将 for 循环嵌套到矢量化函数并在数据框中保存值

Question

我有一个非常大的输出，需要把它放在一个表中。应该有 3380 行和 250 列，表格应该是这样的

。 (=input_template_df_0)

然后我有另一个表，其输出中的列名和行名各在一列中，看起来像这样

。 (=input_lofreq_4)

我知道如何使用嵌套的 for 循环来执行此操作，但是您可以想象这需要很长时间（！）。我（还）不太擅长应用和矢量化函数，所以我希望这个社区中的某个人可以帮助我将我的函数转换为更快的函数？

PS：还有一个 if 函数，因为不是所有的组合都会在 input_lofreq_4 中找到

for(i in 1:length(rownames(input_template_df_0))){
  for(j in 1:length(colnames(input_template_df_0))){
   if(!is_empty(as.numeric(as.character(input_lofreq_4[input_lofreq_4$selectrow==rownames(input_template_df_0)[i] & input_lofreq_4$selectcolumn==colnames(input_template_df_0)[j],"VF"])))) {
  input_template_df_0[i,j] <- as.numeric(as.character(input_lofreq_4[input_lofreq_4$selectrow==rownames(input_template_df)[i] & input_lofreq_4$selectcolumn==colnames(input_template_df_0)[j],"VF"]))
  }
  }
}

谢谢！

编辑：我制作了简化的数据框

selectrow <- c("5000X-WT50-MUT50_ERR5059072","5000X-WT50-MUT50_ERR5059238","5000X-WT50-MUT50_ERR5059260","5000X-WT50-MUT50_ERR5059092","5000X-WT50-MUT50_ERR5059204","5000X-WT50-MUT50_ERR5059123","5000X-WT50-MUT50_ERR5059282","5000X-WT50-MUT50_ERR5059072","5000X-WT50-MUT50_ERR5059238","5000X-WT50-MUT50_ERR5059260","5000X-WT50-MUT50_ERR5059092","5000X-WT50-MUT50_ERR5059204","5000X-WT50-MUT50_ERR5059123","5000X-WT50-MUT50_ERR5059282","5000X-WT50-MUT50_ERR5059072","5000X-WT50-MUT50_ERR5059238","5000X-WT50-MUT50_ERR5059260","5000X-WT50-MUT50_ERR5059092","5000X-WT50-MUT50_ERR5059204","5000X-WT50-MUT50_ERR5059123","5000X-WT50-MUT50_ERR5059282")

selectcolumn <- c("C913T_ERR5059114","C913T_ERR5059114","C913T_ERR5059114","C913T_ERR5059114","C913T_ERR5059114","C913T_ERR5059114","C913T_ERR5059114","C913T_ERR5059253","C913T_ERR5059253","C913T_ERR5059253","C913T_ERR5059253","C913T_ERR5059253","C913T_ERR5059253","C913T_ERR5059253","C913T_ERR5059286","C913T_ERR5059286","C913T_ERR5059286","C913T_ERR5059286","C913T_ERR5059286","C913T_ERR5059286","C913T_ERR5059286")

VF <- c("0.51","0.48","0.52","0.49","0.5","0.5","0.48","0.52","0.51","0.52","0.5","0.5","0.48","0.5","0.5","0.48","0.49","0.51","0.5","0.48","0.52")
input_lofreq_4 <- as.data.frame(cbind(selectrow, selectcolumn, VF))

input_template_df_0 <- as.data.frame(matrix(NA, ncol = 3, nrow = 7))
colnames(input_template_df_0) <- c("C913T_ERR5059114","C913T_ERR5059253","C913T_ERR5059286")
rownames(input_template_df_0) <- c("5000X-WT50-MUT50_ERR5059072","5000X-WT50-MUT50_ERR5059238","5000X-WT50-MUT50_ERR5059260","5000X-WT50-MUT50_ERR5059092","5000X-WT50-MUT50_ERR5059204","5000X-WT50-MUT50_ERR5059123","5000X-WT50-MUT50_ERR5059282")

input_template_df_0
input_lofreq_4

Answer 1

您可以使用lapply：

rn <- rownames(input_template_df_0)

input_template_df_0[] <- lapply(names(input_template_df_0), function(x) {
  with(input_lofreq_4, VF[rn == selectrow & selectcolumn == x])  
})

input_template_df_0
#                            C913T_ERR5059114 C913T_ERR5059253 C913T_ERR5059286
#5000X-WT50-MUT50_ERR5059072             0.51             0.52              0.5
#5000X-WT50-MUT50_ERR5059238             0.48             0.51             0.48
#5000X-WT50-MUT50_ERR5059260             0.52             0.52             0.49
#5000X-WT50-MUT50_ERR5059092             0.49              0.5             0.51
#5000X-WT50-MUT50_ERR5059204              0.5              0.5              0.5
#5000X-WT50-MUT50_ERR5059123              0.5             0.48             0.48
#5000X-WT50-MUT50_ERR5059282             0.48              0.5             0.52

---

如果数据框中有某些值，您可以使用：

tmp <- paste(input_lofreq_4$selectrow, input_lofreq_4$selectcolumn, sep = '-')
input_template_df_0[] <- input_lofreq_4$VF[match(outer(rownames(input_template_df_0), 
                         colnames(input_template_df_0), paste, sep = '-'), tmp)]