Skip to main content
  • Home
  • Development
  • Documentation
  • Donate
  • Operational login
  • Browse the archive

swh logo
SoftwareHeritage
Software
Heritage
Archive
Features
  • Search

  • Downloads

  • Save code now

  • Add forge now

  • Help

https://github.com/cran/sparseFLMM
01 July 2021, 10:59:25 UTC
  • Code
  • Branches (9)
  • Releases (0)
  • Visits
    • Branches
    • Releases
    • HEAD
    • refs/heads/master
    • refs/tags/0.1.0
    • refs/tags/0.1.1
    • refs/tags/0.2.0
    • refs/tags/0.2.2
    • refs/tags/0.3.0
    • refs/tags/0.3.1
    • refs/tags/0.4.0
    • refs/tags/0.4.1
    No releases to show
  • ecde163
  • /
  • R
  • /
  • cov_estimation_whole.R
Raw File Download
Take a new snapshot of a software origin

If the archived software origin currently browsed is not synchronized with its upstream version (for instance when new commits have been issued), you can explicitly request Software Heritage to take a new snapshot of it.

Use the form below to proceed. Once a request has been submitted and accepted, it will be processed as soon as possible. You can then check its processing state by visiting this dedicated page.
swh spinner

Processing "take a new snapshot" request ...

Permalinks

To reference or cite the objects present in the Software Heritage archive, permalinks based on SoftWare Hash IDentifiers (SWHIDs) must be used.
Select below a type of object currently browsed in order to display its associated SWHID and permalink.

  • content
  • directory
  • revision
  • snapshot
origin badgecontent badge Iframe embedding
swh:1:cnt:34942c1c59b62cb4dc394c7f4dc397b489495736
origin badgedirectory badge Iframe embedding
swh:1:dir:cc1453b5539f27411df9cb04b3c75ade6d81af41
origin badgerevision badge
swh:1:rev:b182e9a2447bc977ecd715351503848f37718038
origin badgesnapshot badge
swh:1:snp:a7e81d59d1c390b08089952db41e90a1abb796ee
Citations

This interface enables to generate software citations, provided that the root directory of browsed objects contains a citation.cff or codemeta.json file.
Select below a type of object currently browsed in order to generate citations for them.

  • content
  • directory
  • revision
  • snapshot
Generate software citation in BibTex format (requires biblatex-software package)
Generating citation ...
Generate software citation in BibTex format (requires biblatex-software package)
Generating citation ...
Generate software citation in BibTex format (requires biblatex-software package)
Generating citation ...
Generate software citation in BibTex format (requires biblatex-software package)
Generating citation ...
Tip revision: b182e9a2447bc977ecd715351503848f37718038 authored by Jona Cederbaum on 19 June 2021, 08:10:02 UTC
version 0.4.1
Tip revision: b182e9a
cov_estimation_whole.R
##################################################################################################################
# author: Jona Cederbaum
##################################################################################################################
# description: function to estimate smooth auto-covariance operators using all cross products and without symmetry
# constraint. Gives out auto-covariances evaluated on a pre-specified grid.
##################################################################################################################
estimate_cov_whole_fun <- function(index, use_RI = FALSE, use_simple = FALSE, bf, method = "REML", 
                                   d_grid = 100, grid_row, grid_col, same_subject_grid, same_word_grid, 
                                   same_curve_grid, same_point_grid, bs, m, use_bam, t,
                                   mp = TRUE, para_estim = FALSE, para_estim_nc, 
                                   weights = NULL, np = TRUE, use_discrete = TRUE){
  
  if(use_bam == TRUE){
    #######################
    # covariance estimation
    # using bam
    #######################
    
    ################
    # set cluster
    # for estimation
    # if specified
    ################
    if(para_estim & !use_discrete){
      if(detectCores() > 1){
        nc_use <- min(detectCores(), para_estim_nc)
        if(.Platform$OS.type=="unix"){
          cl_estim <- makeForkCluster(nnodes = nc_use) # only runs on unix
        }else{
          cl_estim <- makeCluster(nc_use) # also runs on windows
        }
      }else{
        cl_estim <- NULL
      }
    }else{
      cl_estim <- NULL  
    }
    
    if(!use_RI){
      ##################
      # for crossed fRIs
      if(use_discrete){
        time_cov_estim <- 
          system.time(gam1 <- try(bam(cross_vec_bivariate ~ - 1 + 
                                        te(row_t_bivariate, col_t_bivariate, by = same_subject, k = bf[1], bs = c(bs, bs), m = m[[1]], mp = mp, np = np) + 
                                        te(row_t_bivariate, col_t_bivariate, by = same_word, k = bf[2], bs = c(bs, bs), m = m[[2]], mp = mp, np = np) + 
                                        te(row_t_bivariate, col_t_bivariate, by = same_curve, k = bf[3], bs = c(bs, bs), m = m[[3]], mp = mp, np = np) + 
                                        same_point, method = method, data = index, 
                                      discrete = TRUE, nthreads = para_estim_nc, weights = weights)))
      }else{
        time_cov_estim <- 
          system.time(gam1 <- try(bam(cross_vec_bivariate ~ - 1 + 
                                        te(row_t_bivariate, col_t_bivariate, by = same_subject, k = bf[1], bs = c(bs, bs), m = m[[1]], mp = mp, np = np) + 
                                        te(row_t_bivariate, col_t_bivariate, by = same_word, k = bf[2], bs = c(bs, bs), m = m[[2]], mp = mp, np = np) + 
                                        te(row_t_bivariate, col_t_bivariate, by = same_curve, k = bf[3], bs = c(bs, bs), m = m[[3]], mp = mp, np = np) + 
                                        same_point, method = method, data = index, cluster = cl_estim, weights = weights)))
      }
      
    }else{
      if(!use_simple){
        #############
        # for one fRI
        if(use_discrete){
          time_cov_estim <- 
            system.time(gam1 <- try(bam(cross_vec_bivariate ~ 1 + 
                                          te(row_t_bivariate, col_t_bivariate, k = bf[1], bs = c(bs, bs), m = m[[1]], mp = mp, np = np) + 
                                          te(row_t_bivariate, col_t_bivariate, by = same_curve, k = bf[2], bs = c(bs, bs), m = m[[2]], mp = mp, np = np) + 
                                          same_point, method = method, data = index, 
                                        discrete = TRUE, nthreads = para_estim_nc, weights = weights)))  
        }else{
          time_cov_estim <- 
            system.time(gam1 <- try(bam(cross_vec_bivariate ~ 1 + 
                                          te(row_t_bivariate, col_t_bivariate, k = bf[1], bs = c(bs, bs), m = m[[1]], mp = mp, np = np) + 
                                          te(row_t_bivariate, col_t_bivariate, by = same_curve, k = bf[2], bs = c(bs, bs), m = m[[2]], mp = mp, np = np) + 
                                          same_point, method = method, data = index, cluster = cl_estim, weights = weights)))
        }
        
      }else{
        ########################
        # for independent curves
        if(use_discrete){
          time_cov_estim <- 
            system.time(gam1 <- try(bam(cross_vec_bivariate ~ 1 + 
                                          te(row_t_bivariate, col_t_bivariate, k = bf[1], bs = c(bs, bs), m = m[[1]], mp = mp, np = np) + 
                                          same_point, method = method, data = index, 
                                        discrete = TRUE, nthreads = para_estim_nc, weights = weights)))    
        }else{
          time_cov_estim <- 
            system.time(gam1 <- try(bam(cross_vec_bivariate ~ 1 + 
                                          te(row_t_bivariate, col_t_bivariate, k = bf[1], bs = c(bs, bs), m = m[[1]], mp = mp, np = np) + 
                                          same_point, method = method, data = index, cluster = cl_estim, weights = weights)))
        }
      
      }
    }
    
    ##########################
    # stop cluster if existing
    ##########################
    if(!is.null(cl_estim)) stopCluster(cl_estim) 
  }else{      
    #######################
    # covariance estimation
    # using gam
    #######################
    
    if(!use_RI){
      ##################
      # for crossed fRIs
      time_cov_estim <- 
        system.time(gam1 <- try(gam(cross_vec_bivariate ~ - 1 + 
                                      te(row_t_bivariate, col_t_bivariate, by = same_subject, k = bf[1], bs = c(bs, bs), m = m[[1]], mp = mp, np = np) + 
                                      te(row_t_bivariate, col_t_bivariate, by = same_word, k = bf[2], bs = c(bs, bs), m = m[[2]], mp = mp, np = np) + 
                                      te(row_t_bivariate, col_t_bivariate, by = same_curve, k = bf[3], bs = c(bs, bs), m = m[[3]], mp = mp, np = np) + 
                                      same_point, method = method, data = index, weights = weights)))
    }else{ 
      if(!use_simple){
        #############
        # for one fRI
        time_cov_estim <- 
          system.time(gam1 <- try(gam(cross_vec_bivariate ~ 1 + 
                                        te(row_t_bivariate, col_t_bivariate, k = bf[1], bs = c(bs, bs), m = m[[1]], mp = mp, np = np) + 
                                        te(row_t_bivariate, col_t_bivariate, by = same_curve, k = bf[2], bs = c(bs, bs), m = m[[2]], mp = mp, np = np) + 
                                        same_point, method = method, data = index, weights = weights)))
      }else{
        ########################
        # for independent curves
        time_cov_estim <- 
          system.time(gam1 <- try(gam(cross_vec_bivariate ~ 1 + 
                                        te(row_t_bivariate, col_t_bivariate, k = bf[1], bs = c(bs, bs), m = m[[1]], mp = mp, np = np) + 
                                        same_point, method = method, data = index, weights = weights)))
      }
      
    }
  }
  
  if(class(gam1)[1] != "try-error"){    
    
    ##############################
    # extract smoothing parameters
    ##############################
    sp <- gam1$sp
    
    if(use_RI){
      ###################
      # extract intercept
      ###################
      intercept <- as.numeric(coefficients(gam1)[1])
    }
    
    #################
    # extract sigmasq
    # and truncate
    #################
    sigmasq <- as.numeric(max(coefficients(gam1)["same_point"], 0))
    
    #################################
    # compute the integral of sigmasq
    #################################
    sigmasq_int <- (max(unlist(t))-min(unlist(t))) * sigmasq
    
    
    ##########################
    # construct data frame for
    # evaluation on grid 
    ##########################
    
    if(!use_RI){
      ##################
      # for crossed fRIs
      grid_data <- data.table(row_t_bivariate = grid_row, col_t_bivariate = grid_col, same_subject = same_subject_grid, 
                              same_word = same_word_grid, same_curve = same_curve_grid, same_point = same_point_grid)
      
      ##########################
      # remove unnecessary stuff
      ##########################
      grid_row <- NULL
      grid_col <- NULL
      same_subject_grid <- NULL
      same_word_grid <- NULL
      same_curve_grid <- NULL
      same_point_grid <- NULL
    }else{
      ###################################
      # for one fRI or independent curves
      grid_data <- data.table(row_t_bivariate = grid_row, col_t_bivariate = grid_col, same_subject = same_subject_grid, 
                              same_curve = same_curve_grid, same_point = same_point_grid)
      
      ##########################
      # remove unnecessary stuff
      ##########################
      grid_row <- NULL
      grid_col <- NULL
      same_subject_grid <- NULL
      same_curve_grid <- NULL
      same_point_grid <- NULL
    }
    
    ####################
    # evaluation on grid
    ####################
    time_cov_pred_grid <- 
      system.time(grid_smooth <- predict(gam1, newdata = grid_data, na.omit = TRUE, type = "terms"))
    
    grid_data <- NULL
    
    #####################
    # extract covariances
    #####################
    if(!use_RI){
      ##################
      # for crossed fRIs
      grid_mat_B <- matrix(grid_smooth[, 2], ncol = d_grid, nrow = d_grid, byrow = TRUE)  
      grid_mat_C <- matrix(grid_smooth[, 3], ncol = d_grid, nrow = d_grid, byrow = TRUE)  
      grid_mat_E <- matrix(grid_smooth[, 4], ncol = d_grid, nrow = d_grid, byrow = TRUE)
    }else{
      if(!use_simple){
        #############
        # for one fRI
        grid_mat_B <- matrix(grid_smooth[, 2], ncol = d_grid, nrow = d_grid, byrow = TRUE) + intercept
        grid_mat_C <- matrix(rep(0, length = d_grid^2), ncol = d_grid, nrow = d_grid, byrow = TRUE)  
        grid_mat_E <- matrix(grid_smooth[, 3], ncol = d_grid, nrow = d_grid, byrow = TRUE)  
      }else{
        ########################
        # for independent curves
        grid_mat_B <- matrix(grid_smooth[, 2], ncol = d_grid, nrow = d_grid, byrow = TRUE) + intercept
        grid_mat_C <- matrix(rep(0, length = d_grid^2), ncol = d_grid, nrow = d_grid, byrow = TRUE)  
        grid_mat_E <- matrix(rep(0, length = d_grid^2), ncol = d_grid, nrow = d_grid, byrow = TRUE)  
      }
      grid_smooth <- NULL    
    }
  }else{
    sigmasq <- NA
    sigmasq_int <- NA
    grid_mat_B <- NA
    grid_mat_C <- NA
    grid_mat_E <- NA
    sp <- NA
    time_cov_pred_grid <- NA
    time_cov_estim <- NA
    warning("covariance estimation did not succeed")
  } 
  
  gam1 <- NULL
  
  ###############
  # return output
  ###############
  out <- list(sigmasq = sigmasq, sigmasq_int = sigmasq_int, grid_mat_B = grid_mat_B, 
              grid_mat_C = grid_mat_C, grid_mat_E = grid_mat_E, 
              sp = sp, time_cov_estim = time_cov_estim,
              time_cov_pred_grid = time_cov_pred_grid)
  return(out)
}

####################################################################################

back to top

Software Heritage — Copyright (C) 2015–2025, The Software Heritage developers. License: GNU AGPLv3+.
The source code of Software Heritage itself is available on our development forge.
The source code files archived by Software Heritage are available under their own copyright and licenses.
Terms of use: Archive access, API— Contact— JavaScript license information— Web API