Day3 学习 简单作图 数据框 列表 矩阵

load("/Users/Desktop/25.2 生信/R_01/gands.Rdata")
# 1.用函数计算向量g的长度
length(g)
# 2.筛选出向量g中下标为偶数的基因名。==取子集
g[seq(2,100,2)]
g[c(F,T)] #用逻辑值挑选，会选出T所在的内容
# 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
g[g %in% s] #看哪些向量是存在的
table(g %in% s) #看有多少个
# 4.生成10个随机数: rnorm(n=10,mean=0,sd=18)，用向量取子集的方法，取出其中小于-2的值
z =  rnorm(n=10,mean=0,sd=18)
z[z<-2] #这里完成两件事1.z <- 2  2.只识别z中第二个值
z
z =  rnorm(n=10,mean=0,sd=18)
z[z<(-2)]

k1 = rnorm(36, mean=5, sd=10);k1
plot(k1)
k2 = rep(c('a','b','c','d'), each=9);k2
boxplot(k1~k2)

df1$gene
mean(df1$score)
## 按坐标 前行后列
df1[2,2]
df1[2,]
df1[,2]
df1[c(1,3),1:2]

## 按名字。''和""均可
df1[,"gene"]
df1[,c('gene','change')]

#改一个格
df1[3,3] <- 5
df1
#改一整列
df1$score <- c(12,23,50,2)     
df1
#？
df1$p.value <- c(0.01,0.02,0.07,0.05) 
df1

#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"

test1 <- data.frame(name = c('jimmy','nicker','Damon','Sophie'), 
                    blood_type = c("A","B","O","AB"))
test1
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))
colnames(test2)[1] <- 'name'
test2

test3 <- data.frame(NAME = c('Damon','jimmy','nicker','tony'),
                    weight = c(140,145,110,138))
test3
merge(test1,test2,by="name")
 # 如果第一列名字不一样，怎么合并？
merge(test1,test3,by.x = "name",by.y = "NAME") #不用专门修改名字，by.x/y函数解决
 # 优先选择改数据，在R里面修改数据

m <- matrix(1:9, nrow = 3)
colnames(m) <- c("a","b","c") #加列名
m #仅取一行，也会给你一个向量的名字
m[2,]
m[,1]
m[2,3]
m[2:3,1:2]
m
t(m) #转置
m1 <- as.data.frame(m) #转换为数据框
#列表 可以用$
x <- list(m1 = matrix(1:9, nrow = 3),
          m2 = matrix(2:9, ncol = 2))
x

x[[1]]
x$m1

# 补充：元素的名字

scores = c(100,59,73,95,45) #单纯的向量，赋予名字之后不修改向量的类型
names(scores) = c("jimmy","nicker","Damon","Sophie","tony")
scores
table(scores)
scores["jimmy"] #jimmy列的数值
scores[c("jimmy","nicker")]

names(scores)[scores>60] #scores>60的向量名

### 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
df1[k,]

#筛选score > 0的基因
df1[k,1]
df1$gene[k]
df1$gene[df1$score>0]

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