技能树Day02_直播课02-04_数据结构、R包、数据读取

原创

sheldor没耳朵

发布于 2024-07-18 18:24:06

1220

发布于 2024-07-18 18:24:06

文章被收录于专栏：生物信息学习

技能树Day02

1 直播课Day02 数据结构—向量

1.1 课堂代码

大部分引用自生信技能树

#####2.1.向量生成🌟#####

#R markdown Mac Os插入代码块快捷键command + option + i
#(1)用 c() 结合到一起
c(2,5,6,2,9)

## [1] 2 5 6 2 9

c("a","f","md","b")

## [1] "a"  "f"  "md" "b"

#(2)连续的数字用冒号“:” 
1:5

## [1] 1 2 3 4 5

#(3)有重复的用rep(),有规律的序列用seq(),随机数用rnorm()
rep("x",times = 3)

## [1] "x" "x" "x"

seq(from = 3,to = 21,by = 3)

## [1]  3  6  9 12 15 18 21

rnorm(n = 3)

## [1] 0.5710862 0.2770823 1.0682798

#(4)通过组合,产生更为复杂的向量。
paste0(rep("x",times = 3),1:3)

## [1] "x1" "x2" "x3"

#####2.2对单个向量进行的操作####
#(1)赋值给一个变量名
x = c(1,3,5,1) #随意的写法
x

## [1] 1 3 5 1

x <- c(1,3,5,1) #规范的赋值符号 Alt+减号
x

## [1] 1 3 5 1

#赋值+输出一起实现
x <- c(1,3,5,1);x

## [1] 1 3 5 1

(x <- c(1,3,5,1))

## [1] 1 3 5 1

#(2)简单数学计算
x+1

## [1] 2 4 6 2

log(x)

## [1] 0.000000 1.098612 1.609438 0.000000

sqrt(x)

## [1] 1.000000 1.732051 2.236068 1.000000

#(3)根据某条件进行判断,生成逻辑型向量
x>3

## [1] FALSE FALSE  TRUE FALSE

x==3

## [1] FALSE  TRUE FALSE FALSE

#(4)初级统计
max(x) #最大值

## [1] 5

min(x) #最小值

## [1] 1

mean(x) #均值

## [1] 2.5

median(x) #中位数

## [1] 2

var(x) #方差

## [1] 3.666667

sd(x) #标准差

## [1] 1.914854

sum(x) #总和

## [1] 10

length(x) #长度

## [1] 4

unique(x) #去重复

## [1] 1 3 5

duplicated(x) #对应元素是否重复

## [1] FALSE FALSE FALSE  TRUE

table(x) #重复值统计

## x
## 1 3 5 
## 2 1 1

sort(x)

## [1] 1 1 3 5

sort(x,decreasing = F)

## [1] 1 1 3 5

sort(x,decreasing = T)

## [1] 5 3 1 1

#####2.3.对两个向量进行的操作#####
x = c(1,3,5,1)
y = c(3,2,5,6)
#(1)比较运算，生成等长的逻辑向量
x == y

## [1] FALSE FALSE  TRUE FALSE

y == x

## [1] FALSE FALSE  TRUE FALSE

#(2)数学计算
x + y

## [1]  4  5 10  7

#(3)连接
paste(x,y,sep=",")

## [1] "1,3" "3,2" "5,5" "1,6"

#paste与paste0的区别
paste(x,y)

## [1] "1 3" "3 2" "5 5" "1 6"

paste0(x,y)

## [1] "13" "32" "55" "16"

paste(x,y,sep = "")

## [1] "13" "32" "55" "16"

paste(x,y,sep = ",")

## [1] "1,3" "3,2" "5,5" "1,6"

#当两个向量长度不一致
x = c(1,3,5,6,2)
y = c(3,2,5)
x == y # 啊！warning！

## [1] FALSE FALSE  TRUE FALSE  TRUE

#循环补齐--看ppt

#利用循环补齐简化代码
paste0(rep("x",3),1:3)

## [1] "x1" "x2" "x3"

paste0("x",1:3)

## [1] "x1" "x2" "x3"

#(4)交集、并集、差集
intersect(x,y)

## [1] 3 5 2

union(x,y)

## [1] 1 3 5 6 2

setdiff(x,y)

## [1] 1 6

setdiff(y,x)

## numeric(0)

x %in% y #x的每个元素在y中存在吗

## [1] FALSE  TRUE  TRUE FALSE  TRUE

y %in% x #y的每个元素在x中存在吗

## [1] TRUE TRUE TRUE

#####2.4.向量筛选(取子集)--看ppt#####

x <- 8:12
#根据逻辑值取子集
x[x == 10]

## [1] 10

x[x < 12]

## [1]  8  9 10 11

x[x %in% c(9,13)]

## [1] 9

#根据位置取子集
x[4]

## [1] 11

x[2:4]

## [1]  9 10 11

x[c(1,5)]

## [1]  8 12

x[-4]

## [1]  8  9 10 12

x[-(2:4)]

## [1]  8 12

####2.5.修改向量中的某个/某些元素：取子集+赋值
x

## [1]  8  9 10 11 12

#改一个元素
x[4] <- 40
x

## [1]  8  9 10 40 12

#改多个元素
x[c(1,5)] <- c(80,20)
x

## [1] 80  9 10 40 20

k1 = rnorm(12);k1

##  [1]  0.1238212  0.9495584 -2.6507704 -1.7917652  2.3110265  0.6795380 -0.4338229 -1.0173876
##  [9] -1.5896614  0.9601339 -2.8067981 -0.9245640

k2 = rep(c("a","b","c","d"),each = 3);k2

##  [1] "a" "a" "a" "b" "b" "b" "c" "c" "c" "d" "d" "d"

plot(k1)

#k1横坐标 k2纵坐标
boxplot(k1~k2)

1.2 练习题

# 练习2-2
# 1.生成1到15之间所有偶数
x <- seq(2,15,2);x

## [1]  2  4  6  8 10 12 14

# 2.生成向量，内容为："student2"  "student4"  "student6"  "student8"  "student10" "student12"
# "student14" 
# 提示：paste0
x <- paste0("student",seq(2,14,2));x

## [1] "student2"  "student4"  "student6"  "student8"  "student10" "student12" "student14"

# 3.将两种不同类型的数据用c()组合在一起，看输出结果
x <- c(2,3,4)
y <- c("a","b")
z <- c(x,y);z

## [1] "2" "3" "4" "a" "b"

# 练习2-4
# 说明：运行load("gands.Rdata"),即可得到和使用我准备的向量g和s，
# 如有报错，说明你的代码写错或project没有正确打开
load("gands.Rdata")
# 1.用函数计算向量g的长度
length(g)

## [1] 100

# 2.筛选出向量g中下标为偶数的基因名。
g[seq(2,length(g),2)]

##  [1] "CRAMP1L"    "PRSS8"      "CRAMP1L"    "SLCO1C1"    "COMMD1"     "CCT4"      
##  [7] "RAB7A"      "ZDHHC16"    "MYL12B"     "SNRPE"      "ZNF586"     "GGT7"      
## [13] "RAB7A"      "AFG3L2"     "AC104581.1" "MPP2"       "ATP2A2"     "SNRPE"     
## [19] "PRSS8"      "ZNF461"     "CECR5"      "CLEC17A"    "ATG10"      "ATG10"     
## [25] "SLC25A25"   "KRTAP4-3"   "SLCO1C1"    "GGT7"       "GSTP1"      "UBAC1"     
## [31] "NYNRIN"     "MYL12B"     "KCND1"      "RGPD3"      "C10orf128"  "SLC30A9"   
## [37] "GGT7"       "TUBA4A"     "KLHDC8A"    "HBP1"       "MARC2"      "LCP1"      
## [43] "OR2D3"      "LIPE"       "LIPE"       "CANX"       "ATP6V1B2"   "MARC2"     
## [49] "LCP1"       "HOOK2"

# 3.向量g中有多少个元素在向量s中存在(要求用函数计算出具体个数)？将这些元素筛选出来
# 提示：%in%
x = g[g%in%s];x

##  [1] "GFM2"          "SLCO1C1"       "NYNRIN"        "COMMD1"        "COMMD1"       
##  [6] "AC017081.1"    "RAB7A"         "CASKIN2"       "GGT7"          "SNRPE"        
## [11] "RGPD3"         "ZNF586"        "COMMD1"        "GGT7"          "URB1"         
## [16] "RAB7A"         "MPP2"          "AFG3L2"        "URB1"          "AC104581.1"   
## [21] "MPP2"          "SNRPE"         "ARHGAP1"       "ZNF461"        "OR2D3"        
## [26] "CECR5"         "SPDL1"         "CLEC17A"       "ZNF461"        "ATG10"        
## [31] "ATG10"         "ATG10"         "SLC25A25"      "SLC30A9"       "SLCO1C1"      
## [36] "GGT7"          "CASKIN2"       "GSTP1"         "MPP2"          "NYNRIN"       
## [41] "INTS12"        "MPP2"          "RGPD3"         "RGPD3"         "SLC30A9"      
## [46] "C10orf128"     "HBD"           "SLC30A9"       "GGT7"          "HEPH"         
## [51] "RP5-1021I20.4" "KLHDC8A"       "HBD"           "ZNF586"        "CECR5"        
## [56] "OR2D3"         "LIPE"          "INTS12"        "LIPE"          "SPDL1"        
## [61] "SLCO1C1"       "GGT7"          "CECR5"

length(x)

## [1] 63

1.3 知识点

R数据结构

脚本是乱码的解决办法

rmd生成md的方式

knitr:knit("*.rmd")

R特有的变量保存格式：Rdata

思维导图

2 直播课Day03 数据结构—数据框、矩阵、列表

2.1 课堂代码

#重点：数据框
#1.数据框来源
# （1）用代码新建
# （2）由已有数据转换或处理得到
# （3）读取表格文件
# （4）R语言内置数据

#2.新建和读取数据框
df1 <- data.frame(gene   = paste0("gene",1:4),
                 change  = rep(c("up","down"),each = 2),
                 score   = c(5,3,-2,-4))
df1

##    gene change score
## 1 gene1     up     5
## 2 gene2     up     3
## 3 gene3   down    -2
## 4 gene4   down    -4

df2 <- read.csv("gene.csv")
df2

##    gene change score
## 1 gene1     up     5
## 2 gene2     up     3
## 3 gene3   down    -2
## 4 gene4   down    -4

#3.数据框属性
#
dim(df1)

## [1] 4 3

nrow(df1)

## [1] 4

ncol(df1)

## [1] 3

#
rownames(df1)

## [1] "1" "2" "3" "4"

colnames(df1)

## [1] "gene"   "change" "score"

#4.数据框取子集
df1$gene  #删掉score，按tab键试试

## [1] "gene1" "gene2" "gene3" "gene4"

mean(df1$score)

## [1] 0.5

## 按坐标
df1[2,2]

## [1] "up"

df1[2,]

##    gene change score
## 2 gene2     up     3

df1[,2]

## [1] "up"   "up"   "down" "down"

df1[c(1,3),1:2]

##    gene change
## 1 gene1     up
## 3 gene3   down

## 按名字
df1[,"gene"]

## [1] "gene1" "gene2" "gene3" "gene4"

df1[,c('gene','change')]

##    gene change
## 1 gene1     up
## 2 gene2     up
## 3 gene3   down
## 4 gene4   down

#5.数据框修改

#改一个格
df1[3,3] <- 5
df1

##    gene change score
## 1 gene1     up     5
## 2 gene2     up     3
## 3 gene3   down     5
## 4 gene4   down    -4

#改一整列
df1$score <- c(12,23,50,2)     
df1

##    gene change score
## 1 gene1     up    12
## 2 gene2     up    23
## 3 gene3   down    50
## 4 gene4   down     2

#？
df1$p.value <- c(0.01,0.02,0.07,0.05) 
df1

##    gene change score p.value
## 1 gene1     up    12    0.01
## 2 gene2     up    23    0.02
## 3 gene3   down    50    0.07
## 4 gene4   down     2    0.05

#改行名和列名
rownames(df1) <- c("r1","r2","r3","r4")
#只修改某一行/列的名
colnames(df1)[2] <- "CHANGE"

#6.两个数据框的连接
test1 <- data.frame(name = c('jimmy','nicker','Damon','Sophie'), 
                    blood_type = c("A","B","O","AB"))
test1

##     name blood_type
## 1  jimmy          A
## 2 nicker          B
## 3  Damon          O
## 4 Sophie         AB

test2 <- data.frame(name = c('Damon','jimmy','nicker','tony'),
                    group = c("group1","group1","group2","group2"),
                    vision = c(4.2,4.3,4.9,4.5))
test2

##     name  group vision
## 1  Damon group1    4.2
## 2  jimmy group1    4.3
## 3 nicker group2    4.9
## 4   tony group2    4.5

test3 <- data.frame(NAME = c('Damon','jimmy','nicker','tony'),
                    weight = c(140,145,110,138))
test3

##     NAME weight
## 1  Damon    140
## 2  jimmy    145
## 3 nicker    110
## 4   tony    138

merge(test1,test2,by="name")

##     name blood_type  group vision
## 1  Damon          O group1    4.2
## 2  jimmy          A group1    4.3
## 3 nicker          B group2    4.9

merge(test1,test3,by.x = "name",by.y = "NAME")

##     name blood_type weight
## 1  Damon          O    140
## 2  jimmy          A    145
## 3 nicker          B    110

#### 矩阵和列表
m <- matrix(1:9, nrow = 3)
colnames(m) <- c("a","b","c") #加列名
m

##      a b c
## [1,] 1 4 7
## [2,] 2 5 8
## [3,] 3 6 9

m[2,]

## a b c 
## 2 5 8

m[,1]

## [1] 1 2 3

m[2,3]

## c 
## 8

m[2:3,1:2]

##      a b
## [1,] 2 5
## [2,] 3 6

##      a b c
## [1,] 1 4 7
## [2,] 2 5 8
## [3,] 3 6 9

t(m)

##   [,1] [,2] [,3]
## a    1    2    3
## b    4    5    6
## c    7    8    9

as.data.frame(m)

##   a b c
## 1 1 4 7
## 2 2 5 8
## 3 3 6 9

#列表
x <- list(m1 = matrix(1:9, nrow = 3),
          m2 = matrix(2:9, nrow = 2))
x

## $m1
##      [,1] [,2] [,3]
## [1,]    1    4    7
## [2,]    2    5    8
## [3,]    3    6    9
## 
## $m2
##      [,1] [,2] [,3] [,4]
## [1,]    2    4    6    8
## [2,]    3    5    7    9

x[[1]]

##      [,1] [,2] [,3]
## [1,]    1    4    7
## [2,]    2    5    8
## [3,]    3    6    9

x$m1

##      [,1] [,2] [,3]
## [1,]    1    4    7
## [2,]    2    5    8
## [3,]    3    6    9

# 补充：元素的名字

scores = c(100,59,73,95,45)
names(scores) = c("jimmy","nicker","Damon","Sophie","tony")
scores

##  jimmy nicker  Damon Sophie   tony 
##    100     59     73     95     45

scores["jimmy"]

## jimmy 
##   100

scores[c("jimmy","nicker")]

##  jimmy nicker 
##    100     59

names(scores)[scores>60]

## [1] "jimmy"  "Damon"  "Sophie"

### 后置的难点
## 按条件（逻辑值）
df1 <- data.frame(gene   = paste0("gene",1:4),
                  change  = rep(c("up","down"),each = 2),
                  score   = c(5,3,-2,-4))
k = df1$score>0;k

## [1]  TRUE  TRUE FALSE FALSE

df1[k,]

##    gene change score
## 1 gene1     up     5
## 2 gene2     up     3

#筛选score > 0的基因
df1[k,1]

## [1] "gene1" "gene2"

df1$gene[k]

## [1] "gene1" "gene2"

df1$gene[df1$score>0]

## [1] "gene1" "gene2"

# 删除 
rm(x)
rm(df1,df2)
rm(list = ls())

2.2 知识点

数据框按照逻辑值筛选子集

筛选Score>0的基因

3 直播课Day04 R包、文件读写

3.1 R包

# R包镜像
# R包安装前先设置镜像，境外如果装包速度快就不需要设置

# 清华镜像
# http://mirrors.tuna.tsinghua.edu.cn/CRAN/
# http://mirrors.tuna.tsinghua.edu.cn/bioconductor/

# 中科大镜像
# http://mirrors.ustc.edu.cn/CRAN/
# http://mirrors.ustc.edu.cn/bioc/

options("repos"=c(CRAN="http://mirrors.tuna.tsinghua.edu.cn/CRAN/"))
options(BioC_mirror="http://mirrors.tuna.tsinghua.edu.cn/bioconductor/")
# 备用：西湖大学
options(BioC_mirror="https://mirrors.westlake.edu.cn/bioconductor")

R包安装