FeatureVectorPtr FeatureEncoder::EncodeAExample (FileDescConstPtr encodedFileDesc,
FeatureVectorPtr src
)
{
FeatureVectorPtr encodedExample = new FeatureVector (numEncodedFeatures);
encodedExample->MLClass (src->MLClass ());
encodedExample->PredictedClass (src->PredictedClass ());
//encodedExample->Version (src->Version ());
encodedExample->TrainWeight (src->TrainWeight ());
const float* featureData = src->FeatureData ();
kkint32 x;
for (x = 0; x < numOfFeatures; x++)
{
float featureVal = featureData [srcFeatureNums[x]];
kkint32 y = destFeatureNums[x];
switch (destWhatToDo[x])
{
case FeWhatToDo::FeAsIs:
{
encodedExample->AddFeatureData (y, featureVal);
}
break;
case FeWhatToDo::FeBinary:
{
for (kkint32 z = 0; z < cardinalityDest[x]; z++)
{
float bVal = ((kkint32)featureVal == z);
encodedExample->AddFeatureData (y, bVal);
y++;
}
}
break;
case FeWhatToDo::FeScale:
{
encodedExample->AddFeatureData (y, (featureVal / (float)cardinalityDest[x]));
}
break;
}
}
return encodedExample;
} /* EncodeAExample */
FeatureVectorListPtr FeatureEncoder::CreateEncodedFeatureVector (FeatureVectorList& srcData)
{
if (srcData.AllFieldsAreNumeric ())
return srcData.DuplicateListAndContents ();
FeatureVectorListPtr encodedFeatureVectorList = new FeatureVectorList (destFileDesc, true);
FeatureVectorList::iterator idx;
for (idx = srcData.begin (); idx != srcData.end (); idx++)
{
FeatureVectorPtr srcExample = *idx;
XSpacePtr encodedData = EncodeAExample (srcExample);
kkint32 zed = 0;
FeatureVectorPtr encodedFeatureVector = new FeatureVector (codedNumOfFeatures);
while (encodedData[zed].index != -1)
{
encodedFeatureVector->AddFeatureData (encodedData[zed].index, (float)encodedData[zed].value);
zed++;
}
encodedFeatureVector->MLClass (srcExample->MLClass ());
encodedFeatureVectorList->PushOnBack (encodedFeatureVector);
delete encodedData;
encodedData = NULL;
}
return encodedFeatureVectorList;
} /* CreateEncodedFeatureVector */
