transpose-dataframe.cpp

#include <Rcpp.h>
using namespace Rcpp;

// [[Rcpp::export(rng = false)]]
List df2list(const DataFrame& x) {
  std::size_t nrows = x.rows();
  std::size_t ncols = x.cols();
  CharacterVector nms = x.names();
  List res(no_init(nrows));
  for (std::size_t i = 0; i < nrows; ++i) {
    List tmp(no_init(ncols));
    tmp.names() = nms;
    for (std::size_t j = 0; j < ncols; ++j) {
      switch(TYPEOF(x[j])) {
      case LGLSXP:
      case INTSXP: {
        tmp[j] = as<LogicalVector>(x[j])[i];
        break;
      }
      case REALSXP: {
        tmp[j] = as<NumericVector>(x[j])[i];
        break;
      }
      case STRSXP: {
        tmp[j] = as<std::string>(as<CharacterVector>(x[j])[i]);
        break;
      }
      case VECSXP: {
        tmp[j] = as<List>(x[j])[i];
        break;
      }
      default: stop("Unsupported type '%s'.", type2name(x));
      }
    }
    res[i] = tmp;
  }
  return res;
}

template <typename T>
void cp(List& l, const T& v, std::size_t n, std::size_t idx) {
  for (std::size_t i = 0; i < n; ++i) {
    List tmp = as<List>(l[i]);
    tmp[idx] = v[i];
  }
}

// [[Rcpp::export(rng = false)]]
List df2list2(const DataFrame& x) {
  std::size_t nrows = x.rows();
  std::size_t ncols = x.cols();
  CharacterVector nms = x.names();
  List res(no_init(nrows));

  for (std::size_t i = 0; i < nrows; ++i) {
    List l(no_init(ncols));
    l.names() = nms;
    res[i] = l;
  }

  for (std::size_t j = 0; j < ncols; ++j) {
    switch(TYPEOF(x[j])) {
    case LGLSXP:
    case INTSXP: {
      cp(res, as<IntegerVector>(x[j]), nrows, j);
      break;
    }
    case REALSXP: {
      cp(res, as<NumericVector>(x[j]), nrows, j);
      break;
    }
    case STRSXP: {
      cp(res, as<std::vector<std::string>>(x[j]), nrows, j);
      break;
    }
    case VECSXP: {
      cp(res, as<List>(x[j]), nrows, j);
      break;
    }
    default: stop("Unsupported type '%s'.", type2name(x));
    }
  }
  return res;
}


/***R
data("Batting", package = "Lahman")
x <- Batting[1:10000, 1:10]
# str(df2list2(x))
# df2list2(iris)

bench::mark(
  df2list(x),
  df2list2(x),
  purrr::transpose(x)
)
*/