bloom-filters - npm Package Compare versions

Comparing version 1.3.4 to 1.3.6

package.json

 {
   "name": "bloom-filters",
-  "version": "1.3.4",
+  "version": "1.3.6",
   "description": "JS implementation of probabilistic data structures: Bloom Filter (and its derived), HyperLogLog, Count-Min Sketch, Top-K and MinHash",
@@ -5,0 +5,0 @@ "main": "dist/api.js",

README.md

@@ -359,3 +359,3 @@ # Bloom-Filters
 
-* `add(element: string) -> void`: add a new occurence of an element to the sketch.
+* `add(element: string, count: number = 1) -> void`: add one or more new occurences of an element to the sketch.
 * `values() -> Array<TopkElement>`: get the top-k values as an array of objects.
@@ -370,3 +370,3 @@ * `iterator() -> Iterator<TopkElement>`: get the top-k values as an iterator that yields objects.
 
-// push some occurrences in the multiset
+// push occurrences one-at-a-time in the multiset
 topk.add('alice')
@@ -376,2 +376,6 @@ topk.add('bob')
 
+// or, equally, push multiple occurrences at-once in the multiset
+// topk.add('alice', 2)
+// topk.add('bob', 1)
+
 // print the top k values
@@ -378,0 +382,0 @@ for(let item of topk.values()) {

src/sketch/topk.ts

@@ -149,3 +149,6 @@ /* file: topk.ts
 
-  @Field()
+  @Field<CountMinSketch>(
+    (sketch: CountMinSketch) => sketch.saveAsJSON(),
+    (json: any) => CountMinSketch.fromJSON(json)
+  )
   private _sketch: CountMinSketch
@@ -179,4 +182,7 @@
    */
-  add (element: string): void {
-    this._sketch.update(element)
+  add (element: string, count: number = 1): void {
+    if (0 >= count) {
+      throw (`count must be > 0 (was ${count})`)
+    }
+    this._sketch.update(element, count)
     const frequency = this._sketch.count(element)
@@ -183,0 +189,0 @@

test/topk-test.js

@@ -45,2 +45,61 @@ /* file : topk-test.js
 
+  describe('#add', () => {
+    it('should produce equivalent TopK estimations when using count parameter', () => {
+      const k = 3
+      const errorRate = 0.001
+      const accuracy = 0.999
+      let freqTable = {}
+
+      /*
+       * Add items to the traditional one-at-a-time variant while concurrently
+       * building a frequency table to be used for the all-at-once variant.
+       */
+      const topkOneAtATime = new TopK(k, errorRate, accuracy)
+      for (const item of lessThanOrEqualTestCaseItems) {
+        topkOneAtATime.add(item)
+        if (!Object.hasOwnProperty.call(freqTable, item)) {
+          freqTable[`${item}`] = 0
+        }
+        ++freqTable[`${item}`]
+      }
+
+      /* Ensure the built frequency table is correct. */
+      const expectedFreqTable = lessThanOrEqualTestCaseItems.reduce(
+        function (acc, curr) {
+
+        if (!Object.hasOwnProperty.call(acc, curr)) {
+          acc[`${curr}`] = 1
+        } else {
+          ++acc[`${curr}`]
+        }
+
+        return acc
+      }, {})
+      freqTable.should.to.deep.equal(expectedFreqTable)
+
+      /* Build a version of TopK using the frequency as count */
+      const topkAllAtOnce = new TopK(k, errorRate, accuracy)
+      for (const [item, freq] of Object.entries(freqTable)) {
+        topkAllAtOnce.add(item, freq)
+      }
+
+      const topkOneAtATimeValues = topkOneAtATime.values()
+      const topkOneAtATimeKeys = topkOneAtATimeValues.map(({value}) => value)
+      const topkAllAtOnceValues = topkAllAtOnce.values()
+      const topkAllAtOnceKeys = topkAllAtOnceValues.map(({value}) => value)
+
+      /* Make sure all expected lengths match */
+      expectedTop.should.to.have.lengthOf(k)
+      topkOneAtATimeKeys.should.to.have.lengthOf(expectedTop.length)
+      topkAllAtOnceKeys.should.to.have.lengthOf(topkOneAtATimeKeys.length)
+
+      /* Make sure all expected keys match */
+      topkOneAtATimeKeys.should.to.deep.equal(expectedTop)
+      topkAllAtOnceKeys.should.to.deep.equal(topkOneAtATimeKeys)
+
+      /* Make sure the objects themselves match */
+      topkAllAtOnceValues.should.to.deep.equal(topkOneAtATimeValues)
+    })
+  })
+
   describe('#values', () => {
@@ -230,3 +289,24 @@ it('should produce valid TopK estimations when there are fewer than K items', () => {
     })
+
+    it('should update an imported TopK', ()=>{
+      const exported = topk.saveAsJSON()
+      const newSketch = TopK.fromJSON(exported)
+      
+      newSketch.add("alice")
+      topk.add("alice")
+      
+      newSketch._k.should.equal(topk._k)
+      newSketch._errorRate.should.equal(topk._errorRate)
+      newSketch._accuracy.should.equal(topk._accuracy)
+      newSketch._seed.should.equal(topk._seed)
+      // inner count min sketch
+      newSketch._sketch._columns.should.equal(topk._sketch._columns)
+      newSketch._sketch._rows.should.equal(topk._sketch._rows)
+      newSketch._sketch._allSums.should.equal(topk._sketch._allSums)
+      newSketch._sketch._seed.should.equal(topk._sketch._seed)
+      newSketch._sketch._matrix.should.deep.equal(topk._sketch._matrix)
+      // inner MinHeap
+      newSketch._heap._content.should.deep.equal(topk._heap._content)
+    })
   })
 })

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Improved metrics

Number of lines in readme file

527

increased by0.76%

Worsened metrics

Total package byte prevSize

233765

decreased by-46.98%

Number of package files

42

decreased by-45.45%

Lines of code

4980

decreased by-50.11%

No dependency changes