# 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 2024-01-25 73 71 113
2 P0002 2024-01-10 24 95 130
3 P0003 2024-01-12 32 74 126
4 P0004 2024-01-13 49 80 98
5 P0005 2024-01-01 95 74 116
6 P0006 2024-01-02 32 79 133
7 P0007 2024-01-24 26 78 119
8 P0008 2024-01-06 57 77 102
9 P0009 2024-01-06 79 70 132
10 P0010 2024-01-02 82 81 136
# 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 2024-01-25 73 71 113
2 P0002 2024-01-10 24 95 130
3 P0003 2024-01-12 32 74 126
4 P0004 2024-01-13 49 80 98
5 P0005 2024-01-01 95 74 116
6 P0006 2024-01-02 32 79 133
7 P0007 2024-01-24 26 78 119
8 P0008 2024-01-06 57 77 102
9 P0009 2024-01-06 79 70 132
10 P0010 2024-01-02 82 81 136
11 P0011 2024-01-05 20 58 107
12 P0012 2024-01-26 42 82 108
13 P0013 2024-01-28 68 82 135
14 P0014 2024-01-01 75 66 126
15 P0015 2024-01-05 55 81 87
16 P0016 2024-01-16 36 79 146
17 P0017 2024-01-26 29 87 135
18 P0018 2024-01-06 61 79 115
19 P0019 2024-01-03 19 72 107
20 P0020 2024-01-26 89 82 125
21 P0021 2024-01-16 67 76 140
22 P0022 2024-01-23 83 83 118
23 P0023 2024-01-31 50 80 122
24 P0024 2024-01-19 25 67 133
25 P0025 2024-01-05 89 77 128
blood_pressure_dia temperature oxygen_saturation
1 83 98.3 96
2 77 99.3 97
3 82 98.7 98
4 80 98.9 96
5 76 98.5 98
6 82 98.8 99
7 84 99.4 99
8 79 98.4 101
9 101 98.8 99
10 75 98.7 95
11 91 99.3 99
12 83 98.4 98
13 65 98.8 101
14 74 99.0 97
15 96 98.4 99
16 88 98.5 101
17 95 99.1 99
18 72 98.5 97
19 89 99.0 96
20 66 98.9 99
21 73 98.3 100
22 87 98.7 100
23 72 98.0 97
24 80 98.3 97
25 93 97.9 99
cholesterol glucose weight_kg height_cm
1 187 86 83.8 170
2 126 110 75.1 180
3 134 103 59.7 155
4 112 101 67.5 167
5 163 99 82.1 166
6 167 99 78.4 176
7 205 80 58.2 167
8 211 113 69.3 177
9 142 97 36.3 173
10 187 137 79.2 164
11 233 131 87.4 161
12 244 81 72.7 166
13 201 118 64.7 163
14 183 110 69.1 171
15 226 93 68.6 169
16 230 90 51.8 156
17 161 58 56.8 182
18 201 80 82.1 184
19 211 137 61.3 178
20 186 114 84.5 193
21 117 96 90.0 179
22 178 76 80.2 177
23 173 108 60.6 179
24 206 118 54.7 167
25 259 136 67.0 164# 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 2024-01-25 73 71 113
2 P0002 2024-01-10 24 95 130
3 P0003 2024-01-12 32 74 126
4 P0004 2024-01-13 49 80 98
5 P0005 2024-01-01 95 74 116
6 P0006 2024-01-02 32 79 133
7 P0007 2024-01-24 26 78 119
8 P0008 2024-01-06 57 77 102
9 P0009 2024-01-06 79 70 132
10 P0010 2024-01-02 82 81 136
11 P0011 2024-01-05 20 58 107
12 P0012 2024-01-26 42 82 108
13 P0013 2024-01-28 68 82 135
14 P0014 2024-01-01 75 66 126
15 P0015 2024-01-05 55 81 87
16 P0016 2024-01-16 36 79 146
17 P0017 2024-01-26 29 87 135
18 P0018 2024-01-06 61 79 115
19 P0019 2024-01-03 19 72 107
20 P0020 2024-01-26 89 82 125
# 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 2024-01-25 73 71 113
2 P0002 2024-01-10 24 95 130
3 P0003 2024-01-12 32 74 126
4 P0004 2024-01-13 49 80 98
5 P0005 2024-01-01 95 74 116
6 P0006 2024-01-02 32 79 133
7 P0007 2024-01-24 26 78 119
8 P0008 2024-01-06 57 77 102
9 P0009 2024-01-06 79 70 132
10 P0010 2024-01-02 82 81 136
11 P0011 2024-01-05 20 58 107
12 P0012 2024-01-26 42 82 108
13 P0013 2024-01-28 68 82 135
14 P0014 2024-01-01 75 66 126
15 P0015 2024-01-05 55 81 87
16 P0016 2024-01-16 36 79 146
17 P0017 2024-01-26 29 87 135
18 P0018 2024-01-06 61 79 115
19 P0019 2024-01-03 19 72 107
20 P0020 2024-01-26 89 82 125
21 P0021 2024-01-16 67 76 140
22 P0022 2024-01-23 83 83 118
23 P0023 2024-01-31 50 80 122
24 P0024 2024-01-19 25 67 133
25 P0025 2024-01-05 89 77 128
# 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 2024-01-25 73 71 113
2 P0002 2024-01-10 24 95 130
3 P0003 2024-01-12 32 74 126
4 P0004 2024-01-13 49 80 98
5 P0005 2024-01-01 95 74 116
6 P0006 2024-01-02 32 79 133
7 P0007 2024-01-24 26 78 119
8 P0008 2024-01-06 57 77 102
9 P0009 2024-01-06 79 70 132
10 P0010 2024-01-02 82 81 136
# 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 2024-01-25 73 71 113 83 98.3 96 187 86 83.8 170
2 P0002 2024-01-10 24 95 130 77 99.3 97 126 110 75.1 180
3 P0003 2024-01-12 32 74 126 82 98.7 98 134 103 59.7 155
4 P0004 2024-01-13 49 80 98 80 98.9 96 112 101 67.5 167
5 P0005 2024-01-01 95 74 116 76 98.5 98 163 99 82.1 166
6 P0006 2024-01-02 32 79 133 82 98.8 99 167 99 78.4 176
7 P0007 2024-01-24 26 78 119 84 99.4 99 205 80 58.2 167
8 P0008 2024-01-06 57 77 102 79 98.4 101 211 113 69.3 177
9 P0009 2024-01-06 79 70 132 101 98.8 99 142 97 36.3 173
10 P0010 2024-01-02 82 81 136 75 98.7 95 187 137 79.2 164
# 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