## ----include = FALSE----------------------------------------------------------
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)

## -----------------------------------------------------------------------------
library(data.checker)

df <- data.frame(
  age = c(10, 11, 13, 15, 22, 34, 80),
  sex = c("M", "F", "M", "F", "M", "F", "M")
)

df

## -----------------------------------------------------------------------------
schema <- list(
  check_duplicates = FALSE,
  check_completeness = FALSE,
  columns = list(
    age = list(type = "integer", optional = FALSE),
    sex = list(type = "character", optional = FALSE)
  )
)

schema

## -----------------------------------------------------------------------------
validator <- data.checker::new_validator(
  data = df,
  schema = schema
)

## ----echo = FALSE-------------------------------------------------------------
anonymise_validator <- function(validator_object){
  
  validator_object[["log"]][[1]][["description"]] <-  "Date: 2025-01-01\nsysname: Windows\nrelease: 10 x64\nversion: \nnodename: \nmachine: \nlogin: username\nuser: username\neffective_user: username\nudomain: \nR version : R version 4.5.1 (2025-06-13 ucrt)\ndata.checker version: 0.0.0.9000\n"
  
  return(validator_object)
  
}

validator <- anonymise_validator(validator)

## -----------------------------------------------------------------------------
print(validator)

## -----------------------------------------------------------------------------
check_results <- data.checker::check(validator)

print(check_results)

## ----eval = FALSE-------------------------------------------------------------
# data.checker::export(check_results, file = "example.html", format = "html")

## ----eval = FALSE-------------------------------------------------------------
# data.checker::check_and_export(df, schema, file = "example.html", format = "html", hard_check = FALSE)

## -----------------------------------------------------------------------------
df <- data.frame(
  id = 1:10,
  age = c(10, 20, 30, 40, 50, 60, 70, 80, 90, 100),
  sex = c("M", "F", "M", "F", "M", "F", "M", "F", "M", "F"),
  country = factor(
    c("England", "England", "Wales", "Scotland", "Wales", "England", "Northern Ireland", "Wales", "Scotland", "Northern Ireland"),
    levels = c("England", "Scotland", "Wales", "Northern Ireland")),
  date = lubridate::ymd(c(
    "2021-01-01",
    "2021-02-01",
    "2021-02-01",
    "2021-03-01",
    "2021-03-01",
    "2021-03-01",
    "2021-04-01",
    "2021-04-01",
    "2021-04-01",
    "2021-05-01"
  ))
)

data_check_results <- data.checker::new_validator(schema = "example_schema.yaml", data = df) |> 
  data.checker::check()

## ----echo = FALSE-------------------------------------------------------------
data_check_results <- anonymise_validator(data_check_results)

## -----------------------------------------------------------------------------
print(data_check_results)

## -----------------------------------------------------------------------------
df <- data.frame(
  id = 1:10,
  age = c(10, 20, 30, 40, 50, 60, 70, 80, 90, 100),
  sex = c("M", "F", "M", "F", "M", "F", "M", "F", "M", "F")
)

schema <- list(
  check_duplicates = FALSE,
  check_completeness = FALSE,
  columns = list(
    id = list(type = "double", optional = FALSE),
    age = list(type = "double", optional = FALSE),
    sex = list(type = "character", optional = FALSE)
  )
)

data_check_results <- data.checker::new_validator(df, schema) |>
  data.checker::check() |>
  data.checker::add_check(description = "There are no males over 90 (tidy evaluation)", condition = !(sex == "M" & age > 90)) |>
  data.checker::add_check(description = "There are no males over 90 (standard evaluation)", condition = !(df$sex == "M" & df$age > 90))



## -----------------------------------------------------------------------------
data_check_results <- anonymise_validator(data_check_results)

## -----------------------------------------------------------------------------
print(data_check_results)

## -----------------------------------------------------------------------------
df <- data.frame(
  age = c(10, 11, 13, 15, 22, 34, 80),
  sex = c("M", "F", "M", "F", "M", "F", "M")
)

schema <- list(
  check_completeness = FALSE,
  check_duplicates = FALSE,
  columns = list(
    age = list(type = "integer", optional = FALSE),
    sex = list(type = "character", optional = FALSE)
  )
)

validator <- data.checker::new_validator(df, schema)

validator <- data.checker::add_qa_entry(
  validator, 
  description = "Example custom log entry",
  entry_type = "info"
)


## -----------------------------------------------------------------------------
validator <- anonymise_validator(validator)

## -----------------------------------------------------------------------------
print(validator)