Fixes #85

NAMESPACE

@@ -62,6 +62,7 @@ export(util_logistic_param_estimate)
 export(util_lognormal_param_estimate)
 export(util_negative_binomial_param_estimate)
 export(util_normal_param_estimate)
+export(util_pareto_estimate)
 importFrom(magrittr,"%>%")
 importFrom(rlang,":=")
 importFrom(rlang,.data)

NEWS.md

@@ -42,6 +42,7 @@ None
 35. Fix #82 - Add function `util_logistic_param_estimate()`
 36. Fix #83 - Add function `util_negative_binomial_param_estimate()`
 37. Fix #84 - Add function `util_normal_param_estimate()`
+38. Fix #85 - Add function `util_pareto_param_estimate()`
 
 ## Fixes and Minor Improvements
 1. Fix #30 - Move `crayon`, `rstudioapi`, and `cli` from Suggests to Imports due to `pillar`

R/est-param-pareto.R

@@ -0,0 +1,123 @@
+#' Estimate Pareto Parameters
+#'
+#' @family Parameter Estimation
+#' @family Pareto
+#'
+#' @author Steven P. Sanderson II, MPH
+#'
+#' @details This function will attempt to estimate the pareto shape and scale
+#' parameters given some vector of values.
+#'
+#' @description The function will return a list output by default, and  if the parameter
+#' `.auto_gen_empirical` is set to `TRUE` then the empirical data given to the
+#' parameter `.x` will be run through the `tidy_empirical()` function and combined
+#' with the estimated beta data.
+#'
+#' Two different methods of shape parameters are supplied:
+#' -  LSE
+#' -  MLE
+#'
+#' @param .x The vector of data to be passed to the function.
+#' @param .auto_gen_empirical This is a boolean value of TRUE/FALSE with default
+#' set to TRUE. This will automatically create the `tidy_empirical()` output
+#' for the `.x` parameter and use the `tidy_combine_distributions()`. The user
+#' can then plot out the data using `$combined_data_tbl` from the function output.
+#'
+#' @examples
+#' library(dplyr)
+#' library(ggplot2)
+#'
+#' x <- mtcars$mpg
+#' output <- util_pareto_estimate(x)
+#'
+#' output$parameter_tbl
+#'
+#' output$combined_data_tbl %>%
+#'   ggplot(aes(x = dx, y = dy, group = dist_type, color = dist_type)) +
+#'   geom_line() +
+#'   theme_minimal() +
+#'   theme(legend.position = "bottom")
+#'
+#' t <- tidy_pareto(50, 1, 1) %>% pull(y)
+#' util_pareto_estimate(t)$parameter_tbl
+#'
+#' @return
+#' A tibble/list
+#'
+#' @export
+#'
+
+util_pareto_estimate <- function(.x, .auto_gen_empirical = TRUE){
+
+    # Tidyeval ----
+    x_term <- as.numeric(.x)
+    minx <- min(x_term)
+    maxx <- max(x_term)
+    n <- length(x_term)
+    unique_terms <- length(unique(x_term))
+
+    # Checks ----
+    if (!is.vector(x_term, mode = "numeric") || is.factor(x_term)){
+        rlang::abort(
+            message = "'.x' must be a numeric vector.",
+            use_cli_format = TRUE
+        )
+    }
+
+    if (n < 2 || any(x_term <= 0) || unique_terms < 2){
+        rlang::abort(
+            message = "'.x' must contain at least two non-missing distinct values.
+      All values of '.x' must be positive.",
+            use_cli_format = TRUE
+        )
+    }
+
+    # Get params ----
+    # EnvStats
+    ppc <- 0.375
+    fhat <- stats::ppoints(n, a = ppc)
+    lse_coef <- stats::lm(log(1 - fhat) ~ log(sort(x_term)))$coefficients
+    lse_scale <- -lse_coef[[2]]
+    lse_shape <- exp(lse_coef[[1]]/lse_scale)
+
+    mle_shape <- min(x_term)
+    mle_scale <- n/sum(log(x_term/mle_shape))
+
+    # Return Tibble ----
+    if (.auto_gen_empirical){
+        te <- tidy_empirical(.x = x_term)
+        td <- tidy_pareto(.n = n, .shape = round(lse_shape, 3), .scale = round(lse_scale, 3))
+        combined_tbl <- tidy_combine_distributions(te, td)
+    }
+
+    ret <- dplyr::tibble(
+        dist_type = rep('Pareto', 2),
+        samp_size = rep(n, 2),
+        min = rep(minx, 2),
+        max = rep(maxx, 2),
+        method = c("LSE", "MLE"),
+        shape = c(lse_shape, mle_shape),
+        scale = c(lse_scale, mle_scale),
+        shape_ratio = c(shape/scale)
+    )
+
+    # Return ----
+    attr(ret, "tibble_type") <- "parameter_estimation"
+    attr(ret, "family") <- "pareto"
+    attr(ret, "x_term") <- .x
+    attr(ret, "n") <- n
+
+    if (.auto_gen_empirical){
+        output <- list(
+            combined_data_tbl = combined_tbl,
+            parameter_tbl     = ret
+        )
+    } else {
+        output <- list(
+            parameter_tbl = ret
+        )
+    }
+
+    return(output)
+
+}

docs/pkgdown.yml

@@ -3,7 +3,7 @@ pkgdown: 2.0.2
 pkgdown_sha: ~
 articles:
   getting-started: getting-started.html
-last_built: 2022-03-08T14:55Z
+last_built: 2022-03-08T15:18Z
 urls:
   reference: https://github.com/spsanderson/TidyDensity/reference
   article: https://github.com/spsanderson/TidyDensity/articles