110 lines
3.3 KiB
JavaScript
110 lines
3.3 KiB
JavaScript
function findPivots(dataSet, sampleSet, remainderSet) {
|
|
var distance = calculateDistancePoker;
|
|
// Initialize
|
|
|
|
var numBuckets = Math.floor(Math.sqrt(sampleSet.length)),
|
|
numPivots = Math.floor(Math.sqrt(sampleSet.length)),
|
|
parents = [],
|
|
maxDists = [],
|
|
bucketWidths = [],
|
|
pivotsBuckets = [];
|
|
|
|
var pivots = createRandomSample(dataSet, sampleSet.length, numPivots);
|
|
|
|
for (var i = 0; i < numPivots; i++) {
|
|
pivotsBuckets[i] = [];
|
|
for (var j = 0; j < numBuckets; j++) {
|
|
pivotsBuckets[i][j] = [];
|
|
}
|
|
}
|
|
|
|
// Pre-processing
|
|
var fullDists = []
|
|
for (var i = 0; i < sampleSet.length; i++) {
|
|
fullDists[i] = [];
|
|
}
|
|
|
|
for (var j = 0, maxDist = -1; j < numPivots; j++) {
|
|
var c1 = pivots[j];
|
|
for (var i = 0; i < sampleSet.length; i++) {
|
|
var c2 = sampleSet[i];
|
|
if (c1 !== c2) {
|
|
var dist = distance(c1, c2);
|
|
// console.log(dist, c1, c2);
|
|
if (dist > maxDist) {
|
|
maxDist = dist;
|
|
}
|
|
fullDists[i][j] = dist;
|
|
} else {
|
|
fullDists[i][j] = 0.0001;
|
|
}
|
|
}
|
|
maxDists.push(maxDist);
|
|
bucketWidths.push(maxDist / numBuckets);
|
|
}
|
|
|
|
// console.log(fullDists);
|
|
|
|
for (var j = 0; j < numPivots; j++) {
|
|
var bucketWidth = bucketWidths[j];
|
|
for (var i = 0; i < sampleSet.length; i++) {
|
|
var tmp = pivotsBuckets[j][Math.floor((fullDists[i][j] - 0.0001) / bucketWidth)];
|
|
// pivotsBuckets[j][Math.floor((fullDists[i][j] - 0.0001) / bucketWidth)].push(sampleSet[i]);
|
|
// console.log(tmp, i, j, bucketWidth, Math.floor((fullDists[i][j] - 0.0001) / bucketWidth));
|
|
tmp.push(sampleSet[i]);
|
|
}
|
|
}
|
|
|
|
// Find parents
|
|
for (var r = 0, bNum, minIndex; r < remainderSet.length; r++) {
|
|
var node = remainderSet[r];
|
|
var clDist = Number.MAX_VALUE;
|
|
for (var p = 0; p < numPivots; p++) {
|
|
var comp = pivots[p];
|
|
var bucketWidth = bucketWidths[p];
|
|
if (node !== comp) {
|
|
var dist = distance(node, comp);
|
|
bNum = Math.floor((dist - 0.0001) / bucketWidth);
|
|
if (bNum >= numBuckets) {
|
|
bNum = numBuckets - 1;
|
|
} else if (bNum < 0) {
|
|
bNum = 0;
|
|
}
|
|
var bucketContents = pivotsBuckets[p][bNum];
|
|
for (var w = 0; w < bucketContents.length; w++) {
|
|
var c1 = bucketContents[w];
|
|
if (c1 != node) {
|
|
dist = distance(c1, node);
|
|
if (dist <= clDist) {
|
|
clDist = dist;
|
|
minIndex = bucketContents[w];
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
parents.push(minIndex);
|
|
}
|
|
return parents;
|
|
}
|
|
|
|
function createRandomSample(nodes, max, size) {
|
|
var randElements = [];
|
|
|
|
for (var i = 0; i < size; ++i) {
|
|
// Stop when no new elements can be found.
|
|
if (randElements.size >= nodes.length) {
|
|
break;
|
|
}
|
|
var rand = Math.floor((Math.random() * max));
|
|
// If the rand is already in random list or in exclude list
|
|
// ignore it and get a new value.
|
|
while (randElements.includes(rand)) {
|
|
rand = Math.floor((Math.random() * max));
|
|
}
|
|
randElements.push(nodes[rand]);
|
|
}
|
|
|
|
return randElements;
|
|
}
|