-
Notifications
You must be signed in to change notification settings - Fork 17
/
Copy path06-2-dplyr.Rmd
114 lines (88 loc) · 3.02 KB
/
06-2-dplyr.Rmd
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
# 推荐一个 R 中很好用的条件判断语句
```{r}
text <- "Gene log2FoldChange padj
a 1 0.1
b 2 0.05
d 3 0.001
e -2 0.0002
G 0 0.0001"
res_output <- read.table(text=text, row.names=NULL, header=T)
padj_thresh = 0.05
log2FC = 1
groupA = 'trt'
groupB = 'untrt'
```
## ifelse 标记差异基因
不想安装额外的包，可以用 `ifelse`，要稍微复杂一点。
```{r}
res_output$level <- ifelse(res_output$padj<=padj_thresh,
ifelse(res_output$log2FoldChange>=log2FC,
paste(groupA,"UP"),
ifelse(res_output$log2FoldChange<=(-1)*(log2FC),
paste(groupB,"UP"), "NoDiff")) , "NoDiff")
```
或
```{r}
res_output$level <-
ifelse(res_output$padj<=padj_thresh & res_output$log2FoldChange>=log2FC, paste(groupA,"UP"),
ifelse(res_output$padj<=padj_thresh & res_output$log2FoldChange<=(-1)*(log2FC), paste(groupB,"UP"),
"NoDiff"))
```
## dplyr::case-when 标记差异基因
比之前简洁了一些，可读性强
```{r}
library(dplyr)
res_output %>% mutate(level = case_when(
(padj<=padj_thresh) & (log2FoldChange>=log2FC) ~ paste(groupA,"UP"),
(padj<=padj_thresh) & (log2FoldChange<=(-1)*log2FC) ~ paste(groupB, "UP"),
TRUE ~ "NoDiff"
))
```
## dplyr::if_else 会更快一点
速度快一点，但可读性弱了一些。
```{r}
res_output %>% mutate(level =
if_else(res_output$padj<=padj_thresh & res_output$log2FoldChange>=log2FC, paste(groupA,"UP"),
if_else(res_output$padj<=padj_thresh & res_output$log2FoldChange<=(-1)*(log2FC), paste(groupB,"UP"),
"NoDiff")))
```
## case-when只保留差异基因的名字
```{r}
library(dplyr)
res_output %>% mutate(diff_gene = case_when(
(padj<=padj_thresh) & (log2FoldChange>=log2FC) ~ Gene,
(padj<=padj_thresh) & (log2FoldChange<=(-1)*log2FC) ~ Gene,
TRUE ~ ""
))
```
## case-when每隔 1 个基因保留 1 个
临时生成列时操作起来更方便了
```{r}
library(dplyr)
res_output %>% mutate(rank=1:n(),
keep_gene = case_when(
rank %% 2 == 1 ~ Gene,
TRUE ~ ""
))
```
## `dplyr::if_else`速度最快！
`dplyr::if_else`速度最快！
```
suppressPackageStartupMessages(library(tidyverse))
microbenchmark::microbenchmark(
case_when(1:1000 < 100 ~ "low", TRUE ~ "high"),
if_else(1:1000 < 3, "low", "high"),
ifelse(1:1000 < 3, "low", "high")
)
#> Unit: microseconds
#> expr min lq mean
#> case_when(1:1000 < 100 ~ "low", TRUE ~ "high") 384.786 418.629 953.4921
#> if_else(1:1000 < 3, "low", "high") 61.943 67.686 128.9811
#> ifelse(1:1000 < 3, "low", "high") 256.797 264.796 391.7180
#> median uq max neval
#> 631.9420 708.4480 33149.364 100
#> 90.0435 127.9885 2496.182 100
#> 327.9695 460.8810 2354.246 100
Ref: https://community.rstudio.com/t/case-when-why-not/2685/2
```
如果不想安装额外包，用`ifelse`；如果是单个条件，用`dplyr::if_else`；如果多个条件，用`dplyr::case_when` (更可读)。