Related
So I've been scouring the web to find a way to do this but nothing I've found fits the exact solution we are looking for.
I have an app that stores float numbers in a circular buffer. The circular buffer class can be found here https://www.npmjs.com/package/circular-buffer.
In my app new numbers are coming in every few miliseconds and the buffer holds around 60K values.
For the purpose of this question though I created a circular buffer of 10 with a stream of 100 randomly generated numbers to simulate the incoming data. This is the line that generates the simulated stream:
for (let i = 0; i < valuesToEnqueueForDemoPurposes.length; i++) {
With my current setup, it is taking the cpu too much time to convert the circular buffer to an array and then calculate its min, max, min position / index number, max position / index number and standard deviations (but the stddev is not the focus of this question).
Here is my current code:
stats = require("stats-lite");
var CircularBuffer = require("circular-buffer");
var circularBuffer10 = new CircularBuffer(10);
var valuesToEnqueueForDemoPurposes = Array.from(Array(100)).map(x=>Math.random() * 1000)
for (let i = 0; i < valuesToEnqueueForDemoPurposes.length; i++) {
var newValue = valuesToEnqueueForDemoPurposes[i];
circularBuffer10.enq(newValue);
let valuesArray = circularBuffer10.toarray();
var maxIndex = valuesArray.reduce((iMax, x, i, arr) => x > arr[iMax] ? i : iMax, 0);
var minIndex = valuesArray.reduce((iMin, x, i, arr) => x < arr[iMin] ? i : iMin, 0);
var max = valuesArray[maxIndex];
var min = valuesArray[minIndex];
var standardDeviation = stats.stdev(valuesArray);
console.log(maxIndex);
console.log(max);
console.log(minIndex);
console.log(min);
console.log(standardDeviation + "\n\n");
}
So I was wondering if it was possible to optimize this code with different data structures.
The closest answer I've found to solve this issue is from this SO answer: https://stackoverflow.com/a/48610455
It uses:
a queue of N items
a Min / Max Heap to track the min / max item.
A hash map to track the frequency of each item.
But the problem with this solution is that the heap is always growing and with the amount of differing incoming data I receive, this would cause a serious problem. And it also only calculates the maximum.
Also found this c++ solution but it is only for a normal queue, a max (not min) and I wasn't able to reproduce in javascript:
https://www.geeksforgeeks.org/design-a-queue-data-structure-to-get-minimum-or-maximum-in-o1-time/
Does anyone know if it would be possible, using whatever combination of data structures, to find the Max or Min in O(1) for this type of scenario (with or without circular buffers)?
Thanks to #thomas's advice I was able to alter the circular buffer class I was using so that the sum, mean,max, min and standard deviations are calculated on average at O(1) but at the worst O(N). Worked like a charm for the performance I needed.
Please note that for my purposes I have only altered the "unshift" method of the CBuffer circular buffer class . So the other methods won't be updating the max, min and standard deviations correctly. Here is the link to the jsfiddle:
https://jsfiddle.net/29f4an7s/
And here is my testing code:
// A standard deviation object constructor. Running deviation (avoid growing arrays) which
// is round-off error resistant. Based on an algorithm found in a Knuth book.
class StandardDeviation {
constructor() {
this.v = 0;
this.w = 0;
this.S = 0;
this.count = 0;
}
// Add a measurement. Also calculates updates to stepwise parameters which are later used
// to determine sigma.
add(measurement) {
this.count += 1;
this.w = this.v;
this.v = this.v + (measurement - this.v) / this.count;
this.S = this.S + (measurement - this.w) * (measurement - this.v);
}
// Performs the final step needed to get the standard deviation and returns it.
get() {
if (this.count < 2) {
// There are less measurements accumulated than necessary to perform computation
return 0.0;
} else {
return Math.sqrt(this.S / (this.count));
}
}
// Replaces the value x currently present in this sample with the
// new value y. In a sliding window, x is the value that
// drops out and y is the new value entering the window. The sample
// count remains constant with this operation.
replace(x, y) {
const deltaYX = y - x;
const deltaX = x - this.v;
const deltaY = y - this.v;
this.v = this.v + deltaYX / this.count;
const deltaYp = y - this.v;
const countMinus1 = this.count - 1;
this.S = this.S - this.count / countMinus1 * (deltaX * deltaX - deltaY * deltaYp) - deltaYX * deltaYp / countMinus1;
}
// Remove a measurement. Also calculates updates to stepwise parameters which are later used
// to determine sigma.
remove(x) {
this.w = (this.count * this.v - x) / (this.count - 1);
this.S -= (x - this.v) * (x - this.w);
this.v = this.w;
this.count -= 1;
}
}
function CBuffer() {
// handle cases where "new" keyword wasn't used
if (!(this instanceof CBuffer)) {
// multiple conditions need to be checked to properly emulate Array
if (arguments.length > 1 || typeof arguments[0] !== 'number') {
return CBuffer.apply(new CBuffer(arguments.length), arguments);
} else {
return new CBuffer(arguments[0]);
}
}
// if no arguments, then nothing needs to be set
if (arguments.length === 0)
throw new Error('Missing Argument: You must pass a valid buffer size');
// this is the same in either scenario
this.length = this.start = 0;
// set to callback fn if data is about to be overwritten
this.overflow = null;
// set to callback fn if data is about to be overwritten
this.maxIndex = null;
this.minIndex = null;
this.max = null;
this.min = null;
this.sum = null;
this.mean = null;
this.standardDeviation = new StandardDeviation();
// emulate Array based on passed arguments
if (arguments.length > 1 || typeof arguments[0] !== 'number') {
this.data = new Array(arguments.length);
this.end = (this.size = arguments.length) - 1;
this.push.apply(this, arguments);
} else {
this.data = new Array(arguments[0]);
this.end = (this.size = arguments[0]) - 1;
}
// need to `return this` so `return CBuffer.apply` works
return this;
}
function defaultComparitor(a, b) {
return a == b ? 0 : a > b ? 1 : -1;
}
function mod(n, m) {
return ((n % m) + m) % m;
}
CBuffer.prototype = {
// properly set constructor
constructor : CBuffer,
/* mutator methods */
// pop last item
pop : function () {
var item;
if (this.length === 0) return;
item = this.data[this.end];
// remove the reference to the object so it can be garbage collected
delete this.data[this.end];
this.end = (this.end - 1 + this.size) % this.size;
this.length--;
return item;
},
// push item to the end
push : function () {
var i = 0;
var returnOverflow = false;
// check if overflow is set, and if data is about to be overwritten
if (this.overflow && this.length + arguments.length > this.size) {
// call overflow function and send data that's about to be overwritten
for (; i < this.length + arguments.length - this.size; i++) {
returnOverflow = this.data[(this.end + i + 1) % this.size];
// this.overflow(this.data[(this.end + i + 1) % this.size], this);
}
}
// push items to the end, wrapping and erasing existing items
// using arguments variable directly to reduce gc footprint
for (i = 0; i < arguments.length; i++) {
this.data[(this.end + i + 1) % this.size] = arguments[i];
}
// recalculate length
if (this.length < this.size) {
if (this.length + i > this.size) this.length = this.size;
else this.length += i;
}
// recalculate end
this.end = (this.end + i) % this.size;
// recalculate start
this.start = (this.size + this.end - this.length + 1) % this.size;
// return number current number of items in CBuffer
return returnOverflow;
},
// reverse order of the buffer
reverse : function () {
var i = 0,
tmp;
for (; i < ~~(this.length / 2); i++) {
tmp = this.data[(this.start + i) % this.size];
this.data[(this.start + i) % this.size] = this.data[(this.start + (this.length - i - 1)) % this.size];
this.data[(this.start + (this.length - i - 1)) % this.size] = tmp;
}
return this;
},
// rotate buffer to the left by cntr, or by 1
rotateLeft : function (cntr) {
if (typeof cntr === 'undefined') cntr = 1;
if (typeof cntr !== 'number') throw new Error("Argument must be a number");
while (--cntr >= 0) {
this.push(this.shift());
}
return this;
},
// rotate buffer to the right by cntr, or by 1
rotateRight : function (cntr) {
if (typeof cntr === 'undefined') cntr = 1;
if (typeof cntr !== 'number') throw new Error("Argument must be a number");
while (--cntr >= 0) {
this.unshift(this.pop());
}
return this;
},
// remove and return first item
shift : function () {
var item;
// check if there are any items in CBuff
if (this.length === 0) return;
// store first item for return
item = this.data[this.start];
// recalculate start of CBuffer
this.start = (this.start + 1) % this.size;
// decrement length
this.length--;
return item;
},
// sort items
sort : function (fn) {
this.data.sort(fn || defaultComparitor);
this.start = 0;
this.end = this.length - 1;
return this;
},
// add item to beginning of buffer
unshift : function () {
var i = 0;
var returnOverflow = false;
if (this.length == this.size) {
returnOverflow = this.last();
}
for (i = 0; i < arguments.length; i++) {
this.data[(this.size + this.start - (i % this.size) - 1) % this.size] = arguments[i];
}
if (this.size - this.length - i < 0) {
this.end += this.size - this.length - i;
if (this.end < 0) this.end = this.size + (this.end % this.size);
}
if (this.length < this.size) {
if (this.length + i > this.size) this.length = this.size;
else this.length += i;
}
this.start -= arguments.length;
if (this.start < 0) this.start = this.size + (this.start % this.size);
this.recalculateMaxMin(arguments[0], returnOverflow);
this.sum += arguments[0];
if (returnOverflow) {
this.sum -= returnOverflow;
this.standardDeviation.replace(returnOverflow, arguments[0])
}
else {
this.standardDeviation.add(arguments[0]);
}
this.mean = this.sum / this.length;
return returnOverflow;
},
/* accessor methods */
// return index of first matched element
indexOf : function (arg, idx) {
if (!idx) idx = 0;
for (; idx < this.length; idx++) {
if (this.data[(this.start + idx) % this.size] === arg) return idx;
}
return -1;
},
// return last index of the first match
lastIndexOf : function (arg, idx) {
if (!idx) idx = this.length - 1;
for (; idx >= 0; idx--) {
if (this.data[(this.start + idx) % this.size] === arg) return idx;
}
return -1;
},
// return the index an item would be inserted to if this
// is a sorted circular buffer
sortedIndex : function(value, comparitor, context) {
comparitor = comparitor || defaultComparitor;
var isFull = this.length === this.size,
low = this.start,
high = isFull ? this.length - 1 : this.length;
// Tricky part is finding if its before or after the pivot
// we can get this info by checking if the target is less than
// the last item. After that it's just a typical binary search.
if (low && comparitor.call(context, value, this.data[high]) > 0) {
low = 0, high = this.end;
}
while (low < high) {
var mid = (low + high) >>> 1;
if (comparitor.call(context, value, this.data[mid]) > 0) low = mid + 1;
else high = mid;
}
return !isFull ? low :
// http://stackoverflow.com/a/18618273/1517919
(((low - this.start) % this.length) + this.length) % this.length;
},
/* iteration methods */
// check every item in the array against a test
every : function (callback, context) {
var i = 0;
for (; i < this.length; i++) {
if (!callback.call(context, this.data[(this.start + i) % this.size], i, this))
return false;
}
return true;
},
// loop through each item in buffer
// TODO: figure out how to emulate Array use better
forEach : function (callback, context) {
var i = 0;
for (; i < this.length; i++) {
callback.call(context, this.data[(this.start + i) % this.size], i, this);
}
},
// construct new CBuffer of same length, apply map function, and return new CBuffer
map : function (callback, context) {
var outCBuffer = new CBuffer(this.size);
for (var i = 0; i < this.length; i++) {
var n = (this.start + i) % this.size;
outCBuffer.push(callback.call(context, this.data[n], i, this));
}
return outCBuffer;
},
// check items agains test until one returns true
// TODO: figure out how to emulate Array use better
some : function (callback, context) {
var i = 0;
for (; i < this.length; i++) {
if (callback.call(context, this.data[(this.start + i) % this.size], i, this))
return true;
}
return false;
},
// calculate the average value of a circular buffer
avg : function () {
return this.length == 0 ? 0 : (this.sum() / this.length);
},
// loop through each item in buffer and calculate sum
sum : function () {
var index = this.length;
var s = 0;
while (index--) s += this.data[index];
return s;
},
// loop through each item in buffer and calculate sum
getMaxPosition : function () {
// return 0
return (this.start + this.start + this.maxIndex) % this.size;
},
// loop through each item in buffer and calculate sum
getStandardDeviation : function () {
// return 0
return this.standardDeviation.get();
},
// loop through each item in buffer and calculate sum
getMinPosition : function () {
// return 0
return (this.start + this.start + this.minIndex) % this.size;
},
recalculateMaxMin : function (newValue, returnOverflow) {
if (this.length == 1) {
this.max = newValue;
this.maxIndex = this.start;
this.min = newValue;
this.minIndex = this.start;
return;
}
// Max / Mins
if (newValue > this.max) {
this.max = newValue;
this.maxIndex = this.start;
}
if (newValue < this.min) {
this.min = newValue;
this.minIndex = this.start;
}
// If overflow max or min recalculate
if (
returnOverflow && (returnOverflow >= this.max || returnOverflow <= this.min)
) {
this.maxIndex = 0;
this.minIndex = 0;
this.max = this.data[0];
this.min = this.data[0];
for (let i = 0; i < this.length; i++) {
if (this.data[i] > this.max) {
this.maxIndex = i;
this.max = this.data[i];
}
if (this.data[i] < this.min) {
this.minIndex = i;
this.min = this.data[i];
}
}
}
},
// loop through each item in buffer and calculate median
median : function () {
if (this.length === 0)
return 0;
var values = this.slice().sort(defaultComparitor);
var half = Math.floor(values.length / 2);
if(values.length % 2)
return values[half];
else
return (values[half-1] + values[half]) / 2.0;
},
/* utility methods */
// reset pointers to buffer with zero items
// note: this will not remove values in cbuffer, so if for security values
// need to be overwritten, run `.fill(null).empty()`
empty : function () {
var i = 0;
this.length = this.start = 0;
this.end = this.size - 1;
return this;
},
// fill all places with passed value or function
fill : function (arg) {
var i = 0;
if (typeof arg === 'function') {
while(this.data[i] = arg(), ++i < this.size);
} else {
while(this.data[i] = arg, ++i < this.size);
}
// reposition start/end
this.start = 0;
this.end = this.size - 1;
this.length = this.size;
return this;
},
// return first item in buffer
first : function () {
return this.data[this.start];
},
// return last item in buffer
last : function () {
return this.data[this.end];
},
// return specific index in buffer
get : function (arg) {
return this.data[mod(this.start + arg, this.size)];
},
isFull : function (arg) {
return this.size === this.length;
},
// set value at specified index
set : function (idx, arg) {
return this.data[(this.start + idx) % this.size] = arg;
},
// return clean array of values
toArray : function () {
return this.slice();
},
// return a string based on the array
join : function(separator) {
if (!separator) separator = ',';
var outString = new String(this.data[0]);
for (var i = 1; i < this.length; i++) {
var n = (this.start + i) % this.size;
outString = outString.concat(separator, this.data[i]);
}
return outString;
},
// slice the buffer to an arraay
slice : function (start, end) {
var size = this.length;
start = +start || 0;
if (start < 0) {
if (start >= end)
return [];
start = (-start > size) ? 0 : size + start;
}
if (end == null || end > size)
end = size;
else if (end < 0)
end += size;
else
end = +end || 0;
size = start < end ? end - start : 0;
var result = Array(size);
for (var index = 0; index < size; index++) {
result[index] = this.data[(this.start + start + index) % this.size];
}
return result;
}
};
var bufferLength = 3;
var numbersToGenerate = 10;
var circularBufferN = new CBuffer(bufferLength);
var valuesToEnqueueForDemoPurposes = Array.from(Array(numbersToGenerate)).map(x=>Math.random() * 1000)
for (let i = 0; i < valuesToEnqueueForDemoPurposes.length; i++) {
var newValue = valuesToEnqueueForDemoPurposes[i];
console.log("\n\nNEW VALUE****************************************************************:");
console.log(newValue);
console.log("STARTING UNSHIFT:");
console.log(circularBufferN.unshift(newValue));
let valuesArray = circularBufferN.data;
var maxIndex = circularBufferN.maxIndex;
var minIndex = circularBufferN.minIndex;
var max = valuesArray[maxIndex];
var min = valuesArray[minIndex];
console.log("Max Index");
console.log(maxIndex);
console.log("Max:");
console.log(max);
console.log("Min Index:");
console.log(minIndex);
console.log("Min:");
console.log(min);
console.log("Start:");
console.log(circularBufferN.start);
console.log("ORDERED ARRAY:");
console.log(circularBufferN.toArray());
console.log("Max Position:");
console.log(circularBufferN.getMaxPosition());
console.log("Min Position:");
console.log(circularBufferN.getMinPosition());
console.log('Sum:');
console.log(circularBufferN.sum);
console.log("mean:");
console.log(circularBufferN.mean);
console.log("Derived Standard Deviation");
console.log(circularBufferN.getStandardDeviation());
}
What I'm doing: I'm developing a mobile dictionary app for a number of languages
How I'm doing it: Using ionic framework with combination of some angular and some pure js (imported from a working online dictionary site of the same languages)
The problem: Our search function is an approximate search that uses a Levenstein distance calculator to rank all entries in the dictionary with respect to the query form. When the dictionary has up to 1,500 words, this isn't a problem at all on phones, but when the dictionary has around 10,000 words, there is about a 5-8 second delay before results are shown, despite it being instantaneous on a web browser using "ionic serve". When I run firebug, the javascript that takes the longest time to process are the distance calculations, so my working assumption is that this is where I should start, but I'm open to any suggestions at all.
Here's the distance calculator:
/**
* editDistance.js
*
* A simple Levenshtein distance calculator, except weighted such
* that insertions at the beginning and deletions at the end cost less.
*
* AUTHOR: Pat Littell
* LAST UPDATED: 2015-05-16
*/
var distanceCalculator = {
insertionCost : 1.0,
deletionCost : 1.0,
insertionAtBeginningCost : 0.11,
deletionAtEndCost : 0.1,
substitutionCost : 1.0,
getEditDistance : function(a, b) {
if(a.length === 0) return b.length;
if(b.length === 0) return a.length;
var matrix = [];
// var currentInsertionCost, currentDeletionCost, currentSubstitutionCost = 0;
// increment along the first column of each row
var i;
for(i = 0; i <= b.length; i++){
matrix[i] = [i * this.insertionAtBeginningCost];
}
// increment each column in the first row
var j;
for(j = 0; j <= a.length; j++){
matrix[0][j] = j;
}
// Fill in the rest of the matrix
for(i = 1; i <= b.length; i++){
for(j = 1; j <= a.length; j++){
currentInsertionCost = matrix[i][j-1] + this.insertionCost;
currentSubstitutionCost = matrix[i-1][j-1] + (b.charAt(i-1) != a.charAt(j-1) ? this.substitutionCost : 0);
currentDeletionCost = matrix[i-1][j] + (j==a.length ? this.deletionAtEndCost : this.deletionCost);
matrix[i][j] = Math.min(currentSubstitutionCost, Math.min(currentInsertionCost, currentDeletionCost));
}
}
return matrix[b.length][a.length];
},
// Given a query <a> and a series of targets <bs>, return the least distance to any target
getLeastEditDistance : function(a, bs) {
var that = this;
return Math.min.apply(null, bs.map(function(b) {
return that.getEditDistance(a,b);
}));
}
}
First of all, if you have a known dictionary you will get the fastest solution with something like a Levenshtein Automata, which will solve this in linear time to get all candidates. You can't beat this with a general purpose implementation.
With that said, this implementation of levenshtein distance is a few times faster than yours.
function distance(s, t) {
if (s === t) {
return 0;
}
var n = s.length, m = t.length;
if (n === 0 || m === 0) {
return n + m;
}
var x = 0, y, py, a, b, c, d, e, f, k;
var p = new Array(n);
for (y = 0; y < n;) {
p[y] = ++y;
}
for (; (x + 3) < m; x += 4) {
var tx0 = t.charCodeAt(x);
var tx1 = t.charCodeAt(x + 1);
var tx2 = t.charCodeAt(x + 2);
var tx3 = t.charCodeAt(x + 3);
a = x;
b = x + 1;
c = x + 2;
d = x + 3;
e = x + 4;
for (y = 0; y < n; y++) {
k = s.charCodeAt(y);
py = p[y];
if (py < a || b < a) {
a = (py > b ? b + 1 : py + 1);
}
else {
if (tx0 !== k) {
a++;
}
}
if (a < b || c < b) {
b = (a > c ? c + 1 : a + 1);
}
else {
if (tx1 !== k) {
b++;
}
}
if (b < c || d < c) {
c = (b > d ? d + 1 : b + 1);
}
else {
if (tx2 !== k) {
c++;
}
}
if (c < d || e < d) {
d = (c > e ? e + 1 : c + 1);
}
else {
if (tx3 !== k) {
d++;
}
}
p[y] = e = d;
d = c;
c = b;
b = a;
a = py;
}
}
for (; x < m;) {
tx0 = t.charCodeAt(x);
a = x;
b = ++x;
for (y = 0; y < n; y++) {
py = p[y];
if (py < a || b < a) {
b = (py > b ? b + 1 : py + 1);
}
else {
if (tx0 !== s.charCodeAt(y)) {
b = a + 1;
}
else {
b = a;
}
}
p[y] = b;
a = py;
}
f = b;
}
return f;
}
I would also not use map in getLeastEditDistance, it is very slow. Just use a normal loop. Also Math.min with many arguments is not very performant.
I am working with Levenstein distances by my self and I have not found a good way to improve performance and will not recommend using it in a non-batch application.
I suggest you use another approach by using a search tree. A binary or ternary search tree can also find near match.
A good place to start is those articles:
http://www.codeproject.com/Articles/5819/Ternary-Search-Tree-Dictionary-in-C-Faster-String
or
http://www.codeproject.com/Articles/68500/Balanced-Binary-Search-Tree-BST-Search-Delete-InOr
The code is relatively simple sp you should not use much time to port it to JavaScript.
I need to solve a cubic equation (ax^3 + bx^2 + c*x + d = 0) analytically and in real numbers, preferably in pure javascript (no libs). As there could be 1 to 3 roots, I think an array of numbers is a reasonable result type.
P.S. Provided my own solution below, hope it'll be useful.
Here you go. Includes handling degenerate cases. Main algorithm is mostly from wikipedia article.
function cuberoot(x) {
var y = Math.pow(Math.abs(x), 1/3);
return x < 0 ? -y : y;
}
function solveCubic(a, b, c, d) {
if (Math.abs(a) < 1e-8) { // Quadratic case, ax^2+bx+c=0
a = b; b = c; c = d;
if (Math.abs(a) < 1e-8) { // Linear case, ax+b=0
a = b; b = c;
if (Math.abs(a) < 1e-8) // Degenerate case
return [];
return [-b/a];
}
var D = b*b - 4*a*c;
if (Math.abs(D) < 1e-8)
return [-b/(2*a)];
else if (D > 0)
return [(-b+Math.sqrt(D))/(2*a), (-b-Math.sqrt(D))/(2*a)];
return [];
}
// Convert to depressed cubic t^3+pt+q = 0 (subst x = t - b/3a)
var p = (3*a*c - b*b)/(3*a*a);
var q = (2*b*b*b - 9*a*b*c + 27*a*a*d)/(27*a*a*a);
var roots;
if (Math.abs(p) < 1e-8) { // p = 0 -> t^3 = -q -> t = -q^1/3
roots = [cuberoot(-q)];
} else if (Math.abs(q) < 1e-8) { // q = 0 -> t^3 + pt = 0 -> t(t^2+p)=0
roots = [0].concat(p < 0 ? [Math.sqrt(-p), -Math.sqrt(-p)] : []);
} else {
var D = q*q/4 + p*p*p/27;
if (Math.abs(D) < 1e-8) { // D = 0 -> two roots
roots = [-1.5*q/p, 3*q/p];
} else if (D > 0) { // Only one real root
var u = cuberoot(-q/2 - Math.sqrt(D));
roots = [u - p/(3*u)];
} else { // D < 0, three roots, but needs to use complex numbers/trigonometric solution
var u = 2*Math.sqrt(-p/3);
var t = Math.acos(3*q/p/u)/3; // D < 0 implies p < 0 and acos argument in [-1..1]
var k = 2*Math.PI/3;
roots = [u*Math.cos(t), u*Math.cos(t-k), u*Math.cos(t-2*k)];
}
}
// Convert back from depressed cubic
for (var i = 0; i < roots.length; i++)
roots[i] -= b/(3*a);
return roots;
}
I am looking for a JavaScript function that can compare two strings and return the likeliness that they are alike. I have looked at soundex but that's not really great for multi-word strings or non-names. I am looking for a function like:
function compare(strA,strB){
}
compare("Apples","apple") = Some X Percentage.
The function would work with all types of strings, including numbers, multi-word values, and names. Perhaps there's a simple algorithm I could use?
Ultimately none of these served my purpose so I used this:
function compare(c, u) {
var incept = false;
var ca = c.split(",");
u = clean(u);
//ca = correct answer array (Collection of all correct answer)
//caa = a single correct answer word array (collection of words of a single correct answer)
//u = array of user answer words cleaned using custom clean function
for (var z = 0; z < ca.length; z++) {
caa = $.trim(ca[z]).split(" ");
var pc = 0;
for (var x = 0; x < caa.length; x++) {
for (var y = 0; y < u.length; y++) {
if (soundex(u[y]) != null && soundex(caa[x]) != null) {
if (soundex(u[y]) == soundex(caa[x])) {
pc = pc + 1;
}
}
else {
if (u[y].indexOf(caa[x]) > -1) {
pc = pc + 1;
}
}
}
}
if ((pc / caa.length) > 0.5) {
return true;
}
}
return false;
}
// create object listing the SOUNDEX values for each letter
// -1 indicates that the letter is not coded, but is used for coding
// 0 indicates that the letter is omitted for modern census archives
// but acts like -1 for older census archives
// 1 is for BFPV
// 2 is for CGJKQSXZ
// 3 is for DT
// 4 is for L
// 5 is for MN my home state
// 6 is for R
function makesoundex() {
this.a = -1
this.b = 1
this.c = 2
this.d = 3
this.e = -1
this.f = 1
this.g = 2
this.h = 0
this.i = -1
this.j = 2
this.k = 2
this.l = 4
this.m = 5
this.n = 5
this.o = -1
this.p = 1
this.q = 2
this.r = 6
this.s = 2
this.t = 3
this.u = -1
this.v = 1
this.w = 0
this.x = 2
this.y = -1
this.z = 2
}
var sndx = new makesoundex()
// check to see that the input is valid
function isSurname(name) {
if (name == "" || name == null) {
return false
} else {
for (var i = 0; i < name.length; i++) {
var letter = name.charAt(i)
if (!(letter >= 'a' && letter <= 'z' || letter >= 'A' && letter <= 'Z')) {
return false
}
}
}
return true
}
// Collapse out directly adjacent sounds
// 1. Assume that surname.length>=1
// 2. Assume that surname contains only lowercase letters
function collapse(surname) {
if (surname.length == 1) {
return surname
}
var right = collapse(surname.substring(1, surname.length))
if (sndx[surname.charAt(0)] == sndx[right.charAt(0)]) {
return surname.charAt(0) + right.substring(1, right.length)
}
return surname.charAt(0) + right
}
// Collapse out directly adjacent sounds using the new National Archives method
// 1. Assume that surname.length>=1
// 2. Assume that surname contains only lowercase letters
// 3. H and W are completely ignored
function omit(surname) {
if (surname.length == 1) {
return surname
}
var right = omit(surname.substring(1, surname.length))
if (!sndx[right.charAt(0)]) {
return surname.charAt(0) + right.substring(1, right.length)
}
return surname.charAt(0) + right
}
// Output the coded sequence
function output_sequence(seq) {
var output = seq.charAt(0).toUpperCase() // Retain first letter
output += "-" // Separate letter with a dash
var stage2 = seq.substring(1, seq.length)
var count = 0
for (var i = 0; i < stage2.length && count < 3; i++) {
if (sndx[stage2.charAt(i)] > 0) {
output += sndx[stage2.charAt(i)]
count++
}
}
for (; count < 3; count++) {
output += "0"
}
return output
}
// Compute the SOUNDEX code for the surname
function soundex(value) {
if (!isSurname(value)) {
return null
}
var stage1 = collapse(value.toLowerCase())
//form.result.value=output_sequence(stage1);
var stage1 = omit(value.toLowerCase())
var stage2 = collapse(stage1)
return output_sequence(stage2);
}
function clean(u) {
var u = u.replace(/\,/g, "");
u = u.toLowerCase().split(" ");
var cw = ["ARRAY OF WORDS TO BE EXCLUDED FROM COMPARISON"];
var n = [];
for (var y = 0; y < u.length; y++) {
var test = false;
for (var z = 0; z < cw.length; z++) {
if (u[y] != "" && u[y] != cw[z]) {
test = true;
break;
}
}
if (test) {
//Don't use & or $ in comparison
var val = u[y].replace("$", "").replace("&", "");
n.push(val);
}
}
return n;
}
Here's an answer based on Levenshtein distance https://en.wikipedia.org/wiki/Levenshtein_distance
function similarity(s1, s2) {
var longer = s1;
var shorter = s2;
if (s1.length < s2.length) {
longer = s2;
shorter = s1;
}
var longerLength = longer.length;
if (longerLength == 0) {
return 1.0;
}
return (longerLength - editDistance(longer, shorter)) / parseFloat(longerLength);
}
For calculating edit distance
function editDistance(s1, s2) {
s1 = s1.toLowerCase();
s2 = s2.toLowerCase();
var costs = new Array();
for (var i = 0; i <= s1.length; i++) {
var lastValue = i;
for (var j = 0; j <= s2.length; j++) {
if (i == 0)
costs[j] = j;
else {
if (j > 0) {
var newValue = costs[j - 1];
if (s1.charAt(i - 1) != s2.charAt(j - 1))
newValue = Math.min(Math.min(newValue, lastValue),
costs[j]) + 1;
costs[j - 1] = lastValue;
lastValue = newValue;
}
}
}
if (i > 0)
costs[s2.length] = lastValue;
}
return costs[s2.length];
}
Usage
similarity('Stack Overflow','Stack Ovrflw')
returns 0.8571428571428571
You can play with it below:
function checkSimilarity(){
var str1 = document.getElementById("lhsInput").value;
var str2 = document.getElementById("rhsInput").value;
document.getElementById("output").innerHTML = similarity(str1, str2);
}
function similarity(s1, s2) {
var longer = s1;
var shorter = s2;
if (s1.length < s2.length) {
longer = s2;
shorter = s1;
}
var longerLength = longer.length;
if (longerLength == 0) {
return 1.0;
}
return (longerLength - editDistance(longer, shorter)) / parseFloat(longerLength);
}
function editDistance(s1, s2) {
s1 = s1.toLowerCase();
s2 = s2.toLowerCase();
var costs = new Array();
for (var i = 0; i <= s1.length; i++) {
var lastValue = i;
for (var j = 0; j <= s2.length; j++) {
if (i == 0)
costs[j] = j;
else {
if (j > 0) {
var newValue = costs[j - 1];
if (s1.charAt(i - 1) != s2.charAt(j - 1))
newValue = Math.min(Math.min(newValue, lastValue),
costs[j]) + 1;
costs[j - 1] = lastValue;
lastValue = newValue;
}
}
}
if (i > 0)
costs[s2.length] = lastValue;
}
return costs[s2.length];
}
<div><label for="lhsInput">String 1:</label> <input type="text" id="lhsInput" oninput="checkSimilarity()" /></div>
<div><label for="rhsInput">String 2:</label> <input type="text" id="rhsInput" oninput="checkSimilarity()" /></div>
<div>Match: <span id="output">No Input</span></div>
Using this library for string similarity worked like a charm for me!
Here's the Example -
var similarity = stringSimilarity.compareTwoStrings("Apples","apple"); // => 0.88
Here is a very simple function that does a comparison and returns a percentage based on equivalency. While it has not been tested for all possible scenarios, it may help you get started.
function similar(a,b) {
var equivalency = 0;
var minLength = (a.length > b.length) ? b.length : a.length;
var maxLength = (a.length < b.length) ? b.length : a.length;
for(var i = 0; i < minLength; i++) {
if(a[i] == b[i]) {
equivalency++;
}
}
var weight = equivalency / maxLength;
return (weight * 100) + "%";
}
alert(similar("test","tes")); // 75%
alert(similar("test","test")); // 100%
alert(similar("test","testt")); // 80%
alert(similar("test","tess")); // 75%
To Find degree of similarity between two strings; we can use more than one or two methods but I am mostly inclined towards the usage of 'Dice's Coefficient' . which is better! well in my knowledge than using 'Levenshtein distance'
Using this 'string-similarity' package from npm you will be able to work on what I said above.
some easy usage examples are
var stringSimilarity = require('string-similarity');
var similarity = stringSimilarity.compareTwoStrings('healed', 'sealed');
var matches = stringSimilarity.findBestMatch('healed', ['edward', 'sealed', 'theatre']);
for more please visit the link given above. Thankyou.
Just one I quickly wrote that might be good enough for your purposes:
function Compare(strA,strB){
for(var result = 0, i = strA.length; i--;){
if(typeof strB[i] == 'undefined' || strA[i] == strB[i]);
else if(strA[i].toLowerCase() == strB[i].toLowerCase())
result++;
else
result += 4;
}
return 1 - (result + 4*Math.abs(strA.length - strB.length))/(2*(strA.length+strB.length));
}
This weighs characters that are the same but different case 1 quarter as heavily as characters that are completely different or missing. It returns a number between 0 and 1, 1 meaning the strings are identical. 0 meaning they have no similarities. Examples:
Compare("Apple", "Apple") // 1
Compare("Apples", "Apple") // 0.8181818181818181
Compare("Apples", "apple") // 0.7727272727272727
Compare("a", "A") // 0.75
Compare("Apples", "appppp") // 0.45833333333333337
Compare("a", "b") // 0
How about function similar_text from PHP.js library?
It is based on a PHP function with the same name.
function similar_text (first, second) {
// Calculates the similarity between two strings
// discuss at: http://phpjs.org/functions/similar_text
if (first === null || second === null || typeof first === 'undefined' || typeof second === 'undefined') {
return 0;
}
first += '';
second += '';
var pos1 = 0,
pos2 = 0,
max = 0,
firstLength = first.length,
secondLength = second.length,
p, q, l, sum;
max = 0;
for (p = 0; p < firstLength; p++) {
for (q = 0; q < secondLength; q++) {
for (l = 0;
(p + l < firstLength) && (q + l < secondLength) && (first.charAt(p + l) === second.charAt(q + l)); l++);
if (l > max) {
max = l;
pos1 = p;
pos2 = q;
}
}
}
sum = max;
if (sum) {
if (pos1 && pos2) {
sum += this.similar_text(first.substr(0, pos2), second.substr(0, pos2));
}
if ((pos1 + max < firstLength) && (pos2 + max < secondLength)) {
sum += this.similar_text(first.substr(pos1 + max, firstLength - pos1 - max), second.substr(pos2 + max, secondLength - pos2 - max));
}
}
return sum;
}
fuzzyset - A fuzzy string set for javascript.
fuzzyset is a data structure that performs something akin to fulltext search against data to determine likely mispellings and approximate string matching. Note that this is a javascript port of a python library.
To some extent, I like the ideas of Dice's coefficient embedded in the string-similarity module. But I feel that considering the bigrams only and not taking into account their multiplicities is missing some important data. Below is a version that also handles multiplicities, and I think is a simpler implementation overall. I don't try to use their API, offering only a function which compares two strings after some manipulation (removing non-alphanumeric characters, lower-casing everything, and compressing but not removing whitespace), built atop one which compares them without that manipulation. It would be easy enough to wrap this back in their API, but I see little need.
const stringSimilarity = (a, b) =>
_stringSimilarity (prep (a), prep (b))
const _stringSimilarity = (a, b) => {
const bg1 = bigrams (a)
const bg2 = bigrams (b)
const c1 = count (bg1)
const c2 = count (bg2)
const combined = uniq ([... bg1, ... bg2])
.reduce ((t, k) => t + (Math .min (c1 [k] || 0, c2 [k] || 0)), 0)
return 2 * combined / (bg1 .length + bg2 .length)
}
const prep = (str) => // TODO: unicode support?
str .toLowerCase () .replace (/[^\w\s]/g, ' ') .replace (/\s+/g, ' ')
const bigrams = (str) =>
[...str] .slice (0, -1) .map ((c, i) => c + str [i + 1])
const count = (xs) =>
xs .reduce ((a, x) => ((a [x] = (a [x] || 0) + 1), a), {})
const uniq = (xs) =>
[... new Set (xs)]
console .log (stringSimilarity (
'foobar',
'Foobar'
)) //=> 1
console .log (stringSimilarity (
"healed",
"sealed"
))//=> 0.8
console .log (stringSimilarity (
"Olive-green table for sale, in extremely good condition.",
"For sale: table in very good condition, olive green in colour."
)) //=> 0.7787610619469026
console .log (stringSimilarity (
"Olive-green table for sale, in extremely good condition.",
"For sale: green Subaru Impreza, 210,000 miles"
)) //=> 0.38636363636363635
console .log (stringSimilarity (
"Olive-green table for sale, in extremely good condition.",
"Wanted: mountain bike with at least 21 gears."
)) //=> 0.1702127659574468
console .log (stringSimilarity (
"The rain in Spain falls mainly on the plain.",
"The run in Spun falls munly on the plun.",
)) //=> 0.7560975609756098
console .log (stringSimilarity (
"Fa la la la la, la la la la",
"Fa la la la la, la la",
)) //=> 0.8636363636363636
console .log (stringSimilarity (
"car crash",
"carcrash",
)) //=> 0.8
console .log (stringSimilarity (
"Now is the time for all good men to come to the aid of their party.",
"Huh?",
)) //=> 0
.as-console-wrapper {max-height: 100% !important; top: 0}
Some of the test cases are from string-similarity, others are my own. They show some significant differences from that package, but nothing untoward. The only one I would call out is the difference between "car crash" and "carcrash", which string-similarity sees as identical and I report with a similarity of 0.8. My version finds more similarity in all the olive-green test-cases than does string-similarity, but as these are in any case fairly arbitrary numbers, I'm not sure how much difference it makes; they certainly position them in the same relative order.
string-similarity lib vs Top answer (by #overloard1234) performance comparation you can find below
Based on #Tushar Walzade's advice to use string-similarity library, you can find, that for example
stringSimilatityLib.findBestMatch('KIA','Kia').bestMatch.rating
will return 0.0
So, looks like better to compare it in lowerCase.
Better base usage (for arrays) :
findBestMatch(str, strArr) {
const lowerCaseArr = strArr.map(element => element.toLowerCase());//creating lower case array
const match = stringSimilatityLib.findBestMatch(str.toLowerCase(), lowerCaseArr).bestMatch; //trying to find bestMatch
if (match.rating > 0) {
const foundIndex = lowerCaseArr.findIndex(x => x === match.target); //finding the index of found best case
return strArr[foundIndex]; //returning initial value from array
}
return null;
},
Performance
Also, i compared top answer here (made by #overloard1234) and string-similarity lib (v4.0.4).
The results you can find here : https://jsbench.me/szkzojoskq/1
Result : string-similarity is ~ twice faster
Just for fun : v2.0 of string-similarity library slower, than latest 4.0.4 about 2.2 times. So update it, if you are still using < 3.0 :)
const str1 = " pARTH PARmar r ";
const str2 = " parmar r par ";
function calculateSimilarity(str1 = "", str2 = "") {
let longer = str1.trim();
let shorter = str2.trim();
let a1 = longer.toLowerCase().split(" ");
let b1 = shorter.toLowerCase().split(" ");
let result = a1.every((aa, i) => aa[0] === b1[i][0]);
if (longer.length < shorter.length) [longer,shorter] = [shorter,longer];
var arr = [];
let count = 0;
for(var i = 0;i<longer.length;i++){
if(shorter && shorter.includes(longer[i])) {
shorter = shorter.replace(longer[i],"")
count++
};
}
return {
score : (count*100)/longer.length,
result
}
}
console.log(calculateSimilarity(str1, str2));
I used #overlord1234 function, but corrected ь: '', cuz English words don't have this letter, and next need return a[char] ?? char instead of return a[char] || char
Hy,
I am trying to implement an Connect Four Game in javascript / jQuery. First off this is no homework or any other duty. I'm just trying to push my abilities.
My "playground" is a simple html table which has 7 rows and 6 columns.
But now I have reached my ken. I'm stuck with the main functionality of checking whether there are 4 same td's around. I am adding a class to determine which color it should represent in the game.
First I thought I could handle this with .nextAll() and .prevAll() but this does not work for me because there is no detection between.
Because I was searching for siblings, when adding a new Item and just looked up the length of siblings which were found and if they matched 4 in the end I supposed this was right, but no its not :D Is there maybe any kind of directNext() which provides all next with a css selector until something different comes up ?
I will put all of my code into this jsfiddle: http://jsfiddle.net/LcUVf/5/
Maybe somebody has ever tried the same or someone comes up with a good idea I'm not asking anybody to do or finish my code. I just want to get hints for implementing such an algorithm or examples how it could be solved !
Thanks in anyway !
DOM traversal is not particularly efficient so, when you can avoid it, I'd recommend doing so. It'd make sense for you to build this as a 2D array to store and update the state of the game. The table would only be a visual representation of the array.
I know that, normally, you would build the array with rows as the first dimension and columns as the second dimension but, for the purposes of being able to add pieces to each column's "stack," I would make the first dimension the columns and the second dimension the rows.
To do the check, take a look at this fiddle I made:
http://jsfiddle.net/Koviko/4dTyw/
There are 4 directions to check: North-South, East-West, Northeast-Southwest, and Southeast-Northwest. This can be represented as objects with the delta defined for X and Y:
directions = [
{ x: 0, y: 1 }, // North-South
{ x: 1, y: 0 }, // East-West
{ x: 1, y: 1 }, // Northeast-Southwest
{ x: 1, y: -1 } // Southeast-Northwest
];
Then, loop through that object and loop through your "table" starting at the farthest bounds that this piece can possibly contribute to a win. So, since you need 4 pieces in a row, the currently placed piece can contribute in a win for up to 3 pieces in any direction.
minX = Math.min(Math.max(placedX - (3 * directions[i].x), 0), pieces.length - 1);
minY = Math.min(Math.max(placedY - (3 * directions[i].y), 0), pieces[0].length - 1);
maxX = Math.max(Math.min(placedX + (3 * directions[i].x), pieces.length - 1), 0);
maxY = Math.max(Math.min(placedY + (3 * directions[i].y), pieces[0].length - 1), 0);
To avoid any issues with less-than and greater-than (which I ran into), calculate the number of steps before looping through your pieces instead of using the calculated bounds as your conditions.
steps = Math.max(Math.abs(maxX - minX), Math.abs(maxY - minY));
Finally, loop through the items keeping a count of consecutive pieces that match the piece that was placed last.
function isVictory(pieces, placedX, placedY) {
var i, j, x, y, maxX, maxY, steps, count = 0,
directions = [
{ x: 0, y: 1 }, // North-South
{ x: 1, y: 0 }, // East-West
{ x: 1, y: 1 }, // Northeast-Southwest
{ x: 1, y: -1 } // Southeast-Northwest
];
// Check all directions
outerloop:
for (i = 0; i < directions.length; i++, count = 0) {
// Set up bounds to go 3 pieces forward and backward
x = Math.min(Math.max(placedX - (3 * directions[i].x), 0), pieces.length - 1);
y = Math.min(Math.max(placedY - (3 * directions[i].y), 0), pieces[0].length - 1);
maxX = Math.max(Math.min(placedX + (3 * directions[i].x), pieces.length - 1), 0);
maxY = Math.max(Math.min(placedY + (3 * directions[i].y), pieces[0].length - 1), 0);
steps = Math.max(Math.abs(maxX - x), Math.abs(maxY - y));
for (j = 0; j < steps; j++, x += directions[i].x, y += directions[i].y) {
if (pieces[x][y] == pieces[placedX][placedY]) {
// Increase count
if (++count >= 4) {
break outerloop;
}
} else {
// Reset count
count = 0;
}
}
}
return count >= 4;
}
I released a fully working version of the game on Github.
It implements an optimised variation on the algorythm Sirko mentioned.
To avoid any unnecessary redunancy, the algorythm directly checks the DOM rather than a JS table. As that algorythm requires a minimum amount of checks, the performance overhead for accessing the DOM is neglectable.
The current player and a flag for keeping track of whether the game has ended are basicly the only statuses stored in the JS itself.
I even used the DOM to store strings. It has no external dependencies and is supported by all versions of IE from IE6 upwards as well as modern browsers.
Code is optimised for filesize and performance. The latest version also includes animation, even though the total JS code of the game is still only 1.216 bytes after minification.
The Code :
Here's the full, un-minified JS code :
(function (doc, win, onclick, gid, classname, content, showMessage) {
var
a, b, c, colorLabel, cid, players, current, finished, newgameLabel, wonLabel, laststart = 1,
cellAt = function (i, j) {
return doc[gid](cid + i + j);
},
isCurrentColor = function (i, j) {
return cellAt(i, j)[classname] === players[current];
},
start = function () {
current = laststart = (laststart + 1) % 2;
finished = 0;
colorLabel[content] = colorLabel[classname] = players[current = (current + 1) % 2];
for (a = 1; a < 7; a++)
for (b = 1; b < 8; b++)
cellAt(a, b)[classname] = '';
},
makeMove = function (i, j, s) {
s > 0 && (cellAt(s, j)[classname] = '');
cellAt(s + 1, j)[classname] = players[current];
s === i - 1 ? function (i, j) {
return function (i, j) {
for (a = j - 1; 0 < a && isCurrentColor(i, a); a--) {
}
for (b = j + 1; 8 > b && isCurrentColor(i, b); b++) {
}
return 4 < b - a;
}(i, j) || function (i, j) {
for (c = i + 1; 7 > c && isCurrentColor(c, j); c++) {
}
return 3 < c - i;
}(i, j) || function (i, j) {
for (a = i - 1, b = j - 1; 0 < a && !(1 > b) && isCurrentColor(a, b); a--)
b--;
for (c = i + 1, b = j + 1; 7 > c && !(7 < b) && isCurrentColor(c, b); c++)
b++;
return 4 < c - a
}(i, j) || function (i, j) {
for (a = i - 1, b = j + 1; 0 < a && !(7 < b) && isCurrentColor(a, b); a--)
b++;
for (c = i + 1, b = j - 1; 7 > c && !(1 > b) && isCurrentColor(c, b); c++)
b--;
return 4 < c - a;
}(i, j);
}(i, j)
? finished = 1 && win[showMessage](doc[gid](wonLabel)[content].replace("%s", players[current].toLowerCase())) && start()
: colorLabel[content] = colorLabel[classname] = players[current = (current + 1) % 2]
: setTimeout(function () {
makeMove(i, j, s + 1)
}, 20);
};
return function (n, w, c, h, p1, p2) {
cid = c;
newgameLabel = n;
wonLabel = w;
colorLabel = doc[gid](c);
players = [doc[gid](p1)[content], doc[gid](p2)[content]];
for (a = 1; a < 7; a++)
for (b = 1; b < 8; b++)
cellAt(a, b)[onclick] = function (b, a) {
return function () {
if (!finished)
for (a = 6; a > 0; a--)
if (!cellAt(a, b)[classname]) {
makeMove(a, b, 0);
break;
}
};
}(b);
;
doc[gid](h)[onclick] = function () {
win[showMessage](doc[gid](newgameLabel)[content]) && start()
};
start();
};
})(document, window, "onclick", "getElementById", "className", "innerHTML", "confirm")("newgame", "won", "color", "restart", "p1", "p2");
A screenshot :
In general a 2dimensional array would be better suited for checking for a line of 4. You could then do something like the following:
function check( lastPiece, playground, player ) {
// check length in each direction
var l = 1,
i = 1;
// top to bottom
while( (playground[ lastPiece.x ][ lastPiece.y - i ] === player) && ((lastPiece.y - i) >= 0) ) { l += 1; i += 1; };
i = 1;
while( (playground[ lastPiece.x ][ lastPiece.y + i ] === player) && ((lastPiece.y + i) <= MAX_Y) ) { l += 1; i += 1; };
if ( l >= 4 ) { return true; }
// left to right
l = 1;
while( (playground[ lastPiece.x - i][ lastPiece.y ] === player) && ((lastPiece.x - i) >= 0) ) { l += 1; i += 1; };
i = 1;
while( (playground[ lastPiece.x + i][ lastPiece.y ] === player) && ((lastPiece.x + i) <= MAX_X) ) { l += 1; i += 1; };
if ( l >= 4 ) { return true; }
// same for top left to bottom right and bottom left to top right
// . . .
// if we got no hit until here, there is no row of 4
return false;
}
EDIT: added checks for borders of the playground