# 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 2024-01-19 22 71 111
2 P0002 2024-01-21 80 61 136
3 P0003 2024-01-29 24 74 130
4 P0004 2024-01-12 58 81 144
5 P0005 2024-01-10 55 74 115
6 P0006 2024-01-08 39 63 140
7 P0007 2024-01-06 39 75 152
8 P0008 2024-01-26 80 71 121
9 P0009 2024-01-23 30 68 121
10 P0010 2024-01-19 59 60 110
# 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 2024-01-19 22 71 111
2 P0002 2024-01-21 80 61 136
3 P0003 2024-01-29 24 74 130
4 P0004 2024-01-12 58 81 144
5 P0005 2024-01-10 55 74 115
6 P0006 2024-01-08 39 63 140
7 P0007 2024-01-06 39 75 152
8 P0008 2024-01-26 80 71 121
9 P0009 2024-01-23 30 68 121
10 P0010 2024-01-19 59 60 110
11 P0011 2024-01-06 26 76 140
12 P0012 2024-01-02 59 73 109
13 P0013 2024-01-02 36 70 105
14 P0014 2024-01-29 39 73 115
15 P0015 2024-01-02 71 78 117
16 P0016 2024-01-26 39 93 127
17 P0017 2024-01-13 67 81 131
18 P0018 2024-01-23 89 70 110
19 P0019 2024-01-02 73 84 132
20 P0020 2024-01-08 32 69 159
21 P0021 2024-01-28 44 62 120
22 P0022 2024-01-07 88 77 112
23 P0023 2024-01-02 90 92 100
24 P0024 2024-01-18 93 76 112
25 P0025 2024-01-21 52 87 121
blood_pressure_dia temperature oxygen_saturation
1 72 98.6 99
2 94 97.4 96
3 75 98.4 95
4 108 97.8 98
5 69 99.2 95
6 82 99.3 97
7 60 100.2 99
8 91 98.5 98
9 86 98.9 97
10 67 98.2 99
11 91 98.8 97
12 81 98.7 101
13 78 99.2 98
14 87 98.4 97
15 81 98.7 99
16 72 98.2 94
17 78 98.6 96
18 68 98.3 97
19 73 97.8 99
20 69 98.9 99
21 101 98.2 100
22 74 98.4 97
23 72 98.9 101
24 71 98.8 97
25 70 98.7 100
cholesterol glucose weight_kg height_cm
1 214 114 87.1 175
2 200 130 58.6 173
3 243 97 63.7 165
4 151 125 64.5 172
5 188 128 89.3 184
6 186 101 67.1 167
7 151 85 76.4 135
8 243 75 51.5 177
9 137 97 65.3 146
10 227 75 64.5 159
11 230 87 71.7 177
12 141 117 46.3 168
13 178 111 68.3 165
14 150 102 56.9 173
15 204 101 74.1 173
16 163 99 86.6 165
17 173 109 52.7 174
18 226 83 54.5 174
19 185 103 61.6 168
20 203 72 40.5 162
21 181 98 104.1 172
22 191 119 76.1 188
23 203 106 65.8 147
24 196 101 75.3 169
25 213 116 51.4 163# 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 2024-01-19 22 71 111
2 P0002 2024-01-21 80 61 136
3 P0003 2024-01-29 24 74 130
4 P0004 2024-01-12 58 81 144
5 P0005 2024-01-10 55 74 115
6 P0006 2024-01-08 39 63 140
7 P0007 2024-01-06 39 75 152
8 P0008 2024-01-26 80 71 121
9 P0009 2024-01-23 30 68 121
10 P0010 2024-01-19 59 60 110
11 P0011 2024-01-06 26 76 140
12 P0012 2024-01-02 59 73 109
13 P0013 2024-01-02 36 70 105
14 P0014 2024-01-29 39 73 115
15 P0015 2024-01-02 71 78 117
16 P0016 2024-01-26 39 93 127
17 P0017 2024-01-13 67 81 131
18 P0018 2024-01-23 89 70 110
19 P0019 2024-01-02 73 84 132
20 P0020 2024-01-08 32 69 159
# 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 2024-01-19 22 71 111
2 P0002 2024-01-21 80 61 136
3 P0003 2024-01-29 24 74 130
4 P0004 2024-01-12 58 81 144
5 P0005 2024-01-10 55 74 115
6 P0006 2024-01-08 39 63 140
7 P0007 2024-01-06 39 75 152
8 P0008 2024-01-26 80 71 121
9 P0009 2024-01-23 30 68 121
10 P0010 2024-01-19 59 60 110
11 P0011 2024-01-06 26 76 140
12 P0012 2024-01-02 59 73 109
13 P0013 2024-01-02 36 70 105
14 P0014 2024-01-29 39 73 115
15 P0015 2024-01-02 71 78 117
16 P0016 2024-01-26 39 93 127
17 P0017 2024-01-13 67 81 131
18 P0018 2024-01-23 89 70 110
19 P0019 2024-01-02 73 84 132
20 P0020 2024-01-08 32 69 159
21 P0021 2024-01-28 44 62 120
22 P0022 2024-01-07 88 77 112
23 P0023 2024-01-02 90 92 100
24 P0024 2024-01-18 93 76 112
25 P0025 2024-01-21 52 87 121
# 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 2024-01-19 22 71 111
2 P0002 2024-01-21 80 61 136
3 P0003 2024-01-29 24 74 130
4 P0004 2024-01-12 58 81 144
5 P0005 2024-01-10 55 74 115
6 P0006 2024-01-08 39 63 140
7 P0007 2024-01-06 39 75 152
8 P0008 2024-01-26 80 71 121
9 P0009 2024-01-23 30 68 121
10 P0010 2024-01-19 59 60 110
# 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 2024-01-19 22 71 111 72 98.6 99 214 114 87.1 175
2 P0002 2024-01-21 80 61 136 94 97.4 96 200 130 58.6 173
3 P0003 2024-01-29 24 74 130 75 98.4 95 243 97 63.7 165
4 P0004 2024-01-12 58 81 144 108 97.8 98 151 125 64.5 172
5 P0005 2024-01-10 55 74 115 69 99.2 95 188 128 89.3 184
6 P0006 2024-01-08 39 63 140 82 99.3 97 186 101 67.1 167
7 P0007 2024-01-06 39 75 152 60 100. 99 151 85 76.4 135
8 P0008 2024-01-26 80 71 121 91 98.5 98 243 75 51.5 177
9 P0009 2024-01-23 30 68 121 86 98.9 97 137 97 65.3 146
10 P0010 2024-01-19 59 60 110 67 98.2 99 227 75 64.5 159
# 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