# 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 2024-01-07 25 70 129
2 P0002 2024-01-20 48 84 105
3 P0003 2024-01-11 78 79 116
4 P0004 2024-01-27 55 65 125
5 P0005 2024-01-16 54 102 108
6 P0006 2024-01-24 24 57 122
7 P0007 2024-01-17 56 57 138
8 P0008 2024-01-18 89 67 131
9 P0009 2024-01-08 29 72 119
10 P0010 2024-01-18 49 92 86
# 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 2024-01-07 25 70 129
2 P0002 2024-01-20 48 84 105
3 P0003 2024-01-11 78 79 116
4 P0004 2024-01-27 55 65 125
5 P0005 2024-01-16 54 102 108
6 P0006 2024-01-24 24 57 122
7 P0007 2024-01-17 56 57 138
8 P0008 2024-01-18 89 67 131
9 P0009 2024-01-08 29 72 119
10 P0010 2024-01-18 49 92 86
11 P0011 2024-01-08 25 66 120
12 P0012 2024-01-13 25 68 95
13 P0013 2024-01-02 74 78 106
14 P0014 2024-01-29 40 85 109
15 P0015 2024-01-04 87 50 127
16 P0016 2024-01-17 86 81 106
17 P0017 2024-01-13 80 87 150
18 P0018 2024-01-20 83 54 111
19 P0019 2024-01-14 83 77 122
20 P0020 2024-01-10 65 85 114
21 P0021 2024-01-26 83 76 96
22 P0022 2024-01-15 64 86 120
23 P0023 2024-01-17 38 88 125
24 P0024 2024-01-24 41 59 118
25 P0025 2024-01-18 63 61 118
blood_pressure_dia temperature oxygen_saturation
1 62 98.5 99
2 69 98.1 102
3 67 98.2 100
4 76 98.9 97
5 87 98.2 99
6 79 98.1 95
7 110 98.2 99
8 68 99.2 98
9 78 98.4 99
10 77 98.8 99
11 98 98.9 99
12 81 99.2 96
13 75 97.6 98
14 78 98.3 96
15 86 97.8 98
16 101 98.0 95
17 82 98.9 97
18 80 98.9 99
19 69 99.4 100
20 86 98.7 101
21 76 98.2 99
22 73 98.8 95
23 76 98.6 95
24 77 98.7 98
25 82 98.6 99
cholesterol glucose weight_kg height_cm
1 225 107 73.1 183
2 205 82 51.2 155
3 206 113 61.3 163
4 221 129 73.1 173
5 176 118 67.3 190
6 196 112 56.3 185
7 146 98 61.2 168
8 185 150 58.7 167
9 159 90 70.2 197
10 172 78 69.8 173
11 97 101 63.6 170
12 206 82 59.2 171
13 220 105 63.1 164
14 208 107 59.2 184
15 189 107 73.7 184
16 138 76 94.6 165
17 223 95 49.4 154
18 168 86 39.6 162
19 225 102 84.7 161
20 238 75 81.1 175
21 205 127 55.3 165
22 164 66 76.8 163
23 206 72 79.2 165
24 154 112 43.0 160
25 112 98 83.9 154# 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 2024-01-07 25 70 129
2 P0002 2024-01-20 48 84 105
3 P0003 2024-01-11 78 79 116
4 P0004 2024-01-27 55 65 125
5 P0005 2024-01-16 54 102 108
6 P0006 2024-01-24 24 57 122
7 P0007 2024-01-17 56 57 138
8 P0008 2024-01-18 89 67 131
9 P0009 2024-01-08 29 72 119
10 P0010 2024-01-18 49 92 86
11 P0011 2024-01-08 25 66 120
12 P0012 2024-01-13 25 68 95
13 P0013 2024-01-02 74 78 106
14 P0014 2024-01-29 40 85 109
15 P0015 2024-01-04 87 50 127
16 P0016 2024-01-17 86 81 106
17 P0017 2024-01-13 80 87 150
18 P0018 2024-01-20 83 54 111
19 P0019 2024-01-14 83 77 122
20 P0020 2024-01-10 65 85 114
# 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 2024-01-07 25 70 129
2 P0002 2024-01-20 48 84 105
3 P0003 2024-01-11 78 79 116
4 P0004 2024-01-27 55 65 125
5 P0005 2024-01-16 54 102 108
6 P0006 2024-01-24 24 57 122
7 P0007 2024-01-17 56 57 138
8 P0008 2024-01-18 89 67 131
9 P0009 2024-01-08 29 72 119
10 P0010 2024-01-18 49 92 86
11 P0011 2024-01-08 25 66 120
12 P0012 2024-01-13 25 68 95
13 P0013 2024-01-02 74 78 106
14 P0014 2024-01-29 40 85 109
15 P0015 2024-01-04 87 50 127
16 P0016 2024-01-17 86 81 106
17 P0017 2024-01-13 80 87 150
18 P0018 2024-01-20 83 54 111
19 P0019 2024-01-14 83 77 122
20 P0020 2024-01-10 65 85 114
21 P0021 2024-01-26 83 76 96
22 P0022 2024-01-15 64 86 120
23 P0023 2024-01-17 38 88 125
24 P0024 2024-01-24 41 59 118
25 P0025 2024-01-18 63 61 118
# 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 2024-01-07 25 70 129
2 P0002 2024-01-20 48 84 105
3 P0003 2024-01-11 78 79 116
4 P0004 2024-01-27 55 65 125
5 P0005 2024-01-16 54 102 108
6 P0006 2024-01-24 24 57 122
7 P0007 2024-01-17 56 57 138
8 P0008 2024-01-18 89 67 131
9 P0009 2024-01-08 29 72 119
10 P0010 2024-01-18 49 92 86
# 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 2024-01-07 25 70 129 62 98.5 99 225 107 73.1 183
2 P0002 2024-01-20 48 84 105 69 98.1 102 205 82 51.2 155
3 P0003 2024-01-11 78 79 116 67 98.2 100 206 113 61.3 163
4 P0004 2024-01-27 55 65 125 76 98.9 97 221 129 73.1 173
5 P0005 2024-01-16 54 102 108 87 98.2 99 176 118 67.3 190
6 P0006 2024-01-24 24 57 122 79 98.1 95 196 112 56.3 185
7 P0007 2024-01-17 56 57 138 110 98.2 99 146 98 61.2 168
8 P0008 2024-01-18 89 67 131 68 99.2 98 185 150 58.7 167
9 P0009 2024-01-08 29 72 119 78 98.4 99 159 90 70.2 197
10 P0010 2024-01-18 49 92 86 77 98.8 99 172 78 69.8 173
# 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