# 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 2024-01-23 20 82 133
2 P0002 2024-01-31 35 81 132
3 P0003 2024-01-06 34 64 117
4 P0004 2024-01-09 77 81 133
5 P0005 2024-01-06 74 46 109
6 P0006 2024-01-23 71 64 118
7 P0007 2024-01-25 87 69 118
8 P0008 2024-01-08 91 71 126
9 P0009 2024-01-23 32 60 108
10 P0010 2024-01-30 65 63 100
# 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 2024-01-23 20 82 133
2 P0002 2024-01-31 35 81 132
3 P0003 2024-01-06 34 64 117
4 P0004 2024-01-09 77 81 133
5 P0005 2024-01-06 74 46 109
6 P0006 2024-01-23 71 64 118
7 P0007 2024-01-25 87 69 118
8 P0008 2024-01-08 91 71 126
9 P0009 2024-01-23 32 60 108
10 P0010 2024-01-30 65 63 100
11 P0011 2024-01-02 83 85 131
12 P0012 2024-01-03 70 79 107
13 P0013 2024-01-07 74 86 139
14 P0014 2024-01-15 47 91 102
15 P0015 2024-01-17 58 82 110
16 P0016 2024-01-30 25 63 132
17 P0017 2024-01-30 71 68 134
18 P0018 2024-01-05 43 80 89
19 P0019 2024-01-26 66 67 114
20 P0020 2024-01-19 56 71 140
21 P0021 2024-01-28 85 76 114
22 P0022 2024-01-17 43 80 109
23 P0023 2024-01-12 37 63 121
24 P0024 2024-01-08 18 78 127
25 P0025 2024-01-30 30 74 137
blood_pressure_dia temperature oxygen_saturation
1 69 98.3 95
2 63 99.0 100
3 85 97.5 96
4 84 98.5 100
5 79 99.2 97
6 76 98.8 99
7 70 98.7 96
8 73 98.0 97
9 78 98.6 100
10 59 99.2 99
11 84 98.2 96
12 81 99.4 97
13 97 98.8 99
14 72 97.7 97
15 78 98.1 95
16 68 98.2 96
17 85 98.4 97
18 86 99.1 95
19 75 98.5 97
20 88 98.6 100
21 77 99.5 101
22 85 97.4 99
23 76 99.1 98
24 62 98.1 100
25 78 98.5 98
cholesterol glucose weight_kg height_cm
1 239 112 66.3 173
2 185 99 90.9 165
3 167 80 88.8 168
4 174 65 75.7 175
5 179 85 94.8 162
6 198 99 55.7 162
7 147 113 84.0 165
8 186 118 79.4 193
9 173 139 72.4 170
10 180 112 73.7 174
11 210 100 46.5 165
12 155 107 80.6 174
13 178 124 80.5 171
14 250 102 80.8 172
15 159 130 77.9 153
16 165 81 60.3 160
17 232 127 82.7 167
18 167 132 47.0 163
19 167 112 84.7 162
20 211 88 65.9 168
21 167 98 76.2 172
22 174 94 77.7 174
23 172 112 63.9 169
24 240 124 72.2 195
25 232 96 72.3 164# 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 2024-01-23 20 82 133
2 P0002 2024-01-31 35 81 132
3 P0003 2024-01-06 34 64 117
4 P0004 2024-01-09 77 81 133
5 P0005 2024-01-06 74 46 109
6 P0006 2024-01-23 71 64 118
7 P0007 2024-01-25 87 69 118
8 P0008 2024-01-08 91 71 126
9 P0009 2024-01-23 32 60 108
10 P0010 2024-01-30 65 63 100
11 P0011 2024-01-02 83 85 131
12 P0012 2024-01-03 70 79 107
13 P0013 2024-01-07 74 86 139
14 P0014 2024-01-15 47 91 102
15 P0015 2024-01-17 58 82 110
16 P0016 2024-01-30 25 63 132
17 P0017 2024-01-30 71 68 134
18 P0018 2024-01-05 43 80 89
19 P0019 2024-01-26 66 67 114
20 P0020 2024-01-19 56 71 140
# 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 2024-01-23 20 82 133
2 P0002 2024-01-31 35 81 132
3 P0003 2024-01-06 34 64 117
4 P0004 2024-01-09 77 81 133
5 P0005 2024-01-06 74 46 109
6 P0006 2024-01-23 71 64 118
7 P0007 2024-01-25 87 69 118
8 P0008 2024-01-08 91 71 126
9 P0009 2024-01-23 32 60 108
10 P0010 2024-01-30 65 63 100
11 P0011 2024-01-02 83 85 131
12 P0012 2024-01-03 70 79 107
13 P0013 2024-01-07 74 86 139
14 P0014 2024-01-15 47 91 102
15 P0015 2024-01-17 58 82 110
16 P0016 2024-01-30 25 63 132
17 P0017 2024-01-30 71 68 134
18 P0018 2024-01-05 43 80 89
19 P0019 2024-01-26 66 67 114
20 P0020 2024-01-19 56 71 140
21 P0021 2024-01-28 85 76 114
22 P0022 2024-01-17 43 80 109
23 P0023 2024-01-12 37 63 121
24 P0024 2024-01-08 18 78 127
25 P0025 2024-01-30 30 74 137
# 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 2024-01-23 20 82 133
2 P0002 2024-01-31 35 81 132
3 P0003 2024-01-06 34 64 117
4 P0004 2024-01-09 77 81 133
5 P0005 2024-01-06 74 46 109
6 P0006 2024-01-23 71 64 118
7 P0007 2024-01-25 87 69 118
8 P0008 2024-01-08 91 71 126
9 P0009 2024-01-23 32 60 108
10 P0010 2024-01-30 65 63 100
# 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 2024-01-23 20 82 133 69 98.3 95 239 112 66.3 173
2 P0002 2024-01-31 35 81 132 63 99 100 185 99 90.9 165
3 P0003 2024-01-06 34 64 117 85 97.5 96 167 80 88.8 168
4 P0004 2024-01-09 77 81 133 84 98.5 100 174 65 75.7 175
5 P0005 2024-01-06 74 46 109 79 99.2 97 179 85 94.8 162
6 P0006 2024-01-23 71 64 118 76 98.8 99 198 99 55.7 162
7 P0007 2024-01-25 87 69 118 70 98.7 96 147 113 84 165
8 P0008 2024-01-08 91 71 126 73 98 97 186 118 79.4 193
9 P0009 2024-01-23 32 60 108 78 98.6 100 173 139 72.4 170
10 P0010 2024-01-30 65 63 100 59 99.2 99 180 112 73.7 174
# 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