tJavaで評価プログラムを作成する

public static class SpamFilterFunction implements 
	org.apache.spark.api.java.function.Function<row7Struct, Boolean>{
	private static final long serialVersionUID = 1L;
	@Override
	public Boolean call(row7Struct row7) throws Exception {
		
		return row7.reallabel.equals("spam");
	}
	
}

// 'negative': ham
// 'positive': spam
// 'false' means the real label & predicted label are different 
// 'true' means the real label & predicted label are the same

public static class TrueNegativeFunction implements 
	org.apache.spark.api.java.function.Function<row7Struct, Boolean>{
	private static final long serialVersionUID = 1L;
	@Override
	public Boolean call(row7Struct row7) throws Exception {
		
		return (row7.label.equals("ham") && row7.reallabel.equals("ham"));
	}
	
}

public static class TruePositiveFunction implements 
	org.apache.spark.api.java.function.Function<row7Struct, Boolean>{
	private static final long serialVersionUID = 1L;
	@Override
	public Boolean call(row7Struct row7) throws Exception {
		// true positive cases
		return (row7.label.equals("spam") && row7.reallabel.equals("spam"));
	}
	
}

public static class FalseNegativeFunction implements 
	org.apache.spark.api.java.function.Function<row7Struct, Boolean>{
	private static final long serialVersionUID = 1L;
	@Override
	public Boolean call(row7Struct row7) throws Exception {
		// false positive cases
		return (row7.label.equals("spam") && row7.reallabel.equals("ham"));
	}
	
}

public static class FalsePositiveFunction implements 
	org.apache.spark.api.java.function.Function<row7Struct, Boolean>{
	private static final long serialVersionUID = 1L;
	@Override
	public Boolean call(row7Struct row7) throws Exception {
		// false positive cases
		return (row7.label.equals("ham") && row7.reallabel.equals("spam"));
	}
	
}

long nbTotal = rdd_tJava_1.count();

long nbSpam = rdd_tJava_1.filter(new SpamFilterFunction()).count();

long nbHam = nbTotal - nbSpam;

// 'negative': ham
// 'positive': spam
// 'false' means the real label & predicted label are different 
// 'true' means the real label & predicted label are the same

long tn = rdd_tJava_1.filter(new TrueNegativeFunction()).count();

long tp = rdd_tJava_1.filter(new TruePositiveFunction()).count();

long fn = rdd_tJava_1.filter(new FalseNegativeFunction()).count();

long fp = rdd_tJava_1.filter(new FalsePositiveFunction()).count();

double mmc = (double)(tp*tn -fp*fn) / java.lang.Math.sqrt((double)((tp+fp)*(tp+fn)*(tn+fp)*(tn+fn)));

System.out.println("Accuracy:"+((double)(tp+tn)/(double)nbTotal));
System.out.println("Spams caught (SC):"+((double)tp/(double)nbSpam));
System.out.println("Blocked hams (BH):"+((double)fp/(double)nbHam));
System.out.println("Matthews correlation coefficient (MCC):" + mmc);