生信入门马拉松之R语言基础- R语言作图(Day 6)

library(ggplot2)
ggplot(data = iris)+
  geom_smooth(mapping = aes(x = Sepal.Length,y = Petal.Length))+
  geom_point(mapping = aes(x = Sepal.Length,y = Petal.Length))#两个geom函数是局部图层+局部图层

ggplot(data = iris,mapping = aes(x = Sepal.Length,y = Petal.Length))+
  geom_smooth()+
  geom_point()#这个代码和上一句代码运行结果一致，简化写法，ggplot()中设置是全局设置，对于代码中所有的geom函数都有效，自定义可以在局部的函数中设置

ggplot(iris)+
  geom_boxplot(mapping = aes(x = Species,y = Sepal.Width,fill = Species))

library(ggplot2)
ggplot(iris)+
  geom_boxplot(mapping = aes(x = Species,y = Sepal.Width,fill = Species))+
  geom_point(mapping = aes(x = Species,y = Sepal.Width))
#或者
ggplot(iris,mapping = aes(x = Species,y = Sepal.Width))+
  geom_boxplot(mapping = aes(fill = Species))+
  geom_point()

ggplot(iris,mapping = aes(x = Species,y = Sepal.Width,fill = Species))+
  geom_boxplot()+
  geom_point(position = "jitter")
#或
ggplot(iris,mapping = aes(x = Species,y = Sepal.Width,fill = Species))+
  geom_boxplot()+
  geom_jitter()

library(ggpubr)
p <- ggboxplot(iris,x = "Species",y = "Sepal.Length",
               color = "Species",shape = "Species",add = "jitter")
p

my_comparisions <- list(c("setosa","versicolor"),
                        c("setosa","virginica"),
                        c("versicolor","virginica"))
p + stat_compare_means(comparisons = my_comparisions,
                     aes(label = after_stat(p.signif)))
#comparisons参数要求很严格：必须有列表；列表里必须是长度为2向量组成的；第三这些向量里""里的的值必须是图的横坐标；三个要求缺一就会报错！！！

library(eoffice)#加载
topptx(p,"iris_box_ggpubr.pptx")#将图(变量p)保存到ppt内

?geom_violin
ggplot(iris,mapping = aes(x = Species,y = Sepal.Width))+
  geom_violin(mapping = aes(fill = Species))+
  geom_boxplot()+
  geom_jitter(aes(shape = Species))+
  coord_flip()

dev.off()#关闭画板
#或
dev.new()#新建画板

rm(list = ls())
if(!require(stringr))install.packages('stringr')
library(stringr)

x <- "The birch canoe slid on the smooth planks."
x
### 1.检测字符串长度
str_length(x)#返回42（字符串的长度）
length(x)#返回1（向量的元素）

### 2.字符串拆分
str_split(x," ")#为何拆分成列表？列表第几个元素，就是拆分出向量的第几个元素
class(str_split(x," "))#列表
x2 = str_split(x," ")[[1]];x2#提取出向量

y = c("jimmy 150","nicker 140","tony 152")
str_split(y," ")
str_split(y," ",simplify = T)#该参数简化作用，输出结果变成矩阵

### 3.按位置提取字符串
str_sub(x,5,9)

### 4.字符检测（非常重要‼️）
str_detect(x2,"h")#产生结果是与x2相等的逻辑值向量，可用于按照逻辑值筛选
str_starts(x2,"T")
str_ends(x2,"e")
### 5.字符串替换
x2
str_replace(x2,"o","A")#只替换每个元素字符串的一个字符
str_replace_all(x2,"o","A")

### 6.字符删除
x
str_remove(x," ")#只删除每个元素字符串的一个字符
str_remove_all(x," ")

#我的回答
x1 = read.csv("group.csv")
x2 <- x1$title
x2
library(stringr)
x3 <- str_remove_all(x2,"A375 cells 24h ")
x3
x4 <- str_remove_all(x3," rep1")
x4
x5 <- str_remove_all(x4," rep2")
x6 <- str_remove_all(x5," rep3")
x6

x7 <- str_replace(x6,"C","c")
x8 <- str_replace(x7,"V","v")
x8

load("test1.Rdata")

#先按照symbol找出不重复的行
unique(ids["symbol"])
或
unique(ids$symbol)
然后提取出相关行的行名
raw <- rownames(unique(ids["symbol"]))
raw
class(raw)#返回结果是字符串

raw2 <- as.numeric(raw)
class(raw2)
raw2#数字组成的向量

ids2 <- ids[raw2,];ids2

#小洁老师的答案,应用了字符串拆分，步骤非常简化，比我的简单多了，我的步骤繁琐。

a <- read.csv("group.csv")
g <- str_split(a$title," ",simplify = T)#转化成矩阵
g
g2 <- g[,4];g2

#或
str_sub(a$title,16,-6)
str_remove_all(a$title,"A375 cells 24h | rep1| rep2| rep3")#我想到了管道符，但是用法错了，我想这里加深了对管道符的理解了

#或
str_remove_all(a$title,"A375 cells 24h | rep\\d")#\\dd代表任意数字

tolower(g[,4])#大写换小写的函数1
str_to_lower(g[,4])#大写换小写的函数2

arrage()#排序

arrage(test,Sepal.Length)#加引号不会排序，而且不会报错。对表格按照第一列排序，默认从小到大

arrage(test,desc(Sepal.Length))#从大到小排序，没有为什么哦！

distinct()#去重复

distinct(test,Species,.keep_all = T)# .keep_all参数意思是是否保留其他列，T保留，F不保留


mutate()#数据框新增列

mutate(test,new = Sepal.Length*Sepal.Width)#运行完这句代码后test有几列？答案是列数不变，因为没有赋值就没有改变。test$new <- test$Sepal.Length*Sepal.Width

select()#筛选列
filter()#筛选行

x1 <- select(iris,-5)
x2 <- as.matrix(x1)
x3 <- head(x2,50)
pheatmap::pheatmap(x3)

#或
pheatmap::pheatmap(head(as.matrix(select(iris,-5)),50))#嵌套函数等于上边4句代码，非常不易读

#管道符号传递%>%

iris %>%
  select(-5) %>%
  as.matrix() %>%
  head() %>%
  pheatmap::pheatmap()# %>%前的代码，默认为下一个函数()里的第一个参数。易读，而且代码简单，缺点是降低运算速度。