/**
*@details A static method that will return a instance of 'FeatureNumList' that will have all non 'Ignore' features
* in '_fileDesc' selected.
*/
FeatureNumList FeatureNumList::AllFeatures (FileDescConstPtr _fileDesc)
{
IntType maxFeatureNum = (IntType)(_fileDesc->NumOfFields () - 1);
FeatureNumList features (maxFeatureNum);
const AttributeTypeVector& attributeTypes = _fileDesc->AttributeVector ();
for (IntType fn = 0; fn <= maxFeatureNum; ++fn)
{
if (attributeTypes[fn] != AttributeType::Ignore)
features.AddFeature (fn);
}
return features;
} /* AllFeatures */
/**
*@brief Constructs a Feature Encoder object.
*@param[in] _param
*@param[in] _fileDesc
*@param[in] _log A log file stream. All important events will be output to this stream
*/
FeatureEncoder2::FeatureEncoder2 (const ModelParam& _param,
FileDescConstPtr _fileDesc
):
attributeVector (_fileDesc->AttributeVector ()),
cardinalityDest (NULL),
cardinalityVector (_fileDesc->CardinalityVector ()),
codedNumOfFeatures (0),
destFeatureNums (NULL),
destWhatToDo (NULL),
encodedFileDesc (NULL),
encodingMethod (ModelParam::EncodingMethodType::NoEncoding),
fileDesc (_fileDesc),
numOfFeatures (0),
srcFeatureNums (NULL),
param (_param)
{
FeatureNumListConstPtr selectedFeatures = param.SelectedFeatures ();
numOfFeatures = param.SelectedFeatures ()->NumOfFeatures ();
encodingMethod = param.EncodingMethod ();
srcFeatureNums = new kkuint16 [numOfFeatures];
cardinalityDest = new kkint32 [numOfFeatures];
destFeatureNums = new kkint32 [numOfFeatures];
destWhatToDo = new FeWhatToDo[numOfFeatures];
VectorKKStr destFieldNames;
kkint32 x;
for (x = 0; x < numOfFeatures; x++)
{
kkuint16 srcFeatureNum = (*selectedFeatures)[x];
srcFeatureNums [x] = srcFeatureNum;
destFeatureNums [x] = codedNumOfFeatures;
cardinalityDest [x] = 1;
destWhatToDo [x] = FeWhatToDo::FeAsIs;
Attribute srcAttribute = (fileDesc->Attributes ())[srcFeatureNum];
switch (encodingMethod)
{
case ModelParam::EncodingMethodType::Binary:
if ((attributeVector[srcFeatureNum] == AttributeType::Nominal) ||
(attributeVector[srcFeatureNum] == AttributeType::Symbolic)
)
{
destWhatToDo [x] = FeWhatToDo::FeBinary;
cardinalityDest [x] = cardinalityVector[srcFeatureNums [x]];
codedNumOfFeatures += cardinalityDest[x];
for (kkint32 zed = 0; zed < cardinalityDest[x]; zed++)
{
KKStr fieldName = srcAttribute.Name () + "_" + srcAttribute.GetNominalValue (zed);
destFieldNames.push_back (fieldName);
}
}
else
{
codedNumOfFeatures++;
destWhatToDo [x] = FeWhatToDo::FeAsIs;
destFieldNames.push_back (srcAttribute.Name ());
}
break;
case ModelParam::EncodingMethodType::Scaled:
codedNumOfFeatures++;
if ((attributeVector[srcFeatureNums[x]] == AttributeType::Nominal) ||
(attributeVector[srcFeatureNums[x]] == AttributeType::Symbolic)
)
destWhatToDo [x] = FeWhatToDo::FeScale;
else
destWhatToDo [x] = FeWhatToDo::FeAsIs;
destFieldNames.push_back (srcAttribute.Name ());
break;
case ModelParam::EncodingMethodType::NoEncoding:
default:
codedNumOfFeatures++;
destWhatToDo [x] = FeWhatToDo::FeAsIs;
destFieldNames.push_back (srcAttribute.Name ());
break;
}
}
encodedFileDesc = FileDesc::NewContinuousDataOnly (destFieldNames);
}