如何将相关分析结果放入 R 中的 csv table

How to put correlation analysis results in a csv table in R

在 R 中,我需要将两个变量之间相关性分析的结果放在 table.csv 文件中。原始数据框由三列组成:第一列(组)包含观察所属的组,而其他两列(var1 和 var2)包含两个变量的值。

df <- data.frame(group = rep(c("G1", "G2"), each = 10),
                 var1 = rnorm(20),
                 var2 = rnorm(20))

我进行了分组相关性分析。

spear <- by(df, df$group, FUN = function(X) cor.test(X$var1, X$var2, method = "spearman"))

我得到了这个输出:

spear
#df$group: G1
#   Spearman's rank correlation rho
#data:  X$var1 and X$var2
#S = 144, p-value = 0.7329
#alternative hypothesis: true rho is not equal to 0
#sample estimates:
#      rho 
#0.1272727 
#--------------------------------------------------------------------------------------- 
#df$group: G2
#   Spearman's rank correlation rho
#data:  X$var1 and X$var2
#S = 122, p-value = 0.4697
#alternative hypothesis: true rho is not equal to 0
#sample estimates:
#      rho 
#0.2606061

现在我需要获取一个 table,第一行为 header,csv 格式,第一列是组的 id,第一列是该组的 rho 值第二列,第三列中该组的 p-value。 table 应如下所示:

group,rho,pvalue
G1,0.1272727,0.7329
G2,0.2606061,0.4697

我们可以使用lapply()从输出对象中提取值,将它们转换为数据帧,并将合并后的数据帧写入csv文件。

set.seed(95014) # to make example reproducible
df <- data.frame(group = rep(c("G1", "G2"), each = 10),
                 var1 = rnorm(20),
                 var2 = rnorm(20))

spear <- by(df, df$group, FUN = function(X) cor.test(X$var1, X$var2, method = "spearman"))

此时对象 spear 是一个列表,每个组包含一个元素。我们将处理每个元素,提取所需的元素并将它们作为 data.frame().

类型的对象列表返回

由于列表中的元素是按组命名的,我们使用unique(df$group)来驱动lapply(),使我们能够将名称分配为输出数据框中的列。

# convert to data frame 
dfList <- lapply(unique(df$group),function(x){
     y <- spear[[x]]
     data.frame(group = x,
                rho_value = y$estimate,
                p_value = y$p.value)
})

最后,我们使用 do.call() 将数据帧列表作为第一个参数绑定到 write.csv(),从而生成单个数据帧,然后以逗号分隔值格式写入磁盘。

write.csv(do.call(rbind,dfList),"./data/rhoCalcs.csv",row.names=FALSE)

...和输出:

"group","rho_value","p_value"
"G1",0.260606060606061,0.469675250206491
"G2",0.333333333333333,0.348846243872153

您可以在 by 函数中创建一个数据框来提取您想要的值。

result <- do.call(rbind, by(df, df$group, FUN = function(x) {
  tmp <- cor.test(x$var1, x$var2, method = "spearman")
  data.frame(group = x$group[1], rho = tmp$estimate, p.value = tmp$p.value)
}))
result
#   group    rho p.value
#G1    G1 -0.261   0.470
#G2    G2 -0.442   0.204

要将数据写入 csv,我们可以使用 write.csv :

write.csv(result, 'result.csv', row.names = FALSE)

spearobject是两个列表的列表(每组一个htest列表):

str(spear)
List of 2
 $ G1:List of 8
  ..$ statistic  : Named num 140
  .. ..- attr(*, "names")= chr "S"
  ..$ parameter  : NULL
  ..$ p.value    : num 0.682
  ..$ estimate   : Named num 0.152
  .. ..- attr(*, "names")= chr "rho"
  ..$ null.value : Named num 0
  .. ..- attr(*, "names")= chr "rho"
  ..$ alternative: chr "two.sided"
  ..$ method     : chr "Spearman's rank correlation rho"
  ..$ data.name  : chr "X$var1 and X$var2"
  ..- attr(*, "class")= chr "htest"
 $ G2:List of 8
  ..$ statistic  : Named num 180
  .. ..- attr(*, "names")= chr "S"
  ..$ parameter  : NULL
  ..$ p.value    : num 0.811
  ..$ estimate   : Named num -0.0909
  .. ..- attr(*, "names")= chr "rho"
  ..$ null.value : Named num 0
  .. ..- attr(*, "names")= chr "rho"
  ..$ alternative: chr "two.sided"
  ..$ method     : chr "Spearman's rank correlation rho"
  ..$ data.name  : chr "X$var1 and X$var2"
  ..- attr(*, "class")= chr "htest"
 - attr(*, "dim")= int 2
 - attr(*, "dimnames")=List of 1
  ..$ df$group: chr [1:2] "G1" "G2"
 - attr(*, "call")= language by.data.frame(data = df, INDICES = df$group, FUN = function(X) cor.test(X$var1,      X$var2, method = "spearman"))
 - attr(*, "class")= chr "by"

broom 包中的 tidy 函数可以将 htest 列表转换为 data.frame(真的是小标题)。

library(broom)
lapply(spear, tidy)
$G1
# A tibble: 1 x 5
  estimate statistic p.value method                          alternative
     <dbl>     <dbl>   <dbl> <chr>                           <chr>      
1    0.152       140   0.682 Spearman's rank correlation rho two.sided  

$G2
# A tibble: 1 x 5
  estimate statistic p.value method                          alternative
     <dbl>     <dbl>   <dbl> <chr>                           <chr>      
1  -0.0909       180   0.811 Spearman's rank correlation rho two.sided  

您仍然有一个列表,但它更实用。使用一些 dplyr 函数,我们可以使这个列表看起来像你想要的那样:

library(dplyr)

lapply(spear, tidy) %>% 
  bind_rows() %>% 
  mutate(group = names(spear)) %>%
  rename(rho = estimate) %>%
  select(group, rho, p.value)

# A tibble: 2 x 3
  group     rho p.value
  <chr>   <dbl>   <dbl>
1 G1     0.152    0.682
2 G2    -0.0909   0.811

使用 sapply 而不是 by 的解决方案。

gu <- unique(df$group)  ## putting the groups into a vector
r <- sapply(gu, function(x) 
  cor.test(~ var1 + var2, df[df$group == x, ], method="spearman")[c("estimate", "p.value")])
r <- cbind(group=gu, matrix(unlist(r), 2, b=T, dimnames=list(NULL, c("rho", "p_value"))))
write.csv(r, file="xyz.csv", row.names=FALSE, quote=FALSE)

或者,如果您需要更频繁地这样做,您可以将其包装在一个小函数中。

my.cor.test <- function(x) {
  ct <- cor.test(~ var1 + var2, df[df$group == x, ], 
                 method="spearman")[c("estimate", "p.value")]
  setNames(c(x, unlist(ct)), c("group", "rho", "p_value"))
}

gu <- unique(df$group)  ## putting unique groups into a vector
r <- t(sapply(gu, my.cor.test))
write.csv(r, file="xyz.csv", row.names=FALSE, quote=FALSE)

给予

group,rho,p_value
G1,-0.696969696969697,0.0311410954595681
G2,0.0545454545454545,0.891638843953118