stringr 12-2

数据准备

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

x <- "The birch canoe slid on the smooth planks."
# x为一个字符串

1.检测字符串长度

length(x)   #一句字符串
str_length(x)    # 字符串长度    

2.字符串拆分与组合

str_split(x," ")      #用空格拆分字符串
[[1]]       #第一个元素
[1] "The"     "birch"   "canoe"   "slid"    "on"      "the"     "smooth" 
[8] "planks."
赋值
x2 = str_split(x," ")[[1]]     #如果含有多句字符串，拆分后每句字符串构成一个元素
str_c(x2,collapse = " ")   #外部用空格连接，复原原数据
[1] "The birch canoe slid on the smooth planks."

str_c(x2,1234,sep = "+")   #内部连接，数据还是被拆分的模式
 [1] "The+1234"     "birch+1234"   "canoe+1234"   "slid+1234"    "on+1234"     
[6] "the+1234"     "smooth+1234"  "planks.+1234"

3.提取字符串的一部分

str_sub(x,5,9)      #提取第5-9位的字符
[1] "birch"

4.大小写转换

str_to_upper(x2)
str_to_lower(x2)
str_to_title(x2) #首字母大写

5.字符串排序

str_sort(x2)   #首字母按24顺序排序

6.字符检测,返回逻辑值向量

str_detect(x2,"h")
str_starts(x2,"T")
str_ends(x2,"e")

与sum和mean连用，可以统计匹配的个数和比例

sum(str_detect(x2,"h"))    #共有几个字符串含有h
[1]4
mean(str_detect(x2,"h"))   #含有h的字符串占总字符串比例
[1]0.5

7.提取匹配到的字符串

str_subset(x2,"h")
x2[str_detect(x2,"h")]   #也能实现

8.字符计数

str_count(x," ")   #x里面有多少空格
str_count(x2,"o")

9.字符串替换

str_replace(x2,"o","A")   #替换出现的第一个o
str_replace_all(x2,"o","A")   #替换所有o

结合正则表达式更加强大

练习6-2

Bioinformatics is a new subject of genetic data collection,analysis and dissemination to the research community.

1.将上面这句话作为一个长字符串，赋值给tmp

2.拆分为一个由单词组成的向量，赋值给tmp2(注意标点符号)

tmp2 <- str_split(tmp," ")[[1]]
tmp2
[1] "Bioinformatics"      "is"                  "a"                   "new"                
 [5] "subject"             "of"                  "genetic"             "data"               
 [9] "collection,analysis" "and"                 "dissemination"       "to"                 
[13] "the"                 "research"            "community."      
#会出现“，”隔开的两单词连接在一起
> str_replace_all(tmp,","," ")
[1] "Bioinformatics is a new subject of genetic data collection analysis and dissemination to the research community." #用空格替代“，”，虚注意“.”指代句号的时候不能直接出现在代码里面，需“[.]”或者“\\.”这两种格式

tmp2 =tmp%>%
  str_replace_all(","," ")%>%
  str_remove("[.]")%>%
  str_split(" ")
tmp2=tmp2[[1]]
[[1]]
 [1] "Bioinformatics" "is"             "a"              "new"            "subject"       
 [6] "of"             "genetic"        "data"           "collection"     "analysis"      
[11] "and"            "dissemination"  "to"             "the"            "research"      
[16] "community"     

3.用函数返回这句话中有多少个单词。

> length(tmp2)
[1] 16

4.用函数返回这句话中每个单词由多少个字母组成。

str_length(tmp2)
[1] 14  2  1  3  7  2  7  4 10  8  3 13  2  3  8  9

5.统计tmp2有多少个单词中含有字母"e"