simulations/plot_example_2_continuous.R

   1 library(arrow)
   2 library(data.table)
   3 library(ggplot2)
   4
   5 df <- data.table(read_feather("example_2_simulation.feather"))
   6
   7 x.naive <- df[,.(N, m, Bxy, Bxy.est.naive, Bxy.ci.lower.naive, Bxy.ci.upper.naive)]
   8 x.naive <- x.naive[,':='(true.in.ci = as.integer((Bxy >= Bxy.ci.lower.naive) & (Bxy <= Bxy.ci.upper.naive)),
   9                          zero.in.ci = (0 >= Bxy.ci.lower.naive) & (0 <= Bxy.ci.upper.naive),
  10                          bias = Bxy - Bxy.est.naive,
  11                          sign.correct = as.integer(sign(Bxy) == sign(Bxy.est.naive)))]
  12
  13 x.naive.plot <- x.naive[,.(p.true.in.ci = mean(true.in.ci),
  14                            mean.bias = mean(bias),
  15                            p.sign.correct = mean(as.integer(sign.correct & (! zero.in.ci))),
  16                            variable='x',
  17                            method='Naive'
  18                            ),
  19                         by=c('N','m')]
  20
  21 g.naive <- df[,.(N, m, Bgy, Bgy.est.naive, Bgy.ci.lower.naive, Bgy.ci.upper.naive)]
  22 g.naive <- g.naive[,':='(true.in.ci = as.integer((Bgy >= Bgy.ci.lower.naive) & (Bgy <= Bgy.ci.upper.naive)),
  23                          zero.in.ci = (0 >= Bgy.ci.lower.naive) & (0 <= Bgy.ci.upper.naive),
  24                          bias = Bgy - Bgy.est.naive,
  25                          sign.correct = as.integer(sign(Bgy) == sign(Bgy.est.naive)))]
  26
  27 g.naive.plot <- g.naive[,.(p.true.in.ci = mean(true.in.ci),
  28                            mean.bias = mean(bias),
  29                            p.sign.correct = mean(as.integer(sign.correct & (! zero.in.ci))),
  30                            variable='g',
  31                            method='Naive'
  32                            ),
  33                         by=c('N','m')]
  34
  35
  36
  37 x.amelia.full <- x.amelia.full[,':='(true.in.ci = (Bxy.est.true >= Bxy.ci.lower.amelia.full) & (Bxy.est.true <= Bxy.ci.upper.amelia.full),
  38                                      zero.in.ci = (0 >= Bxy.ci.lower.amelia.full) & (0 <= Bxy.ci.upper.amelia.full),
  39                                      bias = Bxy.est.true - Bxy.est.amelia.full,
  40                                      sign.correct = sign(Bxy.est.true) == sign(Bxy.est.amelia.full))]
  41
  42 x.amelia.full.plot <- x.amelia.full[,.(p.true.in.ci = mean(as.integer(true.in.ci)),
  43                                        mean.bias = mean(bias),
  44                                        p.sign.correct = mean(as.integer(sign.correct & (! zero.in.ci))),
  45                                        variable='x',
  46                                        method='Multiple imputation'
  47                                        ),
  48                                     by=c('N','m')]
  49
  50
  51
  52 g.amelia.full <- df[,.(N, m, Bgy.est.true, Bgy.est.amelia.full, Bgy.ci.lower.amelia.full, Bgy.ci.upper.amelia.full)]
  53 g.amelia.full <- g.amelia.full[,':='(true.in.ci = (Bgy.est.true >= Bgy.ci.lower.amelia.full) & (Bgy.est.true <= Bgy.ci.upper.amelia.full),
  54                                      zero.in.ci = (0 >= Bgy.ci.lower.amelia.full) & (0 <= Bgy.ci.upper.amelia.full),
  55                                      bias =  Bgy.est.amelia.full - Bgy.est.true,
  56                                      sign.correct = sign(Bgy.est.true) == sign(Bgy.est.amelia.full))]
  57
  58 g.amelia.full.plot <- g.amelia.full[,.(p.true.in.ci = mean(as.integer(true.in.ci)),
  59                                        mean.bias = mean(bias),
  60                                        p.sign.correct = mean(as.integer(sign.correct & (! zero.in.ci))),
  61                                        variable='g',
  62                                        method='Multiple imputation'
  63                                        ),
  64                                     by=c('N','m')]
  65
  66
  67
  68
  69 x.amelia.nok <- df[,.(N, m, Bxy.est.true, Bxy.est.amelia.nok, Bxy.ci.lower.amelia.nok, Bxy.ci.upper.amelia.nok)]
  70 x.amelia.nok <- x.amelia.nok[,':='(true.in.ci = (Bxy.est.true >= Bxy.ci.lower.amelia.nok) & (Bxy.est.true <= Bxy.ci.upper.amelia.nok),
  71                                      zero.in.ci = (0 >= Bxy.ci.lower.amelia.nok) & (0 <= Bxy.ci.upper.amelia.nok),
  72                                      bias =  Bxy.est.amelia.nok - Bxy.est.true,
  73                                      sign.correct = sign(Bxy.est.true) == sign(Bxy.est.amelia.nok))]
  74
  75  x.amelia.nok.plot <- x.amelia.nok[,.(p.true.in.ci = mean(as.integer(true.in.ci)),
  76                                        mean.bias = mean(bias),
  77                                      p.sign.correct = mean(as.integer(sign.correct & (! zero.in.ci))),
  78                                      variable='x',
  79                                      method='Multiple imputation (Classifier features unobserved)'
  80                                      ),
  81                                     by=c('N','m')]
  82
  83 g.amelia.nok <- df[,.(N, m, Bgy.est.true, Bgy.est.amelia.nok, Bgy.ci.lower.amelia.nok, Bgy.ci.upper.amelia.nok)]
  84 g.amelia.nok <- g.amelia.nok[,':='(true.in.ci = (Bgy.est.true >= Bgy.ci.lower.amelia.nok) & (Bgy.est.true <= Bgy.ci.upper.amelia.nok),
  85                                      zero.in.ci = (0 >= Bgy.ci.lower.amelia.nok) & (0 <= Bgy.ci.upper.amelia.nok),
  86                                      bias =  Bgy.est.amelia.nok - Bgy.est.true,
  87                                      sign.correct = sign(Bgy.est.true) == sign(Bgy.est.amelia.nok))]
  88
  89 g.amelia.nok.plot <- g.amelia.nok[,.(p.true.in.ci = mean(as.integer(true.in.ci)),
  90                                        mean.bias = mean(bias),
  91                                      p.sign.correct = mean(as.integer(sign.correct & (! zero.in.ci))),
  92                                      variable='g',
  93                                      method='Multiple imputation (Classifier features unobserved)'
  94                                      ),
  95                                     by=c('N','m')]
  96
  97
  98 plot.df <- rbindlist(list(x.naive.plot,g.naive.plot,x.amelia.full.plot,g.amelia.full.plot,x.amelia.nok.plot,g.amelia.nok.plot))
  99
 100 ggplot(plot.df,aes(y=N,x=m,color=p.sign.correct)) + geom_point() + facet_grid(variable ~ method) + scale_color_viridis_c() + theme_minimal() + xlab("Number of gold standard labels") + ylab("Total sample size")
 101
 102 ggplot(plot.df,aes(y=N,x=m,color=mean.bias)) + geom_point() + facet_grid(variable ~ method) + scale_color_viridis_c() + theme_minimal() + xlab("Number of gold standard labels") + ylab("Total sample size")