R/execute-checks.R
execute_checks.RdExecute the checks against a dataset to return a nested list.
execute_checks(ds, checks, origin)The data.frame to be checked. Required.
The list describing the check. Is the output of
The origin of the dataset.
Currently supports "csv" and "REDCap". Required.
load_checks(). Required.
# Step 0: define paths.
# So this package example executes on every machine, temp files are used.
# Replace the two paths for your specific project
path_data <- system.file("datasets/pt-event-biochemical.rds", package = "trawler")
path_checks <- system.file("checks/checks-biochemical.yml", package = "trawler")
# Step 1: load the check definitions and the dataset to test
ds_pt_event <- readr::read_rds(path_data)
checks <- load_checks(path_checks, origin = "REDCap")
# Step 2: execute the checks and save to an rds file
ds_pt_event |>
execute_checks(checks, origin = "REDCap")
#> $github_file_prefix
#> [1] "https://github.com/OuhscBbmc/validator-1/tree/main"
#>
#> $record_id_name
#> [1] "record_id"
#>
#> $record_id_link
#> [1] "<a href=\"https://bbmc.ouhsc.edu/redcap/redcap_v%s/DataEntry/index.php?pid=%s&arm=%s&id=%s&page=%s\" target=\"_blank\">%s</a>"
#>
#> $baseline_date_name
#> [1] "date_enrolled"
#>
#> $redcap_project_id
#> [1] 1612
#>
#> $redcap_version
#> [1] "10.5.1"
#>
#> $redcap_default_arm
#> [1] 1
#>
#> $redcap_codebook
#> [1] "https://bbmc.ouhsc.edu/redcap/redcap_v10.5.1/Design/data_dictionary_codebook.php?pid=1612"
#>
#> $smells
#> # A tibble: 11 × 12
#> check_name pass description priority debug bound_lower bound_upper
#> <chr> <lgl> <chr> <int> <lgl> <dbl> <dbl>
#> 1 females TRUE Proportion… 2 FALSE 0.4 0.6
#> 2 males TRUE Proportion… 2 FALSE 0.4 0.6
#> 3 age TRUE Mean parti… 2 FALSE 20 60
#> 4 serum_prealbumin_le… FALSE Mean serum… 2 FALSE 32 39
#> 5 serum_creatinine_le… FALSE Mean serum… 2 FALSE 3 15
#> 6 bmi_at_baseline FALSE Mean BMI i… 2 FALSE 18 24
#> 7 serum_cholesterol_l… TRUE Mean chole… 1 FALSE 100 140
#> 8 dialysis_adequacy TRUE Mean Kt/V … 1 FALSE 1.2 5
#> 9 nutritional_counsel… TRUE Most patie… 2 FALSE 0.85 0.99
#> 10 definitive_diagnosis TRUE The propor… 1 FALSE 1 1
#> 11 normalized_protein_… TRUE Mean Norma… 1 FALSE 0 1.2
#> # ℹ 5 more variables: bounds_template <chr>, value_template <chr>,
#> # equation <chr>, boundaries <chr>, value <dbl>
#>
#> $smell_status
#> [1] "11 smells have been sniffed. 3 violation(s) were found."
#>
#> $smells_inactive
#> # A tibble: 1 × 9
#> check_name description priority debug bound_lower bound_upper bounds_template
#> <chr> <chr> <int> <lgl> <dbl> <dbl> <chr>
#> 1 average_se… ??Units co… 1 FALSE 501 1200 [%.0f, %.0f]
#> # ℹ 2 more variables: value_template <chr>, equation <chr>
#>
#> $rules
#> # A tibble: 14 × 8
#> check_name violation_count error_message priority debug redcap_instrument
#> <chr> <int> <chr> <int> <lgl> <chr>
#> 1 baseline_prea… 10 Serum pre-al… 1 FALSE baseline_data
#> 2 missing_serum… 3 Relevant nut… 1 FALSE baseline_data
#> 3 serum_prealbu… 15 Baseline pre… 2 FALSE baseline_data, v…
#> 4 serum_prealbu… 0 Baseline pre… 2 FALSE baseline_data, v…
#> 5 serum_prealbu… 0 Baseline pre… 2 FALSE baseline_data, v…
#> 6 serum_prealbu… 0 serum prealb… 3 FALSE baseline_data, v…
#> 7 baseline_firs… 0 Serum prealb… 3 FALSE baseline_data, v…
#> 8 daily_first_v… 0 In-addition … 3 FALSE baseline_data, p…
#> 9 daily_protein… 0 npcr levels … 3 FALSE baseline_data, p…
#> 10 hospitalizati… 2 Patient was … 1 FALSE completion_proje…
#> 11 optimal_daily… 7 Daily protei… 2 FALSE completion_proje…
#> 12 recommended_n… 10 NPCR values … 2 FALSE completion_data
#> 13 npcr 1 NPCR at comp… 2 FALSE completion_data
#> 14 npcr_comparis… 2 NPCR at comp… 3 FALSE completion_data
#> # ℹ 2 more variables: passing_test <chr>, results <list>
#>
#> $rule_status
#> [1] "14 rules were examined. 8 rule(s) had at least 1 violation. 50 total violation(s) were found."
#>
#> $rules_inactive
#> # A tibble: 1 × 6
#> check_name error_message priority debug redcap_instrument passing_test
#> <chr> <chr> <int> <lgl> <chr> <chr>
#> 1 pre_albumin_levels pre_albumin … 3 FALSE visit_lab_date "function (…
#>
#> attr(,"class")
#> [1] "trawler_checks"
# Save to disk if needed
# ds_pt_event |>
# execute_checks(checks, origin = "REDCap") |>
# readr::write_rds("inst/derived/biochemical.rds")