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

## ----setup--------------------------------------------------------------------
library(scrutr)

## -----------------------------------------------------------------------------
result <- inspect(CO2)
result

## -----------------------------------------------------------------------------
result <- inspect(CO2, nrow = TRUE)

## -----------------------------------------------------------------------------
data_list <- list(
  cars = cars,
  mtcars = mtcars[, c("mpg", "hp", "wt", "speed")  |> intersect(names(mtcars))],
  iris = iris
)

# Which variables are in which datasets?
vars_detect(data_list)

## -----------------------------------------------------------------------------
# Use two datasets that share some columns
shared_list <- list(
  df1 = data.frame(x = 1:3, y = c("a", "b", "c"), stringsAsFactors = FALSE),
  df2 = data.frame(x = c(1.1, 2.2, 3.3), y = c("d", "e", "f"), stringsAsFactors = FALSE)
)

vars_compclasses(shared_list)

## ----eval = FALSE-------------------------------------------------------------
# # Create a temporary folder with example datasets
# mydir <- file.path(tempdir(), "scrutr_demo")
# dir.create(mydir, showWarnings = FALSE)
# 
# saveRDS(cars, file.path(mydir, "cars.rds"))
# saveRDS(mtcars, file.path(mydir, "mtcars.rds"))
# saveRDS(iris, file.path(mydir, "iris.rds"))
# 
# # Run the full inspection pipeline
# inspect_vars(
#   input_path = mydir,
#   output_path = mydir,
#   output_label = "demo",
#   considered_extensions = "rds"
# )
# 
# # The output Excel file contains multiple sheets:
# # dims, inspect_tot, one sheet per dataset, vars_detect, vars_compclasses, etc.
# list.files(mydir, pattern = "\\.xlsx$")

## ----eval = FALSE-------------------------------------------------------------
# convert_all(
#   input_folderpath = mydir,
#   considered_extensions = "rds",
#   to = "csv",
#   output_folderpath = file.path(mydir, "csv")
# )

## ----eval = FALSE-------------------------------------------------------------
# # 1. Generate a mask template
# mask_convert_r(output_path = mydir)
# 
# # 2. Edit the mask in Excel, then:
# convert_r(
#   mask_filepath = file.path(mydir, "mask_convert_r.xlsx"),
#   output_path = mydir
# )

## -----------------------------------------------------------------------------
# Find duplicates in a data frame
df <- data.frame(id = c(1, 2, 2, 3, 3, 3), value = letters[1:6])
dupl_show(df, "id")

## -----------------------------------------------------------------------------
# Check a left join for key issues
left_df <- data.frame(key = c("a", "b", "c"))
right_df <- data.frame(key = c("a", "b", "b", "d"), val = 1:4)
ljoin_checks(left_df, right_df, "key")

## -----------------------------------------------------------------------------
paths <- c("data/raw/2024/file1.csv", "data/raw/2024/file2.csv")

# Keep only the first 2 levels
path_move(paths, "/", 2)

# Remove the last level (filename)
path_move(paths, "/", -1)