reduce(), accumulate() und walk()

Über map() hinaus — Weitere purrr-Verben

library(purrr)

# Example: combining a list of numbers into a single value
nums <- list(1, 2, 3, 4, 5)

# We want: 1 + 2 + 3 + 4 + 5 = 15
# map() can't do this — it returns 5 separate results
# reduce() folds the list into one value
result <- reduce(nums, `+`)
cat('Sum via reduce:', result)

reduce() — Eine Liste auf einen Wert reduzieren

library(purrr)

# reduce with max: find the overall maximum
values <- list(42, 17, 89, 55, 23)
result <- reduce(values, max)
cat('Maximum:', result, '\n')

# reduce with paste: concatenate strings
words <- list('The', 'quick', 'brown', 'fox')
reduce(words, paste)

reduce() mit .init

library(purrr)

# Running count of elements matching a condition
data <- list(5, 12, 3, 18, 7, 15, 2)

# Count values greater than 10, starting from 0
reduce(data, function(count, x) count + (x > 10), .init = 0L)

# Also useful for string building:
reduce(c('A','B','C'), paste, sep='-', .init='START')

reduce() mit Data Frames — Joins verketten

library(purrr)
library(dplyr)

base_df <- data.frame(id=1:3, name=c('Alice','Bob','Carol'))
scores <- data.frame(id=1:3, score=c(85,90,78))
grades <- data.frame(id=1:3, grade=c('B','A','C'))
city <- data.frame(id=1:3, city=c('NYC','LA','Chicago'))

dfs <- list(base_df, scores, grades, city)

reduce(dfs, left_join, by='id')

accumulate() — Zwischenergebnisse behalten

library(purrr)

# Running sum — same as cumsum() but via accumulate
values <- c(100, 120, 95, 140, 160)
accumulate(values, `+`)

# Running maximum
accumulate(c(50, 52, 48, 55, 53, 58), max)

accumulate() für schrittweise Ergebnisse

library(purrr)

# Compound interest step by step
principal <- 1000
rates <- c(0.05, 0.05, 0.05, 0.05, 0.05)  # 5% per year

accumulate(rates, function(balance, rate) {
  round(balance * (1 + rate), 2)
}, .init = principal)

walk() — Nebeneffekte ohne Rückgabewert

library(purrr)

# Print a summary for each dataset
datasets <- list(
  mtcars = mtcars[,1:3],
  iris = iris[,1:3]
)

walk(datasets, function(df) {
  cat('Rows:', nrow(df), '| Cols:', ncol(df),
      '| NAs:', sum(is.na(df)), '\n')
})

walk() in einer Pipeline

library(purrr)
library(dplyr)

results <- list(
  East = data.frame(rep=c('A','B'), sales=c(100,120)),
  West = data.frame(rep=c('C','D'), sales=c(200,190))
)

# Log each region's data, then continue processing
region_totals <- results %>%
  walk(~cat('Processing:', nrow(.x), 'rows\n')) %>%
  map_dbl(~sum(.x$sales))

print(region_totals)

walk2() — Nebeneffekte mit zwei Eingaben

library(purrr)

data_list <- list(
  east = data.frame(x=1:3, y=4:6),
  west = data.frame(x=7:9, y=10:12)
)

file_paths <- list(
  '/tmp/east_data.csv',
  '/tmp/west_data.csv'
)

# Write each data frame to its corresponding path
walk2(data_list, file_paths, function(df, path) {
  write.csv(df, path, row.names=FALSE)
  cat('Written:', path, '\n')
})

iwalk() — walk mit Index

library(purrr)

region_counts <- list(East=150, West=200, North=85, South=120)

# Print each region with its rank
iwalk(region_counts, function(count, name) {
  cat(name, ':', count, 'customers\n')
})

reduce_right() — Reduktion von rechts nach links

library(purrr)

words <- c('fox','brown','quick','The')

# Left-to-right: 'The quick brown fox'
reduce(rev(words), paste)

# Right-to-left: same effect but starting from right
reduce(words, function(a, b) paste(b, a))

Kurzer Test

Zusammenfassung: reduce, accumulate, walk

library(purrr)
library(dplyr)

# reduce() joins a list of data frames, accumulate() shows interim states
monthly_sums <- c(100, 120, 95, 140, 160, 130)

cat('reduce (total):      ', reduce(monthly_sums, `+`), '\n')
cat('accumulate (running):', accumulate(monthly_sums, `+`), '\n')

# walk() for side-effect logging
results <- list(a=42, b=17, c=89)
walk(results, ~cat('Value:', .x, '\n'))