# 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 2024-01-01 64 81 137
2 P0002 2024-01-10 36 69 98
3 P0003 2024-01-02 41 60 121
4 P0004 2024-01-31 67 74 129
5 P0005 2024-01-24 41 80 107
6 P0006 2024-01-19 94 82 100
7 P0007 2024-01-19 90 66 143
8 P0008 2024-01-03 47 85 126
9 P0009 2024-01-11 91 62 161
10 P0010 2024-01-27 69 74 152
# 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 2024-01-01 64 81 137
2 P0002 2024-01-10 36 69 98
3 P0003 2024-01-02 41 60 121
4 P0004 2024-01-31 67 74 129
5 P0005 2024-01-24 41 80 107
6 P0006 2024-01-19 94 82 100
7 P0007 2024-01-19 90 66 143
8 P0008 2024-01-03 47 85 126
9 P0009 2024-01-11 91 62 161
10 P0010 2024-01-27 69 74 152
11 P0011 2024-01-06 46 71 118
12 P0012 2024-01-10 54 89 119
13 P0013 2024-01-22 59 78 108
14 P0014 2024-01-07 78 93 112
15 P0015 2024-01-03 37 75 129
16 P0016 2024-01-16 53 80 115
17 P0017 2024-01-16 70 71 141
18 P0018 2024-01-02 38 67 129
19 P0019 2024-01-03 94 78 134
20 P0020 2024-01-17 35 82 121
21 P0021 2024-01-27 34 88 98
22 P0022 2024-01-16 48 86 129
23 P0023 2024-01-05 68 81 154
24 P0024 2024-01-14 74 64 107
25 P0025 2024-01-25 82 63 111
blood_pressure_dia temperature oxygen_saturation
1 86 98.2 100
2 66 98.5 97
3 68 98.1 96
4 63 98.8 98
5 74 99.2 97
6 84 98.7 98
7 81 98.2 98
8 66 99.6 98
9 74 98.6 97
10 70 98.6 97
11 90 98.3 97
12 80 98.3 98
13 101 99.4 97
14 77 98.8 97
15 97 99.0 97
16 81 97.7 97
17 94 99.0 100
18 83 99.1 99
19 79 98.5 99
20 80 98.7 98
21 77 98.5 97
22 102 98.5 98
23 83 97.6 100
24 83 99.2 102
25 79 98.1 97
cholesterol glucose weight_kg height_cm
1 140 120 70.6 181
2 194 89 101.7 158
3 94 94 61.8 173
4 207 123 73.0 174
5 197 90 53.5 171
6 183 109 36.5 159
7 157 87 84.4 163
8 156 82 79.7 168
9 185 82 69.1 173
10 205 124 67.7 169
11 137 35 82.5 180
12 187 91 101.5 165
13 176 93 81.9 176
14 132 96 40.1 173
15 192 78 68.2 181
16 247 93 46.8 182
17 194 104 79.3 171
18 166 83 81.6 159
19 161 116 78.1 162
20 189 114 72.4 167
21 225 101 67.2 172
22 139 112 65.9 157
23 174 105 88.2 173
24 151 123 92.4 171
25 194 114 69.4 181# 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 2024-01-01 64 81 137
2 P0002 2024-01-10 36 69 98
3 P0003 2024-01-02 41 60 121
4 P0004 2024-01-31 67 74 129
5 P0005 2024-01-24 41 80 107
6 P0006 2024-01-19 94 82 100
7 P0007 2024-01-19 90 66 143
8 P0008 2024-01-03 47 85 126
9 P0009 2024-01-11 91 62 161
10 P0010 2024-01-27 69 74 152
11 P0011 2024-01-06 46 71 118
12 P0012 2024-01-10 54 89 119
13 P0013 2024-01-22 59 78 108
14 P0014 2024-01-07 78 93 112
15 P0015 2024-01-03 37 75 129
16 P0016 2024-01-16 53 80 115
17 P0017 2024-01-16 70 71 141
18 P0018 2024-01-02 38 67 129
19 P0019 2024-01-03 94 78 134
20 P0020 2024-01-17 35 82 121
# 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 2024-01-01 64 81 137
2 P0002 2024-01-10 36 69 98
3 P0003 2024-01-02 41 60 121
4 P0004 2024-01-31 67 74 129
5 P0005 2024-01-24 41 80 107
6 P0006 2024-01-19 94 82 100
7 P0007 2024-01-19 90 66 143
8 P0008 2024-01-03 47 85 126
9 P0009 2024-01-11 91 62 161
10 P0010 2024-01-27 69 74 152
11 P0011 2024-01-06 46 71 118
12 P0012 2024-01-10 54 89 119
13 P0013 2024-01-22 59 78 108
14 P0014 2024-01-07 78 93 112
15 P0015 2024-01-03 37 75 129
16 P0016 2024-01-16 53 80 115
17 P0017 2024-01-16 70 71 141
18 P0018 2024-01-02 38 67 129
19 P0019 2024-01-03 94 78 134
20 P0020 2024-01-17 35 82 121
21 P0021 2024-01-27 34 88 98
22 P0022 2024-01-16 48 86 129
23 P0023 2024-01-05 68 81 154
24 P0024 2024-01-14 74 64 107
25 P0025 2024-01-25 82 63 111
# 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 2024-01-01 64 81 137
2 P0002 2024-01-10 36 69 98
3 P0003 2024-01-02 41 60 121
4 P0004 2024-01-31 67 74 129
5 P0005 2024-01-24 41 80 107
6 P0006 2024-01-19 94 82 100
7 P0007 2024-01-19 90 66 143
8 P0008 2024-01-03 47 85 126
9 P0009 2024-01-11 91 62 161
10 P0010 2024-01-27 69 74 152
# 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 2024-01-01 64 81 137 86 98.2 100 140 120 70.6 181
2 P0002 2024-01-10 36 69 98 66 98.5 97 194 89 102. 158
3 P0003 2024-01-02 41 60 121 68 98.1 96 94 94 61.8 173
4 P0004 2024-01-31 67 74 129 63 98.8 98 207 123 73 174
5 P0005 2024-01-24 41 80 107 74 99.2 97 197 90 53.5 171
6 P0006 2024-01-19 94 82 100 84 98.7 98 183 109 36.5 159
7 P0007 2024-01-19 90 66 143 81 98.2 98 157 87 84.4 163
8 P0008 2024-01-03 47 85 126 66 99.6 98 156 82 79.7 168
9 P0009 2024-01-11 91 62 161 74 98.6 97 185 82 69.1 173
10 P0010 2024-01-27 69 74 152 70 98.6 97 205 124 67.7 169
# 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