Package org.apache.mahout.common.distance

Examples of org.apache.mahout.common.distance.SquaredEuclideanDistanceMeasure.distance()

121
122
123
124
125
126
127
128
129
130
131
    // Given the centroid, we can compute \Delta_1^2(X), the total squared distance for the datapoints
    // this accelerates seed selection.
    double radius = 0;
    DistanceMeasure l2 = new SquaredEuclideanDistanceMeasure();
    for (WeightedVector row : datapoints) {
      radius += l2.distance(row, center);
    }

    // Find the first seed c_1 (and conceptually the second, c_2) as might be done in the 2-means clustering so that
    // the probability of selecting c_1 and c_2 is proportional to || c_1 - c_2 ||^2.  This is done
    // by first selecting c_1 with probability:
View Full Code Here
144
145
146
147
148
149
150
151
152
153
154
    // Multinomial distribution of vector indices for the selection seeds. These correspond to
    // the indices of the vectors in the original datapoints list.
    Multinomial<Integer> seedSelector = new Multinomial<Integer>();
    for (int i = 0; i < datapoints.size(); ++i) {
      double selectionProbability =
          radius + datapoints.size() * l2.distance(datapoints.get(i), center);
      seedSelector.add(i, selectionProbability);
    }

    Centroid c_1 = new Centroid((WeightedVector)datapoints.get(seedSelector.sample()).clone());
    c_1.setIndex(0);
View Full Code Here
154
155
156
157
158
159
160
161
162
163
164
    c_1.setIndex(0);
    // Construct a set of weighted things which can be used for random selection.  Initial weights are
    // set to the squared distance from c_1
    for (int i = 0; i < datapoints.size(); ++i) {
      WeightedVector row = datapoints.get(i);
      final double w = l2.distance(c_1, row) * row.getWeight();
      seedSelector.set(i, w);
    }

    // From here, seeds are selected with probablity proportional to:
    //
View Full Code Here
177
178
179
180
181
182
183
184
185
186
187
      // Don't select this one again.
      seedSelector.set(seedIndex, 0);
      // Re-weight everything according to the minimum distance to a seed.
      for (int currSeedIndex : seedSelector) {
        WeightedVector curr = datapoints.get(currSeedIndex);
        double newWeight = nextSeed.getWeight() * l2.distance(nextSeed, curr);
        if (newWeight < seedSelector.getWeight(currSeedIndex)) {
          seedSelector.set(currSeedIndex, newWeight);
        }
      }
    }
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.