roc_plot {promor}

ROC plot

Description

This function generates Receiver Operating Characteristic (ROC) curves to evaluate models

Usage

roc_plot(
  probability_list,
  split_df,
  ...,
  multiple_plots = TRUE,
  text_size = 10,
  palette = "viridis",
  save = FALSE,
  file_path = NULL,
  file_name = "ROC_plot",
  file_type = "pdf",
  plot_width = 7,
  plot_height = 7,
  dpi = 80
)

Arguments

probability_list

A probability_list object from performing test_models with type = "prob".

split_df

A split_df object from performing split_data

...

Additional arguments to be passed on to roc.

multiple_plots

Logical. If FALSE plots all ROC curves representing algorithms included in the probability_list in a single plot.

text_size

Text size for plot labels, axis labels etc. Default is 10.

palette

Viridis color palette option for plots. Default is "viridis". See viridis for available options.

save

Logical. If TRUE saves a copy of the plot in the directory provided in file_path.

file_path

A string containing the directory path to save the file.

file_name

File name to save the plot. Default is "ROC_plot."

file_type

File type to save the plot. Default is "pdf".

plot_width

Width of the plot. Default is 7.

plot_height

Height of the plot. Default is 7.

dpi

Plot resolution. Default is 80.

Details

• roc_plot first uses probabilities generated during test_models to build a ROC object.

• Next, relevant information is extracted from the ROC object to plot the ROC curves.

Value

A ggplot2 object.

Author(s)

Chathurani Ranathunge

See Also

• test_models

• roc

Examples

## Create a model_df object
covid_model_df <- pre_process(covid_fit_df, covid_norm_df)

## Split the data frame into training and test data sets
covid_split_df <- split_data(covid_model_df)

## Fit models using the default list of machine learning (ML) algorithms
covid_model_list <- train_models(covid_split_df)

# Test a list of models on a test data set and output class probabilities,
covid_prob_list <- test_models(covid_model_list, covid_split_df, type = "prob")

## Plot ROC curves separately for each ML algorithm
roc_plot(covid_prob_list, covid_split_df)

## Plot all ROC curves in one plot
roc_plot(covid_prob_list, covid_split_df, multiple_plots = FALSE)

## Change color palette
roc_plot(covid_prob_list, covid_split_df, palette = "plasma")