Changeset 17476 for branches/3040_VectorBasedGP/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression

Timestamp:

03/12/20 17:51:39 (5 years ago)

Author:

pfleck

Message:

#3040 Worked on TF-based constant optimization.

File:

• branches/3040_VectorBasedGP/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/SingleObjective/Evaluators/TensorFlowConstantOptimizationEvaluator.cs (modified) (4 diffs)

branches/3040_VectorBasedGP/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/SingleObjective/Evaluators/TensorFlowConstantOptimizationEvaluator.cs

@@ -23 +23 @@
 using System.Collections;
 using System.Collections.Generic;
+using System.Diagnostics;
 using System.Linq;
 using System.Threading;
@@ -31 +32 @@
 using HeuristicLab.Parameters;
 using HEAL.Attic;
+using NumSharp;
 using Tensorflow;
 using static Tensorflow.Binding;
@@ -92 +94 @@
       CancellationToken cancellationToken = default(CancellationToken), EvaluationsCounter counter = null) {
 
-      bool success = TreeToTensorConverter.TryConvert(tree, updateVariableWeights, applyLinearScaling,
-        out Tensor prediction, out Dictionary<TreeToTensorConverter.DataForVariable, Tensor> variables/*, out double[] initialConstants*/);
+      var vectorVariables = tree.IterateNodesBreadth()
+        .OfType<VariableTreeNodeBase>()
+        .Where(node => problemData.Dataset.VariableHasType<DoubleVector>(node.VariableName))
+        .Select(node => node.VariableName);
+
+      int? vectorLength = null;
+      if (vectorVariables.Any()) {
+        vectorLength = vectorVariables.Select(var => problemData.Dataset.GetDoubleVectorValues(var, rows)).First().First().Count;
+      }
+      int numRows = rows.Count();
+
+      bool success = TreeToTensorConverter.TryConvert(tree,
+        numRows, vectorLength,
+        updateVariableWeights, applyLinearScaling,
+        out Tensor prediction,
+        out Dictionary<Tensor, string> parameters, out List<Tensor> variables/*, out double[] initialConstants*/);
 
       var target = tf.placeholder(tf.float64, name: problemData.TargetVariable);
@@ -99 +115 @@
       // mse
       var costs = tf.reduce_sum(tf.square(prediction - target)) / (2.0 * samples);
-      var optimizer = tf.train.GradientDescentOptimizer((float)learningRate);
+      var optimizer = tf.train.GradientDescentOptimizer((float)learningRate).minimize(costs);
 
       // features as feed items
       var variablesFeed = new Hashtable();
-      foreach (var kvp in variables) {
-        var variableName = kvp.Key.variableName;
-        var variable = kvp.Value;
-        if (problemData.Dataset.VariableHasType<double>(variableName))
-          variablesFeed.Add(variable, problemData.Dataset.GetDoubleValues(variableName, rows));
-        if (problemData.Dataset.VariableHasType<string>(variableName))
-          variablesFeed.Add(variable, problemData.Dataset.GetStringValues(variableName, rows));
-        if (problemData.Dataset.VariableHasType<DoubleVector>(variableName))
-          variablesFeed.Add(variable, problemData.Dataset.GetDoubleVectorValues(variableName, rows));
-        throw new NotSupportedException($"Type of the variable is not supported: {variableName}");
+      foreach (var kvp in parameters) {
+        var variable = kvp.Key;
+        var variableName = kvp.Value;
+        if (problemData.Dataset.VariableHasType<double>(variableName)) {
+          var data = problemData.Dataset.GetDoubleValues(variableName, rows).ToArray();
+          if (vectorLength.HasValue) {
+            var vectorData = new double[numRows][];
+            for (int i = 0; i < numRows; i++)
+              vectorData[i] = Enumerable.Repeat(data[i], vectorLength.Value).ToArray();
+            variablesFeed.Add(variable, np.array(vectorData));
+          } else
+            variablesFeed.Add(variable, np.array(data, copy: false));
+          //} else if (problemData.Dataset.VariableHasType<string>(variableName)) {
+          //  variablesFeed.Add(variable, problemData.Dataset.GetStringValues(variableName, rows));
+        } else if (problemData.Dataset.VariableHasType<DoubleVector>(variableName)) {
+          var data = problemData.Dataset.GetDoubleVectorValues(variableName, rows).Select(x => x.ToArray()).ToArray();
+          variablesFeed.Add(variable, np.array(data));
+        } else
+          throw new NotSupportedException($"Type of the variable is not supported: {variableName}");
       }
-      variablesFeed.Add(target, problemData.Dataset.GetDoubleValues(problemData.TargetVariable, rows));
+      var targetData = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, rows).ToArray();
+      variablesFeed.Add(target, np.array(targetData, copy: false));
 
 
       using (var session = tf.Session()) {
+        session.run(tf.global_variables_initializer());
+
+        Trace.WriteLine("Weights:");
+        foreach (var v in variables)
+          Trace.WriteLine($"{v.name}: {session.run(v).ToString(true)}");
+
         for (int i = 0; i < maxIterations; i++) {
-          optimizer.minimize(costs);
-          var result = session.run(optimizer, variablesFeed);
+
+          //optimizer.minimize(costs);
+          session.run(optimizer, variablesFeed);
+
+          Trace.WriteLine("Weights:");
+          foreach (var v in variables)
+            Trace.WriteLine($"{v.name}: {session.run(v).ToString(true)}");
         }
       }
-      optimizer.minimize(costs);
 
       if (!success)