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
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
|
test_that("You can parition a skim_df", {
skimmed <- skim(iris)
input <- partition(skimmed)
expect_s3_class(input, "skim_list")
expect_length(input, 2)
expect_named(input, c("factor", "numeric"))
attrs <- attributes(input)
expect_equal(attrs$data_rows, 150)
expect_equal(attrs$data_cols, 5)
expect_identical(attrs$df_name, "`iris`")
expect_identical(attrs$base_skimmers, c("n_missing", "complete_rate"))
expect_identical(
attrs$skimmers_used,
list(
numeric = c("mean", "sd", "p0", "p25", "p50", "p75", "p100", "hist"),
factor = c("ordered", "n_unique", "top_counts")
)
)
# Subtables
expect_s3_class(input$factor, c("one_skim_df", "tbl_df", "tbl", "data.frame"))
expect_n_rows(input$factor, 1)
expect_n_columns(input$factor, 6)
expect_named(input$factor, c(
"skim_variable", "n_missing", "complete_rate", "ordered", "n_unique",
"top_counts"
))
expect_s3_class(input$numeric, c("one_skim_df", "tbl_df", "tbl", "data.frame"))
expect_n_rows(input$numeric, 4)
expect_n_columns(input$numeric, 11)
expect_named(input$numeric, c(
"skim_variable", "n_missing", "complete_rate", "mean",
"sd", "p0", "p25", "p50", "p75", "p100",
"hist"
))
})
test_that("Partitioning works in a round trip", {
skimmed <- skim(iris)
partitioned <- partition(skimmed)
input <- bind(partitioned)
expect_identical(input, skimmed)
})
test_that("You can yank a subtable from a skim_df", {
skimmed <- skim(iris)
input <- yank(skimmed, "numeric")
expect_s3_class(input, c("one_skim_df", "tbl_df", "tbl", "data.frame"))
expect_n_rows(input, 4)
expect_n_columns(input, 11)
expect_named(input, c(
"skim_variable", "n_missing", "complete_rate", "mean",
"sd", "p0", "p25", "p50", "p75", "p100",
"hist"
))
})
test_that("Partition is safe if some skimmers are missing", {
skimmed <- skim(iris)
reduced <- dplyr::select(skimmed, skim_variable, skim_type, n_missing)
partitioned <- partition(reduced)
expect_length(partitioned, 2)
expect_named(partitioned, c("factor", "numeric"))
expect_named(partitioned$numeric, c("skim_variable", "n_missing"))
})
test_that("Partition handles new columns", {
skimmed <- skim(iris)
expanded <- dplyr::mutate(
skimmed,
mean2 = numeric.mean^2,
complete2 = complete_rate^2
)
partitioned <- partition(expanded)
expect_named(partitioned$numeric, c(
"skim_variable", "n_missing", "complete_rate", "mean",
"sd", "p0", "p25", "p50", "p75", "p100",
"hist", "mean2", "complete2"
))
})
test_that("focus() matches select(data, skim_type, skim_variable, ...)", {
skimmed <- skim(iris)
expected <- dplyr::select(
skimmed, skim_type, skim_variable, n_missing
)
expect_equal(focus(skimmed, n_missing), expected, check.attributes = FALSE)
})
test_that("focus() does not allow dropping skim metadata columns", {
skimmed <- skim(iris)
expect_error(focus(skimmed, -skim_variable), "Cannot drop")
expect_error(focus(skimmed, -skim_type), "Cannot drop")
})
test_that("skim_to_wide() returns a deprecation warning", {
expect_warning(skim_to_wide(iris))
})
test_that("skim_to_list() returns a deprecation warning", {
expect_warning(skim_to_list(iris))
})
test_that("to_long() returns a long tidy data frame with 4 columns", {
skimmed_long <- to_long(iris)
# Statistics from the skim_df with values of NA are not included
expect_n_rows(skimmed_long, 45)
expect_equal(
names(skimmed_long),
c("skim_type", "skim_variable", "stat", "formatted")
)
expect_equal(length(unique(skimmed_long$stat)), 13)
expect_equal(length(unique(skimmed_long$skim_type)), 2)
expect_equal(length(unique(skimmed_long$skim_variable)), 5)
})
test_that("to_long() on a skim_df returns a long tidy df with 4 columns", {
skimmed_long <- to_long(skim(iris))
# Statistics from the skim_df with values of NA are not included
expect_n_rows(skimmed_long, 45)
expect_equal(
names(skimmed_long),
c("skim_type", "skim_variable", "stat", "formatted")
)
expect_equal(length(unique(skimmed_long$stat)), 13)
expect_equal(length(unique(skimmed_long$skim_type)), 2)
expect_equal(length(unique(skimmed_long$skim_variable)), 5)
})
test_that("to_long() on a df and a skim_df from same df are identical", {
expect_identical(to_long(skim(chickwts)), to_long(chickwts))
})
|
