This function uses a Large Language Model (LLM) to automatically classify variables in a dataset into quasi-identifiers, sensitive variables, numerical variables, and more, and passes the result to `createSdcObj()`. It optionally uses a codebook and policy context.
KI_createSdcObj(
dat,
codebook = NULL,
policy = c("open", "restricted", "confidential"),
model = "gpt-4",
api_key = Sys.getenv("OPENAI_API_KEY"),
...
)A data.frame containing the microdata.
Optional path to a codebook file (currently not parsed; placeholder for future use).
Data sharing policy context: `"open"` (default), `"restricted"`, or `"confidential"`.
The LLM model to use (default: `"gpt-4"`).
OpenAI API key, defaulting to the `OPENAI_API_KEY` environment variable.
Additional arguments passed to `createSdcObj()`.
An object of class `sdcMicroObj`.
if (FALSE) { # \dontrun{
data(testdata)
sdc <- KI_createSdcObj(dat = testdata, policy = "open")
sdc
} # }