How to find rows with duplicate values in R

March 14, 2026 · 7 min read · Updated March 14, 2026 · beginner

r duplicates dplyr data.table data-frame

Finding duplicate rows is a common data cleaning task. This guide shows you multiple approaches using base R, dplyr, and data.table.

Finding Duplicates in a Vector

Base R: duplicated()

The duplicated() function returns a logical vector indicating which elements have been seen before:

x <- c(1, 2, 2, 3, 3, 3, 4, 5, 5)

duplicated(x)
# [1] FALSE FALSE  TRUE  TRUE  TRUE FALSE  TRUE FALSE  TRUE

To see which values are duplicated (not where they occur):

x <- c(1, 2, 2, 3, 3, 3, 4, 5, 5)

duplicated(x) | duplicated(x, fromLast = TRUE)
# [1]  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE

Which elements are duplicates?

x <- c(1, 2, 2, 3, 3, 3, 4, 5, 5)

# Find positions of duplicated values
which(duplicated(x))
# [1] 3 4 5 7 9

# Get the actual duplicate values
unique(x[duplicated(x)])
# [1] 2 3 5

Finding Duplicate Rows in a Data Frame

Base R

df <- data.frame(
  id = c(1, 2, 2, 3, 4, 1),
  name = c("A", "B", "B", "C", "D", "A"),
  score = c(85, 90, 90, 78, 88, 85)
)

duplicated(df)
# [1] FALSE FALSE  TRUE FALSE FALSE  TRUE

Get the row numbers of duplicates:

which(duplicated(df))
# [1] 3 6

Extract the duplicate rows:

df[duplicated(df), ]
#   id name score
# 3  2    B     90
# 6  1    A     85

Find all duplicates including first occurrence

df[duplicated(df) | duplicated(df, fromLast = TRUE), ]
#   id name score
# 1  1    A     85
# 3  2    B     90
# 6  1    A     85

dplyr

Use duplicated() or the group_by() approach:

library(dplyr)

df <- data.frame(
  id = c(1, 2, 2, 3, 4, 1),
  name = c("A", "B", "B", "C", "D", "A"),
  score = c(85, 90, 90, 78, 88, 85)
)

# Find duplicate rows
df %>% 
  group_by_all() %>% 
  filter(n() > 1) %>%
  ungroup()
# # A tibble: 4 × 3
#      id name  score
#   <dbl> <chr> <dbl>
# 1     1 A        85
# 2     2 B        90
# 3     1 A        85
# 4     2 B        90

Find duplicates in specific columns only

library(dplyr)

df <- data.frame(
  id = c(1, 2, 2, 3, 4, 1),
  name = c("A", "B", "B", "C", "D", "A"),
  score = c(85, 90, 90, 78, 88, 85)
)

# Find duplicates based on id column only
df %>%
  group_by(id) %>%
  filter(n() > 1) %>%
  ungroup()
# # A tibble: 4 × 3
#      id name  score
#   <dbl> <chr> <dbl>
# 1     1 A        85
# 2     2 B        90
# 3     1 A        85
# 4     2 B        90

# Or using the id and name columns
df %>%
  group_by(id, name) %>%
  filter(n() > 1) %>%
  ungroup()

data.table

library(data.table)

dt <- data.table(
  id = c(1, 2, 2, 3, 4, 1),
  name = c("A", "B", "B", "C", "D", "A"),
  score = c(85, 90, 90, 78, 88, 85)
)

# Find duplicate rows
duplicated(dt)
# [1] FALSE FALSE  TRUE FALSE FALSE  TRUE

# Get duplicate rows
dt[duplicated(dt)]
#    id name score
# 1:  2    B     90
# 2:  1    A     85

# Using the anyDuplicated() function - returns index of first duplicate
anyDuplicated(dt)
# [1] 3

# Find duplicates by specific columns
dt[duplicated(dt, by = c("id", "name"))]
#    id name score
# 1:  2    B     90
# 2:  1    A     85

Counting Duplicates

Count total duplicate rows

df <- data.frame(
  id = c(1, 2, 2, 3, 4, 1),
  name = c("A", "B", "B", "C", "D", "A"),
  score = c(85, 90, 90, 78, 88, 85)
)

# Base R
sum(duplicated(df))
# [1] 2

# dplyr
library(dplyr)
df %>%
  summarise(n_dup = sum(duplicated(.)))
# # A tibble: 1 × 1
#   n_dup
#   <int>
# 1     2

Count duplicates per group

library(dplyr)

df <- data.frame(
  id = c(1, 2, 2, 3, 4, 1),
  name = c("A", "B", "B", "C", "D", "A"),
  score = c(85, 90, 90, 78, 88, 85)
)

# Count how many times each combination appears
df %>%
  group_by(id, name) %>%
  mutate(count = n()) %>%
  filter(count > 1)
# # A tibble: 4 × 4
#      id name  score count
#   <dbl> <chr> <dbl> <int>
# 1     1 A        85     2
# 2     2 B        90     2
# 3     1 A        85     2
# 4     2 B        90     2

Count unique vs total rows

df <- data.frame(
  id = c(1, 2, 2, 3, 4, 1),
  name = c("A", "B", "B", "C", "D", "A"),
  score = c(85, 90, 90, 78, 88, 85)
)

nrow(df)                           # Total rows: 6
# [1] 6

nrow(unique(df))                  # Unique rows: 4
# [1] 4

nrow(df) - nrow(unique(df))      # Duplicate rows: 2
# [1] 2

Removing Duplicate Rows

Base R

df <- data.frame(
  id = c(1, 2, 2, 3, 4, 1),
  name = c("A", "B", "B", "C", "D", "A"),
  score = c(85, 90, 90, 78, 88, 85)
)

# Remove all duplicates (keeps first occurrence)
unique(df)
#   id name score
# 1  1    A     85
# 2  2    B     90
# 4  3    C     78
# 5  4    D     88

# Or use duplicated()
df[!duplicated(df), ]
#   id name score
# 1  1    A     85
# 2  2    B     90
# 4  3    C     78
# 5  4    D     88

# Keep last occurrence instead
df[!duplicated(df, fromLast = TRUE), ]
#   id name score
# 3  2    B     90
# 4  3    C     78
# 5  4    D     88
# 6  1    A     85

dplyr

library(dplyr)

df <- data.frame(
  id = c(1, 2, 2, 3, 4, 1),
  name = c("A", "B", "B", "C", "D", "A"),
  score = c(85, 90, 90, 78, 88, 85)
)

# Remove duplicate rows
distinct(df)
# # A tibble: 4 × 3
#      id name  score
#   <dbl> <chr> <dbl>
# 1     1 A        85
# 2     2 B        90
# 3     3 C        78
# 4     4 D        88

# Remove duplicates based on specific columns
distinct(df, id, .keep_all = TRUE)
# # A tibble: 4 × 3
#      id name  score
#   <dbl> <chr> <dbl>
# 1     1 A        85
# 2     2 B        90
# 3     3 C        78
# 4     4 D        88

data.table

library(data.table)

dt <- data.table(
  id = c(1, 2, 2, 3, 4, 1),
  name = c("A", "B", "B", "C", "D", "A"),
  score = c(85, 90, 90, 78, 88, 85)
)

unique(dt)
#    id name score
# 1:  1    A     85
# 2:  2    B     90
# 3:  3    C     78
# 4:  4    D     88

# Remove duplicates by specific columns
unique(dt, by = c("id", "name"))
#    id name score
# 1:  1    A     85
# 2:  2    B     90
# 3:  3    C     78
# 4:  4    D     88

Practical Examples

Find customers with multiple orders

library(dplyr)

orders <- data.frame(
  customer_id = c(101, 101, 102, 103, 103, 103),
  order_id = c(1, 2, 3, 4, 5, 6),
  amount = c(50, 75, 100, 25, 30, 45)
)

# Find customers with more than one order
orders %>%
  group_by(customer_id) %>%
  filter(n() > 1) %>%
  ungroup()
# # A tibble: 5 × 3
#   customer_id order_id amount
#         <dbl>    <dbl>  <dbl>
# 1         101        1     50
# 2         101        2     75
# 3         103        4     25
# 4         103        5     30
# 5         103        6     45

Find records modified more than once

library(dplyr)

logs <- data.frame(
  record_id = c("A", "A", "B", "C", "C"),
  action = c("create", "update", "create", "create", "delete"),
  timestamp = c(1, 2, 3, 4, 5)
)

# Find records that were touched multiple times
logs %>%
  group_by(record_id) %>%
  filter(n() > 1) %>%
  ungroup()

Keep the row with maximum value per group

library(dplyr)

df <- data.frame(
  id = c(1, 1, 2, 2, 3, 3),
  time = c(10, 20, 15, 25, 30, 35),
  value = c(100, 150, 200, 180, 90, 120)
)

# Keep row with maximum value per id
df %>%
  group_by(id) %>%
  slice_max(value, n = 1) %>%
  ungroup()
# # A tibble: 3 × 3
#      id  time value
#   <dbl> <dbl> <dbl>
# 1     1    20   150
# 2     2    25   180
# 3     3    35   120

Performance Comparison

For large datasets, data.table is fastest:

library(data.table)

dt <- data.table(
  id = rep(1:1e6, each = 3),
  value = rnorm(3e6)
)

system.time(dt[!duplicated(dt)])
#    user  system elapsed 
#   0.089   0.010   0.099

Base R unique() is fastest for vectors. Use dplyr::distinct() for readability in pipelines, and data.table::unique() for large data.

Finding Duplicates in a Vector

Base R: duplicated()

Which elements are duplicates?

Finding Duplicate Rows in a Data Frame

Base R

Find all duplicates including first occurrence

dplyr

Find duplicates in specific columns only

data.table

Counting Duplicates

Count total duplicate rows

Count duplicates per group

Count unique vs total rows

Removing Duplicate Rows

Base R

dplyr

data.table

Practical Examples

Find customers with multiple orders

Find records modified more than once

Keep the row with maximum value per group

Performance Comparison

See Also