R File & System Operations - Complete Guide

# Check if file exists
file.exists("data.csv")           # TRUE or FALSE
file.exists("nonexistent.txt")    # FALSE

# Check multiple files
files <- c("data1.csv", "data2.csv", "data3.csv")
file.exists(files)

# Get full path
file_path <- "C:/Users/Documents/data.csv"
file.exists(file_path)

# Check if directory exists
dir.exists("data")                # TRUE or FALSE
dir.exists("/path/to/directory")  # TRUE or FALSE
dir.exists("nonexistent_dir")     # FALSE

# Get current working directory
getwd()

# Set working directory
setwd("C:/Users/Documents/R")
getwd()  # Verify change

# Get file information
file_info <- file.info("data.csv")
print(file_info)
#            size isdir mode               mtime               ctime               atime
# data.csv 12345 FALSE  644 2023-11-15 10:30:00 2023-11-15 10:30:00 2023-11-20 14:22:15

# Extract specific information
file_info$size          # File size in bytes
file_info$isdir         # Is it a directory?
file_info$mtime         # Last modification time

# File size in MB
file_size_mb <- file_info$size / (1024^2)

# List all files in current directory
list.files()

# List files with pattern matching
list.files(pattern = ".csv$")    # Only CSV files
list.files(pattern = "^data")    # Files starting with "data"

# List with full paths
list.files(full.names = TRUE)

# List directories only
list.dirs()

# Recursive listing
list.files(recursive = TRUE)     # All files in subdirectories

# Count files
length(list.files())

# Delete a single file
file.remove("old_data.csv")

# Delete multiple files
files_to_delete <- c("temp1.txt", "temp2.txt", "temp3.txt")
file.remove(files_to_delete)

# Delete and check success
success <- file.remove("unwanted.csv")
if (success) {
  print("File deleted successfully")
} else {
  print("File deletion failed")
}

# Rename single file
file.rename(from = "old_name.csv", to = "new_name.csv")

# Rename with path
file.rename(from = "data/raw.csv", to = "data/processed.csv")

# Batch rename
old_names <- c("file1.txt", "file2.txt", "file3.txt")
new_names <- c("document1.txt", "document2.txt", "document3.txt")
file.rename(from = old_names, to = new_names)

# Rename with timestamp
Sys.time()
timestamp <- format(Sys.time(), "%Y%m%d_%H%M%S")
new_filename <- paste0("data_", timestamp, ".csv")
file.rename("data.csv", new_filename)

# Copy single file
file.copy(from = "original.csv", to = "backup.csv")

# Copy with overwrite
file.copy(from = "original.csv", to = "backup.csv", overwrite = TRUE)

# Copy to directory
file.copy(from = "data.csv", to = "archive/")

# Copy multiple files
files <- c("file1.csv", "file2.csv", "file3.csv")
file.copy(from = files, to = "backup/")

# Create single directory
dir.create("data")

# Create with full path
dir.create("data/raw", recursive = FALSE)

# Create nested directories
dir.create("data/raw/2023", recursive = TRUE)

# Create only if doesn't exist
if (!dir.exists("output")) {
  dir.create("output")
}

# Remove empty directory
unlink("temp_dir", recursive = FALSE)

# Remove directory with contents
unlink("backup_dir", recursive = TRUE)

# Conditional removal
if (dir.exists("old_data")) {
  unlink("old_data", recursive = TRUE)
}

# Save single object
data <- data.frame(x = 1:10, y = rnorm(10))
save(data, file = "mydata.rda")

# Save multiple objects
model <- lm(y ~ x, data = data)
results <- summary(model)
save(data, model, results, file = "analysis.rda")

# Save with compression
save(data, file = "mydata.rda", compress = "gzip")

# Save entire workspace
save.image(file = "workspace.rda")

# Load single RDA file
load("mydata.rda")

# Load specific file into environment
load("mydata.rda", envir = new.env())

# Check what's in RDA before loading
load("analysis.rda")
ls()  # See loaded objects

# Save single object (more flexible)
saveRDS(data, file = "data.rds")

# Load with custom name
loaded_data <- readRDS("data.rds")

# This is cleaner than save/load for single objects

# Write simple text
cat("This is a line of text\n", file = "output.txt")

# Append to file
cat("Another line\n", file = "output.txt", append = TRUE)

# Write vectors
x <- c(1, 2, 3, 4, 5)
cat("Values:", x, "\n", file = "output.txt")

# Write formatted output
writeLines(c("Line 1", "Line 2", "Line 3"), con = "output.txt")

# Start capturing output to file
sink("analysis.txt")

cat("Analysis Results\n")
cat("================\n")
print(summary(mtcars))
cat("\nCorrelation Matrix:\n")
print(cor(mtcars[, 1:5]))

# Stop capturing (return to console)
sink()

# Append to file
sink("analysis.txt", append = TRUE)
cat("\nAdditional Analysis\n")
sink()

# Get current working directory
wd <- getwd()
print(wd)

# File path manipulation
file.path("data", "raw", "2023", "january.csv")
# Returns: "data/raw/2023/january.csv"

# Get file directory
dirname("data/file.csv")  # "data"

# Get file name
basename("data/file.csv")  # "file.csv"

# Path expansion
path_with_tilde <- "~/Documents/data.csv"
path.expand(path_with_tilde)  # Expands ~ to home directory

# List files using system command
system("ls")              # On Mac/Linux
system("dir")             # On Windows

# Capture output
output <- system("ls", intern = TRUE)
print(output)

# Check R version
R.Version()

# Session information
sessionInfo()

# Complete file operations workflow
print("=== File Operations Workflow ===")

# 1. Create project directory structure
if (!dir.exists("project")) {
  dir.create("project", recursive = TRUE)
  dir.create("project/data/raw", recursive = TRUE)
  dir.create("project/data/processed", recursive = TRUE)
  dir.create("project/output", recursive = TRUE)
  dir.create("project/scripts", recursive = TRUE)
}

# 2. Create sample data
sample_data <- data.frame(
  id = 1:100,
  value = rnorm(100),
  group = rep(c("A", "B"), 50)
)

# 3. Save raw data
save(sample_data, file = "project/data/raw/sample_data.rda")

# 4. Save processed version
processed <- sample_data[sample_data$value > 0, ]
save(processed, file = "project/data/processed/filtered_data.rda")

# 5. Export to CSV
write.csv(processed, file = "project/data/processed/filtered_data.csv")

# 6. Create analysis report
sink("project/output/report.txt")
cat("Data Analysis Report\n")
cat("====================\n")
cat("Total observations:", nrow(sample_data), "\n")
cat("Filtered observations:", nrow(processed), "\n")
cat("Mean value:", mean(sample_data$value), "\n")
sink()

# 7. List generated files
cat("Generated files:\n")
print(list.files("project", recursive = TRUE))