-
Notifications
You must be signed in to change notification settings - Fork 51
/
col_is_posix.R
407 lines (369 loc) · 12.7 KB
/
col_is_posix.R
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
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
#------------------------------------------------------------------------------#
#
# _ _ _ _ _
# (_) | | | | | | | |
# _ __ ___ _ _ __ | |_ | |__ | | __ _ _ __ | | __
# | '_ \ / _ \ | || '_ \ | __|| '_ \ | | / _` || '_ \ | |/ /
# | |_) || (_) || || | | || |_ | |_) || || (_| || | | || <
# | .__/ \___/ |_||_| |_| \__||_.__/ |_| \__,_||_| |_||_|\_\
# | |
# |_|
#
# This file is part of the 'rstudio/pointblank' project.
#
# Copyright (c) 2017-2024 pointblank authors
#
# For full copyright and license information, please look at
# https://rstudio.github.io/pointblank/LICENSE.html
#
#------------------------------------------------------------------------------#
#' Do the columns contain `POSIXct` dates?
#'
#' @description
#'
#' The `col_is_posix()` validation function, the `expect_col_is_posix()`
#' expectation function, and the `test_col_is_posix()` test function all check
#' whether one or more columns in a table is of the R `POSIXct` date-time type.
#' Like many of the `col_is_*()`-type functions in **pointblank**, the only
#' requirement is a specification of the column names. The validation function
#' can be used directly on a data table or with an *agent* object (technically,
#' a `ptblank_agent` object) whereas the expectation and test functions can only
#' be used with a data table. Each validation step or expectation will operate
#' over a single test unit, which is whether the column is a `POSIXct`-type
#' column or not.
#'
#' @inheritParams col_vals_gt
#'
#' @return For the validation function, the return value is either a
#' `ptblank_agent` object or a table object (depending on whether an agent
#' object or a table was passed to `x`). The expectation function invisibly
#' returns its input but, in the context of testing data, the function is
#' called primarily for its potential side-effects (e.g., signaling failure).
#' The test function returns a logical value.
#'
#' @section Supported Input Tables:
#'
#' The types of data tables that are officially supported are:
#'
#' - data frames (`data.frame`) and tibbles (`tbl_df`)
#' - Spark DataFrames (`tbl_spark`)
#' - the following database tables (`tbl_dbi`):
#' - *PostgreSQL* tables (using the `RPostgres::Postgres()` as driver)
#' - *MySQL* tables (with `RMySQL::MySQL()`)
#' - *Microsoft SQL Server* tables (via **odbc**)
#' - *BigQuery* tables (using `bigrquery::bigquery()`)
#' - *DuckDB* tables (through `duckdb::duckdb()`)
#' - *SQLite* (with `RSQLite::SQLite()`)
#'
#' Other database tables may work to varying degrees but they haven't been
#' formally tested (so be mindful of this when using unsupported backends with
#' **pointblank**).
#'
#' @section Column Names:
#'
#' `columns` may be a single column (as symbol `a` or string `"a"`) or a vector
#' of columns (`c(a, b, c)` or `c("a", "b", "c")`). `{tidyselect}` helpers
#' are also supported, such as `contains("date")` and `where(is.double)`. If
#' passing an *external vector* of columns, it should be wrapped in `all_of()`.
#'
#' When multiple columns are selected by `columns`, the result will be an
#' expansion of validation steps to that number of columns (e.g.,
#' `c(col_a, col_b)` will result in the entry of two validation steps).
#'
#' Previously, columns could be specified in `vars()`. This continues to work,
#' but `c()` offers the same capability and supersedes `vars()` in `columns`.
#'
#' @section Actions:
#'
#' Often, we will want to specify `actions` for the validation. This argument,
#' present in every validation function, takes a specially-crafted list object
#' that is best produced by the [action_levels()] function. Read that function's
#' documentation for the lowdown on how to create reactions to above-threshold
#' failure levels in validation. The basic gist is that you'll want at least a
#' single threshold level (specified as either the fraction of test units
#' failed, or, an absolute value), often using the `warn_at` argument. This is
#' especially true when `x` is a table object because, otherwise, nothing
#' happens. For the `col_is_*()`-type functions, using `action_levels(warn_at =
#' 1)` or `action_levels(stop_at = 1)` are good choices depending on the
#' situation (the first produces a warning, the other will `stop()`).
#'
#' @section Labels:
#'
#' `label` may be a single string or a character vector that matches the number
#' of expanded steps. `label` also supports `{glue}` syntax and exposes the
#' following dynamic variables contextualized to the current step:
#'
#' - `"{.step}"`: The validation step name
#' - `"{.col}"`: The current column name
#'
#' The glue context also supports ordinary expressions for further flexibility
#' (e.g., `"{toupper(.step)}"`) as long as they return a length-1 string.
#'
#' @section Briefs:
#'
#' Want to describe this validation step in some detail? Keep in mind that this
#' is only useful if `x` is an *agent*. If that's the case, `brief` the agent
#' with some text that fits. Don't worry if you don't want to do it. The
#' *autobrief* protocol is kicked in when `brief = NULL` and a simple brief will
#' then be automatically generated.
#'
#' @section YAML:
#'
#' A **pointblank** agent can be written to YAML with [yaml_write()] and the
#' resulting YAML can be used to regenerate an agent (with [yaml_read_agent()])
#' or interrogate the target table (via [yaml_agent_interrogate()]). When
#' `col_is_posix()` is represented in YAML (under the top-level `steps` key as a
#' list member), the syntax closely follows the signature of the validation
#' function. Here is an example of how a complex call of `col_is_posix()` as a
#' validation step is expressed in R code and in the corresponding YAML
#' representation.
#'
#' R statement:
#'
#' ```r
#' agent %>%
#' col_is_posix(
#' columns = a,
#' actions = action_levels(warn_at = 0.1, stop_at = 0.2),
#' label = "The `col_is_posix()` step.",
#' active = FALSE
#' )
#' ```
#'
#' YAML representation:
#'
#' ```yaml
#' steps:
#' - col_is_posix:
#' columns: c(a)
#' actions:
#' warn_fraction: 0.1
#' stop_fraction: 0.2
#' label: The `col_is_posix()` step.
#' active: false
#' ```
#'
#' In practice, both of these will often be shorter as only the `columns`
#' argument requires a value. Arguments with default values won't be written to
#' YAML when using [yaml_write()] (though it is acceptable to include them with
#' their default when generating the YAML by other means). It is also possible
#' to preview the transformation of an agent to YAML without any writing to disk
#' by using the [yaml_agent_string()] function.
#'
#' @section Examples:
#'
#' The `small_table` dataset in the package has a `date_time` column. The
#' following examples will validate that that column is of the `POSIXct` and
#' `POSIXt` classes.
#'
#' ```{r}
#' small_table
#' ```
#'
#' ## A: Using an `agent` with validation functions and then `interrogate()`
#'
#' Validate that the column `date_time` is indeed a date-time column.
#'
#' ```r
#' agent <-
#' create_agent(tbl = small_table) %>%
#' col_is_posix(columns = date_time) %>%
#' interrogate()
#' ```
#'
#' Printing the `agent` in the console shows the validation report in the
#' Viewer. Here is an excerpt of validation report, showing the single entry
#' that corresponds to the validation step demonstrated here.
#'
#' \if{html}{
#' \out{
#' `r pb_get_image_tag(file = "man_col_is_posix_1.png")`
#' }
#' }
#'
#' ## B: Using the validation function directly on the data (no `agent`)
#'
#' This way of using validation functions acts as a data filter. Data is passed
#' through but should `stop()` if there is a single test unit failing. The
#' behavior of side effects can be customized with the `actions` option.
#'
#' ```{r}
#' small_table %>%
#' col_is_posix(columns = date_time) %>%
#' dplyr::slice(1:5)
#' ```
#'
#' ## C: Using the expectation function
#'
#' With the `expect_*()` form, we would typically perform one validation at a
#' time. This is primarily used in **testthat** tests.
#'
#' ```r
#' expect_col_is_posix(small_table, columns = date_time)
#' ```
#'
#' ## D: Using the test function
#'
#' With the `test_*()` form, we should get a single logical value returned to
#' us.
#'
#' ```{r}
#' small_table %>% test_col_is_posix(columns = date_time)
#' ```
#'
#' @family validation functions
#' @section Function ID:
#' 2-27
#'
#' @name col_is_posix
NULL
#' @rdname col_is_posix
#' @import rlang
#' @export
col_is_posix <- function(
x,
columns,
actions = NULL,
step_id = NULL,
label = NULL,
brief = NULL,
active = TRUE
) {
preconditions <- NULL
values <- NULL
# Capture the `columns` expression
columns <- rlang::enquo(columns)
# Get `columns` as a label
columns_expr <- as_columns_expr(columns)
# Resolve the columns based on the expression
columns <- resolve_columns(x = x, var_expr = columns, preconditions = NULL)
if (is_a_table_object(x)) {
secret_agent <-
create_agent(x, label = "::QUIET::") %>%
col_is_posix(
columns = tidyselect::all_of(columns),
label = label,
brief = brief,
actions = prime_actions(actions),
active = active
) %>%
interrogate()
return(x)
}
agent <- x
if (is.null(brief)) {
brief <-
generate_autobriefs(
agent, columns, preconditions, values, "col_is_posix"
)
}
# Normalize any provided `step_id` value(s)
step_id <- normalize_step_id(step_id, columns, agent)
# Get the next step number for the `validation_set` tibble
i_o <- get_next_validation_set_row(agent)
# Check `step_id` value(s) against all other `step_id`
# values in earlier validation steps
check_step_id_duplicates(step_id, agent)
# Add one or more validation steps based on the
# length of the `column` variable
label <- resolve_label(label, columns)
for (i in seq_along(columns)) {
agent <-
create_validation_step(
agent = agent,
assertion_type = "col_is_posix",
i_o = i_o,
columns_expr = columns_expr,
column = columns[i],
preconditions = NULL,
actions = covert_actions(actions, agent),
step_id = step_id[i],
label = label[[i]],
brief = brief[i],
active = active
)
}
agent
}
#' @rdname col_is_posix
#' @import rlang
#' @export
expect_col_is_posix <- function(
object,
columns,
threshold = 1
) {
fn_name <- "expect_col_is_posix"
vs <-
create_agent(tbl = object, label = "::QUIET::") %>%
col_is_posix(
columns = {{ columns }},
actions = action_levels(notify_at = threshold)
) %>%
interrogate() %>%
.$validation_set
x <- vs$notify
threshold_type <- get_threshold_type(threshold = threshold)
if (threshold_type == "proportional") {
failed_amount <- vs$f_failed
} else {
failed_amount <- vs$n_failed
}
# If several validations were performed serially (due to supplying
# multiple columns)
if (length(x) > 1 && any(x)) {
# Get the index (step) of the first failure instance
fail_idx <- which(x)[1]
# Get the correct, single `failed_amount` for the first
# failure instance
failed_amount <- failed_amount[fail_idx]
# Redefine `x` as a single TRUE value
x <- TRUE
} else {
x <- any(x)
fail_idx <- 1
}
if (inherits(vs$capture_stack[[1]]$warning, "simpleWarning")) {
warning(conditionMessage(vs$capture_stack[[1]]$warning))
}
if (inherits(vs$capture_stack[[1]]$error, "simpleError")) {
stop(conditionMessage(vs$capture_stack[[1]]$error))
}
act <- testthat::quasi_label(enquo(x), arg = "object")
column_text <- prep_column_text(vs$column[[fail_idx]])
col_type <- "POSIXct"
testthat::expect(
ok = identical(!as.vector(act$val), TRUE),
failure_message = glue::glue(
failure_message_gluestring(
fn_name = fn_name, lang = "en"
)
)
)
act$val <- object
invisible(act$val)
}
#' @rdname col_is_posix
#' @import rlang
#' @export
test_col_is_posix <- function(
object,
columns,
threshold = 1
) {
vs <-
create_agent(tbl = object, label = "::QUIET::") %>%
col_is_posix(
columns = {{ columns }},
actions = action_levels(notify_at = threshold)
) %>%
interrogate() %>%
.$validation_set
if (inherits(vs$capture_stack[[1]]$warning, "simpleWarning")) {
warning(conditionMessage(vs$capture_stack[[1]]$warning))
}
if (inherits(vs$capture_stack[[1]]$error, "simpleError")) {
stop(conditionMessage(vs$capture_stack[[1]]$error))
}
all(!vs$notify)
}