java entropy_Java ContingencyTables.entropy方法代码示例

import weka.core.ContingencyTables; //导入方法依赖的package包/类

/**

* Test using Fayyad and Irani's MDL criterion.

*

* @param priorCounts

* @param bestCounts

* @param numInstances

* @param numCutPoints

* @return true if the splits is acceptable

*/

private boolean FayyadAndIranisMDL(double[] priorCounts,

double[][] bestCounts,

double numInstances,

int numCutPoints) {

double priorEntropy, entropy, gain;

double entropyLeft, entropyRight, delta;

int numClassesTotal, numClassesRight, numClassesLeft;

// Compute entropy before split.

priorEntropy = ContingencyTables.entropy(priorCounts);

// Compute entropy after split.

entropy = ContingencyTables.entropyConditionedOnRows(bestCounts);

// Compute information gain.

gain = priorEntropy - entropy;

// Number of classes occuring in the set

numClassesTotal = 0;

for (int i = 0; i < priorCounts.length; i++) {

if (priorCounts[i] > 0) {

numClassesTotal++;

}

}

// Number of classes occuring in the left subset

numClassesLeft = 0;

for (int i = 0; i < bestCounts[0].length; i++) {

if (bestCounts[0][i] > 0) {

numClassesLeft++;

}

}

// Number of classes occuring in the right subset

numClassesRight = 0;

for (int i = 0; i < bestCounts[1].length; i++) {

if (bestCounts[1][i] > 0) {

numClassesRight++;

}

}

// Entropy of the left and the right subsets

entropyLeft = ContingencyTables.entropy(bestCounts[0]);

entropyRight = ContingencyTables.entropy(bestCounts[1]);

// Compute terms for MDL formula

delta = Utils.log2(Math.pow(3, numClassesTotal) - 2) -

(((double) numClassesTotal * priorEntropy) -

(numClassesRight * entropyRight) -

(numClassesLeft * entropyLeft));

// Check if split is to be accepted

return (gain > (Utils.log2(numCutPoints) + delta) / (double)numInstances);

}

本文来自互联网用户投稿，文章观点仅代表作者本人，不代表本站立场，不承担相关法律责任。如若转载，请注明出处。 如若内容造成侵权/违法违规/事实不符，请点击【内容举报】进行投诉反馈！