num4anova 0.0.15-java → 0.0.16-java

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 81c39fe39ac94774f6ce94343e91c968190c63c510c9742d0a4b1e33c6f1a399
-  data.tar.gz: 9ba93973bdf9ad7237dd02702b67cd493335659a9b9f9162976ecb703ae351db
+  metadata.gz: fb1dd347cd1156e1cc9e06ee7b4daff32442d6fc721e35553cbb406ae5d94cf1
+  data.tar.gz: 17d4c4084a40fe8e721829169e2551455d258f64dd4ef6c537b499ef9a5dab15
 SHA512:
-  metadata.gz: c2d3ffd3cbf0bcb0c4955c64c587b48da9d878bb61ce5c3a2b547de4c6563bafbf6852aa032e378d318419e55d6583f4af6467a7456a598501d6acea5f2b9c91
-  data.tar.gz: 7d97f9780f7d68f601810ac5ba5bcda923050b80e11fbff53b78017ceb61d954a788bb62f9a1dc85bc79c7e4fd0be857c538d6647d7506f91c6100295891238d
+  metadata.gz: 768b64803a235265e1dae41341428a0bda9fb12245e7f2fae54a3f75f8aeee607a4cd3709b578b1c7aeb6869fcc7f227b287d2142b99411ed8955248eeafedd4
+  data.tar.gz: da4c649d32a38c9f9a83adadc54d20605bfebe42f822fdd353df7ba8e00df8e3be8fbd8c4775474da5299957a477ec98c4912ec1ac5b8fb0d305c0f11ad91ff0

data/CHANGELOG.md

@@ -2,6 +2,11 @@
 
 ## Unreleased
 
+## [0.0.16] - 2024-04-16
+
+### add
+- add fuction of bonferrono_test in friedman_test.
+
 ## [0.0.15] - 2024-04-13
 
 ### add

data/ext/num4anova/TwoWayLayout.java

@@ -1,6 +1,11 @@
 import org.apache.commons.math3.stat.descriptive.DescriptiveStatistics;
 import org.apache.commons.math3.distribution.FDistribution;
+import org.apache.commons.math3.distribution.ChiSquaredDistribution;
 import java.util.Arrays;
+
+import org.apache.commons.math3.stat.ranking.NaNStrategy;
+import org.apache.commons.math3.stat.ranking.NaturalRanking;
+import org.apache.commons.math3.stat.ranking.TiesStrategy;
 public class TwoWayLayout {
     private static TwoWayLayout twoWay = new TwoWayLayout();
     public static TwoWayLayout getInstance() {
@@ -18,16 +23,26 @@ public class TwoWayLayout {
         double[] statistic = twoway.calcTestStatistic(xij);
         return twoway.execute_test(statistic, a);
     }
+    public boolean friedmanTest(double[][] xij, double a) {
+        OneWayAnovaTest twoway = new FriedmanTest();
+
+        double statistic = twoway.calcTestStatistic(xij);
+        return twoway.execute_test(statistic, a);
+    }
     /*********************************/
     /* interface define              */
     /*********************************/
     private interface TwoWayAnovaTest {
         double[] calcTestStatistic(double[][][] xij);
-        boolean[] execute_test(double statistic[], double a);
+        boolean[] execute_test(double[] statistic, double a);
     }
     private interface TwoWay2AnovaTest {
         double[] calcTestStatistic(double[][] xij);
-        boolean[] execute_test(double statistic[], double a);
+        boolean[] execute_test(double[] statistic, double a);
+    }
+    private interface OneWayAnovaTest {
+        double calcTestStatistic(double[][] xi);
+        boolean execute_test(double statistic, double a);
     }
     /*********************************/
     /* class define                  */
@@ -162,7 +177,7 @@ public class TwoWayLayout {
             }
             return sumDrift;
         }
-        public boolean[] execute_test(double statistic[], double a) {
+        public boolean[] execute_test(double[] statistic, double a) {
             boolean[] ret = new boolean[3];
 
             ret[0] = evaluation(new FDistribution(an, en), statistic[0], a);
@@ -269,7 +284,7 @@ public class TwoWayLayout {
             return sumDrift;
         }
 
-        public boolean[] execute_test(double statistic[], double a) {
+        public boolean[] execute_test(double[] statistic, double a) {
             boolean[] ret = new boolean[2];
 
             ret[0] = evaluation(new FDistribution(an, en), statistic[0], a);
@@ -282,5 +297,64 @@ public class TwoWayLayout {
             return (statistic >= r_val) ? true : false;
         }
     }
+    // フリードマンの検定
+    private class FriedmanTest implements  OneWayAnovaTest{
+        private NaturalRanking naturalRanking;
+        private int n = 0;
+        private int k = 0;
+        public FriedmanTest()  {
+            naturalRanking = new NaturalRanking(NaNStrategy.FIXED, 
+                                                 TiesStrategy.AVERAGE);
+        }
+        public double calcTestStatistic(double[][] xij) {
+            n = xij[0].length;
+            k = xij.length;
+            double[][] z = concatSample(xij);
+            double[][] ranks = calcRankij(z);
+            double[] sumRankXi = calcSumRankXi(ranks);
+            double kw = 0.0;
+
+            for(int i = 0; i < sumRankXi.length; i++) {
+                kw += sumRankXi[i] * sumRankXi[i];
+            }
+            return 12.0 / (n * k * (k + 1.0)) * kw - 3.0 * n * (k + 1.0);
+        }
+        public boolean execute_test(double statistic, double a) {
+            ChiSquaredDistribution chi2Dist = new ChiSquaredDistribution(k - 1);
+
+            double r_val = chi2Dist.inverseCumulativeProbability(1.0 - a);
+
+            return (r_val < statistic) ? true : false;
+        }
+        private double[][] concatSample(double[][] xi) {
+            double[][] z = new double[n][k];
+
+            for(int i = 0; i < k; i++) {
+                for(int j = 0; j < n; j++) {
+                    z[j][i] = xi[i][j];
+                }
+            }
+            return z;
+        }
+        private double[][] calcRankij(double[][] z) {
+            double[][] ranks = new double[n][k];
+
+            for(int i = 0; i < n; i++) {
+                ranks[i] = naturalRanking.rank(z[i]);
+            }
+            return ranks;
+        }
+        private double[] calcSumRankXi(double[][] ranks) {
+            double[] sumRi = new double[k];
+
+            for(int i = 0; i < k; i++) {
+                sumRi[i] = 0.0;
+                for(int j = 0; j < n; j++) {
+                    sumRi[i] += ranks[j][i];
+                }
+            }
+            return sumRi;
+        }
+    }
 }
 

data/lib/num4anova.rb

@@ -157,12 +157,11 @@ module Num4AnovaLib
         #   @param [array]  xi データ(double[][])
         #   @param [double] a         有意水準
         #   @return [boolean] 検定結果(true:棄却域内 false:棄却域外)
+        # @example
         #   xi = [
-        #       [12.2, 18.8, 18.2],
-        #       [22.2, 20.5, 14.6],
-        #       [20.8, 19.5, 26.3],
-        #       [26.4, 32.5, 31.3],
-        #       [24.5, 21.2, 22.4],
+        #        [12.2, 18.8, 18.2],
+        #        [22.2, 20.5, 14.6, 20.8, 19.5, 26.3],
+        #        [26.4, 32.5, 31.3, 24.5, 21.2, 22.4],
         #   ]
         #   oneWay = Num4AnovaLib::OneWayLayoutLib.new 
         #   oneWay.kruskalwallis_test(xi, 0.05)
@@ -236,6 +235,27 @@ module Num4AnovaLib
         def twoway2_anova(xij, a)
             ret = @twoWay.twoway2Anova(xij.to_java(Java::double[]), a)
             return ret.to_a
+        end
+        # フリードマン検定
+        #
+        # @overload friedman_test(xij, a)
+        #   @param [array]  xij データ(double[][])
+        #   @param [double] a         有意水準
+        #   @return [boolean] 検定結果(boolean true:棄却域内 false:棄却域外)
+        # @example
+        #   xij = [
+        #       [13.6, 15.6, 9.2],
+        #       [22.3, 23.3, 13.3],
+        #       [26.7, 28.8, 15.0],
+        #       [28.0, 31.2, 15.8],
+        #   ]
+        #   twoWay = Num4AnovaLib::TwoWayLayoutLib.new 
+        #   twoWay.friedman_test(xij, 0.05)
+        #   =>
+        #     true
+        def friedman_test(xij, a)
+            ret = @twoWay.friedmanTest(xij.to_java(Java::double[]), a)
+            return ret
         end        
     end
     # 共分散分析

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: num4anova
 version: !ruby/object:Gem::Version
-  version: 0.0.15
+  version: 0.0.16
 platform: java
 authors:
 - siranovel
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2024-04-13 00:00:00.000000000 Z
+date: 2024-04-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake