int MetalabelFeature::ExtractFeature(const vector<TokenCitation*>& tokenVector, CitationSet& citationSet, UniGramFeature& uniGrams, BiGramFeature& biGrams, JournalSet& journalSet, FeatureSet& allFeatures, int printLog)
{
int rtn = 0;
allFeatures.mFeatures.clear();
allFeatures.mMaxIndex = uniGrams.mDictionary.rbegin()->first + 1;
allFeatures.mFeatures.resize(tokenVector.size());
FeatureSet biFeatures;
biFeatures.mMaxIndex = biGrams.mDictionary.rbegin()->first + 1;
biFeatures.mFeatures.resize(tokenVector.size());
FeatureSet jourFeatures;
jourFeatures.mMaxIndex = journalSet.mJournals.rbegin()->first + 1;
jourFeatures.mFeatures.resize(tokenVector.size());
int numThreads = omp_get_num_procs();
if (printLog != SILENT)
clog << "CPU number: " << numThreads << endl;
omp_set_num_threads(numThreads);
if (printLog != SILENT)
clog << "Start Parallel Extract Features" << endl;
#pragma omp parallel for schedule(dynamic)
for (int i = 0; i < tokenVector.size(); i++)
{
uniGrams.Extract(*tokenVector[i], allFeatures.mFeatures[i]);
}
#pragma omp parallel for schedule(dynamic)
for (int i = 0; i < tokenVector.size(); i++)
{
biGrams.Extract(*tokenVector[i], biFeatures.mFeatures[i]);
}
#pragma omp parallel for schedule(dynamic)
for (int i = 0; i < tokenVector.size(); ++i)
{
Journal* ptrJournal = NULL;
ptrJournal = journalSet.SearchJournalTitle(citationSet[tokenVector[i]->mPmid]->mJournalTitle);
if (ptrJournal != NULL)
{
jourFeatures.mFeatures[i][ptrJournal->mJournalId] = 1.0;
}
else
{
cerr << "Error: can't find \"" << citationSet[tokenVector[i]->mPmid]->mJournalTitle << " in pmid " << tokenVector[i]->mPmid << endl;
}
}
rtn = allFeatures.Merge(biFeatures);
CHECK_RTN(rtn);
rtn = allFeatures.Merge(jourFeatures);
CHECK_RTN(rtn);
rtn = allFeatures.Normalize();
CHECK_RTN(rtn);
return 0;
}
int MetalabelFeature::ExtractFeature(const vector<TokenCitation*>& tokenVector, UniGramFeature& uniGrams, BiGramFeature& biGrams, feature_node** &featureSpace, int printLog)
{
int numThreads = omp_get_num_procs();
if (printLog != SILENT)
clog << "CPU number: " << numThreads << endl;
omp_set_num_threads(numThreads);
if (printLog != SILENT)
clog << "Extract unigram & bigram" << endl;
if (printLog != SILENT)
clog << "Make Feature table" << endl;
int featureNum = (int)tokenVector.size();
featureSpace = NULL;
featureSpace = Malloc(feature_node*, featureNum);
memset(featureSpace, 0, sizeof(feature_node*)* featureNum);
int uniMaxIndex = uniGrams.mDictionary.rbegin()->first + 1;
int biMaxIndex = biGrams.mDictionary.rbegin()->first + 1;
if (printLog != SILENT)
clog << "Extract features parallel" << endl;
#pragma omp parallel for schedule(dynamic)
for (int i = 0; i < (int)tokenVector.size(); i++)
{
FeatureSet tabAllFeatures;
tabAllFeatures.mMaxIndex = uniMaxIndex;
tabAllFeatures.mFeatures.resize(1);
FeatureSet tabBiFeatures;
tabBiFeatures.mMaxIndex = biMaxIndex;
tabBiFeatures.mFeatures.resize(1);
uniGrams.Extract(*tokenVector[i], tabAllFeatures.mFeatures[0]);
biGrams.Extract(*tokenVector[i], tabBiFeatures.mFeatures[0]);
tabAllFeatures.Merge(tabBiFeatures);
tabAllFeatures.Normalize();
featureSpace[i] = NULL;
LinearMachine::TransFeatures(featureSpace[i], tabAllFeatures.mFeatures[0]);
}
return 0;
}
int MetalabelFeature::ExtractFeature(const vector<TokenCitation*>& tokenVector, UniGramFeature& uniGrams, BiGramFeature& biGrams, FeatureSet& allFeatures, int printLog)
{
int rtn = 0;
allFeatures.mFeatures.clear();
allFeatures.mMaxIndex = uniGrams.mDictionary.rbegin()->first + 1;
allFeatures.mFeatures.resize(tokenVector.size());
FeatureSet biFeatures;
biFeatures.mMaxIndex = biGrams.mDictionary.rbegin()->first + 1;
biFeatures.mFeatures.resize(tokenVector.size());
int numThreads = omp_get_num_procs();
if (printLog != SILENT)
clog << "CPU number: " << numThreads << endl;
omp_set_num_threads(numThreads);
if (printLog != SILENT)
clog << "Start Parallel Extract Features" << endl;
#pragma omp parallel for schedule(dynamic)
for (int i = 0; i < tokenVector.size(); i++)
{
uniGrams.Extract(*tokenVector[i], allFeatures.mFeatures[i]);
}
#pragma omp parallel for schedule(dynamic)
for (int i = 0; i < tokenVector.size(); i++)
{
biGrams.Extract(*tokenVector[i], biFeatures.mFeatures[i]);
}
allFeatures.Merge(biFeatures);
rtn = allFeatures.Normalize();
CHECK_RTN(rtn);
return 0;
}
int MetalabelFeature::ExtractFeature(const vector<TokenCitation*>& tokenVector, CitationSet& citationSet, UniGramFeature& uniGrams, BiGramFeature& biGrams, JournalSet& journalSet, feature_node** &featureSpace, int printLog)
{
int numThreads = omp_get_num_procs();
if (printLog != SILENT)
clog << "CPU number: " << numThreads << endl;
omp_set_num_threads(numThreads);
if (printLog != SILENT)
clog << "Extract unigram & bigram" << endl;
if (printLog != SILENT)
clog << "Make Feature table" << endl;
int featureNum = (int)tokenVector.size();
featureSpace = NULL;
featureSpace = Malloc(feature_node*, featureNum);
memset(featureSpace, 0, sizeof(feature_node*)* featureNum);
int uniMaxIndex = uniGrams.mDictionary.rbegin()->first + 1;
int biMaxIndex = biGrams.mDictionary.rbegin()->first + 1;
int jourMaxIndex = journalSet.mJournals.rbegin()->first + 1;
if (printLog != SILENT)
clog << "Extract features parallel" << endl;
#pragma omp parallel for schedule(dynamic)
for (int i = 0; i < (int)tokenVector.size(); i++)
{
FeatureSet tabAllFeatures;
tabAllFeatures.mMaxIndex = uniMaxIndex;
tabAllFeatures.mFeatures.resize(1);
FeatureSet tabBiFeatures;
tabBiFeatures.mMaxIndex = biMaxIndex;
tabBiFeatures.mFeatures.resize(1);
uniGrams.Extract(*tokenVector[i], tabAllFeatures.mFeatures[0]);
biGrams.Extract(*tokenVector[i], tabBiFeatures.mFeatures[0]);
FeatureSet tabJourFeatures;
tabJourFeatures.mMaxIndex = jourMaxIndex;
tabJourFeatures.mFeatures.resize(1);
if (citationSet[tokenVector[i]->mPmid]->mJournalTitle != NULL)
{
Journal* ptrJournal = journalSet.SearchJournalTitle(citationSet[tokenVector[i]->mPmid]->mJournalTitle);
if (ptrJournal != NULL)
{
tabJourFeatures.mFeatures[0][ptrJournal->mJournalId] = 1.0;
}
else
cerr << "Error: \"" << citationSet[tokenVector[i]->mPmid]->mJournalTitle << "\" can't find journal in journal set in pmid " << tokenVector[i]->mPmid << endl;
}
else
cerr << "Error: " << tokenVector[i]->mPmid << " can't find journal title in citation" << endl;
tabAllFeatures.Merge(tabBiFeatures);
tabAllFeatures.Merge(tabJourFeatures);
tabAllFeatures.Normalize();
featureSpace[i] = NULL;
LinearMachine::TransFeatures(featureSpace[i], tabAllFeatures.mFeatures[0]);
}
return 0;
}
