Reading Data into R

Learn how to import data from various file formats using base R functions

Reading Data into R Using Base Functions

R provides several built-in functions for importing data from various file formats. Here’s how to use the most common ones:

Reading CSV Files

Comma-separated values (CSV) files are one of the most common data formats:

# Create a sample CSV file
write.csv(mtcars[1:5, ], "sample_cars.csv", row.names = TRUE)

# Read the CSV file
cars_data <- read.csv("sample_cars.csv")
head(cars_data)

                  X  mpg cyl disp  hp drat    wt  qsec vs am gear carb
1         Mazda RX4 21.0   6  160 110 3.90 2.620 16.46  0  1    4    4
2     Mazda RX4 Wag 21.0   6  160 110 3.90 2.875 17.02  0  1    4    4
3        Datsun 710 22.8   4  108  93 3.85 2.320 18.61  1  1    4    1
4    Hornet 4 Drive 21.4   6  258 110 3.08 3.215 19.44  1  0    3    1
5 Hornet Sportabout 18.7   8  360 175 3.15 3.440 17.02  0  0    3    2

# Read with specific options
cars_data2 <- read.csv("sample_cars.csv", 
                      header = TRUE,       # First row contains column names
                      sep = ",",           # Separator is a comma
                      stringsAsFactors = FALSE, # Don't convert strings to factors
                      na.strings = c("NA", "N/A", "")) # Values to treat as NA
head(cars_data2)

                  X  mpg cyl disp  hp drat    wt  qsec vs am gear carb
1         Mazda RX4 21.0   6  160 110 3.90 2.620 16.46  0  1    4    4
2     Mazda RX4 Wag 21.0   6  160 110 3.90 2.875 17.02  0  1    4    4
3        Datsun 710 22.8   4  108  93 3.85 2.320 18.61  1  1    4    1
4    Hornet 4 Drive 21.4   6  258 110 3.08 3.215 19.44  1  0    3    1
5 Hornet Sportabout 18.7   8  360 175 3.15 3.440 17.02  0  0    3    2

Reading Tab-Delimited Files

Tab-delimited files are another common format:

# Create a sample tab-delimited file
write.table(mtcars[1:5, ], "sample_cars.txt", sep = "\t", row.names = TRUE)

# Read the tab-delimited file
cars_data_tab <- read.delim("sample_cars.txt")
head(cars_data_tab)

                   mpg cyl disp  hp drat    wt  qsec vs am gear carb
Mazda RX4         21.0   6  160 110 3.90 2.620 16.46  0  1    4    4
Mazda RX4 Wag     21.0   6  160 110 3.90 2.875 17.02  0  1    4    4
Datsun 710        22.8   4  108  93 3.85 2.320 18.61  1  1    4    1
Hornet 4 Drive    21.4   6  258 110 3.08 3.215 19.44  1  0    3    1
Hornet Sportabout 18.7   8  360 175 3.15 3.440 17.02  0  0    3    2

# Or use read.table with tab separator
cars_data_tab2 <- read.table("sample_cars.txt", 
                            header = TRUE, 
                            sep = "\t")
head(cars_data_tab2)

                   mpg cyl disp  hp drat    wt  qsec vs am gear carb
Mazda RX4         21.0   6  160 110 3.90 2.620 16.46  0  1    4    4
Mazda RX4 Wag     21.0   6  160 110 3.90 2.875 17.02  0  1    4    4
Datsun 710        22.8   4  108  93 3.85 2.320 18.61  1  1    4    1
Hornet 4 Drive    21.4   6  258 110 3.08 3.215 19.44  1  0    3    1
Hornet Sportabout 18.7   8  360 175 3.15 3.440 17.02  0  0    3    2

Reading Fixed-Width Files

Fixed-width files have fields of consistent width:

# Create a sample fixed-width file
cat("John  Smith 35\nMary  Jones 28\nDavid Brown 42\n", file = "sample_people.txt")

# Read the fixed-width file
people_data <- read.fwf("sample_people.txt", 
                       widths = c(5, 6, 3),  # Width of each column
                       col.names = c("First", "Last", "Age"))
people_data

  First   Last Age
1 John   Smith  35
2 Mary   Jones  28
3 David  Brown  42

Reading from R Data Files

R has its own binary file format for saving and loading R objects:

# Save R objects to a file
sample_data <- list(x = 1:10, y = letters[1:10])
save(sample_data, file = "sample_data.RData")

# Load the saved objects
load("sample_data.RData")
sample_data

$x
 [1]  1  2  3  4  5  6  7  8  9 10

$y
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j"

# Save a single object
saveRDS(mtcars[1:5, ], "sample_cars.rds")

# Read the saved object
cars_subset <- readRDS("sample_cars.rds")
head(cars_subset)

                   mpg cyl disp  hp drat    wt  qsec vs am gear carb
Mazda RX4         21.0   6  160 110 3.90 2.620 16.46  0  1    4    4
Mazda RX4 Wag     21.0   6  160 110 3.90 2.875 17.02  0  1    4    4
Datsun 710        22.8   4  108  93 3.85 2.320 18.61  1  1    4    1
Hornet 4 Drive    21.4   6  258 110 3.08 3.215 19.44  1  0    3    1
Hornet Sportabout 18.7   8  360 175 3.15 3.440 17.02  0  0    3    2

Reading from URLs

You can read data directly from the web:

# Read CSV from a URL (example with a small dataset)
url <- "https://raw.githubusercontent.com/datasets/iris/master/data/iris.csv"
iris_data <- try(read.csv(url), silent = TRUE)

# Check if the data was loaded successfully
if (!inherits(iris_data, "try-error")) {
  head(iris_data)
} else {
  print("Could not access the URL. Check your internet connection.")
}

[1] "Could not access the URL. Check your internet connection."

Reading Excel Files

While not part of base R, the readxl package is commonly used:

# Check if readxl is installed
if (!requireNamespace("readxl", quietly = TRUE)) {
  message("The readxl package is not installed. You can install it with: install.packages('readxl')")
} else {
  library(readxl)
  # This would read an Excel file if it existed
  # excel_data <- read_excel("sample.xlsx", sheet = 1)
}

Reading from Databases

Base R provides the DBI package for database connections:

# Example of connecting to SQLite (not run)
# if (!requireNamespace("RSQLite", quietly = TRUE)) {
#   message("The RSQLite package is not installed")
# } else {
#   library(DBI)
#   con <- dbConnect(RSQLite::SQLite(), ":memory:")
#   dbWriteTable(con, "mtcars", mtcars)
#   data <- dbGetQuery(con, "SELECT * FROM mtcars WHERE cyl = 4")
#   dbDisconnect(con)
# }

Handling File Paths

R provides functions to work with file paths:

# Get current working directory
getwd()

[1] "C:/Users/riddh/OneDrive/Desktop/rtichoke/get-started"

# List files in the current directory
list.files(pattern = ".csv")

[1] "sample_cars.csv"

# Check if a file exists
file.exists("sample_cars.csv")

[1] TRUE

# Get full path to a file
normalizePath("sample_cars.csv", mustWork = FALSE)

[1] "C:\\Users\\riddh\\OneDrive\\Desktop\\rtichoke\\get-started\\sample_cars.csv"

Cleaning Up

Let’s remove the sample files we created:

# List of files to remove
files_to_remove <- c("sample_cars.csv", "sample_cars.txt", 
                    "sample_people.txt", "sample_data.RData", 
                    "sample_cars.rds")

# Remove files
for (file in files_to_remove) {
  if (file.exists(file)) {
    file.remove(file)
  }
}

Remember to check the documentation with ?read.csv or similar commands to explore all available options for these functions.