├── .DS_Store ├── .gitignore ├── LICENSE ├── README.md ├── bfs.js ├── lib ├── hyperlog-sandwich.js └── utils.js ├── package.json └── test └── hyperlog-sandwich.js /.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chanian/hyperlogsandwich/ce45853a999ba58e492c07de81ea5e45bfe38e7a/.DS_Store -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # Logs 2 | logs 3 | *.log 4 | 5 | # Runtime data 6 | pids 7 | *.pid 8 | *.seed 9 | 10 | # Directory for instrumented libs generated by jscoverage/JSCover 11 | lib-cov 12 | 13 | # Coverage directory used by tools like istanbul 14 | coverage 15 | 16 | # Grunt intermediate storage (http://gruntjs.com/creating-plugins#storing-task-files) 17 | .grunt 18 | 19 | # Compiled binary addons (http://nodejs.org/api/addons.html) 20 | build/Release 21 | 22 | # Dependency directory 23 | # Commenting this out is preferred by some people, see 24 | # https://www.npmjs.org/doc/misc/npm-faq.html#should-i-check-my-node_modules-folder-into-git- 25 | node_modules 26 | 27 | # Users Environment Variables 28 | .lock-wscript 29 | 30 | output -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "{}" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright {yyyy} {name of copyright owner} 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | 203 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # hyperlogsandwich 2 | [View wiki] (https://github.com/chanian/hyperlogsandwich/wiki) 3 | -------------------------------------------------------------------------------- /bfs.js: -------------------------------------------------------------------------------- 1 | /* 2 | 3 | A HyperLog-sandwich 4 | 5 | High cardinality approximation for cumulative frequency partitioning in stream compute. 6 | 7 | HL(Bf) | HL(Bf) | ...... | HL(Bf) 8 | 9 | -> (HyperLogLog(i))(BloomFilter(i)) -> 10 | 11 | */ 12 | var utils = require('./lib/utils.js'); 13 | var HyperLogSandwich = require('./lib/hyperlog-sandwich'); 14 | 15 | var max = 15; 16 | var trials = 5; 17 | var i, bf, hll, hll2, fCounts, output = []; 18 | 19 | // Generate a buncha data 20 | for(var t = 1; t < trials ; t++) { 21 | for(var s = 0; s < 5; s++) { 22 | var epsilon = 1/(Math.pow(10,t)); 23 | var hls = new HyperLogSandwich(max, null, null, null, null, epsilon); 24 | console.log(epsilon); 25 | var inputSet = [] 26 | , streamSize = 100000; 27 | 28 | (function (i) { 29 | // console.log('Generating dataset'); 30 | for (i = 0; i <= streamSize; i++) { 31 | inputSet.push(Math.random().toString()); 32 | } 33 | inputSet = utils.insertDups(inputSet, max); 34 | stream = inputSet; 35 | })(); 36 | 37 | // HyperLogSandwich 38 | var frequency, item; 39 | (function () { 40 | // console.log('Inserting HyperLogSandwich'); 41 | for(i = 0; i < stream.length; i++) { 42 | if (i % 100000 == 0) { 43 | console.log(t + '/' + trials, (Math.floor(i / stream.length * 1000) / 10) + '%'); 44 | } 45 | hls.add(stream[i]); 46 | } 47 | })(); 48 | 49 | var freqMap = {}; 50 | var freqMapCount = {}; 51 | var fCounts = {}; 52 | 53 | // calculate old fashioned way 54 | (function () { 55 | // console.log('Calculating exact counts') 56 | for(i = 0; i < stream.length; i ++) { 57 | if(!freqMap[stream[i]]) { 58 | freqMap[stream[i]] = 1; 59 | } else { 60 | freqMap[stream[i]]++; 61 | } 62 | } 63 | 64 | for(i = 0; i < max; i++) { 65 | for(j in freqMap) { 66 | if(freqMap[j] > i) { 67 | if(!freqMapCount[i]) { 68 | freqMapCount[i] = 1; 69 | } else { 70 | freqMapCount[i]++; 71 | } 72 | } 73 | } 74 | }; 75 | })(); 76 | 77 | function calcError(a, b) { 78 | return (Math.floor(10000 * (Math.abs(a - b) / b)) / 100) || 0; 79 | }; 80 | 81 | // Output the results 82 | (function () { 83 | var i, avgErrHLS = 0, avgErrBloom = 0, avgErrCMS = 0, errCMS = []; 84 | var cmsDepth = []; 85 | cmsDepth.push(epsilon); 86 | // console.log(['Freq', 'Est', 'BChain', 'CMS', 'Actual', 'Err%', 'Err2%', 'Err3%'].join(',\t')); 87 | 88 | for(i = 0; i < max; i++) { 89 | var estimate = hls.getBloomCount(i) || 0; 90 | var actual = freqMapCount[i] || 0; 91 | var cms = hls.get(i) || 0; 92 | var bChain = hls.getBloomCount2(i) || 0; 93 | 94 | var errorHLS = calcError(estimate, actual); 95 | var errorBloom = calcError(bChain, actual); 96 | var errorCMS = calcError(cms, actual); 97 | 98 | avgErrCMS += errorCMS; 99 | avgErrBloom += errorBloom; 100 | avgErrHLS += errorHLS; 101 | 102 | errCMS.push(errorCMS); 103 | 104 | // console.log([i, estimate, bChain, cms, actual, errorHLS, errorBloom, errorCMS].join(',\t') + '%'); 105 | cmsDepth.push(errorCMS); 106 | } 107 | // console.log(cmsDepth.join(', ')); 108 | var medianErrorCMS = errCMS.sort()[Math.floor(errCMS.length / 2)]; 109 | function s (a) { return Math.floor(a * 1000) / 1000; } 110 | // output.push([streamSize, s(avgErrCMS/max), medianErrorCMS]); 111 | output.push(cmsDepth); 112 | // console.log([streamSize, s(avgErrCMS/max), s(avgErrBloom/max), s(avgErrHLS/max)].join(', ')); 113 | })(); 114 | }} 115 | 116 | var out = {} 117 | for(i = 0; i < output.length; i++) { 118 | // console.log(output[i].join(',')); 119 | if (!out[output[i][0]]) { 120 | out[output[i][0]] = []; 121 | } 122 | out[output[i][0]].push(output[i]); 123 | } 124 | for(o in out) { 125 | arr = out[o][0]; 126 | for(i = 1; i < out[o].length; i++) { 127 | for(k = 0 ; k < out[o][0].length; k++) { 128 | arr[k]+= out[o][i][k]; 129 | } 130 | } 131 | out[o] = arr; 132 | for(i = 0; i < out[o].length; i++) { 133 | out[o][i] = out[o][i]/5; 134 | } 135 | } 136 | 137 | for(i in out) { 138 | console.log(out[i].join(', ')); 139 | } 140 | // console.log(out); 141 | -------------------------------------------------------------------------------- /lib/hyperlog-sandwich.js: -------------------------------------------------------------------------------- 1 | var HyperLogLog = require('hyperloglog'); 2 | var CMS = require("count-min-sketch"); 3 | var BloomFilter = require('bloomfilter').BloomFilter; 4 | 5 | function HyperLogSandwich (depth, functions, bits, registers, epsilon, error) { 6 | var i, bf, hll, hll2; 7 | 8 | // Configs to tune 9 | var _functions = functions || 7; 10 | var _registers = registers || 12; 11 | var _bits = bits || 958506; 12 | var _cmsA = epsilon || 0.00001; 13 | var _cmsB = error || 0.001; 14 | 15 | this.max = depth || 15; 16 | 17 | this.HLLs = []; 18 | this.HLL2 = []; 19 | this.BFs = []; 20 | this.cms = CMS(_cmsA, _cmsB); 21 | this.fCounts = {}; 22 | 23 | // Init all the counters 24 | for (i = 0; i < this.max; i++) { 25 | // init the BloomFilters 26 | bf = new BloomFilter(_bits, _functions); 27 | 28 | // init the HyperLogLogs 29 | hll = HyperLogLog(_registers); 30 | hll2 = HyperLogLog(_registers); 31 | 32 | this.HLLs.push(hll); 33 | this.HLL2.push(hll2); 34 | this.BFs.push(bf); 35 | } 36 | } 37 | 38 | // Insert new data into the HyperLogSandwich 39 | HyperLogSandwich.prototype.add = function (item) { 40 | var frequency, hll, hll2, bf, cmsF, itemHash; 41 | 42 | // Strategy #1 43 | // Immediately update sketchmap 44 | var itemHash = HyperLogLog.hash(item); 45 | this.cms.update(itemHash, 1); 46 | cmsF = this.cms.query(itemHash) - 1; 47 | 48 | // Always insert into the 0th HLL, since the CSM will become saturated later 49 | this.HLL2[0].add(itemHash); 50 | if(cmsF < this.max) { 51 | this.HLL2[cmsF].add(itemHash); 52 | } 53 | 54 | // Strategy #2 55 | // Use a LinkedList of BloomFilters 56 | for(frequency = 0 ; frequency < this.max; frequency++) { 57 | hll = this.HLLs[frequency]; 58 | bf = this.BFs[frequency]; 59 | 60 | // Count at least one occurance of this item 61 | hll.add(itemHash); 62 | 63 | // Have we (maybe) seen this item yet? 64 | if (!bf.test(item)) { 65 | // Record each time we set the BloomFilter (strategy #3) 66 | if(!this.fCounts[frequency]) { 67 | this.fCounts[frequency] = 0; 68 | } 69 | this.fCounts[frequency]++; 70 | 71 | // Set this depth's BloomFilter 72 | bf.add(item); 73 | break; 74 | } 75 | } 76 | } 77 | 78 | HyperLogSandwich.prototype.get = function(frequency) { 79 | return this.HLLs2[frequency].count(); 80 | } 81 | 82 | HyperLogSandwich.prototype.getBloomCount = function(frequency) { 83 | return this.HLL[frequency].count(); 84 | } 85 | 86 | HyperLogSandwich.prototype.getBloomCount2 = function(frequency) { 87 | return this.HLL[frequency].count(); 88 | } 89 | 90 | module.exports = HyperLogSandwich; -------------------------------------------------------------------------------- /lib/utils.js: -------------------------------------------------------------------------------- 1 | /** 2 | * Since we don't really care about the input set for this 3 | * analysis, just generate a uniformly distributed 32bit string 4 | * 5 | * Returns a value n E [0.. 2^(n-1)] 6 | */ 7 | function generateRandom32bitStream () { 8 | var val = [] 9 | , n 10 | , nthBit 11 | , binaryString; 12 | 13 | for (n = 0; n < 32; n++) { 14 | nthBit = ((Math.random() > 0.5) + 0); 15 | val.push(nthBit); 16 | } 17 | binaryString = val.join(''); 18 | return binaryString; 19 | } 20 | 21 | /** 22 | * A naive O(n) space, time cardinality check. 23 | * calculates the exact cardinality; 24 | */ 25 | function cardinality (set) { 26 | var counted = {} 27 | , count = 0 28 | , i 29 | , index; 30 | 31 | for (i = 0; i < set.length; i++) { 32 | index = set[i]; 33 | if (!counted[index]) { 34 | count++; 35 | } 36 | counted[index] = true; 37 | } 38 | return count; 39 | } 40 | 41 | /** 42 | * Generate a n-set of uniformly distributed 43 | * 32-bit binary strings which simulates the 44 | * output of running n-data points through a 45 | * hash function f with uniform hash distribution 46 | * into binary space. 47 | */ 48 | function getUniformBitStream (num) { 49 | var output = []; 50 | for (num; num > 0; --num) { 51 | output.push(generateRandom32bitStream()); 52 | } 53 | return output; 54 | }; 55 | 56 | /** 57 | * For the sake of experimentation, forcibly 58 | * insert some duplicates to our dataset. 59 | */ 60 | function insertDups (set, max) { 61 | var dups = [] 62 | , i, k; 63 | 64 | for (i = 0; i < set.length; i++) { 65 | for(k = 0; k < max; k++) { 66 | // exponential distribution 67 | // if (i == 0 || Math.random() < 1/(i/10+1)) { 68 | // dups.push(set[i]); 69 | // } 70 | // linear distribution 71 | if (Math.random() > 0.6) { 72 | dups.push(set[i]); 73 | } 74 | } 75 | } 76 | 77 | // we really don't care about the order 78 | return set.concat(dups); 79 | } 80 | 81 | module.exports = { 82 | generateRandom32bitStream: generateRandom32bitStream, 83 | cardinality: cardinality, 84 | getUniformBitStream: getUniformBitStream, 85 | insertDups: insertDups 86 | }; -------------------------------------------------------------------------------- /package.json: -------------------------------------------------------------------------------- 1 | { 2 | "private": true, 3 | "name": "bf-sandwhich", 4 | "version": "0.0.1", 5 | "dependencies": { 6 | "count-min-sketch": "*", 7 | "hyperloglog": "*", 8 | "bloomfilter": "*" 9 | }, 10 | "devDependencies": { 11 | "should": "1.1.0", 12 | "mocha": "" 13 | }, 14 | "scripts": { 15 | "run": "node runner.js", 16 | "test": "mocha" 17 | } 18 | } -------------------------------------------------------------------------------- /test/hyperlog-sandwich.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chanian/hyperlogsandwich/ce45853a999ba58e492c07de81ea5e45bfe38e7a/test/hyperlog-sandwich.js --------------------------------------------------------------------------------