위키
포럼
도구
바뀐글
랜덤

DC Intermediate R - The apply family

# DC Intermediate R
DC Intermediate R - Conditionals and Control Flow
DC Intermediate R - Loops
DC Intermediate R - Functions
DC Intermediate R - The apply family
DC Intermediate R - Utilities

1 lapply[ | ]

2 Use lapply with a built-in R function[ | ]

# The vector pioneers has already been created for you
pioneers <- c("GAUSS:1777", "BAYES:1702", "PASCAL:1623", "PEARSON:1857")

# Split names from birth year
split_math <- strsplit(pioneers, split = ":")

# Convert to lowercase strings: split_low
split_low <- lapply(split_math, tolower)

# Take a look at the structure of split_low
str(split_low)
## List of 4
##  $ : chr [1:2] "gauss" "1777"
##  $ : chr [1:2] "bayes" "1702"
##  $ : chr [1:2] "pascal" "1623"
##  $ : chr [1:2] "pearson" "1857"

3 Use lapply with your own function[ | ]

# Code from previous exercise:
pioneers <- c("GAUSS:1777", "BAYES:1702", "PASCAL:1623", "PEARSON:1857")
split <- strsplit(pioneers, split = ":")
split_low <- lapply(split, tolower)

# Write function select_first()
select_first <- function(x) {
  x[1]
}

# Apply select_first() over split_low: names
names <- lapply(split_low, select_first)

# Write function select_second()
select_second <- function(x) {
  x[2]
}

# Apply select_second() over split_low: years
years <- lapply(split_low, select_second)

4 lapply and anonymous functions[ | ]

# Definition of split_low
pioneers <- c("GAUSS:1777", "BAYES:1702", "PASCAL:1623", "PEARSON:1857")
split <- strsplit(pioneers, split = ":")
split_low <- lapply(split, tolower)

# Transform: use anonymous function inside lapply
names <- lapply(split_low, function(x) x[1])

# Transform: use anonymous function inside lapply
years <- lapply(split_low, function(x) x[2])

5 Use lapply with additional arguments[ | ]

# Definition of split_low
pioneers <- c("GAUSS:1777", "BAYES:1702", "PASCAL:1623", "PEARSON:1857")
split <- strsplit(pioneers, split = ":")
split_low <- lapply(split, tolower)

# Generic select function
select_el <- function(x, index) {
  x[index]
}

# Use lapply() twice on split_low: names and years
names <- lapply(split_low, select_el, index = 1)
years <- lapply(split_low, select_el, index = 2)

6 Apply functions that return NULL[ | ]

lapply(split_low, function(x) {
  if (nchar(x[1]) > 5) {
    return(NULL)
  } else {
    return(x[2])
  }
})
## [[1]]
## [1] "1777"
## 
## [[2]]
## [1] "1702"
## 
## [[3]]
## NULL
## 
## [[4]]
## NULL

7 sapply[ | ]

8 How to use sapply[ | ]

# temp has already been defined in the workspace
temp <- list(c(3, 7, 9, 6, -1), c(6, 9, 12, 13, 5), c(4, 8, 3, -1, -3), c(1, 4, 7, 2, -2), 
             c(5, 7, 9, 4, 2), c(-3, 5, 8, 9, 4), c(3, 6, 9, 4, 1))
# Use lapply() to find each day's minimum temperature
lapply(temp, min)
## [[1]]
## [1] -1
## 
## [[2]]
## [1] 5
## 
## [[3]]
## [1] -3
## 
## [[4]]
## [1] -2
## 
## [[5]]
## [1] 2
## 
## [[6]]
## [1] -3
## 
## [[7]]
## [1] 1
# Use sapply() to find each day's minimum temperature
sapply(temp, min)
## [1] -1  5 -3 -2  2 -3  1
# Use lapply() to find each day's maximum temperature
lapply(temp, max)
## [[1]]
## [1] 9
## 
## [[2]]
## [1] 13
## 
## [[3]]
## [1] 8
## 
## [[4]]
## [1] 7
## 
## [[5]]
## [1] 9
## 
## [[6]]
## [1] 9
## 
## [[7]]
## [1] 9
# Use sapply() to find each day's maximum temperature
sapply(temp, max)
## [1]  9 13  8  7  9  9  9

9 sapply with your own function[ | ]

# temp is already defined in the workspace

# Finish function definition of extremes_avg
extremes_avg <- function(x) {
  ( min(x) + max(x)) / 2
}

# Apply extremes_avg() over temp using sapply()
sapply(temp, extremes_avg)
## [1] 4.0 9.0 2.5 2.5 5.5 3.0 5.0
# Apply extremes_avg() over temp using lapply()
lapply(temp, extremes_avg)
## [[1]]
## [1] 4
## 
## [[2]]
## [1] 9
## 
## [[3]]
## [1] 2.5
## 
## [[4]]
## [1] 2.5
## 
## [[5]]
## [1] 5.5
## 
## [[6]]
## [1] 3
## 
## [[7]]
## [1] 5

10 sapply with function returning vector[ | ]

# temp is already available in the workspace

# Create a function that returns min and max of a vector: extremes
extremes <- function(x) {
  c(min = min(x), max = max(x))
}

# Apply extremes() over temp with sapply()
sapply(temp, extremes)
##     [,1] [,2] [,3] [,4] [,5] [,6] [,7]
## min   -1    5   -3   -2    2   -3    1
## max    9   13    8    7    9    9    9
# Apply extremes() over temp with lapply()
lapply(temp, extremes)
## [[1]]
## min max 
##  -1   9 
## 
## [[2]]
## min max 
##   5  13 
## 
## [[3]]
## min max 
##  -3   8 
## 
## [[4]]
## min max 
##  -2   7 
## 
## [[5]]
## min max 
##   2   9 
## 
## [[6]]
## min max 
##  -3   9 
## 
## [[7]]
## min max 
##   1   9

11 sapply can't simplify, now what?[ | ]

# temp is already prepared for you in the workspace

# Definition of below_zero()
below_zero <- function(x) {
  return(x[x < 0])
}

# Apply below_zero over temp using sapply(): freezing_s
freezing_s <- sapply(temp, below_zero)

# Apply below_zero over temp using lapply(): freezing_l
freezing_l <- lapply(temp, below_zero)

# Are freezing_s and freezing_l identical?
identical(freezing_s, freezing_l)
## [1] TRUE

12 sapply with functions that return NULL[ | ]

# temp is already available in the workspace

# Definition of print_info()
print_info <- function(x) {
  cat("The average temperature is", mean(x), "\n")
}

# Apply print_info() over temp using sapply()
sapply(temp, print_info)
## The average temperature is 4.8 
## The average temperature is 9 
## The average temperature is 2.2 
## The average temperature is 2.4 
## The average temperature is 5.4 
## The average temperature is 4.6 
## The average temperature is 4.6
## [[1]]
## NULL
## 
## [[2]]
## NULL
## 
## [[3]]
## NULL
## 
## [[4]]
## NULL
## 
## [[5]]
## NULL
## 
## [[6]]
## NULL
## 
## [[7]]
## NULL
# Apply print_info() over temp using lapply()
lapply(temp, print_info)
## The average temperature is 4.8 
## The average temperature is 9 
## The average temperature is 2.2 
## The average temperature is 2.4 
## The average temperature is 5.4 
## The average temperature is 4.6 
## The average temperature is 4.6
## [[1]]
## NULL
## 
## [[2]]
## NULL
## 
## [[3]]
## NULL
## 
## [[4]]
## NULL
## 
## [[5]]
## NULL
## 
## [[6]]
## NULL
## 
## [[7]]
## NULL

13 Reverse engineering sapply[ | ]

sapply(list(runif (10), runif (10)), 
       function(x) c(min = min(x), mean = mean(x), max = max(x)))
##           [,1]       [,2]
## min  0.1902738 0.05612777
## mean 0.4998045 0.54904024
## max  0.8592395 0.84065426

14 vapply[ | ]

15 Use vapply[ | ]

# temp is already available in the workspace

# Definition of basics()
basics <- function(x) {
  c(min = min(x), mean = mean(x), max = max(x))
}

# Apply basics() over temp using vapply()
vapply(temp, basics, numeric(3))
##      [,1] [,2] [,3] [,4] [,5] [,6] [,7]
## min  -1.0    5 -3.0 -2.0  2.0 -3.0  1.0
## mean  4.8    9  2.2  2.4  5.4  4.6  4.6
## max   9.0   13  8.0  7.0  9.0  9.0  9.0

16 Use vapply (2)[ | ]

# temp is already available in the workspace

# Definition of the basics() function
basics <- function(x) {
  c(min = min(x), mean = mean(x), median = median(x), max = max(x))
}

# Fix the error:
vapply(temp, basics, numeric(4))
##        [,1] [,2] [,3] [,4] [,5] [,6] [,7]
## min    -1.0    5 -3.0 -2.0  2.0 -3.0  1.0
## mean    4.8    9  2.2  2.4  5.4  4.6  4.6
## median  6.0    9  3.0  2.0  5.0  5.0  4.0
## max     9.0   13  8.0  7.0  9.0  9.0  9.0

17 From sapply to vapply[ | ]

# temp is already defined in the workspace

# Convert to vapply() expression
vapply(temp, max, numeric(1))
## [1]  9 13  8  7  9  9  9
# Convert to vapply() expression
vapply(temp, function(x, y) { mean(x) > y }, y = 5, logical(1))
## [1] FALSE  TRUE FALSE FALSE  TRUE FALSE FALSE
원본 주소 "https://zetawiki.com/w/index.php?title=DC_Intermediate_R_-_The_apply_family&oldid=501668"
문서 댓글 ({{ doc_comments.length }})
{{ comment.name }} {{ comment.created | snstime }}