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

## ----setup--------------------------------------------------------------------
library(mariposa)
library(dplyr)
data(survey_data)

## ----eval = FALSE-------------------------------------------------------------
# # Read an SPSS file
# data <- read_spss("survey_2024.sav")

## ----eval = FALSE-------------------------------------------------------------
# # Tagged NAs are on by default
# data <- read_spss("survey.sav", tag_na = TRUE)
# 
# # Turn off if you just want regular NAs
# data <- read_spss("survey.sav", tag_na = FALSE)

## ----eval = FALSE-------------------------------------------------------------
# # See a breakdown of missing types
# na_frequencies(data, q1, q2, q3)
# 
# # Convert tagged NAs back to their original codes
# data_with_codes <- untag_na(data, q1, q2)
# 
# # Remove tags but keep NAs
# data_clean <- strip_tags(data)

## ----eval = FALSE-------------------------------------------------------------
# data <- read_stata("survey.dta")

## ----eval = FALSE-------------------------------------------------------------
# # SAS data file
# data <- read_sas("survey.sas7bdat")
# 
# # With a separate catalog file for labels
# data <- read_sas("survey.sas7bdat", catalog_file = "formats.sas7bcat")
# 
# # SAS transport format
# data <- read_xpt("survey.xpt")

## ----eval = FALSE-------------------------------------------------------------
# data <- read_por("survey.por")

## ----eval = FALSE-------------------------------------------------------------
# # Basic Excel import
# data <- read_xlsx("survey.xlsx")
# 
# # Excel file with label metadata (exported by write_xlsx)
# data <- read_xlsx("survey.xlsx", label_sheet = "labels")

## ----eval = FALSE-------------------------------------------------------------
# codebook(survey_data)

## -----------------------------------------------------------------------------
# Find variables related to "trust"
find_var(survey_data, "trust")

# Search by variable label
find_var(survey_data, "satisfaction", search = "label")

## ----eval = FALSE-------------------------------------------------------------
# # Basic export
# write_spss(survey_data, "output.sav")
# 
# # With compression options
# write_spss(survey_data, "output.sav", compress = "zsav")  # smaller file

## ----eval = FALSE-------------------------------------------------------------
# write_stata(survey_data, "output.dta")

## ----eval = FALSE-------------------------------------------------------------
# write_xpt(survey_data, "output.xpt")

## ----eval = FALSE-------------------------------------------------------------
# # Export data only
# write_xlsx(survey_data, "output.xlsx")
# 
# # Export a codebook
# cb <- codebook(survey_data)
# write_xlsx(cb, "codebook.xlsx")
# 
# # Export frequency tables
# freq <- frequency(survey_data, education, employment)
# write_xlsx(freq, "frequencies.xlsx")

## ----eval = FALSE-------------------------------------------------------------
# # 1. Import from SPSS
# original <- read_spss("survey.sav")
# 
# # 2. Work with the data in R
# processed <- original %>%
#   filter(age >= 18) %>%
#   mutate(age_group = rec(., age, rules = "18:29=1; 30:49=2; 50:99=3"))
# 
# # 3. Export back to SPSS
# write_spss(processed, "survey_processed.sav")
# 
# # Variable labels, value labels, and missing value definitions
# # are all preserved in the exported file.