1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
|
# Preparations
df1 <- data.frame(
id = c(1, 2, 3, 1, 3),
year = c(2022, 2022, 2022, 2022, 2000),
item1 = c(NA, 1, 1, 2, 3),
item2 = c(NA, 1, 1, 2, 3),
item3 = c(NA, 1, 1, 2, 3)
)
expected1 <- data.frame(
Row = c(1, 4, 3, 5),
id = c(1, 1, 3, 3),
year = c(2022, 2022, 2022, 2000),
item1 = c(NA, 2, 1, 3),
item2 = c(NA, 2, 1, 3),
item3 = c(NA, 2, 1, 3),
count_na = c(3, 0, 0, 0)
)
expected2 <- data.frame(
Row = c(1, 4),
id = c(1, 1),
year = c(2022, 2022),
item1 = c(NA, 2),
item2 = c(NA, 2),
item3 = c(NA, 2),
count_na = c(3, 0)
)
# Testing
test_that("data_duplicated basic", {
x <- data_duplicated(df1, select = "id")
rownames(x) <- NULL
expect_equal(
x,
expected1
)
})
test_that("data_duplicated unquoted", {
x <- data_duplicated(df1, select = id)
rownames(x) <- NULL
expect_equal(
x,
expected1
)
})
test_that("data_duplicated vector", {
x <- data_duplicated(df1, select = 1)
rownames(x) <- NULL
expect_equal(
x,
expected1
)
})
test_that("data_duplicated select-helper", {
x <- data_duplicated(df1, select = contains("id"))
rownames(x) <- NULL
expect_equal(
x,
expected1
)
})
test_that("data_duplicated multiple IDs", {
x <- data_duplicated(df1, select = c("id", "year"))
rownames(x) <- NULL
expect_equal(
x,
expected2
)
})
test_that("data_duplicated multiple IDs formula", {
x <- data_duplicated(df1, select = ~ id + year)
rownames(x) <- NULL
expect_equal(
x,
expected2
)
})
test_that("data_duplicated multiple IDs vector", {
x <- data_duplicated(df1, select = 1:2)
rownames(x) <- NULL
expect_equal(
x,
expected2
)
})
test_that("data_unique works with groups", {
df <- data.frame(
g = c(1, 1, 2, 2),
x = c(1, 1, 2, 1)
)
df <- data_group(df, "g")
expected <- data.frame(
Row = 1:2,
g = c(1, 1),
x = c(1, 1),
count_na = c(0, 0)
)
expected <- data_group(expected, "g")
expect_identical(data_duplicated(df, "x"), expected, ignore_attr = TRUE)
})
|
