# Tibbles are part of the tibble package, which is included in tidyverse
# You can install/load tibble directly
if(!require(tibble)) {install.packages("tibble");require(tibble);}Loading required package: tibble# For more info see:
#
# help(package="tibble")Tibbles are a modern reimagining of R’s traditional data.frame. They are designed to make working with data frames easier and more consistent. Here’s how to create a basic tibble:
Create a tibble with the tibble function. It’s use is very similar to how you would use the data.frame function to create a dataframe (we’re assuming that you’re familiar with creating dataframes in R)
# Create a tibble directly
my_tibble = tibble(
x = 1:3,
y = letters[1:3],
z = LETTERS[1:3]
)
my_tibble# A tibble: 3 × 3
x y z
<int> <chr> <chr>
1 1 a A
2 2 b B
3 3 c C # convert a dataframe to a tibble
df = data.frame(
numbers = 1:3,
letters = c("a", "b", "c")
)
tbl = as_tibble(df)
tbl
# convert a matrix to a tibble
mat = matrix(seq(10,120,by=10), nrow=3,ncol = 4)
tbl = as_tibble(mat)
tblTibbles have several important differences from traditional data.frames:
# Create a wide tibble with many columns 25 rows.
health_data = tibble(
patient_id = sprintf("P%04d", 1:25),
admit_date = as.Date("2024-01-01") + sample(0:30, 25, replace = TRUE),
age = sample(18:95, 25, replace = TRUE),
heart_rate = round(rnorm(25, 75, 10)),
blood_pressure_sys = round(rnorm(25, 120, 15)),
blood_pressure_dia = round(rnorm(25, 80, 10)),
temperature = round(rnorm(25, 98.6, 0.5), 1),
oxygen_saturation = round(rnorm(25, 98, 2)),
cholesterol = round(rnorm(25, 190, 30)),
glucose = round(rnorm(25, 100, 20)),
weight_kg = round(rnorm(25, 70, 15), 1),
height_cm = round(rnorm(25, 170, 10))
)
# Tibbles show only the first 10 rows by default
# and only columns that fit on screen
health_data# A tibble: 25 × 12
patient_id admit_date age heart_rate blood_pressure_sys
<chr> <date> <int> <dbl> <dbl>
1 P0001 2024-01-08 60 80 131
2 P0002 2024-01-04 70 66 141
3 P0003 2024-01-24 81 64 118
4 P0004 2024-01-02 64 73 108
5 P0005 2024-01-05 63 74 114
6 P0006 2024-01-12 22 62 123
7 P0007 2024-01-16 89 65 123
8 P0008 2024-01-04 78 73 102
9 P0009 2024-01-22 44 64 129
10 P0010 2024-01-10 91 75 101
# ℹ 15 more rows
# ℹ 7 more variables: blood_pressure_dia <dbl>,
# temperature <dbl>, oxygen_saturation <dbl>,
# cholesterol <dbl>, glucose <dbl>, weight_kg <dbl>,
# height_cm <dbl># Compare to data.frame which tries to print everything
as.data.frame(health_data) patient_id admit_date age heart_rate blood_pressure_sys
1 P0001 2024-01-08 60 80 131
2 P0002 2024-01-04 70 66 141
3 P0003 2024-01-24 81 64 118
4 P0004 2024-01-02 64 73 108
5 P0005 2024-01-05 63 74 114
6 P0006 2024-01-12 22 62 123
7 P0007 2024-01-16 89 65 123
8 P0008 2024-01-04 78 73 102
9 P0009 2024-01-22 44 64 129
10 P0010 2024-01-10 91 75 101
11 P0011 2024-01-12 80 55 124
12 P0012 2024-01-17 65 74 128
13 P0013 2024-01-21 83 70 119
14 P0014 2024-01-19 58 77 121
15 P0015 2024-01-13 46 53 119
16 P0016 2024-01-11 50 74 118
17 P0017 2024-01-26 67 80 89
18 P0018 2024-01-12 18 97 137
19 P0019 2024-01-31 24 80 134
20 P0020 2024-01-28 33 75 129
21 P0021 2024-01-07 83 67 114
22 P0022 2024-01-03 54 86 123
23 P0023 2024-01-12 20 67 139
24 P0024 2024-01-23 73 79 125
25 P0025 2024-01-15 81 72 125
blood_pressure_dia temperature oxygen_saturation
1 73 98.2 96
2 83 99.4 96
3 89 98.2 100
4 63 98.4 99
5 73 99.2 94
6 81 98.0 100
7 70 99.2 101
8 85 98.5 96
9 81 98.6 98
10 80 98.1 98
11 82 98.1 98
12 83 98.6 97
13 88 97.7 100
14 79 98.7 102
15 94 98.9 96
16 80 98.7 95
17 89 98.8 97
18 84 98.1 94
19 73 98.3 99
20 92 98.3 99
21 74 99.2 94
22 85 99.0 97
23 81 98.2 97
24 82 98.8 101
25 75 98.7 102
cholesterol glucose weight_kg height_cm
1 203 91 64.5 163
2 206 95 86.3 175
3 186 130 91.1 163
4 156 73 56.9 169
5 181 146 102.3 180
6 216 86 82.1 174
7 170 125 92.2 173
8 188 108 48.3 168
9 183 79 60.3 160
10 168 70 65.8 160
11 232 91 67.8 149
12 185 92 66.2 171
13 188 86 70.1 186
14 196 125 68.6 171
15 121 108 67.1 170
16 205 132 78.4 166
17 138 101 61.0 163
18 192 130 92.8 175
19 186 114 74.1 169
20 177 78 69.7 155
21 206 112 54.8 157
22 152 106 71.0 160
23 203 99 77.8 174
24 172 113 56.5 165
25 168 91 42.4 180# By default, print() shows 10 rows. Use n= to show more rows
print(health_data, n = 20) # Shows 20 rows# A tibble: 25 × 12
patient_id admit_date age heart_rate blood_pressure_sys
<chr> <date> <int> <dbl> <dbl>
1 P0001 2024-01-08 60 80 131
2 P0002 2024-01-04 70 66 141
3 P0003 2024-01-24 81 64 118
4 P0004 2024-01-02 64 73 108
5 P0005 2024-01-05 63 74 114
6 P0006 2024-01-12 22 62 123
7 P0007 2024-01-16 89 65 123
8 P0008 2024-01-04 78 73 102
9 P0009 2024-01-22 44 64 129
10 P0010 2024-01-10 91 75 101
11 P0011 2024-01-12 80 55 124
12 P0012 2024-01-17 65 74 128
13 P0013 2024-01-21 83 70 119
14 P0014 2024-01-19 58 77 121
15 P0015 2024-01-13 46 53 119
16 P0016 2024-01-11 50 74 118
17 P0017 2024-01-26 67 80 89
18 P0018 2024-01-12 18 97 137
19 P0019 2024-01-31 24 80 134
20 P0020 2024-01-28 33 75 129
# ℹ 5 more rows
# ℹ 7 more variables: blood_pressure_dia <dbl>,
# temperature <dbl>, oxygen_saturation <dbl>,
# cholesterol <dbl>, glucose <dbl>, weight_kg <dbl>,
# height_cm <dbl># To see all rows
print(health_data, n = Inf)# A tibble: 25 × 12
patient_id admit_date age heart_rate blood_pressure_sys
<chr> <date> <int> <dbl> <dbl>
1 P0001 2024-01-08 60 80 131
2 P0002 2024-01-04 70 66 141
3 P0003 2024-01-24 81 64 118
4 P0004 2024-01-02 64 73 108
5 P0005 2024-01-05 63 74 114
6 P0006 2024-01-12 22 62 123
7 P0007 2024-01-16 89 65 123
8 P0008 2024-01-04 78 73 102
9 P0009 2024-01-22 44 64 129
10 P0010 2024-01-10 91 75 101
11 P0011 2024-01-12 80 55 124
12 P0012 2024-01-17 65 74 128
13 P0013 2024-01-21 83 70 119
14 P0014 2024-01-19 58 77 121
15 P0015 2024-01-13 46 53 119
16 P0016 2024-01-11 50 74 118
17 P0017 2024-01-26 67 80 89
18 P0018 2024-01-12 18 97 137
19 P0019 2024-01-31 24 80 134
20 P0020 2024-01-28 33 75 129
21 P0021 2024-01-07 83 67 114
22 P0022 2024-01-03 54 86 123
23 P0023 2024-01-12 20 67 139
24 P0024 2024-01-23 73 79 125
25 P0025 2024-01-15 81 72 125
# ℹ 7 more variables: blood_pressure_dia <dbl>,
# temperature <dbl>, oxygen_saturation <dbl>,
# cholesterol <dbl>, glucose <dbl>, weight_kg <dbl>,
# height_cm <dbl># width argument to print specifies the number of characters that should
# be printed in the widest row. In effect, this limits the number of columns
# being output to those columns that fit in the specified width.
print(health_data, width = 75)# A tibble: 25 × 12
patient_id admit_date age heart_rate blood_pressure_sys
<chr> <date> <int> <dbl> <dbl>
1 P0001 2024-01-08 60 80 131
2 P0002 2024-01-04 70 66 141
3 P0003 2024-01-24 81 64 118
4 P0004 2024-01-02 64 73 108
5 P0005 2024-01-05 63 74 114
6 P0006 2024-01-12 22 62 123
7 P0007 2024-01-16 89 65 123
8 P0008 2024-01-04 78 73 102
9 P0009 2024-01-22 44 64 129
10 P0010 2024-01-10 91 75 101
# ℹ 15 more rows
# ℹ 7 more variables: blood_pressure_dia <dbl>, temperature <dbl>,
# oxygen_saturation <dbl>, cholesterol <dbl>, glucose <dbl>,
# weight_kg <dbl>, height_cm <dbl># Show all columns by setting width to Inf
print(health_data, width = Inf)# A tibble: 25 × 12
patient_id admit_date age heart_rate blood_pressure_sys blood_pressure_dia temperature oxygen_saturation cholesterol glucose weight_kg height_cm
<chr> <date> <int> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 P0001 2024-01-08 60 80 131 73 98.2 96 203 91 64.5 163
2 P0002 2024-01-04 70 66 141 83 99.4 96 206 95 86.3 175
3 P0003 2024-01-24 81 64 118 89 98.2 100 186 130 91.1 163
4 P0004 2024-01-02 64 73 108 63 98.4 99 156 73 56.9 169
5 P0005 2024-01-05 63 74 114 73 99.2 94 181 146 102. 180
6 P0006 2024-01-12 22 62 123 81 98 100 216 86 82.1 174
7 P0007 2024-01-16 89 65 123 70 99.2 101 170 125 92.2 173
8 P0008 2024-01-04 78 73 102 85 98.5 96 188 108 48.3 168
9 P0009 2024-01-22 44 64 129 81 98.6 98 183 79 60.3 160
10 P0010 2024-01-10 91 75 101 80 98.1 98 168 70 65.8 160
# ℹ 15 more rows# data.frames can have row names
df_rownames = data.frame(
x = 1:3,
y = letters[1:3],
row.names = c("row1", "row2", "row3")
)
df_rownames x y
row1 1 a
row2 2 b
row3 3 c# Tibbles don't support row names
# If you convert a data.frame with row names to a tibble,
# the row names become a regular column called 'rowname'
as_tibble(df_rownames, rownames = "id")# A tibble: 3 × 3
id x y
<chr> <int> <chr>
1 row1 1 a
2 row2 2 b
3 row3 3 c You can create tibbles in several ways:
# Using tibble()
t1 = tibble(
x = 1:5,
y = x * 2, # Note: you can refer to columns created earlier
z = letters[1:5]
)
t1# A tibble: 5 × 3
x y z
<int> <dbl> <chr>
1 1 2 a
2 2 4 b
3 3 6 c
4 4 8 d
5 5 10 e While reading the raw code for creating a dataframe or a tibble, it can be challenging to visualize what the actual dataframe/tibble will look like. This is because when typing the data into the code, each column is typed horrizontally instead of vertically. For example:
# Using tribble() for transposed input
# Useful for small, manual data entry
stuff = tribble(
col1 = c("a", "b", "c"),
col2 = c( 1, 2, 3)
col3 = c(TRUE, FALSE, TRUE))
# The code above lays out columns horizontally.
# The actual dataframe displays columns vertically.
stuffA “tribble” (i.e. TRansposed tIBBLE) is just a different way of typing the code that becomes a tibble. Each column heading is prefixed with a tilde (~). The columns can be laid out vertically in the code, making the code much more readable. See the example below.
# Using tribble() for transposed input
# Useful for small, manual data entry
stuff = tribble(
~col1, ~col2, ~col3,
"a", 1, TRUE,
"b", 2, FALSE,
"c", 3, TRUE
)
# The following looks much more similar to the code that created it.
stuff# Convert data.frame to tibble
df = data.frame(
x = 1:3,
y = letters[1:3]
)
tbl = as_tibble(df)
# Convert tibble back to data.frame
df_again = as.data.frame(tbl)
# Check classes
class(tbl)[1] "tbl_df" "tbl" "data.frame"class(df_again)[1] "data.frame"# data.frames modify non-syntactic names
df_names = data.frame(
`1` = 1:3,
`2+2` = 4:6,
check.names = TRUE # default behavior
)
names(df_names) # Names are modified[1] "X1" "X2.2"# Tibbles preserve original names
tbl_names = tibble(
`1` = 1:3,
`2+2` = 4:6
)
names(tbl_names) # Original names kept[1] "1" "2+2"# Subsetting differences
# data.frame allows partial matching of variable names
df = data.frame(numbers = 1:3, letters = c("a", "b", "c"))
df$num # Partial matching works[1] 1 2 3# Tibbles require exact matching
tbl = tibble(numbers = 1:3, letters = c("a", "b", "c"))
try(tbl$num) # This will raise an errorWarning: Unknown or uninitialised column: `num`.NULL