R Notebook

library(tidyverse)
library(lubridate)

302页第四题： Create functions that take a vector as input and return: a. The last value. Should you use [ or [[?

last_value <- function(x){
  if(is.atomic(x)){
    x[length(x)]
  }
  else{
    x[[length(x)]]
  }
}
last_value(c(1,2,3))

[1] 3

last_value(list(1,2,3))

[1] 3

2. The elements at even numbered positions.

even_position <- function(x){
  index=seq(2,length(x),2)
   if(is.atomic(x)){
    x[index]
  }
  else{
    unlist(x)[index]
  }
}
even_position(letters)

 [1] "b" "d" "f" "h" "j" "l" "n" "p" "r" "t" "v" "x" "z"

even_position(list(1,2))

[1] 2

3. Every element except the last value

except_last_value <- function(x){
  if(is.atomic(x)){
    x[-length(x)]
  }
  else{
    unlist(x)[-length(x)]
  }
}
except_last_value(c(1,2,3))

[1] 1 2

except_last_value(list(1,2,3))

[1] 1 2

4. Only even numbers (and no missing values)

even_noNA <- function(x){
  index=seq(2,length(x),2)
   if(is.atomic(x)){
    intersect(x[index],x[!is.na(x)])
  }
  else{
    intersect(unlist(x)[index],unlist(x)[!is.na(x)])
  }
}
even_noNA(list(1,2,3,NA,2,3))

[1] 2 3

5. Why is x[-which(x > 0)] not the same as x[x <= 0]? 6. What happens when you subset with a positive integer

x <- c(NaN,NA,-1,1)

x[x<=0]

[1] NA NA -1

x[-which(x>0)]

[1] NaN  NA  -1

6. What happens when you subset with a positive integer that’s bigger than the length of the vector? What happens when you subset with a name that doesn’t exist?

数据整理

table2

spread(table2,key=type,value = count)

table3

separate(table3,rate,into=c("cases","population"),sep="/")

table4a

gather(table4a,"1999","2000",key="year",value = "cases")

table4b

gather(table4b,"1999","2000",key="year",value = "population")

table5

unite(table5,year,century,year,sep="")

flights <- nycflights13::flights
weather <- nycflights13::weather
airports <- nycflights13::airports

如何将隐含缺失变为明确缺失？

stocks <- tibble(
  year=c(2015,2015,2015,2015,2016,2016,2016),
  qtr=c(1,2,3,4,2,3,4),
  return=c(12,2,3,NA,23,23,23)
)
stocks

complete(stocks,year,qtr)

虚假缺失

treatment <- tribble(   ~ person,           ~ treatment, ~response,   
                        "Derrick Whitmore", 1,           7,   
                        NA,                 2,           10,   
                        NA,                 3,           9,   
                        "Katherine Burke",  1,           4 )
treatment

fill(treatment,person)

exercise 156页 1.Why are gather() and spread() not perfectly symmetrical? Carefully consider the following example

stocks <- tibble(   year   = c(2015, 2015, 2016, 2016),   
                    half  = c(   1,    2,     1,    2),   
                    return = c(1.88, 0.59, 0.92, 0.17) ) 
stocks

stocks %>%
  spread(year, return) %>%
  gather("year", "return", `2015`:`2016`)

stocks %>%
  spread(year, return) 

stocks %>%
  spread(year, return) %>%
  gather("year", "return", `2015`:`2016`,convert = TRUE)

Both spread() and gather() have a convert argument. What does it do?

2.Why does spreading this tibble fail? How could you add a new column to fix the problem

people <- tribble(   ~name,             ~key,    ~value,
                     "Phillip Woods",   "age",       45,   
                     "Phillip Woods",   "height",   186,   
                     "Phillip Woods",   "age",       50,   
                     "Jessica Cordero", "age",       37,   
                     "Jessica Cordero", "height",   156 )
people

people$times=c(1,1,2,1,1)
spread(people,key,value)

4. Tidy this simple tibble. Do you need to spread or gather it? What are the variables?

 preg <- tribble(   ~pregnant, ~male, ~female,   "yes",     NA,    10,   "no",      20,    12 )
preg

preg <- gather(preg,male,female,key = sex,value = count)
preg

spread(preg,pregnant,count)

数据转换

1.everything函数的作用？

2.偏移函数

x <- 1:10

lead(x)

 [1]  2  3  4  5  6  7  8  9 10 NA

lag(x)

 [1] NA  1  2  3  4  5  6  7  8  9

3.滚动聚合

cumprod(x)

 [1]       1       2       6      24     120     720    5040   40320  362880 3628800

4.排名函数

y <- c(2,1,NA,-1,8,-1)

min_rank(y)

[1]  4  3 NA  1  5  1

dense_rank(y)

[1]  3  2 NA  1  4  1

row_number(y)

[1]  4  3 NA  1  5  2

percent_rank(y)

[1] 0.75 0.50   NA 0.00 1.00 0.00

cume_dist(y)

[1] 0.8 0.6  NA 0.4 1.0 0.4

5.汇总函数

x <- seq(1,11)
x

 [1]  1  2  3  4  5  6  7  8  9 10 11

四分位间距

IQR(x)

[1] 5

quantile(x,0.25)

25% 
3.5 

quantile(x,0.75)

75% 
8.5 

绝对中位差

mad(x)

[1] 4.4478

定位度量

nth(x,5)

[1] 5

last(x)

[1] 11

计数 样本个数

flighs <- nycflights13::flights
flighs

flights共有多少个样本？

flighs%>%
  summarise(n=n())

exercise 1. Find all flights that: a. Had an arrival delay of two or more hours

flighs%>%filter(arr_delay>=120)

2. Flew to Houston (IAH or HOU)

3. Were operated by United, American, or Delta

flights%>%
  filter(carrier %in% c("AA","UA","DL"))

4. Departed in summer (July, August, and September)

flights%>%
  filter(month %in% c(6,7,8))

5. Arrived more than two hours late, but didn’t leave late

flights%>%
  filter(dep_delay<=0 & arr_delay>=120)

6. Were delayed by at least an hour, but made up over 30 minutes in flight

flights%>%
  filter(arr_delay>=60 &(dep_delay-arr_delay)==30)

7. Departed between midnight and 6 a.m. (inclusive)

58页第一题 1. Currently dep_time and sched_dep_time are convenient to look at, but hard to compute with because they’re not really continu‐ous numbers. Convert them to a more convenient representa‐tion of number of minutes since midnight

73页第六题 6. For each plane, count the number of flights before the first delay of greater than 1 hour.

flights%>%
  group_by(tailnum)%>%
  filter(!(is.na(arr_delay)))%>%
  arrange(year,month,day,dep_time)%>%
  summarise(n=sum(cumall(arr_delay<=60)))%>%
  arrange(desc(n))

75页第七题 7. Find all destinations that are flown by at least two carriers. Use that information to rank the carriers

flights%>%
  group_by(dest)%>%
  filter(!is.na(carrier))%>%
  summarise(n=n_distinct(carrier))%>%
  arrange(desc(n))

数据整合

x <- tribble(   ~key, ~val_x,      
                1, "x1",      
                2, "x2",     
                3, "x3" ) 
y <- tribble(   ~key, ~val_y,      1, "y1",      2, "y2",      4, "y3" )
x

y

合并连接

内连接

x%>%
  inner_join(y,"key")

外连接

左连接

x%>%
  left_join(y,"key")

右连接

x%>%
  right_join(y,"key")

全连接

x%>%
  full_join(y,"key")

重复键

x <- tribble(   ~key, ~val_x,      1, "x1",      2, "x2",      2, "x3",      3, "x4" ) 
y <- tribble(   ~key, ~val_y,      1, "y1",      2, "y2",      2, "y3",     3, "y4" ) 
x

y

x%>%
  left_join(y,"key")

定义键列

by=null

flights%>%
  left_join(weather)

by=c(“a”=“b”)

flights%>%
  left_join(airports,by=c("dest"="faa"))

筛选连接

semi_join 作用 anti_join 作用

集合操作

df1 <- tribble(   ~x, ~y,    
                  1,  1,    
                  2,  1 ) 
df2 <- tribble(   ~x, ~y,    
                  1,  1,   
                  1,  2 )
df1

df2

intersect(df1,df2)

union(df1,df2)

setdiff(df1,df2)

exercise

187页第二题 2. Add the location of the origin and destination (i.e., the lat and lon) to flights

airports1 <- airports%>%
  select(faa,lat,lon)
flighs%>%
  left_join(airports1,by=c("origin"="faa"))%>%
  left_join(airports1,by=c("dest"="faa"),suffix=c(".origin",".dest"))

191页第2题 2. Filter flights to only show flights with planes that have flown at least 100 flights

flights_100 <- flights%>%
  count(tailnum)%>%
  filter(n>=100)%>%
  select(tailnum)
flights%>%
  semi_join(flights_100,"tailnum")

文本分析

字符串运算

str <- c("a","R for data science",NA)
str

[1] "a"                  "R for data science" NA                  

字符串长度

str_length(str)

[1]  1 18 NA

字符串拼接

str <- c("abc",NA)
str

[1] "abc" NA   

str_c("|-",str_replace_na(str),"-|",collapse = "-")

[1] "|-abc-|-|-NA-|"

字符串截取

x <- c("Apple","Bannana","Pear")
x

[1] "Apple"   "Bannana" "Pear"   

str_sub(x,-3,-1)

[1] "ple" "ana" "ear"

正则表达式

x <- "1888 is the longest year in Roman numerals: MDCCCLXXXVIII" 
x

[1] "1888 is the longest year in Roman numerals: MDCCCLXXXVIII"

str_view(x,"CC?")

str_view(x,"CC+")

str_view(x,"C[XL]+")

如何匹配美国电话号码 xxx-xxx- xxxx 或(xxx)xxx- xxxx 或xxx-xxxx?

x <- c("123-456-1234","(123)456-1234","123-1234","133423")
x

[1] "123-456-1234"  "(123)456-1234" "123-1234"      "133423"       

str_view(x,"((\\d{3}\\-)|\\(\\d{3}\\)|)\\d{3}\\-\\d{4}")

如何改为懒惰匹配？

x <- "1888 is the longest year in Roman numerals: MDCCCLXXXVIII" 
x

[1] "1888 is the longest year in Roman numerals: MDCCCLXXXVIII"

str_view(x,"C{2,3}?")

str_view(x,"C[XL]+?")

数据来自fruit

str_view(fruit,"(..)\\1",match = TRUE)

exercise 1.匹配words中以3个辅音字母开头的单词(str_view中使用match=TRUE)

str_view(words,"^[^aeiou]{3}",match = TRUE)

2.匹配words中以相同字母开头结尾的单词(str_view中使用match=TRUE)

str_view(words,"(^.$)|(^(.).*\\3$)",match = TRUE)

3. 如何匹配字符序列 “’ ？

x <- "asdas\"'\\"
writeLines(x)

asdas"'\

str_view(x,"\"'\\\\")

4.给定 stringr::words 中的常用单词语料库，创建正则表达式以找出满足下列条件的所有单词。 a. 以 y 开头的单词。

str_view(words,"^y",match = TRUE)

2. 以 x 结尾的单词。

str_view(words,"$x",match = TRUE)

3. 长度正好为 3 个字符的单词。 （不要使用str_length()函数，这是作弊！）

str_view(words,"^...$",match = TRUE)

4. 具有 7 个或更多字符的单词。

str_view(words,".{7,}",match = TRUE)

5.(1) 创建正则表达式来找出符合以下条件的所有单词。 b. 只包含辅音字母的单词（提示：考虑一下匹配“非”元音字母)。

str_view(words,"^[^aeoiu]*$",match = TRUE)

3. 以 ed 结尾，但不以 eed 结尾的单词。

str_view(words,"[^e](ed)$",match = TRUE)

4. 以 ing 或 ize 结尾的单词。

str_view(words,"(ing|ize)$",match = TRUE)

5. 有连续 3 个或更多元音字母的单词。

str_view(words,"[aeiou]{3,}",match=TRUE)

6. 有连续 2 个或更多元音—辅音配对的单词。

str_view(words,"([aeiou][^aeoiu]){2,}",match = TRUE)

g.包含一对重复字母的单词

str_view(words,"(.{1,}).*\\1",match = TRUE)

h.包含一个至少重复 3 次的字母的单词

str_view(words,"(.)(.*\\1){2,}",match = TRUE)

工具

如何计算words有多少个单词以元音字母结尾

mean(str_detect(words,"[aeoiu]$"))

[1] 0.2765306

如何提取出words中符合以元音字母结尾的单词

str_subset(words,"[aeiou]$")

  [1] "a"           "able"        "absolute"    "achieve"     "active"      "advertise"   "age"         "ago"        
  [9] "agree"       "also"        "america"     "appropriate" "area"        "argue"       "arrange"     "associate"  
 [17] "assume"      "available"   "aware"       "balance"     "base"        "be"          "because"     "become"     
 [25] "before"      "believe"     "bloke"       "blue"        "bottle"      "cake"        "care"        "case"       
 [33] "cause"       "centre"      "chance"      "change"      "charge"      "choice"      "choose"      "close"      
 [41] "clothe"      "coffee"      "colleague"   "college"     "come"        "committee"   "compare"     "complete"   
 [49] "compute"     "continue"    "converse"    "couple"      "course"      "create"      "date"        "debate"     
 [57] "decide"      "definite"    "degree"      "describe"    "die"         "difference"  "divide"      "do"         
 [65] "double"      "drive"       "due"         "educate"     "else"        "encourage"   "engine"      "europe"     
 [73] "evidence"    "example"     "excuse"      "exercise"    "expense"     "experience"  "extra"       "eye"        
 [81] "face"        "figure"      "file"        "finance"     "fine"        "fire"        "five"        "force"      
 [89] "fortune"     "france"      "free"        "future"      "game"        "give"        "go"          "goodbye"    
 [97] "hate"        "have"        "he"          "here"        "home"        "hope"        "horse"       "house"      
[105] "hullo"       "idea"        "imagine"     "improve"     "include"     "income"      "increase"    "inside"     
[113] "insure"      "into"        "introduce"   "involve"     "issue"       "judge"       "language"    "large"      
[121] "late"        "leave"       "lie"         "life"        "like"        "line"        "little"      "live"       
[129] "lose"        "love"        "machine"     "make"        "manage"      "maybe"       "measure"     "middle"     
[137] "mile"        "minute"      "more"        "move"        "name"        "nature"      "nice"        "nine"       
[145] "no"          "none"        "note"        "notice"      "office"      "once"        "one"         "operate"    
[153] "oppose"      "organize"    "otherwise"   "page"        "pence"       "people"      "picture"     "piece"      
[161] "place"       "please"      "police"      "positive"    "possible"    "practise"    "prepare"     "pressure"   
[169] "presume"     "price"       "private"     "probable"    "produce"     "programme"   "propose"     "provide"    
[177] "purpose"     "quite"       "radio"       "raise"       "range"       "rate"        "realise"     "receive"    
[185] "recognize"   "reduce"      "require"     "resource"    "responsible" "rise"        "role"        "rule"       
[193] "safe"        "sale"        "same"        "save"        "scheme"      "science"     "score"       "secure"     
[201] "see"         "sense"       "separate"    "serve"       "service"     "settle"      "share"       "she"        
[209] "shoe"        "side"        "simple"      "since"       "single"      "site"        "situate"     "size"       
[217] "smoke"       "so"          "some"        "space"       "square"      "stage"       "state"       "strike"     
[225] "structure"   "suppose"     "sure"        "surprise"    "table"       "take"        "tape"        "tea"        
[233] "telephone"   "terrible"    "the"         "there"       "therefore"   "thou"        "three"       "tie"        
[241] "time"        "to"          "too"         "trade"       "tree"        "trouble"     "true"        "twelve"     
[249] "two"         "type"        "unite"       "use"         "value"       "video"       "village"     "vote"       
[257] "wage"        "waste"       "we"          "wee"         "welcome"     "where"       "while"       "white"      
[265] "who"         "whole"       "wide"        "wife"        "worse"       "write"       "you"        

如何计算words中每个单词含有a字母的个数

str_count(words,"a")

  [1] 1 1 1 1 1 1 1 1 1 1 2 1 1 1 1 1 1 1 1 2 2 1 1 1 1 1 1 1 1 1 2 1 1 1 2 2 1 1 1 1 1 2 2 2 1 1 2 2 2 1 1 1 2 1 1 1 2 1
 [59] 1 1 1 3 2 2 1 1 1 1 1 2 1 1 1 1 1 0 1 1 1 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 1 1 0 0 0 0 0 0 0 0 1 0 1 0 1 0 0
[117] 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1 1 1 0 0 1 1 2 1 1 1 2 1 1 0 0 0 0 0 1 0 0 1 1 1 1 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0
[175] 0 1 1 0 0 0 0 0 0 0 1 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 1 1 1 1 1 1 1 1 0 0 0 0 0 1 0 0 0 1 0 0 0 0 0 0
[233] 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 1 1 1 1 1 0 1 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 1 1 0 0 0 0 0 0 1 1 0 0 0 0 0
[291] 0 0 1 0 1 0 1 1 1 1 1 1 1 1 1 1 0 0 0 0 0 0 0 0 0 1 1 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 1 0 1 0 1 0 0 0 0 0 0 0
[349] 0 0 1 1 1 1 1 0 0 0 1 0 0 0 0 0 1 1 1 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1 1 0 1 1 1 1 1 1 0 0 0 0 0 0 0 1 0 0 0 0 1 0 0 0
[407] 0 0 0 0 1 1 0 0 1 1 0 0 0 0 1 0 1 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 2 1 1 1 1 1 1 1 1
[465] 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 2 1 1 1 1 1 1 1 1 1 1 1 0 0 0 0 0 0 0 0 0
[523] 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 1 0 0 0 0 0 0 1 0 0 0 0 0 0 1
[581] 0 0 0 0 1 1 0 0 0 0 0 0 1 1 1 1 1 3 1 1 1 1 2 1 1 1 1 0 0 0 0 0 0 1 0 0 1 0 0 0 1 1 1 1 0 0 0 0 0 0 0 0 0 0 0 0 1 1
[639] 0 0 0 0 0 0 0 0 1 1 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 1 1 0 0 0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 0 0 0 0 0 0 0 0 0 1 0 1 0
[697] 0 0 0 1 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 1 1 1 2 1 1 0 0 0 0 1 1 0 1 0 0 0 0 0 0 0 0 2 0 0 0 0 0 0 0 1 1 0 0 0 0 0
[755] 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 1 0 0 0 0 0 1 0 0 1 0 0 0 0 0 0 0 0 1 1 1 0 0 0 0 1 1 1 1 1 2 1 1 1 1 0 0 0 0 0 1 1
[813] 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 0 0 0 0 0 0 0 0 1 1 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0
[871] 1 0 0 0 1 0 0 0 0 0 1 0 1 0 1 1 1 1 1 1 0 0 0 0 0 1 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 1 1 1 0 0 0 1 0 0 1 1 1 1 1 1 1
[929] 1 1 1 1 1 0 1 1 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 1 0 1 0 0 0

如何找出words中每个单词中u出现的位置

x <- "apple"
head(str_locate_all(words,"a"))

[[1]]
     start end
[1,]     1   1

[[2]]
     start end
[1,]     1   1

[[3]]
     start end
[1,]     1   1

[[4]]
     start end
[1,]     1   1

[[5]]
     start end
[1,]     1   1

[[6]]
     start end
[1,]     1   1

如何提取sentnce中的表示颜色的单词

colors <- c("red","yellow","orange","green","blue","purple")
colors_a <- str_c(" ",colors," ",collapse = "|")
colors_a

[1] " red | yellow | orange | green | blue | purple "

has_color <- str_subset(sentences,colors_a)
colors_b <- str_c(colors,collapse = "|")
colors_b

[1] "red|yellow|orange|green|blue|purple"

str_extract_all(has_color,colors_b,simplify = TRUE)

      [,1]     [,2] 
 [1,] "blue"   ""   
 [2,] "blue"   ""   
 [3,] "blue"   ""   
 [4,] "yellow" ""   
 [5,] "green"  ""   
 [6,] "red"    ""   
 [7,] "blue"   ""   
 [8,] "blue"   "red"
 [9,] "green"  ""   
[10,] "red"    ""   
[11,] "red"    ""   
[12,] "red"    ""   
[13,] "green"  ""   
[14,] "purple" ""   
[15,] "green"  ""   
[16,] "red"    ""   
[17,] "blue"   ""   
[18,] "red"    ""   
[19,] "green"  ""   
[20,] "green"  "red"
[21,] "yellow" ""   
[22,] "orange" "red"
[23,] "red"    ""   
[24,] "red"    ""   

如何提取出sentence中所有的冠词组合

noun <- "(a|an|the) ([^ ]+)"
has_noun <- str_subset(sentences,noun)
str_match(has_noun,noun)

       [,1]            [,2]  [,3]       
  [1,] "the smooth"    "the" "smooth"   
  [2,] "the sheet"     "the" "sheet"    
  [3,] "the depth"     "the" "depth"    
  [4,] "a chicken"     "a"   "chicken"  
  [5,] "the parked"    "the" "parked"   
  [6,] "the sun"       "the" "sun"      
  [7,] "the huge"      "the" "huge"     
  [8,] "the ball"      "the" "ball"     
  [9,] "the woman"     "the" "woman"    
 [10,] "a helps"       "a"   "helps"    
 [11,] "the man's"     "the" "man's"    
 [12,] "the sea."      "the" "sea."     
 [13,] "the booth"     "the" "booth"    
 [14,] "a hole"        "a"   "hole"     
 [15,] "the bent"      "the" "bent"     
 [16,] "the pants"     "the" "pants"    
 [17,] "an dive"       "an"  "dive"     
 [18,] "the view"      "the" "view"     
 [19,] "the tank."     "the" "tank."    
 [20,] "the tall"      "the" "tall"     
 [21,] "the same"      "the" "same"     
 [22,] "the load"      "the" "load"     
 [23,] "the winding"   "the" "winding"  
 [24,] "the size"      "the" "size"     
 [25,] "the grease"    "the" "grease"   
 [26,] "the coat"      "the" "coat"     
 [27,] "the bell"      "the" "bell"     
 [28,] "the state"     "the" "state"    
 [29,] "the sharp"     "the" "sharp"    
 [30,] "the third"     "the" "third"    
 [31,] "the hot"       "the" "hot"      
 [32,] "the cool"      "the" "cool"     
 [33,] "the square"    "the" "square"   
 [34,] "the seven"     "the" "seven"    
 [35,] "the fence"     "the" "fence"    
 [36,] "the drug"      "the" "drug"     
 [37,] "the coat."     "the" "coat."    
 [38,] "the mouse."    "the" "mouse."   
 [39,] "a flop"        "a"   "flop"     
 [40,] "a tool"        "a"   "tool"     
 [41,] "the soldiers"  "the" "soldiers" 
 [42,] "a rosebush"    "a"   "rosebush" 
 [43,] "the raging"    "the" "raging"   
 [44,] "the slide"     "the" "slide"    
 [45,] "a pencil"      "a"   "pencil"   
 [46,] "an half"       "an"  "half"     
 [47,] "the third"     "the" "third"    
 [48,] "the field."    "the" "field."   
 [49,] "a hit,"        "a"   "hit,"     
 [50,] "a grand"       "a"   "grand"    
 [51,] "the edge"      "the" "edge"     
 [52,] "the cue"       "the" "cue"      
 [53,] "the point"     "the" "point"    
 [54,] "the sand."     "the" "sand."    
 [55,] "the finished"  "the" "finished" 
 [56,] "a fight."      "a"   "fight."   
 [57,] "an out"        "an"  "out"      
 [58,] "a nice"        "a"   "nice"     
 [59,] "the car"       "the" "car"      
 [60,] "a thin"        "a"   "thin"     
 [61,] "the big"       "the" "big"      
 [62,] "the cat"       "the" "cat"      
 [63,] "an two"        "an"  "two"      
 [64,] "the fence"     "the" "fence"    
 [65,] "the pie"       "the" "pie"      
 [66,] "the barn"      "the" "barn"     
 [67,] "a limb."       "a"   "limb."    
 [68,] "the street."   "the" "street."  
 [69,] "the blue"      "the" "blue"     
 [70,] "an eggs."      "an"  "eggs."    
 [71,] "the clear"     "the" "clear"    
 [72,] "the boat,"     "the" "boat,"    
 [73,] "the other."    "the" "other."   
 [74,] "an to"         "an"  "to"       
 [75,] "the crate"     "the" "crate"    
 [76,] "the sum"       "the" "sum"      
 [77,] "the high"      "the" "high"     
 [78,] "the vat"       "the" "vat"      
 [79,] "the pine"      "the" "pine"     
 [80,] "the fall."     "the" "fall."    
 [81,] "the wind"      "the" "wind"     
 [82,] "the log"       "the" "log"      
 [83,] "the logs"      "the" "logs"     
 [84,] "the carpet"    "the" "carpet"   
 [85,] "a weed"        "a"   "weed"     
 [86,] "the simplest"  "the" "simplest" 
 [87,] "the less"      "the" "less"     
 [88,] "an the"        "an"  "the"      
 [89,] "an cleanse"    "an"  "cleanse"  
 [90,] "a rusty"       "a"   "rusty"    
 [91,] "the farther"   "the" "farther"  
 [92,] "the heat"      "the" "heat"     
 [93,] "a swim."       "a"   "swim."    
 [94,] "the same"      "the" "same"     
 [95,] "the bright"    "the" "bright"   
 [96,] "an ten."       "an"  "ten."     
 [97,] "the eyes"      "the" "eyes"     
 [98,] "the wise"      "the" "wise"     
 [99,] "a fond"        "a"   "fond"     
[100,] "a bad"         "a"   "bad"      
[101,] "a strong"      "a"   "strong"   
[102,] "the rusty"     "the" "rusty"    
[103,] "the results"   "the" "results"  
[104,] "the right"     "the" "right"    
[105,] "a high"        "a"   "high"     
[106,] "a graceful"    "a"   "graceful" 
[107,] "the blotter"   "the" "blotter"  
[108,] "the front"     "the" "front"    
[109,] "a hole"        "a"   "hole"     
[110,] "the tin"       "the" "tin"      
[111,] "an can"        "an"  "can"      
[112,] "a new"         "a"   "new"      
[113,] "the couch."    "the" "couch."   
[114,] "the crew"      "the" "crew"     
[115,] "the coin"      "the" "coin"     
[116,] "the torn"      "the" "torn"     
[117,] "a cushion"     "a"   "cushion"  
[118,] "the back"      "the" "back"     
[119,] "the air"       "the" "air"      
[120,] "the two"       "the" "two"      
[121,] "the prize."    "the" "prize."   
[122,] "a dull"        "a"   "dull"     
[123,] "the skill"     "the" "skill"    
[124,] "the hot"       "the" "hot"      
[125,] "the broken"    "the" "broken"   
[126,] "the small"     "the" "small"    
[127,] "a sound"       "a"   "sound"    
[128,] "the stone"     "the" "stone"    
[129,] "the best"      "the" "best"     
[130,] "the ship"      "the" "ship"     
[131,] "the store's"   "the" "store's"  
[132,] "the players."  "the" "players." 
[133,] "the column"    "the" "column"   
[134,] "a good"        "a"   "good"     
[135,] "the flood"     "the" "flood"    
[136,] "a head"        "a"   "head"     
[137,] "a fig"         "a"   "fig"      
[138,] "an be"         "an"  "be"       
[139,] "the noise"     "the" "noise"    
[140,] "a buyer"       "a"   "buyer"    
[141,] "the ice"       "the" "ice"      
[142,] "the next"      "the" "next"     
[143,] "the third"     "the" "third"    
[144,] "the oat"       "the" "oat"      
[145,] "the attic."    "the" "attic."   
[146,] "the soap"      "the" "soap"     
[147,] "a tall"        "a"   "tall"     
[148,] "the rink"      "the" "rink"     
[149,] "the dance"     "the" "dance"    
[150,] "the new"       "the" "new"      
[151,] "the inn."      "the" "inn."     
[152,] "the worst"     "the" "worst"    
[153,] "the second"    "the" "second"   
[154,] "the wall."     "the" "wall."    
[155,] "a wooden"      "a"   "wooden"   
[156,] "an brass."     "an"  "brass."   
[157,] "the bank"      "the" "bank"     
[158,] "a young"       "a"   "young"    
[159,] "a steady"      "a"   "steady"   
[160,] "the axe"       "the" "axe"      
[161,] "a loud"        "a"   "loud"     
[162,] "the rubbish"   "the" "rubbish"  
[163,] "the gold"      "the" "gold"     
[164,] "the court"     "the" "court"    
[165,] "the raft"      "the" "raft"     
[166,] "an X"          "an"  "X"        
[167,] "the rope"      "the" "rope"     
[168,] "the best"      "the" "best"     
[169,] "the islands"   "the" "islands"  
[170,] "an as"         "an"  "as"       
[171,] "the world"     "the" "world"    
[172,] "the egg."      "the" "egg."     
[173,] "a bright"      "a"   "bright"   
[174,] "the fence"     "the" "fence"    
[175,] "the curtain"   "the" "curtain"  
[176,] "the middle"    "the" "middle"   
[177,] "the same"      "the" "same"     
[178,] "a compass."    "a"   "compass." 
[179,] "an others."    "an"  "others."  
[180,] "the front"     "the" "front"    
[181,] "the pail"      "the" "pail"     
[182,] "the big"       "the" "big"      
[183,] "the empty"     "the" "empty"    
[184,] "a served"      "a"   "served"   
[185,] "the hot-cross" "the" "hot-cross"
[186,] "the field"     "the" "field"    
[187,] "the twin"      "the" "twin"     
[188,] "the cord"      "the" "cord"     
[189,] "the smuggled"  "the" "smuggled" 
[190,] "the corner"    "the" "corner"   
[191,] "the bond"      "the" "bond"     
[192,] "the ruins."    "the" "ruins."   
[193,] "a mouldy"      "a"   "mouldy"   
[194,] "a pine"        "a"   "pine"     
[195,] "the cloth"     "the" "cloth"    
[196,] "the swan"      "the" "swan"     
[197,] "the screen."   "the" "screen."  
[198,] "the end"       "the" "end"      
[199,] "the clay"      "the" "clay"     
[200,] "a smooth"      "a"   "smooth"   
[201,] "the crackers." "the" "crackers."
[202,] "the high"      "the" "high"     
[203,] "a pierced"     "a"   "pierced"  
[204,] "an was"        "an"  "was"      
[205,] "the log"       "the" "log"      
[206,] "the stalk"     "the" "stalk"    
[207,] "an but"        "an"  "but"      
[208,] "a brew"        "a"   "brew"     
[209,] "the box"       "the" "box"      
[210,] "the window."   "the" "window."  
[211,] "the workmen's" "the" "workmen's"
[212,] "the breeze."   "the" "breeze."  
[213,] "a swan,"       "a"   "swan,"    
[214,] "the tire"      "the" "tire"     
[215,] "the old"       "the" "old"      
[216,] "the last"      "the" "last"     
[217,] "a person"      "a"   "person"   
[218,] "the sleeping"  "the" "sleeping" 
[219,] "the fire"      "the" "fire"     
[220,] "the round"     "the" "round"    
[221,] "an and"        "an"  "and"      
[222,] "the ink"       "the" "ink"      
[223,] "a big"         "a"   "big"      
[224,] "the records"   "the" "records"  
[225,] "the snow"      "the" "snow"     
[226,] "the sun's"     "the" "sun's"    
[227,] "the wall."     "the" "wall."    
[228,] "the and"       "the" "and"      
[229,] "a is"          "a"   "is"       
[230,] "the dog"       "the" "dog"      
[231,] "a book."       "a"   "book."    
[232,] "the fine"      "the" "fine"     
[233,] "an half"       "an"  "half"     
[234,] "the central"   "the" "central"  
[235,] "the rough"     "the" "rough"    
[236,] "the new"       "the" "new"      
[237,] "the lathe"     "the" "lathe"    
[238,] "the pole"      "the" "pole"     
[239,] "a dish"        "a"   "dish"     
[240,] "an gathered"   "an"  "gathered" 
[241,] "the day"       "the" "day"      
[242,] "the strip"     "the" "strip"    
[243,] "the stew"      "the" "stew"     
[244,] "an went"       "an"  "went"     
[245,] "the road."     "the" "road."    
[246,] "the clear"     "the" "clear"    
[247,] "a king's"      "a"   "king's"   
[248,] "a good"        "a"   "good"     
[249,] "the white"     "the" "white"    
[250,] "the stream."   "the" "stream."  
[251,] "the lead"      "the" "lead"     
[252,] "the lock."     "the" "lock."    
[253,] "the council"   "the" "council"  
[254,] "the red"       "the" "red"      
[255,] "the ledge."    "the" "ledge."   
[256,] "the sheep"     "the" "sheep"    
[257,] "a lot"         "a"   "lot"      
[258,] "the spot"      "the" "spot"     
[259,] "a fair"        "a"   "fair"     
[260,] "an wash"       "an"  "wash"     
[261,] "the game"      "the" "game"     
[262,] "a long"        "a"   "long"     
[263,] "the strong"    "the" "strong"   
[264,] "the rain"      "the" "rain"     
[265,] "the hot"       "the" "hot"      
[266,] "the story"     "the" "story"    
[267,] "the eastern"   "the" "eastern"  
[268,] "the line"      "the" "line"     
[269,] "the cuts"      "the" "cuts"     
[270,] "a dense"       "a"   "dense"    
[271,] "the knee"      "the" "knee"     
[272,] "the shaky"     "the" "shaky"    
[273,] "the odor."     "the" "odor."    
[274,] "an some"       "an"  "some"     
[275,] "the sail"      "the" "sail"     
[276,] "the dart"      "the" "dart"     
[277,] "a new"         "a"   "new"      
[278,] "the base."     "the" "base."    
[279,] "a dog."        "a"   "dog."     
[280,] "a dime,"       "a"   "dime,"    
[281,] "an that"       "an"  "that"     
[282,] "the shore."    "the" "shore."   
[283,] "the wall"      "the" "wall"     
[284,] "the oath"      "the" "oath"     
[285,] "the sill"      "the" "sill"     
[286,] "the steel"     "the" "steel"    
[287,] "a lag"         "a"   "lag"      
[288,] "the spring"    "the" "spring"   
[289,] "the chart"     "the" "chart"    
[290,] "the crowd"     "the" "crowd"    
[291,] "a and"         "a"   "and"      
[292,] "the wide"      "the" "wide"     
[293,] "the dust"      "the" "dust"     
[294,] "the porch"     "the" "porch"    
[295,] "the finish."   "the" "finish."  
[296,] "the deep"      "the" "deep"     
[297,] "the dice"      "the" "dice"     
[298,] "the frail"     "the" "frail"    
[299,] "the valve"     "the" "valve"    
[300,] "the shoe"      "the" "shoe"     
[301,] "the sausage"   "the" "sausage"  
[302,] "the rose"      "the" "rose"     
[303,] "the colt."     "the" "colt."    
[304,] "a hot"         "a"   "hot"      
[305,] "an wore"       "an"  "wore"     
[306,] "the bike"      "the" "bike"     
[307,] "the ashes"     "the" "ashes"    
[308,] "the used"      "the" "used"     
[309,] "an neck"       "an"  "neck"     
[310,] "the tall"      "the" "tall"     
[311,] "a thin"        "a"   "thin"     
[312,] "the lantern"   "the" "lantern"  
[313,] "the soft"      "the" "soft"     
[314,] "the tenth"     "the" "tenth"    
[315,] "an to"         "an"  "to"       
[316,] "a good"        "a"   "good"     
[317,] "a vest"        "a"   "vest"     
[318,] "the figs,"     "the" "figs,"    
[319,] "the door"      "the" "door"     
[320,] "the fire"      "the" "fire"     
[321,] "the print."    "the" "print."   
[322,] "the limits"    "the" "limits"   
[323,] "the high"      "the" "high"     
[324,] "an end"        "an"  "end"      
[325,] "the old"       "the" "old"      
[326,] "the dark"      "the" "dark"     
[327,] "a shaggy"      "a"   "shaggy"   
[328,] "the corner"    "the" "corner"   
[329,] "the hatch"     "the" "hatch"    
[330,] "the walnut"    "the" "walnut"   
[331,] "the form"      "the" "form"     
[332,] "the stuff"     "the" "stuff"    
[333,] "the most"      "the" "most"     
 [ reached getOption("max.print") -- omitted 162 rows ]

如果sentences是tibble，如何操作？

tibble(sentence=sentences)%>%
  extract(sentence,c("article","nuon"),"(a|an|the) ([^ ]+)",remove = FALSE)

如何使用boundary切分单词

x <- "This is a sentence. This is another sentence."
x

[1] "This is a sentence. This is another sentence."

str_split(x,boundary("word"))

[[1]]
[1] "This"     "is"       "a"        "sentence" "This"     "is"       "another"  "sentence"

str_split(x," ",simplify = TRUE)

     [,1]   [,2] [,3] [,4]        [,5]   [,6] [,7]      [,8]       
[1,] "This" "is" "a"  "sentence." "This" "is" "another" "sentence."

另外参数n可以设定切分到片段个数

时间和日期数据

创建日期时间型数据

通过字符串创建

x <- 20190112
x

[1] 20190112

ymd(x)

[1] "2019-01-12"

x <- "January 31 2017"
x

[1] "January 31 2017"

mdy(x)

[1] "2017-01-31"

x <- "2017-01-31 20:11:59"
x

[1] "2017-01-31 20:11:59"

ymd_hms(x)

[1] "2017-01-31 20:11:59 UTC"

通过各个成分创建

flights%>%
  transmute(date=make_datetime(year,month,day,minute))

通过其他类型数据创建

as_datetime(today())

[1] "2019-01-15 UTC"

as_date(now())

[1] "2019-01-15"

Unix时间戳

as_datetime(60*60*24)

[1] "1970-01-02 UTC"

as_date(365*10+1)

[1] "1979-12-31"

d4 <- c("August 19 (2015)", "July 1 (2015)")
d4

[1] "August 19 (2015)" "July 1 (2015)"   

mdy(d4)

[1] "2015-08-19" "2015-07-01"

In strsplit(code, "\n", fixed = TRUE) :
  input string 1 is invalid in this locale

d5

[1] "12/30/14"

mdy(d5)

[1] "2014-12-30"

日期时间成分

datetime <- ymd_hms("2016-07-08 12:34:56")
datetime

[1] "2016-07-08 12:34:56 UTC"

某月的第几天

mday(datetime)

[1] 8

某年的第几天

yday(datetime)

[1] 190

一周的第几天

wday(datetime)

[1] 6

舍入

head(floor_date(ymd_hms(flights$dep_time),"week"))

[1] NA NA NA NA NA NA

全部变成一周的第一天的日期

时间间隔

时期

h_age <- today()-ymd(19790112)
h_age

Time difference of 14613 days

as.duration(h_age)

[1] "1262563200s (~40.01 years)"

把年转换成秒

dyears(2)

[1] "63072000s (~2 years)"

跨度

夏令时到冬令时可用

days(2)

[1] "2d 0H 0M 0S"

today()+days(2)

[1] "2019-01-17"

时区

如何查询系统时区

Sys.timezone()

[1] "Asia/Taipei"

修改时区，不修改时间

with_tz(today())

[1] "2019-01-15"

修改时区，并修改时间

force_tz(today())

[1] "2019-01-15"

分层柱状团

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

map2

mu <- list(5,10,-3)
sigma <- list(1,5,10)
map2(mu,sigma,rnorm,n=10)

[[1]]
 [1] 4.947986 5.467590 5.913339 4.274208 4.581593 4.788442 5.614764 4.234672 3.534121 6.198214

[[2]]
 [1]  5.725682  8.920260 14.269808  7.049484 13.500637 16.859337 10.962061  6.890432 10.254318 16.126379

[[3]]
 [1]  -8.693185 -19.604794 -12.804712   6.664651  -4.711103  -3.668457  -7.773991   3.056113  12.705577  20.735267

map

三种不同索引方式 公式

models <- mtcars%>%
  split(.$cyl)%>%
  map(~lm(mpg~wt,data=.))
models

$`4`

Call:
lm(formula = mpg ~ wt, data = .)

Coefficients:
(Intercept)           wt  
     39.571       -5.647  


$`6`

Call:
lm(formula = mpg ~ wt, data = .)

Coefficients:
(Intercept)           wt  
      28.41        -2.78  


$`8`

Call:
lm(formula = mpg ~ wt, data = .)

Coefficients:
(Intercept)           wt  
     23.868       -2.192  

字符向量

models%>%
  map(summary)%>%
  map("r.squared")

$`4`
[1] 0.5086326

$`6`
[1] 0.4645102

$`8`
[1] 0.4229655

数字向量

x <- list(list(1,2,3),list(4,5,6),list(7,8,9))

x%>%
  map(2)

[[1]]
[1] 2

[[2]]
[1] 5

[[3]]
[1] 8

如何生成方差不同均值相同的正态分布随机数

mu <- list(5,10,3)
mu%>%
  map(rnorm,n=10,mean=1)

[[1]]
 [1]  6.822252 -4.427688  4.998521  3.544448  2.806287 -7.899798  5.790980  0.258452  5.080364  1.120691

[[2]]
 [1]   3.03120660   0.09106127 -12.44283242 -13.53326395  11.12894609 -13.93980763  -6.59596567  11.50021244  21.48651232
[10]   0.31815504

[[3]]
 [1]  1.5483942 -2.4945495  0.8785752 -2.0193341  3.5006245  1.8130725  5.0713825  2.0278612  3.7317933  7.2131028

pmap

n <- list(10,20,4)
pmap(list(n,mu,sigma),rnorm)

[[1]]
 [1] 4.509272 6.182599 5.696206 5.285198 6.005597 3.434809 4.957345 6.709828 4.398375 5.999906

[[2]]
 [1] 13.098816 20.457712 10.746364 12.954228 16.622434  2.002508  3.818095 12.747614  8.466130 19.015718 12.322974
[12]  2.501040  7.620018 13.092890  6.295540 18.705108  7.535133 14.868748  8.395464  2.067585

[[3]]
[1]  -9.1810444 -23.4396420  -0.7616694  -4.3489155

invoke_map

f <- c("rnorm","runif","rpois")
params <- list(list(mean=5,sd=5),list(min=1,max=10),list(lambda=10))
invoke_map(f,params,n=10)

[[1]]
 [1]  9.545631  8.507999  6.656743  1.534669 14.356332  6.906555  1.337314  6.341718  3.252099 12.137012

[[2]]
 [1] 1.495842 1.921696 9.472208 7.557108 6.842509 9.649270 8.729320 7.507460 7.324795 8.749119

[[3]]
 [1] 12  6 11  8 12  8  8 15 11  9

列表列

x <- list(a=1:5,b=3:4,c=5:6)
x

$`a`
[1] 1 2 3 4 5

$b
[1] 3 4

$c
[1] 5 6

df <-enframe(x)
df

df%>%
  mutate(smry=map2_chr(name,value,~str_c(.x,":",.y[1])))

df%>%
  group_by(name)%>%
  mutate(smry=map2_chr(name,unlist(value)[1],str_c,sep=":"))

library(modelr)
library(tidyverse)
library(gapminder)
gapminder

by_country <- gapminder%>%
  nest(-country,-continent)
by_country

如何取出data列的第一个元素

by_country$data[[1]]

拟合每个国家模型

country_model <- function(df){
  lm(lifeExp~year,data=df)
}
by_country <- by_country%>%
  mutate(model=map(data,country_model))
by_country

添加残差

by_country <- by_country%>%
  mutate(resid=map2(data,model,add_residuals))
by_country

unnest 画出残差图

resid <- by_country%>%
  unnest(resid)
resid

使用broom获取模型摘要

library(broom)
by_country%>%
  mutate(glance=map(model,glance))%>%
  unnest(glance,.drop = TRUE)