Arbeitsverzeichnisse und Dateipfade

Was ist das Arbeitsverzeichnis?

# getwd() returns the current working directory
current_dir <- getwd()
cat('Working directory:', current_dir)

# All relative file references start from this location:
# read.csv('data.csv')         <- looks in current_dir/data.csv
# source('R/helpers.R')        <- looks in current_dir/R/helpers.R

setwd() – Arbeitsverzeichnis ändern

# Set a new working directory
old_dir <- setwd('/tmp')
cat('Now in:', getwd(), '\n')

# Restore original directory
setwd(old_dir)
cat('Restored to:', getwd(), '\n')

# Common anti-pattern (breaks on other machines):
# setwd('/Users/alice/Desktop/my_project')  <- hardcoded!

# Better: use RStudio Projects which set wd automatically

file.path() – Portable Pfade erstellen

# Build a path from components
data_path <- file.path('data', 'raw', 'sales.csv')
cat('Path:', data_path)
# On Unix:    data/raw/sales.csv
# On Windows: data\raw\sales.csv

# Multiple levels
output_file <- file.path('output', '2024', 'Q1', 'report.pdf')
cat('Output:', output_file)

# Combine with getwd() for a full absolute path
full_path <- file.path(getwd(), 'data', 'sales.csv')
cat('Full path:', full_path)

normalizePath() – In einen absoluten Pfad auflösen

# Resolve relative paths to absolute
abs_path <- normalizePath('.')
cat('Absolute cwd:', abs_path, '\n')

# Resolve a relative path
data_abs <- normalizePath(file.path('..', 'data', 'sales.csv'),
                          mustWork = FALSE)
cat('Resolved:', data_abs, '\n')

# mustWork = FALSE: do not error if file does not exist yet
# mustWork = TRUE (default): error if path does not exist

# Useful for building reliable log messages or config files
cat('normalizePath demo complete')

dirname() und basename()

path <- '/Users/alice/projects/analysis/data/sales_2024.csv'

# Extract the directory
folder <- dirname(path)
cat('Directory:', folder, '\n')
# /Users/alice/projects/analysis/data

# Extract the file name
filename <- basename(path)
cat('File name:', filename, '\n')
# sales_2024.csv

# Remove file extension
name_only <- tools::file_path_sans_ext(filename)
cat('Name only:', name_only)

file.exists() – Vor dem Lesen prüfen

data_file <- file.path('data', 'sales.csv')

# Check existence before reading
if (file.exists(data_file)) {
  cat('File found, loading...\n')
  # df <- read.csv(data_file)
} else {
  cat('File not found:', data_file, '\n')
  stop('Cannot proceed without data file.')
}

# Check multiple files at once
files <- c('data/a.csv', 'data/b.csv', 'data/c.csv')
exists_vec <- file.exists(files)
cat('Files found:', sum(exists_vec), 'of', length(files))

Sys.getenv() – Pfade aus Umgebungsvariablen

# Get the home directory
home_dir <- Sys.getenv('HOME')
cat('Home:', home_dir, '\n')

# Get the temp directory
tmp_dir <- Sys.getenv('TMPDIR')
cat('Temp:', tmp_dir, '\n')

# Custom environment variable (set in .Renviron)
data_root <- Sys.getenv('DATA_ROOT', unset = '/default/data')
cat('Data root:', data_root, '\n')

# Use env vars to build portable paths
config_file <- file.path(home_dir, '.config', 'myapp', 'settings.json')
cat('Config path:', config_file)

path.expand() – Tilde-Erweiterung

# Expand tilde to full home path
short_path <- '~/.Rprofile'
full_path  <- path.expand(short_path)
cat('Expanded:', full_path)
# e.g. /Users/alice/.Rprofile

# Useful when passing paths to external tools or logging
config_dir <- path.expand('~/.config/R')
cat('Config dir:', config_dir)

# Can expand multiple paths at once
paths <- c('~/data', '~/output', '~/scripts')
expanded <- path.expand(paths)
cat(expanded, sep = '\n')

Dateien mit list.files() auflisten

# List all files in current directory
all_files <- list.files('.')
cat('Files found:', length(all_files), '\n')

# Filter by extension
csv_files <- list.files('data', pattern = '\\.csv$', full.names = TRUE)
cat('CSV files:',  length(csv_files), '\n')

# Recursive: include subdirectories
r_files <- list.files('R', pattern = '\\.R$',
                       full.names = TRUE, recursive = TRUE)
cat('R scripts:', length(r_files))

Pfade erstellen und entfernen

# Create a directory (will not error if it already exists)
dir.create('output/figures', recursive = TRUE, showWarnings = FALSE)
cat('Directory created\n')

# Create a temporary file
tmp_file <- tempfile(fileext = '.csv')
write.csv(data.frame(x = 1:3), tmp_file, row.names = FALSE)
cat('Temp file:', tmp_file, '\n')

# Remove the file when done
if (file.remove(tmp_file)) {
  cat('Temp file cleaned up')
}

Paket here – projektrelative Pfade

# install.packages('here')
# library(here)

# Always resolves from project root:
# here('data', 'raw', 'sales.csv')
# here('R', 'helpers.R')
# here('output', 'report.html')

# Without here: setwd() headaches when script is in a subfolder
# With here: same path works from any subfolder

# Demonstrate base-R equivalent approach:
project_root <- normalizePath(file.path(getwd(), '..'), mustWork = FALSE)
data_path    <- file.path(project_root, 'data', 'sales.csv')
cat('Data path:', data_path)

Schnelltest

Dateipfade – wichtigste Erkenntnisse

# Robust file loading pattern:
data_file <- file.path('data', 'raw', 'sales.csv')

if (!file.exists(data_file)) {
  stop(paste('Missing file:', normalizePath(data_file, mustWork = FALSE)))
}

# df <- read.csv(data_file)
cat('File path:', data_file, '\n')
cat('Full path:', normalizePath(data_file, mustWork = FALSE))