void MatrixMxN<Scalar>::singularValueDecomposition(MatrixMxN<Scalar> &left_singular_vectors,
VectorND<Scalar> &singular_values,
MatrixMxN<Scalar> &right_singular_vectors) const
{
#ifdef PHYSIKA_USE_EIGEN_MATRIX
//hack: Eigen::SVD does not support integer types, hence we cast Scalar to long double for decomposition
unsigned int rows = this->rows(), cols = this->cols();
Eigen::Matrix<long double,Eigen::Dynamic,Eigen::Dynamic> temp_matrix(rows,cols);
for(unsigned int i = 0; i < rows; ++i)
for(unsigned int j = 0; j < cols; ++j)
temp_matrix(i,j) = static_cast<long double>((*ptr_eigen_matrix_MxN_)(i,j));
Eigen::JacobiSVD<Eigen::Matrix<long double,Eigen::Dynamic,Eigen::Dynamic> > svd(temp_matrix,Eigen::ComputeThinU|Eigen::ComputeThinV);
const Eigen::Matrix<long double,Eigen::Dynamic,Eigen::Dynamic> &left = svd.matrixU(), &right = svd.matrixV();
const Eigen::Matrix<long double,Eigen::Dynamic,1> &values = svd.singularValues();
//resize if have to
if(left_singular_vectors.rows() != left.rows() || left_singular_vectors.cols() != left.cols())
left_singular_vectors.resize(left.rows(),left.cols());
if(right_singular_vectors.rows() != right.rows() || right_singular_vectors.cols() != right.cols())
right_singular_vectors.resize(right.rows(),right.cols());
if(singular_values.dims() != values.rows())
singular_values.resize(values.rows());
//copy the result
for(unsigned int i = 0; i < left.rows(); ++i)
for(unsigned int j = 0; j < left.cols(); ++j)
left_singular_vectors(i,j) = static_cast<Scalar>(left(i,j));
for(unsigned int i = 0; i < right.rows(); ++i)
for(unsigned int j = 0; j < right.cols(); ++j)
right_singular_vectors(i,j) = static_cast<Scalar>(right(i,j));
for(unsigned int i = 0; i < values.rows(); ++i)
singular_values[i] = static_cast<Scalar>(values(i,0));
#elif defined(PHYSIKA_USE_BUILT_IN_MATRIX)
std::cerr<<"SVD not implemeted for built in matrix!\n";
std::exit(EXIT_FAILURE);
#endif
}
void MatrixMxN<Scalar>::eigenDecomposition(VectorND<Scalar> &eigen_values_real, VectorND<Scalar> &eigen_values_imag,
MatrixMxN<Scalar> &eigen_vectors_real, MatrixMxN<Scalar> &eigen_vectors_imag)
{
unsigned int rows = this->rows(), cols = this->cols();
if(rows != cols)
{
std::cerr<<"Eigen decomposition is only valid for square matrix!\n";
std::exit(EXIT_FAILURE);
}
#ifdef PHYSIKA_USE_EIGEN_MATRIX
//hack: Eigen::EigenSolver does not support integer types, hence we cast Scalar to long double for decomposition
Eigen::Matrix<long double,Eigen::Dynamic,Eigen::Dynamic> temp_matrix(rows,cols);
for(unsigned int i = 0; i < rows; ++i)
for(unsigned int j = 0; j < cols; ++j)
temp_matrix(i,j) = static_cast<long double>((*ptr_eigen_matrix_MxN_)(i,j));
Eigen::EigenSolver<Eigen::Matrix<long double,Eigen::Dynamic,Eigen::Dynamic> > eigen(temp_matrix);
Eigen::Matrix<std::complex<long double>,Eigen::Dynamic,Eigen::Dynamic> vectors = eigen.eigenvectors();
const Eigen::Matrix<std::complex<long double>,Eigen::Dynamic,1> &values = eigen.eigenvalues();
//resize if have to
if(eigen_vectors_real.rows() != vectors.rows() || eigen_vectors_real.cols() != vectors.cols())
eigen_vectors_real.resize(vectors.rows(),vectors.cols());
if(eigen_vectors_imag.rows() != vectors.rows() || eigen_vectors_imag.cols() != vectors.cols())
eigen_vectors_imag.resize(vectors.rows(),vectors.cols());
if(eigen_values_real.dims() != values.rows())
eigen_values_real.resize(values.rows());
if(eigen_values_imag.dims() != values.rows())
eigen_values_imag.resize(values.rows());
//copy the result
for(unsigned int i = 0; i < vectors.rows(); ++i)
for(unsigned int j = 0; j < vectors.cols(); ++j)
{
eigen_vectors_real(i,j) = static_cast<Scalar>(vectors(i,j).real());
eigen_vectors_imag(i,j) = static_cast<Scalar>(vectors(i,j).imag());
}
for(unsigned int i = 0; i < values.rows(); ++i)
{
eigen_values_real[i] = static_cast<Scalar>(values(i,0).real());
eigen_values_imag[i] = static_cast<Scalar>(values(i,0).imag());
}
#elif defined(PHYSIKA_USE_BUILT_IN_MATRIX)
std::cerr<<"Eigen decomposition not implemeted for built in matrix!\n";
std::exit(EXIT_FAILURE);
#endif
}
//input from console and output the result predict by the model
void AspectTool::realTest(string model_file)
{
//initialize word vector tool
Word2VecTool word_vec_tool("../res/glove.42B.300d.txt", false);
//word_vec_tool.initWordIndexDict();
word_vec_tool.loadWordDict("word_index_dictionary");
cout << "Please input the test sectence : " << endl;
string sentence;
getline(cin, sentence);
cout << sentence << endl;
StringTool st;
vector<string> word_token = st.tokenize(sentence);
MatrixXd *p_input_data = new MatrixXd(word_vec_tool.getVectorLength(), word_token.size());
for (int i = 0; i < word_token.size(); ++i)
{
MatrixXd temp_matrix(word_vec_tool.getVectorLength(), 1);
word_vec_tool.getWrodVect(word_token[i], temp_matrix);
p_input_data -> col(i) = temp_matrix;
}
vector<MatrixXd*> input_datas;
input_datas.push_back(p_input_data);
//cout << *p_input_data << endl;
LSTM lstm(model_file);
vector<MatrixXd*> predict_labels = lstm.predict(input_datas);
MatrixXd temp_label = *(predict_labels[0]);
cout << temp_label << endl;
string aspect_term = "";
for (int i = 0; i < temp_label.cols(); ++i)
{
if (temp_label(1, i) == 1)
{
aspect_term = aspect_term + " " + word_token[i];
}
else if (temp_label(2, i) == 1 && aspect_term.size() > 0)
{
aspect_term = aspect_term + " " + word_token[i];
}
else if (temp_label(0, i) == 1)
{
if (aspect_term.size() > 0)
{
cout << "Aspect Term : " << aspect_term << endl;
}
aspect_term = "";
}
}
if (aspect_term.size() > 0)
{
cout << "Aspect Term : " << aspect_term << endl;
}
return;
}
void AspectTool::getInputData(string file_name, vector<MatrixXd*> &input_datas, vector<MatrixXd*> &input_labels)
{
ifstream input_stream(file_name.c_str());
if (!input_stream)
{
cout << file_name << " dose not exist !" << endl;
return;
}
Word2VecTool word_vec_tool("../res/glove.42B.300d.txt", false);
//word_vec_tool.initWordIndexDict();
word_vec_tool.loadWordDict("word_index_dictionary");
string temp_word;
vector<string> temp_word_list;
vector<char> temp_label_list;
//int count = 0;
while (input_stream >> temp_word)
{
if (temp_word == "<end_of_sentence>")
{
//construct input matrix of current sequence
MatrixXd *temp_input_mp = new MatrixXd(word_vec_tool.getVectorLength(), temp_word_list.size());
for (int t = 0; t < temp_word_list.size(); ++t)
{
MatrixXd temp_matrix(word_vec_tool.getVectorLength(), 1);
word_vec_tool.getWrodVect(temp_word_list[t], temp_matrix);
temp_input_mp -> col(t) = temp_matrix;
}
//construct label matrix of current sequence
MatrixXd *temp_label_mp = new MatrixXd(3, temp_label_list.size());
*temp_label_mp = MatrixXd::Zero(3, temp_label_list.size());
for (int t = 0; t < temp_label_list.size(); ++t)
{
if (temp_label_list[t] == 'O')
{
(*temp_label_mp)(0, t) = 1;
}
else if (temp_label_list[t] == 'B')
{
(*temp_label_mp)(1, t) = 1;
}
else if (temp_label_list[t] == 'I')
{
(*temp_label_mp)(2, t) = 1;
}
}
//insert current input data and label
input_datas.push_back(temp_input_mp);
input_labels.push_back(temp_label_mp);
//clear the list
temp_word_list.clear();
temp_label_list.clear();
}
else
{
temp_word_list.push_back(temp_word);
char temp_char;
input_stream >> temp_char;
temp_label_list.push_back(temp_char);
}
}// end 'while'
return;
}//end 'getInputData'
