0)){
// In this cases, we need to generate a sample query set for
// computing the optimal parameters.
// Generate a sample query set.
FILE *queryFile = fopen(args[7], "rt");
if (strcmp(args[7], ".") == 0 || queryFile == NULL || nQueries <= 0){
// Choose several data set points for the sample query points.
for(IntT i = 0; i < nSampleQueries; i++){
sampleQueries[i] = dataSetPoints[genRandomInt(0, nPoints - 1)];
}
}else{
// Choose several actual query points for the sample query points.
nSampleQueries = MIN(nSampleQueries, nQueries);
Int32T sampleIndeces[nSampleQueries];
for(IntT i = 0; i < nSampleQueries; i++){
sampleIndeces[i] = genRandomInt(0, nQueries - 1);
}
qsort(sampleIndeces, nSampleQueries, sizeof(*sampleIndeces), compareInt32T);
//printIntVector("sampleIndeces: ", nSampleQueries, sampleIndeces);
Int32T j = 0;
for(Int32T i = 0; i < nQueries; i++){
if (i == sampleIndeces[j]){
sampleQueries[j] = readPoint(queryFile);
j++;
while (i == sampleIndeces[j]){
sampleQueries[j] = sampleQueries[j - 1];
j++;
}
}else{
fscanf(queryFile, "%[^\n]", sBuffer);
fscanf(queryFile, "\n");
}
}
nSampleQueries = j;
fclose(queryFile);
}
// Compute the array sampleQBoundaryIndeces that specifies how to
// segregate the sample query points according to their distance
// to NN.
sortQueryPointsByRadii(pointsDimension,
nSampleQueries,
sampleQueries,
nPoints,
dataSetPoints,
nRadii,
listOfRadii,
sampleQBoundaryIndeces);
}
RNNParametersT *algParameters = NULL;
PRNearNeighborStructT *nnStructs = NULL;
if (nargs > 9) {
// Additional command-line parameter is specified.
if (strcmp("-c", args[9]) == 0) {
// Only compute the R-NN DS parameters and output them to stdout.
printf("%d\n", nRadii);
transformMemRatios();
for(IntT i = 0; i < nRadii; i++){
// which sample queries to use
Int32T segregatedQStart = (i == 0) ? 0 : sampleQBoundaryIndeces[i - 1];
Int32T segregatedQNumber = nSampleQueries - segregatedQStart;
if (segregatedQNumber == 0) {
// XXX: not the right answer
segregatedQNumber = nSampleQueries;
segregatedQStart = 0;
}
ASSERT(segregatedQStart < nSampleQueries);
ASSERT(segregatedQStart >= 0);
ASSERT(segregatedQStart + segregatedQNumber <= nSampleQueries);
ASSERT(segregatedQNumber >= 0);
RNNParametersT optParameters = computeOptimalParameters(listOfRadii[i],
successProbability,
nPoints,
pointsDimension,
dataSetPoints,
segregatedQNumber,
sampleQueries + segregatedQStart,
(MemVarT)((availableTotalMemory - totalAllocatedMemory) * memRatiosForNNStructs[i]));
printRNNParameters(stdout, optParameters);
}
exit(0);
} else if (strcmp("-p", args[9]) == 0) {
// Read the R-NN DS parameters from the given file and run the
// queries on the constructed data structure.
if (nargs < 10){
usage(args[0]);
exit(1);
}
FILE *pFile = fopen(args[10], "rt");
FAILIFWR(pFile == NULL, "Could not open the params file.");
fscanf(pFile, "%d\n", &nRadii);
DPRINTF1("Using the following R-NN DS parameters:\n");
DPRINTF("N radii = %d\n", nRadii);
FAILIF(NULL == (nnStructs = (PRNearNeighborStructT*)MALLOC(nRadii * sizeof(PRNearNeighborStructT))));
FAILIF(NULL == (algParameters = (RNNParametersT*)MALLOC(nRadii * sizeof(RNNParametersT))));
for(IntT i = 0; i < nRadii; i++){
algParameters[i] = readRNNParameters(pFile);
printRNNParameters(stderr, algParameters[i]);
nnStructs[i] = initLSH_WithDataSet(algParameters[i], nPoints, dataSetPoints);
}
pointsDimension = algParameters[0].dimension;
FREE(listOfRadii);
FAILIF(NULL == (listOfRadii = (RealT*)MALLOC(nRadii * sizeof(RealT))));
for(IntT i = 0; i < nRadii; i++){
listOfRadii[i] = algParameters[i].parameterR;
}
} else{
// Wrong option.
usage(args[0]);
exit(1);
}
} else {
FAILIF(NULL == (nnStructs = (PRNearNeighborStructT*)MALLOC(nRadii * sizeof(PRNearNeighborStructT))));
// Determine the R-NN DS parameters, construct the DS and run the queries.
transformMemRatios();
for(IntT i = 0; i < nRadii; i++){
// XXX: segregate the sample queries...
nnStructs[i] = initSelfTunedRNearNeighborWithDataSet(listOfRadii[i],
successProbability,
nPoints,
pointsDimension,
dataSetPoints,
nSampleQueries,
sampleQueries,
(MemVarT)((availableTotalMemory - totalAllocatedMemory) * memRatiosForNNStructs[i]));
}
}
DPRINTF1("X\n");
IntT resultSize = nPoints;
PPointT *result = (PPointT*)MALLOC(resultSize * sizeof(*result));
PPointT queryPoint;
FAILIF(NULL == (queryPoint = (PPointT)MALLOC(sizeof(PointT))));
FAILIF(NULL == (queryPoint->coordinates = (RealT*)MALLOC(pointsDimension * sizeof(RealT))));
FILE *queryFile = fopen(args[7], "rt");
FAILIF(queryFile == NULL);
TimeVarT meanQueryTime = 0;
PPointAndRealTStructT *distToNN = NULL;
for(IntT i = 0; i < nQueries; i++){
RealT sqrLength = 0;
// read in the query point.
for(IntT d = 0; d < pointsDimension; d++){
FSCANF_REAL(queryFile, &(queryPoint->coordinates[d]));
sqrLength += SQR(queryPoint->coordinates[d]);
}
queryPoint->sqrLength = sqrLength;
//printRealVector("Query: ", pointsDimension, queryPoint->coordinates);
// get the near neighbors.
IntT nNNs = 0;
for(IntT r = 0; r < nRadii; r++){
nNNs = getRNearNeighbors(nnStructs[r], queryPoint, result, resultSize);
printf("Total time for R-NN query at radius %0.6lf (radius no. %d):\t%0.6lf\n", (double)(listOfRadii[r]), r, timeRNNQuery);
meanQueryTime += timeRNNQuery;
if (nNNs > 0){
printf("Query point %d: found %d NNs at distance %0.6lf (%dth radius). First %d NNs are:\n", i, nNNs, (double)(listOfRadii[r]), r, MIN(nNNs, MAX_REPORTED_POINTS));
// compute the distances to the found NN, and sort according to the distance
FAILIF(NULL == (distToNN = (PPointAndRealTStructT*)REALLOC(distToNN, nNNs * sizeof(*distToNN))));
for(IntT p = 0; p < nNNs; p++){
distToNN[p].ppoint = result[p];
distToNN[p].real = distance(pointsDimension, queryPoint, result[p]);
}
qsort(distToNN, nNNs, sizeof(*distToNN), comparePPointAndRealTStructT);
// Print the points
for(IntT j = 0; j < MIN(nNNs, MAX_REPORTED_POINTS); j++){
ASSERT(distToNN[j].ppoint != NULL);
printf("%09d\tDistance:%0.6lf\n", distToNN[j].ppoint->index, distToNN[j].real);
CR_ASSERT(distToNN[j].real <= listOfRadii[r]);
//DPRINTF("Distance: %lf\n", distance(pointsDimension, queryPoint, result[j]));
//printRealVector("NN: ", pointsDimension, result[j]->coordinates);
}
break;
}
}
if (nNNs == 0){
printf("Query point %d: no NNs found.\n", i);
}
}
if (nQueries > 0){
meanQueryTime = meanQueryTime / nQueries;
printf("Mean query time: %0.6lf\n", (double)meanQueryTime);
}
for(IntT i = 0; i < nRadii; i++){
freePRNearNeighborStruct(nnStructs[i]);
}
// XXX: should ideally free the other stuff as well.
return 0;
}
// Determines the run-time coefficients of the different parts of the
// query algorithm. Values that are computed and returned are
// <lshPrecomp>, <uhashOver>, <distComp>. <lshPrecomp> is the time for
// pre-computing one function from the LSH family. <uhashOver> is the
// time for getting a bucket from a hash table (of buckets).<distComp>
// is the time to compute one distance between two points. These times
// are computed by constructing a R-NN DS on a sample data set and
// running a sample query set on it.
void determineRTCoefficients(RealT thresholdR,
RealT successProbability,
BooleanT useUfunctions,
IntT typeHT,
IntT dimension,
Int32T nPoints,
PPointT *realData,
RealT &lshPrecomp,
RealT &uhashOver,
RealT &distComp){
// use a subset of the original data set.
// there is not much theory behind the formula below.
IntT n = nPoints / 50;
if (n < 100) {
n = nPoints;
}
if (n > 10000) {
n = 10000;
}
// Initialize the data set to use.
PPointT *dataSet;
FAILIF(NULL == (dataSet = (PPointT*)MALLOC(n * sizeof(PPointT))));
for(IntT i = 0; i < n; i++){
dataSet[i] = realData[genRandomInt(0, nPoints - 1)];
}
IntT hashTableSize = n;
RNNParametersT algParameters;
algParameters.parameterR = thresholdR;
algParameters.successProbability = successProbability;
algParameters.dimension = dimension;
#ifdef USE_L1_DISTANCE
algParameters.parameterR2 = thresholdR;
#else
algParameters.parameterR2 = SQR(thresholdR);
#endif
algParameters.useUfunctions = useUfunctions;
algParameters.parameterK = 16;
algParameters.parameterW = PARAMETER_W_DEFAULT;
algParameters.parameterT = n;
algParameters.typeHT = typeHT;
if (algParameters.useUfunctions){
algParameters.parameterM = computeMForULSH(algParameters.parameterK, algParameters.successProbability);
algParameters.parameterL = algParameters.parameterM * (algParameters.parameterM - 1) / 2;
}else{
algParameters.parameterM = computeLfromKP(algParameters.parameterK, algParameters.successProbability);
algParameters.parameterL = algParameters.parameterM;
}
// FAILIF(NULL == (dataSet = (PPointT*)MALLOC(n * sizeof(PPointT))));
// for(IntT i = 0; i < n; i++){
// FAILIF(NULL == (dataSet[i] = (PPointT)MALLOC(sizeof(PointT))));
// FAILIF(NULL == (dataSet[i]->coordinates = (RealT*)MALLOC(dimension * sizeof(RealT))));
// dataSet[i]->index = i;
// sqrLength = 0;
// for(IntT d = 0; d < dimension; d++){
// if (i == 0) {
// dataSet[i]->coordinates[d] = genUniformRandom(-100, 100);
// }else{
// dataSet[i]->coordinates[d] = dataSet[0]->coordinates[d];
// }
// sqrLength += SQR(dataSet[i]->coordinates[d]);
// }
// dataSet[i]->sqrLength = sqrLength;
// }
// switch on timing
BooleanT tempTimingOn = timingOn;
timingOn = TRUE;
// initialize result arrays
PPointT *result = NULL;
IntT resultSize = 0;
IntT nNNs;
IntT nSucReps;
do{
// create the test structure
PRNearNeighborStructT nnStruct;
switch(algParameters.typeHT){
case HT_LINKED_LIST:
nnStruct = initLSH(algParameters, n);
// add points to the test structure
for(IntT i = 0; i < n; i++){
addNewPointToPRNearNeighborStruct(nnStruct, realData[i]);
}
break;
case HT_HYBRID_CHAINS:
nnStruct = initLSH_WithDataSet(algParameters, n, dataSet);
break;
default:
ASSERT(FALSE);
}
// query point
PPointT queryPoint;
// FAILIF(NULL == (queryPoint = (PPointT)MALLOC(sizeof(PointT))));
// FAILIF(NULL == (queryPoint->coordinates = (RealT*)MALLOC(dimension * sizeof(RealT))));
// RealT sqrLength = 0;
// for(IntT i = 0; i < dimension; i++){
// queryPoint->coordinates[i] = dataSet[0]->coordinates[i];
// //queryPoint->coordinates[i] = 0.1;
// sqrLength += SQR(queryPoint->coordinates[i]);
// }
//queryPoint->coordinates[0] = dataPoint->coordinates[0] + 0.0001;
//queryPoint->sqrLength = sqrLength;
// reset the R parameter so that there are no NN neighbors.
setResultReporting(nnStruct, FALSE);
//DPRINTF1("X\n");
lshPrecomp = 0;
uhashOver = 0;
distComp = 0;
IntT nReps = 20;
nSucReps = 0;
for(IntT rep = 0; rep < nReps; rep++){
queryPoint = realData[genRandomInt(0, nPoints - 1)];
timeComputeULSH = 0;
timeGetBucket = 0;
timeCycleBucket = 0;
nOfDistComps = 0;
nNNs = getNearNeighborsFromPRNearNeighborStruct(nnStruct, queryPoint, result, resultSize);
//DPRINTF("Time to compute LSH: %0.6lf\n", timeComputeULSH);
//DPRINTF("Time to get bucket: %0.6lf\n", timeGetBucket);
//DPRINTF("Time to cycle through buckets: %0.9lf\n", timeCycleBucket);
//DPRINTF("N of dist comp: %d\n", nOfDistComps);
ASSERT(nNNs == 0);
if (nOfDistComps >= MIN(n / 10, 100)){
nSucReps++;
lshPrecomp += timeComputeULSH / algParameters.parameterK / algParameters.parameterM;
uhashOver += timeGetBucket / algParameters.parameterL;
distComp += timeCycleBucket / nOfDistComps;
}
}
if (nSucReps >= 5){
lshPrecomp /= nSucReps;
uhashOver /= nSucReps;
distComp /= nSucReps;
DPRINTF1("RT coeffs computed.\n");
}else{
algParameters.parameterR *= 2; // double the radius and repeat
DPRINTF1("Could not determine the RT coeffs. Repeating.\n");
}
freePRNearNeighborStruct(nnStruct);
}while(nSucReps < 5);
FREE(dataSet);
FREE(result);
timingOn = tempTimingOn;
}