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

## ----base---------------------------------------------------------------------
base <- weighting_spec(sample_one, base_weights = pw) |>
  step_unknown_eligibility(unknown = unknown_elig, by = "region",
                           cluster = "household_id") |>
  step_drop_ineligible(ineligible = ineligible) |>
  step_nonresponse(respondent = hh_responded, method = "weighting_class",
                   by = "region", cluster = "household_id") |>
  step_select_within(prob = p_within)

## ----boost, eval = requireNamespace("xgboost", quietly = TRUE)----------------
fit_boost <- base |>
  step_nonresponse(respondent = responded, method = "propensity",
                   formula = ~ region + sex + age, engine = "boost",
                   num_classes = 5) |>
  prep()

## ----crossfit, eval = requireNamespace("xgboost", quietly = TRUE)-------------
fit_cf <- base |>
  step_nonresponse(respondent = responded, method = "propensity",
                   formula = ~ region + sex + age, engine = "boost",
                   num_classes = 5, crossfit = 5, crossfit_seed = 1) |>
  prep()

## ----crossfit-deff, eval = requireNamespace("xgboost", quietly = TRUE)--------
c(in_sample = design_effect(collect_weights(fit_boost)$.weight)$deff,
  crossfit  = design_effect(collect_weights(fit_cf)$.weight)$deff)

## ----modelcal, eval = requireNamespace("xgboost", quietly = TRUE)-------------
fit_mc <- weighting_spec(sample_survey, base_weights = pw) |>
  step_nonresponse(respondent = responded, method = "weighting_class",
                   by = "region") |>
  step_model_calibration(
    x_formula  = ~ region + sex,
    models     = list(income = y_model(income ~ age + sex + region,
                                       engine = "boost")),
    population = population, crossfit = 5, crossfit_seed = 1) |>
  prep()

fit_mc$steps[[2]]$diagnostics

## ----ridge--------------------------------------------------------------------
pop_totals <- c("(Intercept)" = nrow(population),
                regionSouth = sum(population$region == "South"),
                regionEast  = sum(population$region == "East"),
                regionWest  = sum(population$region == "West"),
                sexM        = sum(population$sex == "M"))

fit_ridge <- weighting_spec(sample_survey, base_weights = pw) |>
  step_nonresponse(respondent = responded, method = "weighting_class",
                   by = "region") |>
  step_calibrate(method = "linear", formula = ~ region + sex,
                 totals = pop_totals, penalty = 1) |>
  prep()

fit_ridge$steps[[2]]$diagnostics

## ----potter-------------------------------------------------------------------
trimmed_tukey <- base |>
  step_nonresponse(respondent = responded, method = "weighting_class",
                   by = c("region", "sex")) |>
  step_trim_weights(method = "tukey") |>
  prep()

trimmed_potter <- base |>
  step_nonresponse(respondent = responded, method = "weighting_class",
                   by = c("region", "sex")) |>
  step_trim_weights(method = "potter") |>
  prep()

trimmed_tukey$steps[[6]]$diagnostics[, c("method", "upper", "n_capped")]
trimmed_potter$steps[[6]]$diagnostics[, c("method", "upper", "n_capped")]