crosstab: Weighted Cross Tabulation

In laresbernardo/lares: Analytics & Machine Learning Sidekick

Weighted Cross Tabulation

Description

A cross-tabulation function with output similar to STATA, tidy friendly, with weighting possibility.

Usage

crosstab(
  df,
  ...,
  wt = NULL,
  prow = FALSE,
  pcol = FALSE,
  pall = FALSE,
  decimals = 2,
  rm.na = FALSE,
  total = TRUE,
  order = TRUE
)

Arguments

df	Data.frame.
...	Variables. Dependent and independent variables.
wt	Variable, numeric. Weights.
prow, pcol, pall	Boolean. Calculate percent values for rows, columns, or the whole table, respectively.
decimals	Integer. How many decimals should be returned?
rm.na	Boolean. Remove NA values?
total	Boolean. Return total values column?
order	Boolean. Sort columns and rows by frequencies? Else, will be sorted alphabetically

Value

data.frame. Result of crossing the variables provided in ... and counting how many observations (rows) fall into each criteria.

See Also

Other Exploratory: corr_cross(), corr_var(), df_str(), distr(), freqs_df(), freqs_list(), freqs_plot(), freqs(), lasso_vars(), missingness(), plot_cats(), plot_df(), plot_nums(), tree_var()

Examples

data(dft) # Titanic dataset
crosstab(dft, Survived, Pclass, total = FALSE)
# Show values in percentages
crosstab(dft, Pclass, Survived, prow = TRUE)
crosstab(dft, Pclass, Survived, pall = TRUE)
# Weighted by another variable
crosstab(dft, Survived, Pclass, wt = Fare, prow = TRUE)

laresbernardo/lares documentation built on April 19, 2024, 9:40 p.m.