Example usage for org.apache.mahout.math.stats OnlineSummarizer getSD

List of usage examples for org.apache.mahout.math.stats OnlineSummarizer getSD

Introduction

In this page you can find the example usage for org.apache.mahout.math.stats OnlineSummarizer getSD.

Prototype

public double getSD() 

Source Link

Usage

From source file:org.conan.mymahout.clustering.streaming.tools.ClusterQualitySummarizer.java

License:Apache License

public static void printSummaries(List<OnlineSummarizer> summarizers, String type, PrintWriter fileOut) {
    double maxDistance = 0;
    for (int i = 0; i < summarizers.size(); ++i) {
        OnlineSummarizer summarizer = summarizers.get(i);
        if (summarizer.getCount() > 1) {
            maxDistance = Math.max(maxDistance, summarizer.getMax());
            System.out.printf("Average distance in cluster %d [%d]: %f\n", i, summarizer.getCount(),
                    summarizer.getMean());
            // If there is just one point in the cluster, quartiles cannot be estimated. We'll just assume all the quartiles
            // equal the only value.
            if (fileOut != null) {
                fileOut.printf("%d,%f,%f,%f,%f,%f,%f,%f,%d,%s\n", i, summarizer.getMean(), summarizer.getSD(),
                        summarizer.getQuartile(0), summarizer.getQuartile(1), summarizer.getQuartile(2),
                        summarizer.getQuartile(3), summarizer.getQuartile(4), summarizer.getCount(), type);
            }//from w w  w.j a v  a2  s . co  m
        } else {
            System.out.printf("Cluster %d is has %d data point. Need atleast 2 data points in a cluster for"
                    + " OnlineSummarizer.\n", i, summarizer.getCount());
        }
    }
    System.out.printf("Num clusters: %d; maxDistance: %f\n", summarizers.size(), maxDistance);
}