SEXP getDocTermMatrix(string termWeighting){
Rcpp::List dimnms = Rcpp::List::create(extDocIDs, terms);
if(termWeighting == "tf"){
NumericMatrix d = Rcpp::wrap(resultsData.tfMatrix);
d.attr("dimnames") = dimnms;
return d;
}else if(termWeighting == "tf_normalized"){
arma::mat tfnorm = resultsData.tfMatrix;
arma::rowvec docLen = arma::sum(tfnorm, 0);
tfnorm.each_row() /= docLen;
NumericMatrix d = Rcpp::wrap(tfnorm);
d.attr("dimnames") = dimnms;
return d;
}else if(termWeighting == "tfidf"){
arma::mat tfidfMat = resultsData.tfMatrix;
arma::vec idf = arma::log((environment.documentCount() + 1) /
(resultsData.dfVector + 0.5));
tfidfMat.each_row() %= idf.t();
NumericMatrix d = Rcpp::wrap(tfidfMat);
d.attr("dimnames") = dimnms;
return d;
}else if(termWeighting == "idf"){
}
}
//[[Rcpp::export]]
SEXP do_getcq_dense( NumericMatrix X, const IntegerVector& mcs0idx){
List vnl = clone(List(X.attr("dimnames")));
CharacterVector vn=vnl[0];
int nrX = X.rows(), i, ii, j, k, l, past;
IntegerVector pas( nrX ), vec_s( nrX ), vec2_s( nrX );
IntegerVector ggg( nrX );
// pas.setZero();
for (i=0; i<nrX; ++i){
j = mcs0idx[i]; // Rprintf("i=%d, j=%d, past=%d\n", i, j, past);
vec_s = X(_, j );
vec2_s = vec_s * pas ;
past = sum( vec2_s );
pas[i] = 1;
ggg[ mcs0idx[i] ] = past;
}
// // cout << vec_s.transpose() << endl; cout << pas.transpose() << endl;
IntegerVector ladder( nrX );
for (i=0; i<nrX-1; ++i){
if( ggg[i]+1>ggg[i+1]) ladder[i] = 1;
}
ladder[nrX-1]=1; //Rprintf("ladder: "); Rf_PrintValue( ladder );
int ncq = sum( ladder );
List cqlist(ncq);
for (i=0; i<nrX; ++i) pas[i]=0;
// pas.setZero();
l=0;
for (i=0; i<nrX; ++i){
if (ladder[i]>0){
j = mcs0idx[i];
vec_s = X(_, j );
vec2_s = vec_s * pas;
past = sum( vec2_s ) ; //Rprintf("i=%d, j=%d, past=%d\n", i, j, past);
IntegerVector cq(past+1);
//cout << "vec2_s " << vec2_s.transpose() << endl; Rf_PrintValue( cq );
k=0;
for (ii=0; ii<nrX; ++ii){
if (vec2_s[ii] != 0)
cq[k++] = ii;
}
cq[past] = j;
CharacterVector cq2(past+1);
for (k=0; k<past+1;++k) cq2[k]=vn[cq[k]];
cqlist[l++] = cq2; //Rf_PrintValue( cq );
}
pas[i] = 1;
}
return cqlist; //List::create( cqlist );
//return List::create(1);
}
// use calc_resid_linreg for a 3-dim array
// [[Rcpp::export]]
NumericVector calc_resid_linreg_3d(const NumericMatrix& X, const NumericVector& P)
{
int nrowx = X.rows();
int sizep = P.size();
NumericMatrix pr(nrowx, sizep/nrowx);
std::copy(P.begin(), P.end(), pr.begin()); // FIXME I shouldn't need to copy
NumericMatrix result = calc_resid_linreg(X, pr);
result.attr("dim") = P.attr("dim");
return result;
}
// use calc_resid_linreg for a 3-dim array
// [[Rcpp::export]]
NumericVector calc_resid_linreg_3d(const NumericMatrix& X, const NumericVector& P,
const double tol=1e-12)
{
const unsigned int nrowx = X.rows();
const Dimension d = P.attr("dim");
if(d[0] != nrowx)
throw std::range_error("nrow(X) != nrow(P)");
NumericMatrix pr(nrowx, d[1]*d[2]);
std::copy(P.begin(), P.end(), pr.begin()); // FIXME I shouldn't need to copy
NumericMatrix result = calc_resid_eigenqr(X, pr, tol);
result.attr("dim") = d;
return result;
}
// use calc_resid_linreg for a 3-dim array
// [[Rcpp::export]]
NumericVector calc_resid_linreg_3d(const NumericMatrix& X, const NumericVector& P,
const double tol=1e-12)
{
const int nrowx = X.rows();
if(Rf_isNull(P.attr("dim")))
throw std::invalid_argument("P should be a 3d array but has no dim attribute");
const Dimension d = P.attr("dim");
if(d.size() != 3)
throw std::invalid_argument("P should be a 3d array");
if(d[0] != nrowx)
throw std::range_error("nrow(X) != nrow(P)");
NumericMatrix pr(nrowx, d[1]*d[2]);
std::copy(P.begin(), P.end(), pr.begin()); // FIXME I shouldn't need to copy
NumericMatrix result = calc_resid_eigenqr(X, pr, tol);
result.attr("dim") = d;
return result;
}
// seqDist
// [[Rcpp::export]]
double seqDistRcpp(std::string seq1, std::string seq2,
NumericMatrix dist_mat) {
// Check that seq1 and seq2 have same length
int len_seq1 = seq1.length();
int len_seq2 = seq2.length();
if (len_seq1 != len_seq2) {
throw std::range_error("Sequences of different length.");
}
int len_seqs = len_seq1;
List dist_mat_dims = dist_mat.attr("dimnames");
//print (dist_mat_dims);
CharacterVector dist_mat_rownames = dist_mat_dims[0];
CharacterVector dist_mat_colnames = dist_mat_dims[1];
int num_rows = dist_mat_rownames.size();
int num_cols = dist_mat_colnames.size();
List row_key_idx;
List col_key_idx;
std::map<std::string, int> rows_map;
std::map<std::string, int> cols_map;
for (int i = 0; i < num_rows; i++)
{
//const char *this_col = dist_mat_colnames[i].c_str();
std::string this_row = as<std::string>(dist_mat_rownames[i]);
rows_map[this_row] = i;
}
for (int i = 0; i < num_cols; i++)
{
//const char *this_col = dist_mat_colnames[i].c_str();
std::string this_col = as<std::string>(dist_mat_colnames[i]);
cols_map[this_col] = i;
}
int d_seen = 0;
int indels = 0;
// sum(d[d>0])
double d_sum = 0;
for (int i = 0; i < len_seqs; i++)
{
// find row index
int row_idx;
char row_char = (char)seq1[i];
std::string row_string;
row_string+=row_char;
auto search_row = rows_map.find(row_string);
if(search_row != rows_map.end()) {
row_idx = search_row->second;
}
else {
throw std::range_error("Character not found in dist_mat.");
}
// find col index
int col_idx;
char col_char = (char)seq2[i];
std::string col_string;
col_string+=col_char;
auto search_col = cols_map.find(col_string);
if(search_col != cols_map.end()) {
col_idx = search_col->second;
}
else {
throw std::range_error("Character not found in dist_mat.");
}
// distance for current i
double d_i = dist_mat(row_idx, col_idx);
if (d_i > 0){
// Sum distance
d_sum = d_sum + d_i;
}
else if ( (d_i == -1 ) & (d_seen != -1) )
{
// Count indel
indels++;
}
d_seen = d_i;
}
double distance = d_sum + indels;
return (distance);
}
// [[Rcpp::export]]
Rcpp::List userRMA(const NumericMatrix x2,
Rcpp::List probesets,
CharacterVector colnames,
NumericVector quantile,
NumericVector alpha) {
NumericMatrix x = clone(x2);
CharacterVector probesets2 = probesets.names();
int n = x.nrow();
int m = x.ncol();
int p = probesets2.size();
NumericMatrix xnorm(n,m);
arma::rowvec cdelta(m, arma::fill::none);
IntegerVector match2 = seq_len(n);
IntegerVector h5 = seq_len(n);
IntegerVector h3 = seq_len(n);
IntegerVector revh3 = clone<IntegerVector>(h3);
std::reverse(revh3.begin(), revh3.end());
NumericMatrix xsum (p, m);
Rcpp::List dimns = List::create(probesets2, colnames);
xsum.attr("dimnames") = dimns;
NumericMatrix xsort(n,m);
NumericVector h1 (p);
for (int j = 0; j < m; ++j) {
h1 = x(_, j);
h1 = h1.sort();
NumericVector revh1 = clone<NumericVector>(h1);
std::reverse(revh1.begin(), revh1.end());
NumericVector revx = clone<NumericVector>(x(_, j));
std::reverse(revx.begin(), revx.end());
match2 = match(revx, revh1);
IntegerVector revmatch2 = clone<IntegerVector>(match2);
std::reverse(revmatch2.begin(), revmatch2.end());
for (int i = 0; i < n; ++i) {
xsort(i, j) = quantile(revh3(revmatch2(i)-1)-1);
}
}
for (int j = 0; j < m; ++j) {
xnorm(_,j) = log(xsort(_, j))/log(2) - alpha;
}
double count = 0;
double n2 = 0;
for (int l = 0; l < p; ++l) {
CharacterVector probes = probesets(l);
n2 = probes.size();
IntegerVector x5(n2);
x5 = seq(count, count + probes.size());
count += n2;
arma::mat x3(n2, m);
for (int j = 0; j < n2; ++j) {
cdelta =xnorm(x5(j), _);
x3(j, arma::span::all) = cdelta;
}
cdelta = arma::median(x3, 0);
for (int j = 0; j < m; ++j) {
xsum(l, j) = cdelta(j);
}
}
return List::create(Named("exprs") = xsum);
}
