Top 50 R Libraries

library(dplyr)

students |>
  filter(score >= 80) |>
  group_by(class) |>
  summarise(avg = mean(score))

library(tidyr)

wide_df |>
  pivot_longer(cols = Jan:Mar, names_to = "month", values_to = "sales")

library(tibble)

df <- tibble(name = c("Rafi","Meera"), score = c(88,92))

library(magrittr)

students %>% filter(score > 80) %>% nrow()

library(purrr)

map_dbl(1:5, ~ .x^2)

library(readr)

df <- read_csv("students.csv")

library(readxl)

df <- read_excel("data.xlsx", sheet = 1)

library(writexl)

write_xlsx(df, "output.xlsx")

library(haven)

df <- read_sav("survey.sav")

library(jsonlite)

data <- fromJSON("https://api.example.com/data")

library(DBI)

con <- dbConnect(RSQLite::SQLite(), "mydb.sqlite")
result <- dbGetQuery(con, "SELECT * FROM students")

library(RSQLite)

con <- DBI::dbConnect(SQLite(), ":memory:")

library(httr)

response <- GET("https://api.example.com/data")
data <- httr::content(response, as = "parsed")

library(ggplot2)

ggplot(df, aes(x, y)) + geom_point()

library(plotly)

p <- ggplot(df, aes(x, y)) + geom_point()
ggplotly(p)   # same chart, now interactive

library(lattice)

xyplot(score ~ study_hours | group, data = df)

library(RColorBrewer)

colours <- brewer.pal(3, "Set2")

library(scales)

ggplot(df, aes(x, y)) + geom_col() +
  scale_y_continuous(labels = scales::percent)

library(gridExtra)

grid.arrange(plot1, plot2, ncol = 2)

library(patchwork)

p1 + p2   # side by side
p1 / p2   # stacked

library(stringr)

str_detect(c("apple","banana"), "an")

library(lubridate)

d <- ymd("2026-07-17")
wday(d, label = TRUE)

library(glue)

name <- "Rafi"; score <- 88
glue("{name} scored {score} points")

# stats is always loaded automatically - no library() call needed
t.test(score ~ group, data = df)

library(car)

vif(model)   # variance inflation factor - checks multicollinearity

library(lme4)

model <- lmer(score ~ study_hours + (1|school), data = df)

library(survival)

fit <- survfit(Surv(time, status) ~ group, data = df)

library(MASS)

model <- MASS::glm.nb(count ~ x, data = df)  # negative binomial regression

library(caret)

model <- train(class ~ ., data = df, method = "rf")

library(randomForest)

model <- randomForest(class ~ ., data = df, ntree = 500)

library(xgboost)

model <- xgboost(data = X_matrix, label = y, nrounds = 100)

library(glmnet)

model <- cv.glmnet(X_matrix, y, alpha = 1)  # alpha=1 is Lasso

library(e1071)

model <- svm(class ~ ., data = df)

library(tidymodels)

model_spec <- linear_reg() |> set_engine("lm")

library(rpart)

tree <- rpart(class ~ ., data = df, method = "class")

---
title: "My Report"
output: html_document
---

```{r}
summary(df)
```

library(knitr)

knit("report.Rmd")

library(shiny)

ui <- fluidPage(sliderInput("n", "N", 1, 100, 50), plotOutput("plot"))

---
title: "Dashboard"
output: flexdashboard::flex_dashboard
---

library(rvest)

page <- read_html("https://example.com")
titles <- page |> html_elements("h2") |> html_text()

library(data.table)

DT <- as.data.table(df)
DT[score > 80, .(avg = mean(score)), by = class]

library(Rcpp)

cppFunction("int add(int x, int y) { return x + y; }")
add(2, 3)

library(parallel)

results <- mclapply(1:4, function(x) x^2, mc.cores = 4)

library(foreach)

foreach(i = 1:3) %do% { i^2 }

library(doParallel)

registerDoParallel(cores = 4)
foreach::foreach(i = 1:3) %dopar% { i^2 }

library(devtools)

load_all()   # reload your in-development package

library(testthat)

test_that("addition works", {
  expect_equal(2 + 2, 4)
})

library(here)

df <- read.csv(here("data", "students.csv"))

library(janitor)

df <- df |> clean_names()   # "Student Name" -> "student_name"

library(forcats)

df$class <- fct_relevel(df$class, "B", "A")   # set custom level order