Package be.bagofwords.db.bloomfilter

Examples of be.bagofwords.db.bloomfilter.LongBloomFilter

117
118
119
120
121
122
123
        if (first.getNumOfHashFunctions() != second.getNumOfHashFunctions()) {
            throw new RuntimeException("Unequal number of hash functions!");
        }
        LongBloomFilter.BitArray bitArray1 = first.getBits();
        LongBloomFilter.BitArray bitArray2 = second.getBits();
        return new LongBloomFilter(bitArray1.mergeWith(bitArray2), first.getNumOfHashFunctions());
    }
View Full Code Here
84
85
86
87
88
89
90
91
92
93
94
            return filterCounts.mightContain(key);
        }
    }

    public void makeNonSparse() {
        this.filterCounts = new LongBloomFilter(numberOfFeatures, FPP);
        for (Long key : cachedKeys) {
            filterCounts.put(key);
        }
        this.cachedKeys = null;
    }
View Full Code Here
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
            result.setCachedKeys(new ArrayList<>(this.getCachedKeys()));
            for (Long key : second.getCachedKeys()) {
                result.addKey(key);
            }
        } else {
            LongBloomFilter mergedCounts;
            if (!this.isSparse() && !second.isSparse()) {
                mergedCounts = ApproximateCountsUtils.mergeBloomFilters(this.getFilterCounts(), second.getFilterCounts());
            } else {
                if (!this.isSparse()) {
                    mergedCounts = this.getFilterCounts().clone();
                } else if (!second.isSparse()) {
                    mergedCounts = second.getFilterCounts().clone();
                } else {
                    //Both sparse
                    mergedCounts = new LongBloomFilter(this.getNumberOfFeatures(), CompactIndex.FPP);
                }
            }
            if (this.isSparse()) {
                for (Long key : this.getCachedKeys()) {
                    mergedCounts.put(key);
                }
            }
            if (second.isSparse()) {
                for (Long key : second.getCachedKeys()) {
                    mergedCounts.put(key);
                }
            }
            result = new CompactIndex(this.getNumberOfFeatures(), mergedCounts, this.getNumberOfCounts() + second.getNumberOfCounts());
        }
        return result;
View Full Code Here
10
11
12
13
14
15
16
17
18
19
20
public class TestBloomFiltersSpeed {

    private static final int NUM_OF_VALUES = 1000000;

    public static void main(String[] args) {
        LongBloomFilter bloomFilter1 = new LongBloomFilter(NUM_OF_VALUES, 0.001);

        BloomFilter<Long> bloomFilter2 = BloomFilter.create(new Funnel<Long>() {
            @Override
            public void funnel(Long from, PrimitiveSink into) {
                into.putLong(from);
View Full Code Here
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
                    averageValues[i] = 1;
                }
            }
        }
        long[] numOfExpectedValues = countValues(dataInterface);
        LongBloomFilter oneCountsBloomFilter = new LongBloomFilter(numOfExpectedValues[0], fpp);
        LongCountsBloomFilter otherCountsBloomFilter = new LongCountsBloomFilter(numOfExpectedValues[1], fpp);
        UI.write("Adding all counts to the filter with size " + otherCountsBloomFilter.getBytes().size() + "+" + (oneCountsBloomFilter.getBits().size() / 8) + ". This might take a while");
        it = dataInterface.iterator();
        while (it.hasNext()) {
            KeyValue<Long> value = it.next();
            if (value.getValue() == 1) {
                oneCountsBloomFilter.put(value.getKey());
            } else {
                int bin = NumUtils.getBin(binBorders, value.getValue());
                otherCountsBloomFilter.addCount(value.getKey(), bin + 1);
            }
        }
View Full Code Here
85
86
87
88
89
90
91
        long[] averages = new long[0];
        return new ApproximateCountsFilter(averages, createEmptyBloomFilter(), bloomFilter);
    }

    public static LongBloomFilter createEmptyBloomFilter() {
        return new LongBloomFilter(1, 0.1);
    }
View Full Code Here
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
            if (it.next().getValue() >= minFrequency) {
                numOfValuesToAdd++;
            }
        }
        it.close();
        LongBloomFilter result = new LongBloomFilter(numOfValuesToAdd, 0.01);
        it = totalCountsDI.iterator();
        while (it.hasNext()) {
            KeyValue<Long> next = it.next();
            if (next.getValue() >= minFrequency) {
                result.put(next.getKey());
            }
        }
        it.close();
        UI.write("Creating bloom filter took " + (System.currentTimeMillis() - start) + " ms for " + numOfValuesToAdd + " values, taking " + (result.getBits().getData().length * 8) + " bytes");
        return result;
    }
View Full Code Here
TOP

Related Classes of be.bagofwords.db.bloomfilter.LongBloomFilter

  • be.bagofwords.db.data.ApproximateCountsUtils
  • be.bagofwords.db.data.CompactIndex
  • be.bagofwords.main.tests.bloomfilter.TestBloomFiltersSpeed
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.