/*
* Operations that affect all the samples as a whole
*/
// Normalize the data by range
// Each feature will have new values in the range
public ClassificationData NormalizeToRange( double lower, double upper )
{
// Check the boundaries of the target interval
if (upper <= lower)
{
throw new ArgumentException( );
}
// Initialize the ranges
int numFeatures = samples[0].FeatureVector.Count;
double[] minFeatureValues = new double[numFeatures];
double[] maxFeatureValues = new double[numFeatures];
for (int i = 0; i < numFeatures; i++)
{
minFeatureValues[i] = double.MaxValue;
maxFeatureValues[i] = double.MinValue;
}
// First calculate the range of the features
foreach (ISample sample in samples)
{
for (int iFeature = 0; iFeature < numFeatures; iFeature++)
{
// Update the min
if (sample.FeatureVector[iFeature] < minFeatureValues[iFeature])
{
minFeatureValues[iFeature] = sample.FeatureVector[iFeature];
}
// Update the max
if (sample.FeatureVector[iFeature] > maxFeatureValues[iFeature])
{
maxFeatureValues[iFeature] = sample.FeatureVector[iFeature];
}
}
}
// To prevent division by zero, if max = min all features are equal
// to the min, if max -> max + 1 the tranform values are the same
for (int i = 0; i < numFeatures; i++)
{
if (maxFeatureValues[i] == minFeatureValues[i])
{
maxFeatureValues[i]++;
}
}
// Create the new samples
ClassificationData result = new ClassificationData( );
for (int i = 0; i < samples.Count; i++)
{
SampleBasic sample = new SampleBasic( );
sample.Description = samples[i].Description;
sample.FeatureVector = new List<double>( numFeatures );
sample.Classify( samples[i].Category );
result.Samples.Add( sample );
}
// Obtain the new feature values by a linear transformation
// feature = (original - min) / (max - min) goes from 0 to 1
// feature = original * (upper - lower) + lower goes from lower to upper
double featureValue;
for (int iSample = 0; iSample < samples.Count; iSample++)
{
for (int iFeature = 0; iFeature < numFeatures; iFeature++)
{
featureValue = samples[iSample].FeatureVector[iFeature];
// Transform to [0,1]
featureValue = (featureValue - minFeatureValues[iFeature]) /
(maxFeatureValues[iFeature] - minFeatureValues[iFeature]);
// Transform to [lower,upper]
featureValue = featureValue * (upper - lower) + lower;
result.Samples[iSample].FeatureVector.Insert( iFeature, featureValue );
}
}
return result;
}
/*
* Operations that affect all the samples as a whole
*/
// Normalize the data by range
// Each feature will have new values in the range
public ClassificationData NormalizeToRange(double lower, double upper)
{
// Check the boundaries of the target interval
if (upper <= lower)
{
throw new ArgumentException( );
}
// Initialize the ranges
int numFeatures = samples[0].FeatureVector.Count;
double[] minFeatureValues = new double[numFeatures];
double[] maxFeatureValues = new double[numFeatures];
for (int i = 0; i < numFeatures; i++)
{
minFeatureValues[i] = double.MaxValue;
maxFeatureValues[i] = double.MinValue;
}
// First calculate the range of the features
foreach (ISample sample in samples)
{
for (int iFeature = 0; iFeature < numFeatures; iFeature++)
{
// Update the min
if (sample.FeatureVector[iFeature] < minFeatureValues[iFeature])
{
minFeatureValues[iFeature] = sample.FeatureVector[iFeature];
}
// Update the max
if (sample.FeatureVector[iFeature] > maxFeatureValues[iFeature])
{
maxFeatureValues[iFeature] = sample.FeatureVector[iFeature];
}
}
}
// To prevent division by zero, if max = min all features are equal
// to the min, if max -> max + 1 the tranform values are the same
for (int i = 0; i < numFeatures; i++)
{
if (maxFeatureValues[i] == minFeatureValues[i])
{
maxFeatureValues[i]++;
}
}
// Create the new samples
ClassificationData result = new ClassificationData( );
for (int i = 0; i < samples.Count; i++)
{
SampleBasic sample = new SampleBasic( );
sample.Description = samples[i].Description;
sample.FeatureVector = new List <double>(numFeatures);
sample.Classify(samples[i].Category);
result.Samples.Add(sample);
}
// Obtain the new feature values by a linear transformation
// feature = (original - min) / (max - min) goes from 0 to 1
// feature = original * (upper - lower) + lower goes from lower to upper
double featureValue;
for (int iSample = 0; iSample < samples.Count; iSample++)
{
for (int iFeature = 0; iFeature < numFeatures; iFeature++)
{
featureValue = samples[iSample].FeatureVector[iFeature];
// Transform to [0,1]
featureValue = (featureValue - minFeatureValues[iFeature]) /
(maxFeatureValues[iFeature] - minFeatureValues[iFeature]);
// Transform to [lower,upper]
featureValue = featureValue * (upper - lower) + lower;
result.Samples[iSample].FeatureVector.Insert(iFeature, featureValue);
}
}
return(result);
}