Changeset 12492

Timestamp:

06/22/15 20:04:01 (10 years ago)

Author:

gkronber

Message:

#2392: implemented PearsonsRCalculator to fix incorrect correlation values in the correlation matrix.

Location:

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4

Files:

• HeuristicLab.Problems.DataAnalysis-3.4.csproj (modified) (1 diff)
• OnlineCalculators/DependencyCalculator/PearsonsRDependenceCalculator.cs (modified) (1 diff)
• OnlineCalculators/OnlinePearsonsRCalculator.cs (copied) (copied from trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/OnlineCalculators/OnlinePearsonsRSquaredCalculator.cs) (5 diffs)
• OnlineCalculators/OnlinePearsonsRSquaredCalculator.cs (modified) (4 diffs)

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/HeuristicLab.Problems.DataAnalysis-3.4.csproj

@@ -222 +222 @@
     <Compile Include="OnlineCalculators\OnlineMeanSquaredErrorCalculator.cs" />
     <Compile Include="OnlineCalculators\OnlineNormalizedMeanSquaredErrorCalculator.cs" />
+    <Compile Include="OnlineCalculators\OnlinePearsonsRCalculator.cs" />
     <Compile Include="OnlineCalculators\OnlinePearsonsRSquaredCalculator.cs" />
     <Compile Include="Implementation\Regression\RegressionSolution.cs" />

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/OnlineCalculators/DependencyCalculator/PearsonsRDependenceCalculator.cs

@@ -33 +33 @@
 
     public double Calculate(IEnumerable<double> originalValues, IEnumerable<double> estimatedValues, out OnlineCalculatorError errorState) {
-      return Math.Sqrt(OnlinePearsonsRSquaredCalculator.Calculate(originalValues, estimatedValues, out errorState));
+      return OnlinePearsonsRCalculator.Calculate(originalValues, estimatedValues, out errorState);
     }
   }

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/OnlineCalculators/OnlinePearsonsRCalculator.cs

@@ -25 +25 @@
 
 namespace HeuristicLab.Problems.DataAnalysis {
-  public class OnlinePearsonsRSquaredCalculator : IOnlineCalculator {
+  public class OnlinePearsonsRCalculator : IOnlineCalculator {
     private OnlineCovarianceCalculator covCalculator = new OnlineCovarianceCalculator();
     private OnlineMeanAndVarianceCalculator sxCalculator = new OnlineMeanAndVarianceCalculator();
     private OnlineMeanAndVarianceCalculator syCalculator = new OnlineMeanAndVarianceCalculator();
 
-    public double RSquared {
+    public double R {
       get {
         double xVar = sxCalculator.PopulationVariance;
@@ -37 +37 @@
           return 0.0;
         } else {
-          double r = covCalculator.Covariance / (Math.Sqrt(xVar) * Math.Sqrt(yVar));
-          return r * r;
+          return covCalculator.Covariance / (Math.Sqrt(xVar) * Math.Sqrt(yVar));
         }
       }
     }
 
-    public OnlinePearsonsRSquaredCalculator() { }
+    public OnlinePearsonsRCalculator() { }
 
     #region IOnlineCalculator Members
@@ -50 +49 @@
     }
     public double Value {
-      get { return RSquared; }
+      get { return R; }
     }
     public void Reset() {
@@ -70 +69 @@
       IEnumerator<double> firstEnumerator = first.GetEnumerator();
       IEnumerator<double> secondEnumerator = second.GetEnumerator();
-      OnlinePearsonsRSquaredCalculator rSquaredCalculator = new OnlinePearsonsRSquaredCalculator();
+      var calculator = new OnlinePearsonsRCalculator();
 
       // always move forward both enumerators (do not use short-circuit evaluation!)
@@ -76 +75 @@
         double original = firstEnumerator.Current;
         double estimated = secondEnumerator.Current;
-        rSquaredCalculator.Add(original, estimated);
-        if (rSquaredCalculator.ErrorState != OnlineCalculatorError.None) break;
+        calculator.Add(original, estimated);
+        if (calculator.ErrorState != OnlineCalculatorError.None) break;
       }
 
       // check if both enumerators are at the end to make sure both enumerations have the same length
-      if (rSquaredCalculator.ErrorState == OnlineCalculatorError.None &&
+      if (calculator.ErrorState == OnlineCalculatorError.None &&
            (secondEnumerator.MoveNext() || firstEnumerator.MoveNext())) {
         throw new ArgumentException("Number of elements in first and second enumeration doesn't match.");
       } else {
-        errorState = rSquaredCalculator.ErrorState;
-        return rSquaredCalculator.RSquared;
+        errorState = calculator.ErrorState;
+        return calculator.R;
       }
     }

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/OnlineCalculators/OnlinePearsonsRSquaredCalculator.cs

@@ -25 +25 @@
 
 namespace HeuristicLab.Problems.DataAnalysis {
+  [Obsolete("Use OnlinePearsonsRCalculator directly")]
   public class OnlinePearsonsRSquaredCalculator : IOnlineCalculator {
-    private OnlineCovarianceCalculator covCalculator = new OnlineCovarianceCalculator();
-    private OnlineMeanAndVarianceCalculator sxCalculator = new OnlineMeanAndVarianceCalculator();
-    private OnlineMeanAndVarianceCalculator syCalculator = new OnlineMeanAndVarianceCalculator();
+    private readonly OnlinePearsonsRCalculator rCalculator = new OnlinePearsonsRCalculator();
 
     public double RSquared {
       get {
-        double xVar = sxCalculator.PopulationVariance;
-        double yVar = syCalculator.PopulationVariance;
-        if (xVar.IsAlmost(0.0) || yVar.IsAlmost(0.0)) {
-          return 0.0;
-        } else {
-          double r = covCalculator.Covariance / (Math.Sqrt(xVar) * Math.Sqrt(yVar));
-          return r * r;
-        }
+        if (rCalculator.ErrorState != OnlineCalculatorError.None) return 0.0;
+        else return rCalculator.R * rCalculator.R;
       }
     }
@@ -47 +40 @@
     #region IOnlineCalculator Members
     public OnlineCalculatorError ErrorState {
-      get { return covCalculator.ErrorState | sxCalculator.PopulationVarianceErrorState | syCalculator.PopulationVarianceErrorState; }
+      get { return rCalculator.ErrorState; }
     }
     public double Value {
@@ -53 +46 @@
     }
     public void Reset() {
-      covCalculator.Reset();
-      sxCalculator.Reset();
-      syCalculator.Reset();
+      rCalculator.Reset();
     }
 
     public void Add(double x, double y) {
-      // no need to check validity of values explicitly here as it is checked in all three evaluators 
-      covCalculator.Add(x, y);
-      sxCalculator.Add(x);
-      syCalculator.Add(y);
+      rCalculator.Add(x, y);
     }
 
@@ -68 +56 @@
 
     public static double Calculate(IEnumerable<double> first, IEnumerable<double> second, out OnlineCalculatorError errorState) {
-      IEnumerator<double> firstEnumerator = first.GetEnumerator();
-      IEnumerator<double> secondEnumerator = second.GetEnumerator();
-      OnlinePearsonsRSquaredCalculator rSquaredCalculator = new OnlinePearsonsRSquaredCalculator();
-
-      // always move forward both enumerators (do not use short-circuit evaluation!)
-      while (firstEnumerator.MoveNext() & secondEnumerator.MoveNext()) {
-        double original = firstEnumerator.Current;
-        double estimated = secondEnumerator.Current;
-        rSquaredCalculator.Add(original, estimated);
-        if (rSquaredCalculator.ErrorState != OnlineCalculatorError.None) break;
-      }
-
-      // check if both enumerators are at the end to make sure both enumerations have the same length
-      if (rSquaredCalculator.ErrorState == OnlineCalculatorError.None &&
-           (secondEnumerator.MoveNext() || firstEnumerator.MoveNext())) {
-        throw new ArgumentException("Number of elements in first and second enumeration doesn't match.");
-      } else {
-        errorState = rSquaredCalculator.ErrorState;
-        return rSquaredCalculator.RSquared;
-      }
+      var r = OnlinePearsonsRCalculator.Calculate(first, second, out errorState);
+      return r * r;
     }
   }