In jared-fowler/prettyglm: Pretty Summaries of Generalized Linear Model Coefficients

The function one_way_ave() creates one-way actual vs expect plots.

Pre-processing

A critical step for this package to work is to set all categorical predictors as factors.

library(dplyr)
library(prettyglm)
data('titanic')

# Easy way to convert multiple columns to a factor.
columns_to_factor <- c('Pclass',
                       'Sex',
                       'Cabin', 
                       'Embarked',
                       'Cabintype')
meanage <- base::mean(titanic$Age, na.rm=T)
titanic  <- titanic  %>%
  dplyr::mutate_at(columns_to_factor, list(~factor(.))) %>%
  dplyr::mutate(Age =base::ifelse(is.na(Age)==T,meanage,Age)) %>% 
  dplyr::mutate(Age_Cat = prettyglm::cut3(Age, levels.mean = TRUE, g =10))

# Build a basic glm
survival_model <- stats::glm(Survived ~ Pclass + 
                                        Sex + 
                                        Fare +
                                        Age_Cat +
                                        Embarked + 
                                        SibSp + 
                                        Parch, 
                             data = titanic, 
                             family = binomial(link = 'logit'))

Visualising one-way performance {.tabset}

Continuous Variable

For continuous variables one_way_ave will bucket value into 30 buckets by default, and plot the density on a dual axis.

one_way_ave(feature_to_plot = 'Age',
            model_object = survival_model,
            target_variable = 'Survived',
            data_set = titanic,
            upper_percentile_to_cut = 0.1,
            lower_percentile_to_cut = 0.1)

Discrete Variable

one_way_ave(feature_to_plot = 'Cabintype',
            model_object = survival_model,
            target_variable = 'Survived',
            data_set = titanic)

Customing one-way performance plots {.tabset}

Faceting

You can facet the one_way_ave plot by providing a variable to facet by in facetby.

one_way_ave(feature_to_plot = 'Age',
            model_object = survival_model,
            target_variable = 'Survived',
            facetby = 'Sex',
            data_set = titanic,
            upper_percentile_to_cut = 0.1,
            lower_percentile_to_cut = 0.1)

Custom Predict Function

By default one_way_ave uses \link[stats]{predict.glm}. If you would like to use one_way_ave with another model type (which is not compatible with predict.glm), or provide modified predictions, one_way_ave allows a custom prediction function.

This function must return a data.frame with two columns: "Actual_Values" and "Predicted_Values".

# Custom Predict Function and facet
a_custom_predict_function <- function(target, model_object, dataset){
  dataset <- base::as.data.frame(dataset)
  Actual_Values <- dplyr::pull(dplyr::select(dataset, tidyselect::all_of(c(target))))
  if(class(Actual_Values) == 'factor'){
    Actual_Values <- base::as.numeric(as.character(Actual_Values))
  }
  Predicted_Values <- base::as.numeric(stats::predict(model_object, dataset, type='response'))

  to_return <-  base::data.frame(Actual_Values = Actual_Values,
                                 Predicted_Values = Predicted_Values)

  to_return <- to_return %>%
    dplyr::mutate(Predicted_Values = base::ifelse(Predicted_Values > 0.4,0.4,Predicted_Values))
  return(to_return)
}

one_way_ave(feature_to_plot = 'Age',
            model_object = survival_model,
            target_variable = 'Survived',
            data_set = titanic,
            upper_percentile_to_cut = 0.1,
            lower_percentile_to_cut = 0.1,
            predict_function = a_custom_predict_function)

jared-fowler/prettyglm documentation built on Feb. 4, 2024, 6:41 p.m.