public double calculateEntropy(Temperature temp) {
double T = temp.getK();
double entropy;
if (T < 298) throw new TemperatureOutOfRangeException();
else if (T < middleTemperature) {
double[] a = new double[7];
a = lowTemperatureCoefficients;
entropy =
a[0] * Math.log(T)
+ a[1] * T
+ a[2] * T * T / 2
+ a[3] * T * T * T / 3
+ a[4] * T * T * T * T / 4
+ a[6];
entropy = entropy * GasConstant.getCalMolK();
return entropy;
} else if (T < highTemperature) {
double[] a = new double[7];
a = highTemperatureCoefficients;
entropy =
a[0] * Math.log(T)
+ a[1] * T
+ a[2] * T * T / 2
+ a[3] * T * T * T / 3
+ a[4] * T * T * T * T / 4
+ a[6];
entropy = entropy * GasConstant.getCalMolK();
return entropy;
} else throw new TemperatureOutOfRangeException();
}
public static String humanReadableByteCount(long bytes, boolean si) {
int unit = si ? 1000 : 1024;
if (bytes < unit) return bytes + " B";
int exp = (int) (Math.log(bytes) / Math.log(unit));
String pre = (si ? "kMGTPE" : "KMGTPE").charAt(exp - 1) + (si ? "" : "i");
return String.format("%.1f %sB", bytes / Math.pow(unit, exp), pre);
}
private NBWeights trainWeightsJL(int[][] data, int[] labels, int numFeatures, int numClasses) {
int[] numValues = numberValues(data, numFeatures);
double[] priors = new double[numClasses];
double[][][] weights = new double[numClasses][numFeatures][];
// init weights array
for (int cl = 0; cl < numClasses; cl++) {
for (int fno = 0; fno < numFeatures; fno++) {
weights[cl][fno] = new double[numValues[fno]];
}
}
for (int i = 0; i < data.length; i++) {
priors[labels[i]]++;
for (int fno = 0; fno < numFeatures; fno++) {
weights[labels[i]][fno][data[i][fno]]++;
}
}
for (int cl = 0; cl < numClasses; cl++) {
for (int fno = 0; fno < numFeatures; fno++) {
for (int val = 0; val < numValues[fno]; val++) {
weights[cl][fno][val] =
Math.log(
(weights[cl][fno][val] + alphaFeature)
/ (priors[cl] + alphaFeature * numValues[fno]));
}
}
priors[cl] = Math.log((priors[cl] + alphaClass) / (data.length + alphaClass * numClasses));
}
return new NBWeights(priors, weights);
}
/* Function for calculating laplacePerTerm for individual query terms */
public static double laplacePerTerm(
String termFreq, double docLen, double avgLen, long vocabSize, int queryWords) {
// System.out.println("Query Words:::");
String[] termFs = termFreq.split(" ");
// System.out.println("TermFs::: "+ termFreq);
double log_p_lap = 0.0;
/*
* if(termFs.length <= queryWords){
*
* for(int j=0;j<(queryWords-termFs.length); j++){ log_p_lap +=
* Math.log(((0 + 1) / (docLen + vocabSize)); } log_p_lap+= (Math.log((0
* + 1) / (docLen + vocabSize))) * (queryWords - termFs.length);
*
* }
*/
if (termFs.length < queryWords) {
log_p_lap += (Math.log((0 + 1) / (docLen + vocabSize))) * (queryWords - termFs.length);
}
for (int i = 0; i < termFs.length; i++) {
log_p_lap += Math.log(((Integer.parseInt(termFs[i])) + 1) / (docLen + vocabSize));
}
return log_p_lap;
}
public Double eval(Double gamma) {
double c1 = 0.0;
double c3 = -1.0 / (double) Math.sqrt(2.0 * variance);
double sum = 0.0;
double cpart = -0.5 * Math.log(Math.sqrt(2.0 * Math.PI * variance));
for (Integer i : transcripts.get(gammat)) {
c1 += cpart;
double pi = 0.0;
for (int t = 0; t < fiveprime.length; t++) {
if (transcripts.get(t).contains(i)) {
double gammai = gammat == t ? gamma : gammas[t][gammak];
double dit = delta(i, t);
double pit = gammai * Math.exp(-lambda * dit);
pi += pit;
}
}
double zi = Math.log(pi);
double err = data.values(i)[channels[gammak]] - zi;
sum += (err * err);
}
return c1 + c3 * sum;
}
public Double eval(Double lmbda) {
double c1 = 0.0;
double c3 = -1.0 / (double) Math.sqrt(2.0 * variance);
double sum = 0.0;
double cpart = -0.5 * Math.log(Math.sqrt(2.0 * Math.PI * variance));
for (int i = 0; i < data.size(); i++) {
for (int k = 0; k < channels.length; k++) {
c1 += cpart;
double pi = 0.0;
for (Integer t : transcripts.keySet()) {
if (transcripts.get(t).contains(i)) {
double dit = delta(i, t);
double gammai = gammas[t][k];
double pit = gammai * Math.exp(-lmbda * dit);
pi += pit;
}
}
double zi = Math.log(pi);
double err = data.values(i)[channels[k]] - zi;
sum += (err * err);
}
}
return c1 + c3 * sum;
}
/** Applies mutation in the new poblation */
public void mutate() {
int posiciones, i, j;
double m;
posiciones = n_genes * long_poblacion;
if (prob_mutacion > 0)
while (Mu_next < posiciones) {
/* Se determina el cromosoma y el gen que corresponden a la posicion que
se va a mutar */
i = Mu_next / n_genes;
j = Mu_next % n_genes;
/* Se efectua la mutacion sobre ese gen */
poblacion[i].mutate(j);
/* Se marca el cromosoma mutado para su posterior evaluacion */
poblacion[i].setEvaluated(false);
/* Se calcula la siguiente posicion a mutar */
if (prob_mutacion < 1) {
m = Randomize.Rand();
Mu_next += Math.ceil(Math.log(m) / Math.log(1.0 - prob_mutacion));
} else Mu_next += 1;
}
Mu_next -= posiciones;
}
/**
* Calculates the sample likelihood and BIC score for i given its parents in a simple SEM model.
*/
private double localSemScore(int i, int[] parents) {
try {
ICovarianceMatrix cov = getCovMatrix();
double varianceY = cov.getValue(i, i);
double residualVariance = varianceY;
int n = sampleSize();
int p = parents.length;
int k = (p * (p + 1)) / 2 + p;
// int k = (p + 1) * (p + 1);
// int k = p + 1;
TetradMatrix covxx = cov.getSelection(parents, parents);
TetradMatrix covxxInv = covxx.inverse();
TetradVector covxy = cov.getSelection(parents, new int[] {i}).getColumn(0);
TetradVector b = covxxInv.times(covxy);
residualVariance -= covxy.dotProduct(b);
if (residualVariance <= 0 && verbose) {
out.println(
"Nonpositive residual varianceY: resVar / varianceY = "
+ (residualVariance / varianceY));
return Double.NaN;
}
double c = getPenaltyDiscount();
// return -n * log(residualVariance) - 2 * k; //AIC
return -n * Math.log(residualVariance) - c * k * Math.log(n);
// return -n * log(residualVariance) - c * k * (log(n) - log(2 * PI));
} catch (Exception e) {
e.printStackTrace();
throw new RuntimeException(e);
// throwMinimalLinearDependentSet(parents, cov);
}
}
/**
* Returns the <sup>10</sup>log() of a value
*
* @return the <sup>10</sup>log()
*/
static double log10(int v) {
double dl = 0.0;
if (v != 0.0) {
dl = Math.log(v) / Math.log(10);
}
return dl;
}
public void addObservedResult(double result, int timeElapsed, String passCode)
throws IllegalStateValueDataModificationException {
if (!this.passCode.equals(passCode)) {
throw new IllegalStateValueDataModificationException();
}
sum += result;
sum2 += (result * result);
count++;
average = sum / count;
double variance = Math.abs(sum2 / count - average * average);
sdev = Math.sqrt(variance);
sharpe = average * average / variance;
Integer timeClass = (int) (Math.log(timeElapsed) / Math.log(2));
Integer distClass = (int) (result / res);
if (!dist.containsKey(timeClass)) {
dist.put(timeClass, new TreeMap<Integer, Double>());
}
if (!dist.get(timeClass).containsKey(distClass)) {
dist.get(timeClass).put(distClass, 0.0);
}
dist.get(timeClass).put(distClass, dist.get(timeClass).get(distClass) + 1);
if (!collapsedDist.containsKey(distClass)) {
collapsedDist.put(distClass, 0.0);
}
collapsedDist.put(distClass, collapsedDist.get(distClass) + 1);
}
/**
* <br>
* In the first round,</br> <br>
* In the paper the server is supposed to ask sensors for uncoded data.</br> <br>
* We sent the maximum number of bits: 63 bits = "111111"</br> <br>
* Sensor will encode in IEEE double format</br> <br>
* Calculates the i (number of requested bits), as given in the paper</br>
*/
@Override
public String sendRequest(int sensor_id) {
if (is_first_round[sensor_id] || sensor_id == 0 || round_number < M) {
requested_bits[sensor_id] = maximum_number_of_bits_askable;
return "111111";
}
double delta = code_book.getD();
int i =
(int)
Math.ceil(
(0.5
* (Math.log((sigma[sensor_id] * sigma[sensor_id]) / (delta * delta * P_e))
/ Math.log(2.0)))
+ 1);
i = Math.min(i, maximum_number_of_bits_askable); // request not more that 63 bits
i = Math.max(0, i); // request no less than 0 bits
requested_bits[sensor_id] = i;
String bit_string =
tools.pad0ToFront(
Integer.toBinaryString(i),
bits_needed_to_represent_maximum_askable); // pad it to make length 6
return tools.reverse(bit_string);
}
private double calcMean(
HashMap<Integer, String> singleGeneCaseValueMap,
String groupType,
String profileStableId) { // group type: altered or unaltered
switch (groupType) {
case "altered":
int _index_altered = 0;
double[] alteredArray = new double[alteredSampleIds.size()];
for (Integer alteredSampleId : alteredSampleIds) {
if (singleGeneCaseValueMap.containsKey(alteredSampleId)) {
if (profileStableId.indexOf("rna_seq") != -1) {
try {
alteredArray[_index_altered] =
Math.log(Double.parseDouble(singleGeneCaseValueMap.get(alteredSampleId)))
/ Math.log(2);
} catch (NumberFormatException e) {
e.getStackTrace();
}
} else {
try {
alteredArray[_index_altered] =
Double.parseDouble(singleGeneCaseValueMap.get(alteredSampleId));
} catch (NumberFormatException e) {
e.getStackTrace();
}
}
_index_altered += 1;
}
}
return StatUtils.mean(alteredArray);
case "unaltered":
int _index_unaltered = 0;
double[] unalteredArray = new double[unalteredSampleIds.size()];
for (Integer unalteredSampleId : unalteredSampleIds) {
if (singleGeneCaseValueMap.containsKey(unalteredSampleId)) {
if (profileStableId.indexOf("rna_seq") != -1) {
try {
unalteredArray[_index_unaltered] =
Math.log(Double.parseDouble(singleGeneCaseValueMap.get(unalteredSampleId)))
/ Math.log(2);
} catch (NumberFormatException e) {
e.getStackTrace();
}
} else {
try {
unalteredArray[_index_unaltered] =
Double.parseDouble(singleGeneCaseValueMap.get(unalteredSampleId));
} catch (NumberFormatException e) {
e.getStackTrace();
}
}
_index_unaltered += 1;
}
}
return StatUtils.mean(unalteredArray);
default:
return Double.NaN; // error
}
}
private static JointClassification jointJointClassify(ssd.Document doc) {
double[][] classprobs = new double[PartsOfSpeech.length][CATEGORIES.length];
double[] jointprobs = new double[CATEGORIES.length];
double[] ranks = new double[CATEGORIES.length];
double[] classif_variances = new double[PartsOfSpeech.length];
for (double d : jointprobs) d = 0;
for (int i = 0; i < CATEGORIES.length; i++) ranks[i] = 0;
JointClassification jc = new JointClassification(CATEGORIES, jointprobs);
for (int i = 0; i < PartsOfSpeech.length; i++) {
String pos = PartsOfSpeech[i];
if (doc.mPosTexts.get(pos) != null) {
JointClassification jc1 = compiledClassifiers.get(pos).classify(doc.mPosTexts.get(pos));
for (int j = 0; j < CATEGORIES.length; j++)
classprobs[i][j] = getCategoryConditionalProbability(CATEGORIES[j], jc1);
}
}
for (int i = 0; i < classif_variances.length; i++) {
classif_variances[i] =
variance(classprobs[i]); // get the variance of each classifier into classif_variances
}
double average_variance = 0, max_classif_variance = -1, sum_variance = 0;
for (double d : classif_variances) {
sum_variance += d;
if (d > max_classif_variance) max_classif_variance = d;
}
average_variance = sum_variance / classif_variances.length;
// say we cheat and let the average be the same as the 'all' partofspeech
for (int i = 0; i < PartsOfSpeech.length; i++)
if (PartsOfSpeech[i].equals("all")) average_variance = classif_variances[i];
// average_variance=max_classif_variance;
/*switch this all back, write the paper, finish the presentation. WRAP THE F**K UP */
/* No! this method achieves 67% accuracy on 20news! */
for (int i = 0; i < CATEGORIES.length; i++)
for (int j = 0; j < classif_variances.length; j++)
ranks[i] += classif_variances[j] * classprobs[j][i] / sum_variance;
double ranksum = 0;
for (double r : ranks) ranksum += r;
for (int i = 0; i < CATEGORIES.length; i++) ranks[i] = ranks[i] / ranksum;
for (int i = 0; i < CATEGORIES.length; i++) ranks[i] = Math.log(ranks[i]) / Math.log(2);
ranks = sort_with_categories(ranks);
// the new transformed matrix is a matrix of log2 of probabilities of belonging calculated from
// ranks
jc = new JointClassification(CATEGORIES, ranks);
return jc;
}
public boolean isIndependent(Node x, Node y, List<Node> z) {
int[] all = new int[z.size() + 2];
all[0] = variablesMap.get(x);
all[1] = variablesMap.get(y);
for (int i = 0; i < z.size(); i++) {
all[i + 2] = variablesMap.get(z.get(i));
}
int sampleSize = data.get(0).rows();
List<Double> pValues = new ArrayList<Double>();
for (int m = 0; m < ncov.size(); m++) {
TetradMatrix _ncov = ncov.get(m).getSelection(all, all);
TetradMatrix inv = _ncov.inverse();
double r = -inv.get(0, 1) / sqrt(inv.get(0, 0) * inv.get(1, 1));
double fisherZ =
sqrt(sampleSize - z.size() - 3.0) * 0.5 * (Math.log(1.0 + r) - Math.log(1.0 - r));
double pValue;
if (Double.isInfinite(fisherZ)) {
pValue = 0;
} else {
pValue = 2.0 * (1.0 - RandomUtil.getInstance().normalCdf(0, 1, abs(fisherZ)));
}
pValues.add(pValue);
}
double _cutoff = alpha;
if (fdr) {
_cutoff = StatUtils.fdrCutoff(alpha, pValues, false);
}
Collections.sort(pValues);
int index = (int) round((1.0 - percent) * pValues.size());
this.pValue = pValues.get(index);
// if (this.pValue == 0) {
// System.out.println("Zero pvalue "+ SearchLogUtils.independenceFactMsg(x, y, z,
// getPValue()));
// }
boolean independent = this.pValue > _cutoff;
if (verbose) {
if (independent) {
TetradLogger.getInstance()
.log("independencies", SearchLogUtils.independenceFactMsg(x, y, z, getPValue()));
// System.out.println(SearchLogUtils.independenceFactMsg(x, y, z, getPValue()));
} else {
TetradLogger.getInstance()
.log("dependencies", SearchLogUtils.dependenceFactMsg(x, y, z, getPValue()));
}
}
return independent;
}
public void testEstimateWNoValues() throws Exception {
double[] y = new double[] {};
double sigma = 30;
double[] initialW = new double[] {Math.log(.5), Math.log(.5)};
assertEquals(1, scorer.estimate(y, initialW, 200, sigma, new double[y.length]).w0, 0.0001);
}
@Test
public void testLikelihood() throws Exception {
double[] y = NODEL_ISIZES;
double l =
scorer.likelihood(
y, new double[] {Math.log(.5), Math.log(.5)}, new double[] {100, 1100}, 15);
assertEquals(-29.90017, l, 0.0001);
}
@Test
public void testEstimateW() throws Exception {
double[] y = HET_DEL_5X_5N;
double sigma = 30;
double[] initialW = new double[] {Math.log(.5), Math.log(.5)};
assertEquals(.5, scorer.estimate(y, initialW, 200, sigma, new double[y.length]).w0, 0.0001);
}
private double runTTest(HashMap<Integer, String> singleGeneCaseValueMap, String profileStableId)
throws IllegalArgumentException {
double[] unalteredArray = new double[unalteredSampleIds.size()];
double[] alteredArray = new double[alteredSampleIds.size()];
int _index_unaltered = 0, _index_altered = 0;
for (Integer alteredSampleId : alteredSampleIds) {
if (singleGeneCaseValueMap.containsKey(alteredSampleId)) {
if (profileStableId.indexOf("rna_seq") != -1) {
try {
alteredArray[_index_altered] =
Math.log(Double.parseDouble(singleGeneCaseValueMap.get(alteredSampleId)))
/ Math.log(2);
} catch (NumberFormatException e) {
e.getStackTrace();
}
} else {
try {
alteredArray[_index_altered] =
Double.parseDouble(singleGeneCaseValueMap.get(alteredSampleId));
} catch (NumberFormatException e) {
e.getStackTrace();
}
}
_index_altered += 1;
}
}
for (Integer unalteredSampleId : unalteredSampleIds) {
if (singleGeneCaseValueMap.containsKey(unalteredSampleId)) {
if (profileStableId.indexOf("rna_seq") != -1) {
try {
unalteredArray[_index_unaltered] =
Math.log(Double.parseDouble(singleGeneCaseValueMap.get(unalteredSampleId)))
/ Math.log(2);
} catch (NumberFormatException e) {
e.getStackTrace();
}
} else {
try {
unalteredArray[_index_unaltered] =
Double.parseDouble(singleGeneCaseValueMap.get(unalteredSampleId));
} catch (NumberFormatException e) {
e.getStackTrace();
}
}
_index_unaltered += 1;
}
}
if (alteredArray.length < 2 || unalteredArray.length < 2) return Double.NaN;
else {
double pvalue = TestUtils.tTest(alteredArray, unalteredArray);
return pvalue;
}
}
double computeEntropy(Vector v, int numValues) {
double ent = 0;
for (int i = 0, size = v.size(); i < size; i++) {
double prob = ((Integer) v.elementAt(i)).intValue();
prob /= (double) numValues;
ent += prob * Math.log(prob) / Math.log(2);
}
return -ent;
}
static double optimalCompressedLength(int[] a) {
int max = 0;
for (int x : a) max = Math.max(max, x);
int[] freq = new int[max + 1];
for (int x : a) ++freq[x];
double optimalLength = 0;
for (int f : freq)
if (f > 0) optimalLength += f * Math.log((double) a.length / f) / Math.log(2) / 8;
return optimalLength;
}
private double errors(double N, double e, double CF) {
// Some constants for the interpolation.
double Val[] = {
0,
0.000000001,
0.00000001,
0.0000001,
0.000001,
0.00001,
0.00005,
0.0001,
0.0005,
0.001,
0.005,
0.01,
0.05,
0.10,
0.20,
0.40,
1.00
};
double Dev[] = {
100, 6.0, 5.61, 5.2, 4.75, 4.26, 3.89, 3.72, 3.29, 3.09, 2.58, 2.33, 1.65, 1.28, 0.84, 0.25,
0.00
};
double Val0, Pr, Coeff;
int i;
Coeff = 0;
i = 0;
while (CF > Val[i]) i++;
Coeff = Dev[i - 1] + (Dev[i] - Dev[i - 1]) * (CF - Val[i - 1]) / (Val[i] - Val[i - 1]);
Coeff = Coeff * Coeff;
if (e < 1E-6) return N * (1.0 - Math.exp(Math.log(CF) / N));
else {
if (e < 0.9999) {
Val0 = N * (1 - Math.exp(Math.log(CF) / N));
return (Val0 + e * (errors(N, 1.0, CF) - Val0));
} else {
if (e + 0.5 >= N) return (0.67 * (N - e));
else {
Pr =
(e
+ 0.5
+ Coeff / 2
+ Math.sqrt(Coeff * ((e + 0.5) * (1 - (e + 0.5) / N) + Coeff / 4)))
/ (N + Coeff);
return (N * Pr - e);
}
}
}
}
public static double getEntropy(double[] P) {
double entropy = 0;
for (double p : P) if (1 / (p * Math.log(1 / p)) != 0) entropy += -p * Math.log(p);
double psum = 0;
for (double p : P) psum += p;
System.err.println("Sum of probs: " + psum + "[ ");
for (double p : P) System.err.printf("%1.2f,", p);
System.err.println("Entropy: " + entropy);
return entropy;
}
String visualize() {
int ubDepth = (int) Math.ceil(Math.log(size) / Math.log(m_order)) * elemHeight;
int ubWidth = size * elemWidth;
java.io.StringWriter sw = new java.io.StringWriter();
java.io.PrintWriter pw = new java.io.PrintWriter(sw);
pw.println("<html><head></head><body>");
visualize(root, pw, 0, 0, ubWidth, ubDepth);
pw.println("</body></html>");
pw.flush();
return sw.toString();
}
private double branchLLInPopsIOtree(PopsIONode node, double alpha, double beta) {
int q = node.coalcount;
double gamma = node.coalintensity;
double llhood = 0.0;
for (int i = 1; i <= q - 1; i++) {
llhood += Math.log(alpha + i);
}
llhood += alpha * Math.log(beta);
llhood -= (alpha + q) * Math.log(beta + gamma);
return llhood;
}
private double calcSTDev(
HashMap<Integer, String> singleGeneCaseValueMap, String groupType, String profileStableId) {
switch (groupType) {
case "altered":
DescriptiveStatistics stats_altered = new DescriptiveStatistics();
for (Integer alteredSampleId : alteredSampleIds) {
if (singleGeneCaseValueMap.containsKey(alteredSampleId)) {
if (profileStableId.indexOf("rna_seq") != -1) {
try {
stats_altered.addValue(
Math.log(Double.parseDouble(singleGeneCaseValueMap.get(alteredSampleId)))
/ Math.log(2));
} catch (NumberFormatException e) {
e.getStackTrace();
}
} else {
try {
stats_altered.addValue(
Double.parseDouble(singleGeneCaseValueMap.get(alteredSampleId)));
} catch (NumberFormatException e) {
e.getStackTrace();
}
}
}
}
return stats_altered.getStandardDeviation();
case "unaltered":
DescriptiveStatistics stats_unaltered = new DescriptiveStatistics();
for (Integer unalteredSampleId : unalteredSampleIds) {
if (singleGeneCaseValueMap.containsKey(unalteredSampleId)) {
if (profileStableId.indexOf("rna_seq") != -1) {
try {
stats_unaltered.addValue(
Math.log(Double.parseDouble(singleGeneCaseValueMap.get(unalteredSampleId)))
/ Math.log(2));
} catch (NumberFormatException e) {
e.getStackTrace();
}
} else {
try {
stats_unaltered.addValue(
Double.parseDouble(singleGeneCaseValueMap.get(unalteredSampleId)));
} catch (NumberFormatException e) {
e.getStackTrace();
}
}
}
}
return stats_unaltered.getStandardDeviation();
default:
return Double.NaN; // error
}
}
public static void main(String[] args) {
double delta = 0.0001;
double sigma = 0.005;
double P_e = 0.01;
int i =
(int)
Math.ceil(
(0.5 * (Math.log((sigma * sigma) / (delta * delta * P_e)) / Math.log(2.0))) + 1);
i = Math.min(i, 63); // request not more that 63 bits
i = Math.max(0, i); // request no less than 0 bits
}
public TopicScores getTokenDocumentDiscrepancies() {
TopicScores scores = new TopicScores("token-doc-diff", numTopics, numTopWords);
scores.wordScoresDefined = true;
for (int topic = 0; topic < numTopics; topic++) {
int[][] matrix = topicCodocumentMatrices[topic];
TreeSet<IDSorter> sortedWords = topicSortedWords.get(topic);
double topicScore = 0.0;
double[] wordDistribution = new double[numTopWords];
double[] docDistribution = new double[numTopWords];
double wordSum = 0.0;
double docSum = 0.0;
int position = 0;
Iterator<IDSorter> iterator = sortedWords.iterator();
while (iterator.hasNext() && position < numTopWords) {
IDSorter info = iterator.next();
wordDistribution[position] = info.getWeight();
docDistribution[position] = matrix[position][position];
wordSum += wordDistribution[position];
docSum += docDistribution[position];
position++;
}
for (position = 0; position < numTopWords; position++) {
double p = wordDistribution[position] / wordSum;
double q = docDistribution[position] / docSum;
double meanProb = 0.5 * (p + q);
double score = 0.0;
if (p > 0) {
score += 0.5 * p * Math.log(p / meanProb);
}
if (q > 0) {
score += 0.5 * q * Math.log(q / meanProb);
}
scores.setTopicWordScore(topic, position, score);
topicScore += score;
}
scores.setTopicScore(topic, topicScore);
}
return scores;
}
public void addCrossNumericProximity(Counter<String> features, final NumericMentionExpression e) {
List<NumericTuple> args = e.expression.arguments();
if (args.size() > 1) {
double multiplier = args.get(0).val / args.get(1).val;
features.incrementCount("abs-numeric-distance-12", Math.abs(Math.log(multiplier)));
}
if (args.size() > 2) {
double multiplier13 = args.get(0).val / args.get(2).val;
double multiplier23 = args.get(1).val / args.get(2).val;
features.incrementCount("abs-numeric-distance-13", Math.abs(Math.log(multiplier13)));
features.incrementCount("abs-numeric-distance-23", Math.abs(Math.log(multiplier23)));
}
}
// Entropy(S) = - sum(1..n) [ p(i)*log(pi)}
private double computeEntropy() {
double sum = 0.0;
int numTags = myTags.size();
for (int i = 0; i < numTags; i++) {
String tag = (String) myTags.elementAt(i);
if (!tag.equals(boundaryTag)) {
double probTag = getUnigramProb(tag);
double logProbTag = Math.log(probTag) / Math.log(2.0); // Math.log is natural log, base e
sum += probTag * logProbTag;
}
}
return -sum;
}
/**
* specifies the function LND6 on double[] x.
*
* @param x double[]
* @return double
*/
private double evalArray(double[] x) {
double res = Double.NEGATIVE_INFINITY;
for (int i = 0; i < x.length; i++) {
double gxi = Math.log(Math.abs(x[i]) + 1);
if (gxi > res) res = gxi;
}
double sum = 0.0;
for (int i = 0; i < x.length; i++) {
sum += x[i];
}
sum = Math.log(Math.abs(sum) + 1);
if (sum > res) res = sum;
return res;
}