R语言基础5（绘图基础）

plot(iris[,1],iris[,3],col = iris[,5]) 
text(6.5,4, labels = 'hello')

dev.off() #关闭画板

library(ggplot2)
#1.入门级绘图模板：作图数据，横纵坐标
ggplot(data = iris)+
  geom_point(mapping = aes(x = Sepal.Length,
                           y = Petal.Length))
#列名不添加引号
#两个函数用+连接

#2.属性设置（颜色、大小、透明度、点的形状，线型等）

#2.1 手动设置，需要设置为有意义的值

ggplot(data = iris) + 
  geom_point(mapping = aes(x = Sepal.Length,
                           y = Petal.Length), 
             color = "blue")

ggplot(data = iris) + 
  geom_point(mapping = aes(x = Sepal.Length, y = Petal.Length), 
             size = 5,     # 点的大小5mm
             alpha = 0.5,  # 透明度 50%
             shape = 8)  # 点的形状

##颜色：字符串，blue, red等；


#2.2 映射：按照数据框的某一列来定义图的某个属性
ggplot(data = iris)+
  geom_point(mapping = aes(x = Sepal.Length,
                           y = Petal.Length,
                           color = Species))

#color是aes的参数，则选列名，color是geom_point的参数则为具体颜色；

## Q1 能不能自行指定映射的具体颜色？

ggplot(data = iris)+
  geom_point(mapping = aes(x = Sepal.Length,
                           y = Petal.Length,
                           color = Species))+
  scale_color_manual(values = c("blue","grey","red"))

## Q2 区分color和fill两个属性
### Q2-1 空心形状和实心形状都用color设置颜色
ggplot(data = iris)+
  geom_point(mapping = aes(x = Sepal.Length,
                           y = Petal.Length,
                           color = Species),
             shape = 17) #17号，实心的例子

ggplot(data = iris)+
  geom_point(mapping = aes(x = Sepal.Length,
                           y = Petal.Length,
                           color = Species),
             shape = 2) #2号，空心的例子
### Q2-2 既有边框又有内心的，才需要color和fill两个参数

ggplot(data = iris)+
  geom_point(mapping = aes(x = Sepal.Length,
                           y = Petal.Length,
                           color = Species),
             shape = 24,
             fill = "black") #24号，双色的例子

#3.分面
ggplot(data = iris) + 
  geom_point(mapping = aes(x = Sepal.Length, y = Petal.Length)) + 
  facet_wrap(~ Species) 
#双分面
dat = iris
dat$Group = sample(letters[1:5],150,replace = T)
###新增一列，sample表示抽样；

ggplot(data = dat) + 
  geom_point(mapping = aes(x = Sepal.Length, y = Petal.Length)) + 
  facet_grid(Group ~ Species) 

#4.几何对象

#局部设置和全局设置

ggplot(data = iris) + 
  geom_smooth(mapping = aes(x = Sepal.Length, 
                          y = Petal.Length))+
  geom_point(mapping = aes(x = Sepal.Length, 
                           y = Petal.Length))
###局部设置
ggplot(data = iris,mapping = aes(x = Sepal.Length, y = Petal.Length))+
  geom_smooth()+
  geom_point()
###全局设置

#5.统计变换-条形图
View(diamonds)
table(diamonds$cut)

ggplot(data = diamonds) + 
  geom_bar(mapping = aes(x = cut))

ggplot(data = diamonds) + 
  stat_count(mapping = aes(x = cut))

#统计变换使用场景
#5.1.不统计，数据直接做图
fre = as.data.frame(table(diamonds$cut))
fre

ggplot(data = fre) +
  geom_bar(mapping = aes(x = Var1, y = Freq), stat = "identity")

#5.2count改为prop（比例））
ggplot(data = diamonds) + 
  geom_bar(mapping = aes(x = cut, y = after_stat(prop), group = 1))


#6.位置关系

# 6.1抖动的点图
ggplot(data = iris,mapping = aes(x = Species, 
                                 y = Sepal.Width,
                                 fill = Species)) + 
  geom_boxplot()+
  geom_point()

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

# 6.2 条形图
ggplot(data = diamonds) + 
  geom_bar(mapping = aes(x = cut,fill=clarity))

ggplot(data = diamonds) +
  geom_bar(mapping = aes(x = cut,fill = clarity),
           position = "fill")

ggplot(data = diamonds) + 
  geom_bar(mapping = aes(x = cut, fill = clarity), 
           position = "dodge")

#7.坐标系

bar <- ggplot(data = diamonds) + 
  geom_bar(mapping = aes(x = cut, fill = cut),
           width = 1) + 
  theme(aspect.ratio = 1) +
  labs(x = NULL, y = NULL)
bar
bar + coord_flip()#翻转coord_flip()
bar + coord_polar()#极坐标系coord_polar()

library(ggplot2)
ggplot(data = iris)+
  geom_violin(mapping = aes(x = Species,
                           y = Sepal.Width,
                           fill = Species))+
  scale_color_manual(values = c("pink","green","blue"))+
  geom_boxplot(mapping = aes(x = Species,
                             y = Sepal.Width))+
  geom_jitter(mapping = aes(x = Species,
                            y = Sepal.Width,
              shape=Species))+
  coord_flip()

library(ggplot2)
ggplot(data = iris,aes(x = Species,
                       y = Sepal.Width))+
  geom_violin(aes(fill = Species))+
  scale_color_manual(values = c("pink","green","blue"))+
  geom_boxplot()+
  geom_jitter(aes(shape=Species))+
  coord_flip()

# ggpubr 搜代码直接用，基本不需要系统学习

# sthda上有大量ggpubr出的图
library(ggpubr)
ggscatter(iris,x="Sepal.Length",
          y="Petal.Length",
          color="Species")

p <- ggboxplot(iris, x = "Species", 
               y = "Sepal.Length",
               color = "Species", 
               shape = "Species",
               add = "jitter")
p
my_comparisons <- list( c("setosa", "versicolor"), 
                        c("setosa", "virginica"), 
                        c("versicolor", "virginica") )
p + stat_compare_means(comparisons = my_comparisons)+ # Add pairwise comparisons p-value
  stat_compare_means(label.y = 9) 

#1.基础包作图的保存
pdf("iris_box_ggpubr.pdf")
boxplot(iris[,1]~iris[,5])
text(6.5,4, labels = 'hello')
dev.off()

#2.ggplot系列图(包括ggpubr)通用的简便保存 ggsave
p <- ggboxplot(iris, x = "Species", 
               y = "Sepal.Length",
               color = "Species", 
               shape = "Species",
               add = "jitter")
ggsave(p,filename = "iris_box_ggpubr.png")

#3.eoffice包 导出为ppt,全部元素都是可编辑模式
library(eoffice)
topptx(p,"iris_box_ggpubr.pptx")
###超多的点或行列的热图不适用，PPT会卡顿。
#https://mp.weixin.qq.com/s/p7LLLvzR5LPgHhuRGhYQBQ

library(stringr)
str_split(x," ")##按照空格分隔
str_split(x," "，simplify=T)##列表简化为矩阵

# arrange，数据框按照某一列排序
sort()##只排序某一列，其他列不改变；无法改变对应关系。
library(dplyr)
arrange(test, Sepal.Length) #将Sepal.LengthSepal.Length这一列从小到大排序
arrange(test, desc(Sepal.Length)) #从大到小

# distinct，数据框按照某一列去重复
distinct(test,Species,.keep_all = T)##将Species列去重复，保留所有列；

# mutate，数据框新增一列
mutate(test, new = Sepal.Length * Sepal.Width)
test$new= .....
##筛选行列
select()
filter()

# 连续的步骤
# 1.多次赋值，产生多个中间的变量
x1 = select(iris,-5)
x2 = as.matrix(x1)
x3 = head(x2,50)
pheatmap::pheatmap(x3)

# 2. 嵌套，代码不易读
pheatmap::pheatmap(head(as.matrix(select(iris,-5)),50))

# 3.管道符号传递，简洁明了
iris %>%
  select(-5) %>%
  as.matrix() %>%
  head(50) %>% 
  pheatmap::pheatmap()
##将管道符前面所有的结果传递给后面的函数，作为他的第一个参数
#用之前需要加载stringr包或dplyr包，快捷键ctrl+shift+M

rm(list = ls())

## 一.条件语句

###1.if(){ }

#### (1)只有if没有else，那么条件是FALSE时就什么都不做

i = -1
if (i<0) print('up')
if (i>0) print('up')

#理解下面代码
if(!require(tidyr)) install.packages('tidyr')

#### (2)有else
i =1
if (i>0){
  print('+')
} else {
  print("-")
}
i = 1
ifelse(i>0,"+","-")
ifelse(x,yes,no)
x:逻辑值或逻辑向量；
yes：逻辑值为TRUE时的返回值
no：逻辑值为FALSE时的返回值

x = rnorm(3)
x
ifelse(x>0,"+","-")

#ifelse()+str_detect(),王炸
samples = c("tumor1","tumor2","tumor3","normal1","normal2","normal3")
k1 = str_detect(samples,"tumor");k1
ifelse(k1,"tumor","normal")
k2 = str_detect(samples,"normal");k2
ifelse(k2,"normal","tumor")

#### (3)多个条件
i = 0
if (i>0){
  print('+')
} else if (i==0) {
  print('0')
} else if (i< 0){
  print('-')
}


library(dplyr)
i = 0
case_when(i>0 ~ "+",
          i<0 ~ "-",
          T ~ "0")
options(scipen = 20)
x = c(0.01,0.001,0.07,0.03,0.00001)
x
?ggpubr::stat_compare_means

case_when(x <= 0.0001~"****",
          x <= 0.001 ~"***",
          x <= 0.01 ~ "**",
          x <= 0.05 ~ "*",
          T ~"ns"
          )


ifelse(i>0,"+",ifelse(i<0,"-","0"))

## 二、for循环

for( i in 1:4){
  print(i)
}

#批量画图
par(mfrow = c(2,2))
for(i in 1:4){
  plot(iris[,i],col = iris[,5])
}
#批量装包
pks = c("tidyr","dplyr","stringr")
for(g in pks){
  if(!require(g,character.only = T))
    install.packages(g,ask = F,update = F)
}

# 隐式循环
apply(x, margin, fun, ...)
#x是数据框或者矩阵
#margin为行则是1，margin为列是2;
#fun为函数
#apply(test,2,mean)
#对test的每一列求平均值

sort(x)
#对x从小到大排序

head(x)
tail(x)
tail(x,1000)
#对x取前五或者后五；

identical(x1,x2)#判断x1和x2是否完全一致；

##举例
load(file="test2.Rdata")
a=apply(test,1,var)

x1=names(tail(sort(a),1000))

library(stringr)
x2=test %>%
  apply(1,var) %>%
  sort() %>%
  tail(1000) %>%
  names()
identical(x1,x2)

## 向量、列表的隐式循环——lappy
lappy(list,FUN, ...)
#对列表向量中的每个元素实施相同的操作
lappy(1:4,rnorm)

#inner_join：取交集
#full_join：全连接
#left_join：左连接
#right_join：右链接

# 表达矩阵
set.seed(10086)#生成随机数，随机种子为10086
exp = matrix(rnorm(18),ncol = 6)
exp = round(exp,2)##保留两位小数；round(exp)为取整；
rownames(exp) = paste0("gene",1:3)
colnames(exp) = paste0("test",1:6)
exp[,1:3] = exp[,1:3]+1
exp

library(tidyr)
library(tibble)
library(dplyr)
dat = t(exp) %>% 
  as.data.frame() %>% 
  rownames_to_column() %>% 
  mutate(group = rep(c("control","treat"),each = 3))

pdat = dat%>% 
  pivot_longer(cols = starts_with("gene"),###cols=2:4
               names_to = "gene",##合并为一列，列名为gene
               values_to = "count")##合并为一列，列名为count
###pivot_longer宽变长
library(ggplot2)
p = ggplot(pdat,aes(gene,count))+
  geom_boxplot(aes(fill = group))+
  theme_bw()
p
p + facet_wrap(~gene,scales = "free")

# 1.match-----
load("matchtest.Rdata")
x
y
## 如何把y的列名正确替换为x里面的ID？

## (1)分步解法
a = colnames(y)
b = x$file_name
k = match(a,b);k
#match(a,b)的意思是a里的每个元素在b的第几个位置上。
#是b的下标，可以给b取子集，也可以给与b对应的其他向量取子集。
colnames(y) = x$ID[k]

## (2)一步解法
load("matchtest.Rdata")
colnames(y) = x$ID[match(colnames(y),x$file_name)]

## (3)放弃match的解法
load("matchtest.Rdata")
rownames(x) = x$file_name
x = x[colnames(y),]
colnames(y) = x$ID

# 2.一些搞文件的函数----
dir() # 列出工作目录下的文件
dir(pattern = ".R$") #列出工作目录下以.R结尾的文件

file.create("douhua.txt") #用代码创建文件
file.exists("douhua.txt") #某文件在工作目录下是否存在
file.remove("douhua.txt") #用代码删除文件
file.exists("douhua.txt") #删掉了就不存在啦

## 可以批量的新建和删除
f = paste0("douhua",1:100,".txt")
file.create(f)
file.remove(f)