R for data science || 使用purrr实现
2019-08-06 本文已影响55人
周运来就是我
永远不要重复复制黏贴超过两次
减少重复，节约空间，主要有三个好处：
- 更容易看清代码的意图
- 更容易对变化做出反应
- 更容易减少程序bug
减少重复有两个办法： 函数和迭代。这一节主要讲使用purrr实现迭代。
迭代是重复反馈过程的活动，其目的通常是为了逼近所需目标或结果。每一次对过程的重复称为一次“迭代”，而每一次迭代得到的结果会作为下一次迭代的初始值。
for 循环
df <- tibble(
a = rnorm(10),
b = rnorm(10),
c = rnorm(10),
d = rnorm(10)
)
df
# A tibble: 10 x 4
a b c d
<dbl> <dbl> <dbl> <dbl>
1 0.498 -0.591 -0.0151 0.732
2 -0.744 0.617 0.349 0.634
3 1.24 -0.804 0.534 -0.587
4 -0.746 -1.03 0.764 -1.16
5 -0.626 -1.47 -0.545 0.284
6 0.151 0.606 -0.179 0.276
7 0.245 0.228 0.689 0.394
8 -1.27 0.341 0.398 1.01
9 1.35 -1.04 -0.143 0.286
10 1.30 -0.150 -1.60 -0.393
求中位数
output <- vector("double", ncol(df)) # 1. output
for (i in seq_along(df)) { # 2. sequence
output[[i]] <- median(df[[i]]) # 3. body
}
output
造容器，然后循环填充。
为什么不用apply？
apply(df, 2, median)
a b c d
0.1981378 -0.3706323 0.1669836 0.2846104
for 循环的变体
df <- tibble(
a = rnorm(10),
b = rnorm(10),
c = rnorm(10),
d = rnorm(10)
)
rescale01 <- function(x) {
rng <- range(x, na.rm = TRUE)
(x - rng[1]) / (rng[2] - rng[1])
}
df$a <- rescale01(df$a)
df$b <- rescale01(df$b)
df$c <- rescale01(df$c)
df$d <- rescale01(df$d)
for (i in seq_along(df)) {
df[[i]] <- rescale01(df[[i]])
}
循环模式
(i in seq_along(xs))for (x in xs)for (nm in names(xs))
未知的输出长度
将结果保存到一个列表中，循环结束再组合成一个向量。
means <- c(0, 1, 2)
out <- vector("list", length(means))
for (i in seq_along(means)) {
n <- sample(100, 1)
out[[i]] <- rnorm(n, means[[i]])
}
str(out)
#> List of 3
#> $ : num [1:83] 0.367 1.13 -0.941 0.218 1.415 ...
#> $ : num [1:21] -0.485 -0.425 2.937 1.688 1.324 ...
#> $ : num [1:40] 2.34 1.59 2.93 3.84 1.3 ...
str(unlist(out))
#> num [1:144] 0.367 1.13 -0.941 0.218 1.415 ...
for 循环与函数式编程
col_summary <- function(df, fun) {
out <- vector("double", length(df))
for (i in seq_along(df)) {
out[i] <- fun(df[[i]])
}
out
}
col_summary(df, median)
#> [1] 0.237 -0.218 0.254 -0.133
col_summary(df, mean)
#> [1] 0.2026 -0.2068 0.1275 -0.0917
将函数作为参数传入另一个函数的这种做法是一种十分强大的功能，它是使R成为函数式编程语言的因素之一。
映射函数
map函数是学习purrr最佳入门。先对向量进行循环，对每个元素进行一番处理，最后保存结果。这种模式太常见了，因此purrr提供了一个函数来替你完成任务。
- map() makes a list.
- map_lgl() makes a logical vector.
- map_int() makes an integer vector.
- map_dbl() makes a double vector.
- map_chr() makes a character vector.
map_dbl(df, mean)
#> a b c d
#> 0.2026 -0.2068 0.1275 -0.0917
map_dbl(df, median)
#> a b c d
#> 0.237 -0.218 0.254 -0.133
map_dbl(df, sd)
#> a b c d
#> 0.796 0.759 1.164 1.062
与管道结合
df %>% map_dbl(mean)
#> a b c d
#> 0.2026 -0.2068 0.1275 -0.0917
df %>% map_dbl(median)
#> a b c d
#> 0.237 -0.218 0.254 -0.133
df %>% map_dbl(sd)
#> a b c d
#> 0.796 0.759 1.164 1.062
快捷方式
对于参数.f你可以使用几种快捷方式来减少输入量。
> mtcars
mpg cyl disp hp drat wt qsec vs am gear carb
Mazda RX4 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4
Mazda RX4 Wag 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4
Datsun 710 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1
Hornet 4 Drive 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1
Hornet Sportabout 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2
Valiant 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1
Duster 360 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4
Merc 240D 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2
Merc 230 22.8 4 140.8 95 3.92 3.150 22.90 1 0 4 2
models <- mtcars %>%
split(.$cyl) %>%
map(~lm(mpg ~ wt, data = .))
models
$`4`
Call:
lm(formula = mpg ~ wt, data = .)
Coefficients:
(Intercept) wt
39.571 -5.647
$`6`
Call:
lm(formula = mpg ~ wt, data = .)
Coefficients:
(Intercept) wt
28.41 -2.78
·····
models <- mtcars %>%
split(.$cyl) %>%
map(~lm(mpg ~ wt, data = .))
多个模型的:
models %>%
map(summary) %>%
map_dbl(~.$r.squared)
#> 4 6 8
#> 0.509 0.465 0.423
models %>%
map(summary) %>%
map_dbl("r.squared")
#> 4 6 8
#> 0.509 0.465 0.423
R基础函数
x1 <- list(
c(0.27, 0.37, 0.57, 0.91, 0.20),
c(0.90, 0.94, 0.66, 0.63, 0.06),
c(0.21, 0.18, 0.69, 0.38, 0.77)
)
x2 <- list(
c(0.50, 0.72, 0.99, 0.38, 0.78),
c(0.93, 0.21, 0.65, 0.13, 0.27),
c(0.39, 0.01, 0.38, 0.87, 0.34)
)
threshold <- function(x, cutoff = 0.8) x[x > cutoff]
x1 %>% sapply(threshold) %>% str()
#> List of 3
#> $ : num 0.91
#> $ : num [1:2] 0.9 0.94
#> $ : num(0)
x2 %>% sapply(threshold) %>% str()
#> num [1:3] 0.99 0.93 0.87
对操作失败的处理
safe_log <- safely(log)
str(safe_log(10))
#> List of 2
#> $ result: num 2.3
#> $ error : NULL
str(safe_log("a"))
#> List of 2
#> $ result: NULL
#> $ error :List of 2
#> ..$ message: chr "non-numeric argument to mathematical function"
#> ..$ call : language .Primitive("log")(x, base)
#> ..- attr(*, "class")= chr [1:3] "simpleError" "error" "condition"
x <- list(1, 10, "a")
y <- x %>% map(safely(log))
str(y)
#> List of 3
#> $ :List of 2
#> ..$ result: num 0
#> ..$ error : NULL
#> $ :List of 2
#> ..$ result: num 2.3
#> ..$ error : NULL
#> $ :List of 2
#> ..$ result: NULL
#> ..$ error :List of 2
#> .. ..$ message: chr "non-numeric argument to mathematical function"
#> .. ..$ call : language .Primitive("log")(x, base)
#> .. ..- attr(*, "class")= chr [1:3] "simpleError" "error" "condition"
str(y)
#> List of 2
#> $ result:List of 3
#> ..$ : num 0
#> ..$ : num 2.3
#> ..$ : NULL
#> $ error :List of 3
#> ..$ : NULL
#> ..$ : NULL
#> ..$ :List of 2
#> .. ..$ message: chr "non-numeric argument to mathematical function"
#> .. ..$ call : language .Primitive("log")(x, base)
#> .. ..- attr(*, "class")= chr [1:3] "simpleError" "error" "condition"
多参数映射
mu <- list(5, 10, -3)
mu %>%
map(rnorm, n = 5) %>%
str()
#> List of 3
#> $ : num [1:5] 5.45 5.5 5.78 6.51 3.18
#> $ : num [1:5] 10.79 9.03 10.89 10.76 10.65
#> $ : num [1:5] -3.54 -3.08 -5.01 -3.51 -2.9
sigma <- list(1, 5, 10)
seq_along(mu) %>%
map(~rnorm(5, mu[[.]], sigma[[.]])) %>%
str()
#> List of 3
#> $ : num [1:5] 4.94 2.57 4.37 4.12 5.29
#> $ : num [1:5] 11.72 5.32 11.46 10.24 12.22
#> $ : num [1:5] 3.68 -6.12 22.24 -7.2 10.37
map2(mu, sigma, rnorm, n = 5) %>% str()
#> List of 3
#> $ : num [1:5] 4.78 5.59 4.93 4.3 4.47
#> $ : num [1:5] 10.85 10.57 6.02 8.82 15.93
#> $ : num [1:5] -1.12 7.39 -7.5 -10.09 -2.7
map2 <- function(x, y, f, ...) {
out <- vector("list", length(x))
for (i in seq_along(x)) {
out[[i]] <- f(x[[i]], y[[i]], ...)
}
out
}
n <- list(1, 3, 5)
args1 <- list(n, mu, sigma)
args1 %>%
pmap(rnorm) %>%
str()
#> List of 3
#> $ : num 4.55
#> $ : num [1:3] 13.4 18.8 13.2
#> $ : num [1:5] 0.685 10.801 -11.671 21.363 -2.562
args2 <- list(mean = mu, sd = sigma, n = n)
args2 %>%
pmap(rnorm) %>%
str()
params <- tribble(
~mean, ~sd, ~n,
5, 1, 1,
10, 5, 3,
-3, 10, 5
)
params %>%
pmap(rnorm)
#> [[1]]
#> [1] 4.68
#>
#> [[2]]
#> [1] 23.44 12.85 7.28
#>
#> [[3]]
#> [1] -5.34 -17.66 0.92 6.06 9.02
调用不同的函数
f <- c("runif", "rnorm", "rpois")
param <- list(
list(min = -1, max = 1),
list(sd = 5),
list(lambda = 10)
)
invoke_map(f, param, n = 5) %>% str()
#> List of 3
#> $ : num [1:5] 0.762 0.36 -0.714 0.531 0.254
#> $ : num [1:5] 3.07 -3.09 1.1 5.64 9.07
#> $ : int [1:5] 9 14 8 9 7
sim <- tribble(
~f, ~params,
"runif", list(min = -1, max = 1),
"rnorm", list(sd = 5),
"rpois", list(lambda = 10)
)
sim %>%
mutate(sim = invoke_map(f, params, n = 10))
游走函数
x <- list(1, "a", 3)
x %>%
walk(print)
#> [1] 1
#> [1] "a"
#> [1] 3
library(ggplot2)
plots <- mtcars %>%
split(.$cyl) %>%
map(~ggplot(., aes(mpg, wt)) + geom_point())
paths <- stringr::str_c(names(plots), ".pdf")
pwalk(list(paths, plots), ggsave, path = tempdir())
Saving 7 x 7 in image
Saving 7 x 7 in image
Saving 7 x 7 in image
> paths
[1] "4.pdf" "6.pdf" "8.pdf"
for 循环的其他模式
iris %>%
keep(is.factor) %>%
str()
#> 'data.frame': 150 obs. of 1 variable:
#> $ Species: Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...
iris %>%
discard(is.factor) %>%
str()
#> 'data.frame': 150 obs. of 4 variables:
#> $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
#> $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
#> $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
#> $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
x <- list(1:5, letters, list(10))
x %>%
some(is_character)
#> [1] TRUE
x %>%
every(is_vector)
#> [1] TRUE
x <- sample(10)
x
#> [1] 8 7 5 6 9 2 10 1 3 4
x %>%
detect(~ . > 5)
#> [1] 8
x %>%
detect_index(~ . > 5)
#> [1] 1
x %>%
head_while(~ . > 5)
#> [1] 8 7
x %>%
tail_while(~ . > 5)
#> integer(0)
归约与累计
dfs <- list(
age = tibble(name = "John", age = 30),
sex = tibble(name = c("John", "Mary"), sex = c("M", "F")),
trt = tibble(name = "Mary", treatment = "A")
)
dfs %>% reduce(full_join)
#> Joining, by = "name"
#> Joining, by = "name"
#> # A tibble: 2 x 4
#> name age sex treatment
#> <chr> <dbl> <chr> <chr>
#> 1 John 30 M <NA>
#> 2 Mary NA F A
vs <- list(
c(1, 3, 5, 6, 10),
c(1, 2, 3, 7, 8, 10),
c(1, 2, 3, 4, 8, 9, 10)
)
vs %>% reduce(intersect)
#> [1] 1 3 10
x <- sample(10)
x
#> [1] 6 9 8 5 2 4 7 1 10 3
x %>% accumulate(`+`)
#> [1] 6 15 23 28 30 34 41 42 52 55
purrr鲜为人知的技巧
To purrr or not to purrr
purrr-tutorial
「递归」和「迭代」有哪些区别？
