R
CHEAT SHEET.

Basic Syntax

# Comments start with #
x <- 5          # Assignment (preferred)
y = 10           # Also valid
z <- x + y       # Arithmetic

# Print to console
print(z)
print("Hello, World!")

# Functions
sum(1, 2, 3)     # 6
sqrt(16)         # 4
abs(-5)          # 5

Data Types

Type Checking

class(x)           # class of object
typeof(x)          # internal type
is.numeric(x)      # TRUE/FALSE
is.character(x)
is.logical(x)
is.na(x)           # check for NA
is.null(x)         # check for NULL

Vectors

# Create vectors
v <- c(1, 2, 3, 4, 5)
v <- 1:5           # sequence
v <- seq(1, 10, 2) # 1, 3, 5, 7, 9

# Named vectors
v <- c(a=1, b=2, c=3)

# Access
v[1]               # first element
v[1:3]             # first 3
v[-1]              # all except first
v["a"]             # by name

# Vector operations (element‑wise)
v + 1
v * 2
v > 3
v[v > 2]           # filtering

# Common functions
length(v)          # number of elements
sum(v)             # sum
mean(v)            # mean
median(v)          # median
sd(v)              # standard deviation
var(v)             # variance
min(v) / max(v)    # min / max
sort(v)            # sorted
rev(v)             # reversed
unique(v)          # unique values

Matrices

# Create matrix
m <- matrix(1:9, nrow=3, ncol=3)
m <- matrix(1:9, nrow=3, byrow=TRUE)

# Access
m[2, 3]            # row 2, col 3
m[2, ]             # row 2
m[, 3]             # col 3

# Matrix operations
t(m)               # transpose
m %*% m            # matrix multiplication
m * m              # element‑wise
diag(m)            # diagonal
dim(m)             # dimensions
nrow(m) / ncol(m)  # rows / columns

Lists

# Create list
lst <- list(a=1, b="hello", c=c(1,2,3))

# Access
lst$a              # by name
lst[["a"]]         # by name (string)
lst[[1]]           # by index

# Add / modify
lst$d <- TRUE
lst[["e"]] <- 42

# Remove
lst$d <- NULL

# Merge lists
c(lst1, lst2)

Data Frames

# Create data frame
df <- data.frame(
    name = c("Alice", "Bob", "Charlie"),
    age = c(25, 30, 35),
    city = c("Delhi", "Mumbai", "Bangalore"),
    stringsAsFactors = FALSE
)

# Access
df$name           # column
df[["name"]]      # column (string)
df[1, ]           # row 1
df[, 2]           # column 2
df[1:2, c("name", "age")]  # subset

# View
head(df)          # first 6 rows
tail(df)          # last 6 rows
str(df)           # structure
summary(df)       # summary statistics
dim(df)           # dimensions
colnames(df)      # column names
rownames(df)      # row names

Control Flow

if / else

if (x > 0) {
    print("positive")
} else if (x == 0) {
    print("zero")
} else {
    print("negative")
}

for Loop

for (i in 1:5) {
    print(i)
}

# Iterate over vector
for (name in c("Alice", "Bob", "Charlie")) {
    print(paste("Hello", name))
}

while Loop

i <- 1
while (i <= 5) {
    print(i)
    i <- i + 1
}

repeat (infinite)

i <- 1
repeat {
    print(i)
    i <- i + 1
    if (i > 5) break
}

apply family

apply(matrix, 1, sum)   # rows
apply(matrix, 2, mean)  # columns

lapply(list, function)   # list → list
sapply(list, function)   # list → vector
vapply(list, function, FUN.VALUE)  # typed

tapply(vector, factor, mean)  # group by
mapply(function, ...)         # multiple vectors

Functions

my_function <- function(arg1, arg2 = 10) {
    result <- arg1 * arg2
    return(result)
}

# Default arguments
greet <- function(name, greeting = "Hello") {
    paste(greeting, name)
}

# Anonymous functions
sapply(1:5, function(x) x^2)

# Ellipsis (...)
my_sum <- function(...) {
    sum(...)
}

Data Manipulation (dplyr)

Installation

install.packages("dplyr")
library(dplyr)

Common Functions

# Select columns
select(df, name, age)
select(df, -city)

# Filter rows
filter(df, age > 25)
filter(df, age > 25 & city == "Delhi")

# Arrange (sort)
arrange(df, age)
arrange(df, desc(age))

# Mutate (create new columns)
mutate(df, age_sq = age^2)
mutate(df, age_sq = age^2, .before = age)

# Summarise
summarise(df, avg_age = mean(age), count = n())

# Group by
group_by(df, city) %>%
    summarise(avg_age = mean(age))

# Piping
df %>%
    filter(age > 25) %>%
    select(name, age) %>%
    arrange(desc(age))

# Rename
rename(df, new_name = old_name)

Tidy Data (tidyr)

# Installation
install.packages("tidyr")
library(tidyr)

# Pivot longer (wide → long)
df_long <- pivot_longer(df, cols = starts_with("col"), names_to = "key", values_to = "value")

# Pivot wider (long → wide)
df_wide <- pivot_wider(df_long, names_from = "key", values_from = "value")

# Separate a column
df <- separate(df, col, into = c("part1", "part2"), sep = "-")

# Unite columns
df <- unite(df, new_col, col1, col2, sep = "_")

# Complete missing combinations
df <- complete(df, nesting(col1), fill = list(value = 0))

# Replace NAs
df <- replace_na(df, list(value = 0))

Data Visualisation (ggplot2)

Installation

install.packages("ggplot2")
library(ggplot2)

Basic Plot

# Scatter plot
ggplot(df, aes(x = x, y = y)) +
    geom_point()

# Line plot
ggplot(df, aes(x = x, y = y)) +
    geom_line()

# Bar plot
ggplot(df, aes(x = category, y = value)) +
    geom_bar(stat = "identity")

# Histogram
ggplot(df, aes(x = value)) +
    geom_histogram(binwidth = 1)

# Box plot
ggplot(df, aes(x = category, y = value)) +
    geom_boxplot()

# With colour
ggplot(df, aes(x = x, y = y, colour = group)) +
    geom_point()

# Facets
ggplot(df, aes(x = x, y = y)) +
    geom_point() +
    facet_wrap(~group)

# Themes
ggplot(df, aes(x, y)) +
    geom_point() +
    theme_minimal()

# Labels
ggplot(df, aes(x, y)) +
    geom_point() +
    labs(
        title = "Title",
        x = "X‑axis",
        y = "Y‑axis",
        caption = "Source: data"
    )

Statistical Functions

# Descriptive statistics
mean(x)            # mean
median(x)          # median
sd(x)              # standard deviation
var(x)             # variance
cor(x, y)          # correlation
cov(x, y)          # covariance
quantile(x)        # quartiles
summary(x)         # five‑number summary

# t‑test
t.test(x, y)       # two‑sample
t.test(x, mu = 0)  # one‑sample

# ANOVA
aov(y ~ group, data = df)

# Linear regression
lm(y ~ x, data = df)
lm(y ~ x1 + x2, data = df)
lm(y ~ ., data = df)  # all variables

# GLM
glm(y ~ x, family = binomial, data = df)

# Chi‑square test
chisq.test(table(df$col1, df$col2))

# Random sampling
sample(x, size = 10)
sample(x, size = 10, replace = TRUE)
set.seed(123)      # reproducible

Common Packages

Reading & Writing Data

# CSV
write.csv(df, "file.csv", row.names = FALSE)
df <- read.csv("file.csv")

# Readr (faster, better default)
library(readr)
write_csv(df, "file.csv")
df <- read_csv("file.csv")

# Excel
library(readxl)
df <- read_excel("file.xlsx", sheet = 1)

library(writexl)
write_xlsx(df, "file.xlsx")

# RDS (native R format)
saveRDS(df, "file.rds")
df <- readRDS("file.rds")

# Feather (fast binary)
library(feather)
write_feather(df, "file.feather")
df <- read_feather("file.feather")

# JSON
library(jsonlite)
toJSON(df)
fromJSON("file.json")

R Tips

• Use <- for assignment (not =) – it's the R standard.
• Use tibble over data.frame – better printing and handling.
• Use %>% (pipe) for readable code (from magrittr).
• Avoid attach() – use with() or dplyr verbs.
• Use str() to inspect any object.
• Use rm(list = ls()) to clear environment.
• Use sessionInfo() to check package versions.
• Use set.seed() for reproducible results.
• Use RStudio – the best IDE for R.
• Use install.packages() for packages, library() to load.