# 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 2024-01-09 26 83 144
2 P0002 2024-01-08 76 70 109
3 P0003 2024-01-30 82 68 113
4 P0004 2024-01-06 82 93 122
5 P0005 2024-01-18 51 78 119
6 P0006 2024-01-13 90 85 111
7 P0007 2024-01-24 41 48 122
8 P0008 2024-01-21 26 67 99
9 P0009 2024-01-14 21 80 120
10 P0010 2024-01-19 64 78 132
# 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 2024-01-09 26 83 144
2 P0002 2024-01-08 76 70 109
3 P0003 2024-01-30 82 68 113
4 P0004 2024-01-06 82 93 122
5 P0005 2024-01-18 51 78 119
6 P0006 2024-01-13 90 85 111
7 P0007 2024-01-24 41 48 122
8 P0008 2024-01-21 26 67 99
9 P0009 2024-01-14 21 80 120
10 P0010 2024-01-19 64 78 132
11 P0011 2024-01-02 30 100 139
12 P0012 2024-01-29 22 68 129
13 P0013 2024-01-21 41 70 115
14 P0014 2024-01-18 75 94 93
15 P0015 2024-01-17 71 58 97
16 P0016 2024-01-04 37 80 125
17 P0017 2024-01-07 91 87 119
18 P0018 2024-01-23 87 54 115
19 P0019 2024-01-02 51 73 100
20 P0020 2024-01-04 84 88 124
21 P0021 2024-01-04 76 71 114
22 P0022 2024-01-14 34 71 137
23 P0023 2024-01-07 73 64 108
24 P0024 2024-01-05 65 73 146
25 P0025 2024-01-28 82 95 128
blood_pressure_dia temperature oxygen_saturation
1 65 98.3 98
2 77 98.7 97
3 86 99.0 98
4 67 98.5 93
5 72 99.1 99
6 80 98.4 100
7 63 98.4 101
8 57 99.3 97
9 83 98.6 99
10 90 98.8 96
11 74 99.2 100
12 70 98.2 98
13 70 98.2 99
14 78 98.7 100
15 80 98.6 101
16 77 97.4 99
17 79 98.4 98
18 77 99.0 96
19 63 98.9 99
20 95 98.2 100
21 88 98.5 99
22 90 98.9 100
23 97 98.3 100
24 89 98.3 100
25 76 97.9 98
cholesterol glucose weight_kg height_cm
1 230 144 73.5 173
2 162 107 97.0 174
3 197 124 89.4 173
4 201 105 66.1 166
5 186 131 72.4 151
6 170 104 62.8 178
7 179 98 83.2 180
8 170 94 60.2 148
9 150 94 71.5 186
10 182 122 88.5 185
11 212 75 76.3 179
12 164 107 71.6 172
13 228 94 84.7 167
14 229 118 78.1 159
15 222 99 100.4 187
16 165 58 52.3 163
17 165 123 96.3 153
18 169 115 66.9 171
19 185 95 57.6 175
20 183 127 40.2 177
21 236 106 70.0 177
22 225 115 75.0 149
23 113 98 78.0 179
24 215 65 36.7 177
25 195 87 70.3 191# 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 2024-01-09 26 83 144
2 P0002 2024-01-08 76 70 109
3 P0003 2024-01-30 82 68 113
4 P0004 2024-01-06 82 93 122
5 P0005 2024-01-18 51 78 119
6 P0006 2024-01-13 90 85 111
7 P0007 2024-01-24 41 48 122
8 P0008 2024-01-21 26 67 99
9 P0009 2024-01-14 21 80 120
10 P0010 2024-01-19 64 78 132
11 P0011 2024-01-02 30 100 139
12 P0012 2024-01-29 22 68 129
13 P0013 2024-01-21 41 70 115
14 P0014 2024-01-18 75 94 93
15 P0015 2024-01-17 71 58 97
16 P0016 2024-01-04 37 80 125
17 P0017 2024-01-07 91 87 119
18 P0018 2024-01-23 87 54 115
19 P0019 2024-01-02 51 73 100
20 P0020 2024-01-04 84 88 124
# 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 2024-01-09 26 83 144
2 P0002 2024-01-08 76 70 109
3 P0003 2024-01-30 82 68 113
4 P0004 2024-01-06 82 93 122
5 P0005 2024-01-18 51 78 119
6 P0006 2024-01-13 90 85 111
7 P0007 2024-01-24 41 48 122
8 P0008 2024-01-21 26 67 99
9 P0009 2024-01-14 21 80 120
10 P0010 2024-01-19 64 78 132
11 P0011 2024-01-02 30 100 139
12 P0012 2024-01-29 22 68 129
13 P0013 2024-01-21 41 70 115
14 P0014 2024-01-18 75 94 93
15 P0015 2024-01-17 71 58 97
16 P0016 2024-01-04 37 80 125
17 P0017 2024-01-07 91 87 119
18 P0018 2024-01-23 87 54 115
19 P0019 2024-01-02 51 73 100
20 P0020 2024-01-04 84 88 124
21 P0021 2024-01-04 76 71 114
22 P0022 2024-01-14 34 71 137
23 P0023 2024-01-07 73 64 108
24 P0024 2024-01-05 65 73 146
25 P0025 2024-01-28 82 95 128
# 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 2024-01-09 26 83 144
2 P0002 2024-01-08 76 70 109
3 P0003 2024-01-30 82 68 113
4 P0004 2024-01-06 82 93 122
5 P0005 2024-01-18 51 78 119
6 P0006 2024-01-13 90 85 111
7 P0007 2024-01-24 41 48 122
8 P0008 2024-01-21 26 67 99
9 P0009 2024-01-14 21 80 120
10 P0010 2024-01-19 64 78 132
# 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 2024-01-09 26 83 144 65 98.3 98 230 144 73.5 173
2 P0002 2024-01-08 76 70 109 77 98.7 97 162 107 97 174
3 P0003 2024-01-30 82 68 113 86 99 98 197 124 89.4 173
4 P0004 2024-01-06 82 93 122 67 98.5 93 201 105 66.1 166
5 P0005 2024-01-18 51 78 119 72 99.1 99 186 131 72.4 151
6 P0006 2024-01-13 90 85 111 80 98.4 100 170 104 62.8 178
7 P0007 2024-01-24 41 48 122 63 98.4 101 179 98 83.2 180
8 P0008 2024-01-21 26 67 99 57 99.3 97 170 94 60.2 148
9 P0009 2024-01-14 21 80 120 83 98.6 99 150 94 71.5 186
10 P0010 2024-01-19 64 78 132 90 98.8 96 182 122 88.5 185
# 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