1. List

l = list(vec_numeric = 5:8,
         mat         = matrix(1:8, 2, 4),
         vec_logical = c(TRUE, FALSE),
         summary     = summary(rnorm(1000)))
l

## $vec_numeric
## [1] 5 6 7 8
## 
## $mat
##      [,1] [,2] [,3] [,4]
## [1,]    1    3    5    7
## [2,]    2    4    6    8
## 
## $vec_logical
## [1]  TRUE FALSE
## 
## $summary
##     Min.  1st Qu.   Median     Mean  3rd Qu.     Max. 
## -3.00805 -0.69737 -0.03532 -0.01165  0.68843  3.81028

For loop:

df = list(
  a = rnorm(20, 3, 1),
  b = rnorm(20, 0, 5),
  c = rnorm(20, 10, .2),
  d = rnorm(20, -3, 1)
)

mean_and_sd = function(x) {
  
  if (!is.numeric(x)) {
    stop("Argument x should be numeric")
  } else if (length(x) == 1) {
    stop("Cannot be computed for length 1 vectors")
  }
  
  mean_x = mean(x)
  sd_x = sd(x)

  tibble(
    mean = mean_x, 
    sd = sd_x
  )
}

mean_and_sd(df[[1]])

## # A tibble: 1 x 2
##    mean    sd
##   <dbl> <dbl>
## 1  2.70  1.12

output = vector("list", length = 4)

for (i in 1:4) {
  output[[i]] = mean_and_sd(df[[i]])
}

Map function:

output = map(df, mean_and_sd)

output_median = map(df, median)

output_median_1 = map_dbl(df, median)

output_median_2 = map_dfr(df, median)

# more specific
output = map(df, ~mean_and_sd(.x))

An Example

library(rvest)

## Loading required package: xml2

## 
## Attaching package: 'rvest'

## The following object is masked from 'package:purrr':
## 
##     pluck

## The following object is masked from 'package:readr':
## 
##     guess_encoding

## Loading required package: xml2
## 
## Attaching package: 'rvest'
## The following object is masked from 'package:purrr':
## 
##     pluck
## The following object is masked from 'package:readr':
## 
##     guess_encoding

read_page_reviews = function(url) {
  
  h = read_html(url)
  
  title = h %>%
    html_nodes("#cm_cr-review_list .review-title") %>%
    html_text()
  
  stars = h %>%
    html_nodes("#cm_cr-review_list .review-rating") %>%
    html_text() %>%
    str_extract("\\d") %>%
    as.numeric()
  
  text = h %>%
    html_nodes(".review-data:nth-child(5)") %>%
    html_text()
  
  data_frame(title, stars, text)
}


url_base = "https://www.amazon.com/product-reviews/B00005JNBQ/ref=cm_cr_arp_d_viewopt_rvwer?ie=UTF8&reviewerType=avp_only_reviews&sortBy=recent&pageNumber="

vec_urls = str_c(url_base, 1:5)

dynamite_reviews = map_df(vec_urls, read_page_reviews)

2. List columns

weather = 
  rnoaa::meteo_pull_monitors(
    c("USW00094728", "USC00519397", "USS0023B17S"),
    var = c("PRCP", "TMIN", "TMAX"), 
    date_min = "2016-01-01",
    date_max = "2016-12-31") %>%
  mutate(
    name = recode(id, USW00094728 = "CentralPark_NY", 
                      USC00519397 = "Waikiki_HA",
                      USS0023B17S = "Waterhole_WA"),
    tmin = tmin / 10,
    tmax = tmax / 10) %>%
  select(name, id, everything())


weather_nest = 
  weather %>% 
  nest(data = date:tmin)

weather_nest

## # A tibble: 3 x 3
##   name           id                    data
##   <chr>          <chr>       <list<df[,4]>>
## 1 CentralPark_NY USW00094728      [366 × 4]
## 2 Waikiki_HA     USC00519397      [366 × 4]
## 3 Waterhole_WA   USS0023B17S      [366 × 4]

weather_nest %>% 
  pull(data) %>% 
  .[[1]]

## # A tibble: 366 x 4
##   date        prcp  tmax  tmin
##   <date>     <dbl> <dbl> <dbl>
## 1 2016-01-01     0   5.6   1.1
## 2 2016-01-02     0   4.4   0  
## 3 2016-01-03     0   7.2   1.7
## # … with 363 more rows

weather_nest$data[[1]]

## # A tibble: 366 x 4
##   date        prcp  tmax  tmin
##   <date>     <dbl> <dbl> <dbl>
## 1 2016-01-01     0   5.6   1.1
## 2 2016-01-02     0   4.4   0  
## 3 2016-01-03     0   7.2   1.7
## # … with 363 more rows

weather_nest %>% 
  unnest()

## Warning: `cols` is now required.
## Please use `cols = c(data)`

## # A tibble: 1,098 x 6
##   name           id          date        prcp  tmax  tmin
##   <chr>          <chr>       <date>     <dbl> <dbl> <dbl>
## 1 CentralPark_NY USW00094728 2016-01-01     0   5.6   1.1
## 2 CentralPark_NY USW00094728 2016-01-02     0   4.4   0  
## 3 CentralPark_NY USW00094728 2016-01-03     0   7.2   1.7
## # … with 1,095 more rows

Operations on list columns

central_park_df = 
  weather_nest$data[[1]]

lm(tmax ~ tmin, data = central_park_df)

## 
## Call:
## lm(formula = tmax ~ tmin, data = central_park_df)
## 
## Coefficients:
## (Intercept)         tmin  
##       7.779        1.045

lm(tmax ~ tmin, data = weather_nest$data[[1]])

## 
## Call:
## lm(formula = tmax ~ tmin, data = weather_nest$data[[1]])
## 
## Coefficients:
## (Intercept)         tmin  
##       7.779        1.045

# into map statement

weather_lm = function(df){
  lm(tmax ~ tmin, data = df)
}

output = map(weather_nest$data, weather_lm)

weather_nest %>% 
  mutate(
    lin_model = map(data, weather_lm)
  )

## # A tibble: 3 x 4
##   name           id                    data lin_model
##   <chr>          <chr>       <list<df[,4]>> <list>   
## 1 CentralPark_NY USW00094728      [366 × 4] <lm>     
## 2 Waikiki_HA     USC00519397      [366 × 4] <lm>     
## 3 Waterhole_WA   USS0023B17S      [366 × 4] <lm>

List Columns and Iteration

1. List

An Example

2. List columns

Operations on list columns