Changeset 14117 for stable/HeuristicLab.Problems.Instances.DataAnalysis/3.3/Regression/VariableNetworks

Timestamp:

07/19/16 16:53:37 (8 years ago)

Author:

mkommend

Message:

#2618: Merged r13939, r13963, r14110 into stable.

Location:

stable

Files:

• . (modified) (1 prop)
• HeuristicLab.Problems.Instances.DataAnalysis (modified) (1 prop)
• HeuristicLab.Problems.Instances.DataAnalysis/3.3/Regression/VariableNetworks (copied) (copied from trunk/sources/HeuristicLab.Problems.Instances.DataAnalysis/3.3/Regression/VariableNetworks)
• HeuristicLab.Problems.Instances.DataAnalysis/3.3/Regression/VariableNetworks/VariableNetwork.cs (modified) (8 diffs)
• HeuristicLab.Problems.Instances.DataAnalysis/3.3/Regression/VariableNetworks/VariableNetworkInstanceProvider.cs (modified) (2 diffs)

stable/HeuristicLab.Problems.Instances.DataAnalysis/3.3/Regression/VariableNetworks/VariableNetwork.cs

@@ -23 +23 @@
 using System.Collections.Generic;
 using System.Linq;
-using System.Text;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
@@ -86 +85 @@
 
     protected override List<List<double>> GenerateValues() {
-      // var shuffledIdx = Enumerable.Range(0, numberOfFeatures).Shuffle(random).ToList();
-
       // variable names are shuffled in the beginning (and sorted at the end)
       variableNames = variableNames.Shuffle(random).ToArray();
 
-      // a third of all variables are independen vars
+      // a third of all variables are independent vars
       List<List<double>> lvl0 = new List<List<double>>();
       int numLvl0 = (int)Math.Ceiling(numberOfFeatures * 0.33);
 
       List<string> description = new List<string>(); // store information how the variable is actually produced
+      List<string[]> inputVarNames = new List<string[]>(); // store information to produce graphviz file
 
       var nrand = new NormalDistributedRandom(random, 0, 1);
       for (int c = 0; c < numLvl0; c++) {
         var datai = Enumerable.Range(0, TestPartitionEnd).Select(_ => nrand.NextDouble()).ToList();
+        inputVarNames.Add(new string[] { });
         description.Add("~ N(0, 1)");
         lvl0.Add(datai);
@@ -108 +107 @@
       int numLvl1 = (int)Math.Ceiling(numberOfFeatures * 0.33);
       for (int c = 0; c < numLvl1; c++) {
-        string desc;
-        var x = GenerateRandomFunction(random, lvl0, out desc);
+        string[] selectedVarNames;
+        var x = GenerateRandomFunction(random, lvl0, out selectedVarNames);
         var sigma = x.StandardDeviation();
         var noisePrng = new NormalDistributedRandom(random, 0, sigma * Math.Sqrt(noiseRatio / (1.0 - noiseRatio)));
         lvl1.Add(x.Select(t => t + noisePrng.NextDouble()).ToList());
+
+        inputVarNames.Add(selectedVarNames);
+        var desc = string.Format("f({0})", string.Join(",", selectedVarNames));
         description.Add(string.Format(" ~ N({0}, {1:N3})", desc, noisePrng.Sigma));
       }
@@ -120 +122 @@
       int numLvl2 = (int)Math.Ceiling(numberOfFeatures * 0.2);
       for (int c = 0; c < numLvl2; c++) {
-        string desc;
-        var x = GenerateRandomFunction(random, lvl0.Concat(lvl1).ToList(), out desc);
+        string[] selectedVarNames;
+        var x = GenerateRandomFunction(random, lvl0.Concat(lvl1).ToList(), out selectedVarNames);
         var sigma = x.StandardDeviation();
         var noisePrng = new NormalDistributedRandom(random, 0, sigma * Math.Sqrt(noiseRatio / (1.0 - noiseRatio)));
         lvl2.Add(x.Select(t => t + noisePrng.NextDouble()).ToList());
+
+        inputVarNames.Add(selectedVarNames);
+        var desc = string.Format("f({0})", string.Join(",", selectedVarNames));
         description.Add(string.Format(" ~ N({0}, {1:N3})", desc, noisePrng.Sigma));
       }
@@ -132 +137 @@
       int numLvl3 = numberOfFeatures - numLvl0 - numLvl1 - numLvl2;
       for (int c = 0; c < numLvl3; c++) {
-        string desc;
-        var x = GenerateRandomFunction(random, lvl0.Concat(lvl1).Concat(lvl2).ToList(), out desc);
+        string[] selectedVarNames;
+        var x = GenerateRandomFunction(random, lvl0.Concat(lvl1).Concat(lvl2).ToList(), out selectedVarNames);
         var sigma = x.StandardDeviation();
         var noisePrng = new NormalDistributedRandom(random, 0, sigma * Math.Sqrt(noiseRatio / (1.0 - noiseRatio)));
         lvl3.Add(x.Select(t => t + noisePrng.NextDouble()).ToList());
+
+        inputVarNames.Add(selectedVarNames);
+        var desc = string.Format("f({0})", string.Join(",", selectedVarNames));
         description.Add(string.Format(" ~ N({0}, {1:N3})", desc, noisePrng.Sigma));
       }
+
+      networkDefinition = string.Join(Environment.NewLine, variableNames.Zip(description, (n, d) => n + d));
+      // for graphviz
+      networkDefinition += Environment.NewLine + "digraph G {";
+      foreach (var t in variableNames.Zip(inputVarNames, Tuple.Create).OrderBy(t => t.Item1)) {
+        var name = t.Item1;
+        var selectedVarNames = t.Item2;
+        foreach (var selectedVarName in selectedVarNames) {
+          networkDefinition += Environment.NewLine + selectedVarName + " -> " + name;
+        }
+      }
+      networkDefinition += Environment.NewLine + "}";
 
       // return a random permutation of all variables
       var allVars = lvl0.Concat(lvl1).Concat(lvl2).Concat(lvl3).ToList();
-      networkDefinition = string.Join(Environment.NewLine, variableNames.Zip(description, (n, d) => n + d));
       var orderedVars = allVars.Zip(variableNames, Tuple.Create).OrderBy(t => t.Item2).Select(t => t.Item1).ToList();
       variableNames = variableNames.OrderBy(n => n).ToArray();
@@ -149 +168 @@
 
     // sample the input variables that are actually used and sample from a Gaussian process
-    private IEnumerable<double> GenerateRandomFunction(IRandom rand, List<List<double>> xs, out string desc) {
-      int nRows = xs.First().Count;
-
+    private IEnumerable<double> GenerateRandomFunction(IRandom rand, List<List<double>> xs, out string[] selectedVarNames) {
       double r = -Math.Log(1.0 - rand.NextDouble()) * 2.0; // r is exponentially distributed with lambda = 2
       int nl = (int)Math.Floor(1.5 + r); // number of selected vars is likely to be between three and four
@@ -160 +177 @@
 
       var selectedVars = selectedIdx.Select(i => xs[i]).ToArray();
-      desc = string.Format("f({0})", string.Join(",", selectedIdx.Select(i => VariableNames[i])));
+      selectedVarNames = selectedIdx.Select(i => VariableNames[i]).ToArray();
       return SampleGaussianProcess(random, selectedVars);
     }
@@ -171 +188 @@
       // sample length-scales
       var l = Enumerable.Range(0, nl)
-        .Select(_ => random.NextDouble()*2+0.5)
+        .Select(_ => random.NextDouble() * 2 + 0.5)
         .ToArray();
       // calculate covariance matrix

stable/HeuristicLab.Problems.Instances.DataAnalysis/3.3/Regression/VariableNetworks/VariableNetworkInstanceProvider.cs

@@ -22 +22 @@
 using System;
 using System.Collections.Generic;
-using System.Linq;                                                         
+using System.Linq;
 using HeuristicLab.Problems.DataAnalysis;
 using HeuristicLab.Random;
@@ -56 +56 @@
       if (varNetwork == null) throw new ArgumentException("VariableNetworkInstanceProvider expects an VariableNetwork data descriptor.");
       // base call generates a regression problem data
-      var regProblemData = base.LoadData(varNetwork);
-      var problemData =
-        new RegressionProblemData(
-          regProblemData.Dataset, regProblemData.AllowedInputVariables, regProblemData.TargetVariable);
-
-      // copy values from regProblemData to feature selection problem data
-      problemData.Name = regProblemData.Name;
+      var problemData = base.LoadData(varNetwork);
       problemData.Description = varNetwork.Description + Environment.NewLine + varNetwork.NetworkDefinition;
-      problemData.TrainingPartition.Start = regProblemData.TrainingPartition.Start;
-      problemData.TrainingPartition.End = regProblemData.TrainingPartition.End;
-      problemData.TestPartition.Start = regProblemData.TestPartition.Start;
-      problemData.TestPartition.End = regProblemData.TestPartition.End;
-
       return problemData;
     }