Create a decision Curve
Usage
create_decision_curve(
probs,
reals,
by = 0.01,
stratified_by = "probability_threshold",
chosen_threshold = NA,
interactive = TRUE,
color_values = c("#1b9e77", "#d95f02", "#7570b3", "#e7298a", "#07004D", "#E6AB02",
"#FE5F55", "#54494B", "#006E90", "#BC96E6", "#52050A", "#1F271B", "#BE7C4D",
"#63768D", "#08A045", "#320A28", "#82FF9E", "#2176FF", "#D1603D", "#585123"),
size = NULL,
type = "conventional",
min_p_threshold = 0,
max_p_threshold = 1
)Arguments
- probs
a list of vectors of estimated probabilities (one for each model or one for each population)
- reals
a list of vectors of binary outcomes (one for each population)
- by
number: increment of the sequence.
- stratified_by
Performance Metrics can be stratified by Probability Threshold or alternatively by Predicted Positives Condition Rate
- chosen_threshold
a chosen threshold to display (for non-interactive)
- interactive
whether the plot should be interactive plots
- color_values
color palette
- size
the size of the curve
- type
What type of Decision Curve, default choice is "conventional". Alternatives are "interventions avoided" and "combined" for both "conventional" and "interventions avoided" on the same view.
- min_p_threshold
The minimum Probability Threshold value to be displayed
- max_p_threshold
The maximum Probability Threshold value to be displayed
Examples
if (FALSE) {
create_decision_curve(
probs = list(example_dat$estimated_probabilities),
reals = list(example_dat$outcome)
)
create_decision_curve(
probs = list(example_dat$estimated_probabilities),
reals = list(example_dat$outcome,
type = "interventions avoided"
)
)
create_decision_curve(
probs = list(example_dat$estimated_probabilities),
reals = list(example_dat$outcome,
type = "combined"
)
)
create_decision_curve(
probs = list(
"First Model" = example_dat$estimated_probabilities,
"Second Model" = example_dat$random_guess
),
reals = list(example_dat$outcome)
)
create_decision_curve(
probs = list(
"First Model" = example_dat$estimated_probabilities,
"Second Model" = example_dat$random_guess
),
reals = list(example_dat$outcome),
type = "interventions avoided"
)
create_decision_curve(
probs = list(
"First Model" = example_dat$estimated_probabilities,
"Second Model" = example_dat$random_guess
),
reals = list(example_dat$outcome),
type = "combined"
)
create_decision_curve(
probs = list(
"train" = example_dat %>%
dplyr::filter(type_of_set == "train") %>%
dplyr::pull(estimated_probabilities),
"test" = example_dat %>% dplyr::filter(type_of_set == "test") %>%
dplyr::pull(estimated_probabilities)
),
reals = list(
"train" = example_dat %>% dplyr::filter(type_of_set == "train") %>%
dplyr::pull(outcome),
"test" = example_dat %>% dplyr::filter(type_of_set == "test") %>%
dplyr::pull(outcome)
)
)
create_decision_curve(
probs = list(
"train" = example_dat %>%
dplyr::filter(type_of_set == "train") %>%
dplyr::pull(estimated_probabilities),
"test" = example_dat %>% dplyr::filter(type_of_set == "test") %>%
dplyr::pull(estimated_probabilities)
),
reals = list(
"train" = example_dat %>% dplyr::filter(type_of_set == "train") %>%
dplyr::pull(outcome),
"test" = example_dat %>% dplyr::filter(type_of_set == "test") %>%
dplyr::pull(outcome)
),
type = "interventions avoided"
)
create_decision_curve(
probs = list(
"train" = example_dat %>%
dplyr::filter(type_of_set == "train") %>%
dplyr::pull(estimated_probabilities),
"test" = example_dat %>% dplyr::filter(type_of_set == "test") %>%
dplyr::pull(estimated_probabilities)
),
reals = list(
"train" = example_dat %>% dplyr::filter(type_of_set == "train") %>%
dplyr::pull(outcome),
"test" = example_dat %>% dplyr::filter(type_of_set == "test") %>%
dplyr::pull(outcome)
),
type = "combined"
)
}