Changeset 14232 for branches/symbreg-factors-2650/HeuristicLab.Problems.DataAnalysis.Symbolic/3.4/Interpreter

Timestamp:

08/03/16 18:54:14 (8 years ago)

Author:

gkronber

Message:

created a feature branch for #2650 (support for categorical variables in symb reg) with a first set of changes

work in progress...

Location:

branches/symbreg-factors-2650

Files:

• . (copied) (copied from trunk/sources)
• HeuristicLab.Problems.DataAnalysis.Symbolic/3.4/Interpreter/OpCodes.cs (modified) (2 diffs)
• HeuristicLab.Problems.DataAnalysis.Symbolic/3.4/Interpreter/SymbolicDataAnalysisExpressionTreeILEmittingInterpreter.cs (modified) (2 diffs)
• HeuristicLab.Problems.DataAnalysis.Symbolic/3.4/Interpreter/SymbolicDataAnalysisExpressionTreeInterpreter.cs (modified) (3 diffs)
• HeuristicLab.Problems.DataAnalysis.Symbolic/3.4/Interpreter/SymbolicDataAnalysisExpressionTreeLinearInterpreter.cs (modified) (2 diffs)

branches/symbreg-factors-2650/HeuristicLab.Problems.DataAnalysis.Symbolic/3.4/Interpreter/OpCodes.cs

@@ -83 +83 @@
     public const byte Erf = 43;
     public const byte Bessel = 44;
+    public const byte FactorVariable = 46;
 
     private static Dictionary<Type, byte> symbolToOpcode = new Dictionary<Type, byte>() {
@@ -130 +131 @@
       { typeof(Norm), OpCodes.Norm},
       { typeof(Erf), OpCodes.Erf},
-      { typeof(Bessel), OpCodes.Bessel}   
+      { typeof(Bessel), OpCodes.Bessel},
+      { typeof(FactorVariable), OpCodes.FactorVariable }
     };
 

branches/symbreg-factors-2650/HeuristicLab.Problems.DataAnalysis.Symbolic/3.4/Interpreter/SymbolicDataAnalysisExpressionTreeILEmittingInterpreter.cs

@@ -66 +66 @@
     private static MethodInfo erf = thisType.GetMethod("Erf", new Type[] { typeof(double) });
     private static MethodInfo bessel = thisType.GetMethod("Bessel", new Type[] { typeof(double) });
+    private static MethodInfo string_eq = typeof(string).GetMethod("Equals", new Type[] {typeof(string)});
     #endregion
 
@@ -627 +628 @@
             return;
           }
+        case OpCodes.FactorVariable: {
+            FactorVariableTreeNode varNode = currentInstr.dynamicNode as FactorVariableTreeNode;
+            il.Emit(System.Reflection.Emit.OpCodes.Ldarg_1); // load columns array
+            il.Emit(System.Reflection.Emit.OpCodes.Ldc_I4, (int)currentInstr.data);
+            // load correct column of the current variable
+            il.Emit(System.Reflection.Emit.OpCodes.Ldelem_Ref);
+            il.Emit(System.Reflection.Emit.OpCodes.Ldarg_0); // rowIndex
+            if (!state.InLaggedContext) {
+              il.Emit(System.Reflection.Emit.OpCodes.Call, listGetValue);
+              il.Emit(System.Reflection.Emit.OpCodes.Ldc_R8, varNode.VariableValue); 
+              il.Emit(System.Reflection.Emit.OpCodes.Call, string_eq);
+              // TODO: convert bool to 1 / 0?
+            } else {
+              var nanResult = il.DefineLabel();
+              var normalResult = il.DefineLabel();
+              il.Emit(System.Reflection.Emit.OpCodes.Dup);
+              il.Emit(System.Reflection.Emit.OpCodes.Ldc_I4_0);
+              il.Emit(System.Reflection.Emit.OpCodes.Blt, nanResult);
+              il.Emit(System.Reflection.Emit.OpCodes.Dup);
+              il.Emit(System.Reflection.Emit.OpCodes.Ldc_I4, ds.Rows);
+              il.Emit(System.Reflection.Emit.OpCodes.Bge, nanResult);
+              il.Emit(System.Reflection.Emit.OpCodes.Call, listGetValue);
+              il.Emit(System.Reflection.Emit.OpCodes.Ldc_R8, varNode.VariableValue);
+              il.Emit(System.Reflection.Emit.OpCodes.Call, string_eq);
+              // TODO: convert bool to 1 / 0?
+              il.Emit(System.Reflection.Emit.OpCodes.Br, normalResult);
+              il.MarkLabel(nanResult);
+              il.Emit(System.Reflection.Emit.OpCodes.Pop); // rowIndex
+              il.Emit(System.Reflection.Emit.OpCodes.Pop); // column reference
+              il.Emit(System.Reflection.Emit.OpCodes.Ldc_R8, double.NaN);
+              il.MarkLabel(normalResult);
+            }
+            return;
+          }
         case OpCodes.LagVariable: {
             var nanResult = il.DefineLabel();

branches/symbreg-factors-2650/HeuristicLab.Problems.DataAnalysis.Symbolic/3.4/Interpreter/SymbolicDataAnalysisExpressionTreeInterpreter.cs

@@ -22 +22 @@
 using System;
 using System.Collections.Generic;
+using System.Linq;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
@@ -143 +144 @@
           var variableTreeNode = (VariableTreeNode)instr.dynamicNode;
           instr.data = dataset.GetReadOnlyDoubleValues(variableTreeNode.VariableName);
+        } else if (instr.opCode == OpCodes.FactorVariable) {
+          var factorTreeNode = instr.dynamicNode as FactorVariableTreeNode;
+          instr.data = dataset.GetReadOnlyStringValues(factorTreeNode.VariableName); 
         } else if (instr.opCode == OpCodes.LagVariable) {
           var laggedVariableTreeNode = (LaggedVariableTreeNode)instr.dynamicNode;
@@ -455 +459 @@
             return ((IList<double>)currentInstr.data)[row] * variableTreeNode.Weight;
           }
+        case OpCodes.FactorVariable: {
+            if (row < 0 || row >= dataset.Rows) return double.NaN;
+            var factorVarTreeNode = currentInstr.dynamicNode as FactorVariableTreeNode;
+            return ((IList<string>)currentInstr.data)[row] == factorVarTreeNode.VariableValue ? 1 : 0;
+          }
         case OpCodes.LagVariable: {
             var laggedVariableTreeNode = (LaggedVariableTreeNode)currentInstr.dynamicNode;

branches/symbreg-factors-2650/HeuristicLab.Problems.DataAnalysis.Symbolic/3.4/Interpreter/SymbolicDataAnalysisExpressionTreeLinearInterpreter.cs

@@ -147 +147 @@
             var variableTreeNode = (VariableTreeNode)instr.dynamicNode;
             instr.value = ((IList<double>)instr.data)[row] * variableTreeNode.Weight;
+          }
+        } else if (instr.opCode == OpCodes.FactorVariable) {
+          if (row < 0 || row >= dataset.Rows) instr.value = double.NaN;
+          else {
+            var factorTreeNode = instr.dynamicNode as FactorVariableTreeNode;
+            instr.value = ((IList<string>)instr.data)[row] == factorTreeNode.VariableValue ? 1 : 0;
           }
         } else if (instr.opCode == OpCodes.LagVariable) {
@@ -392 +398 @@
             }
             break;
+          case OpCodes.FactorVariable: {
+              var factorVariableTreeNode = instr.dynamicNode as FactorVariableTreeNode;
+              instr.data = dataset.GetReadOnlyStringValues(factorVariableTreeNode.VariableName);
+            }
+            break;
           case OpCodes.LagVariable: {
               var laggedVariableTreeNode = (LaggedVariableTreeNode)instr.dynamicNode;