top_curves_to_points: Pull the points from the top (1-alpha)% percent of curves.

In skgallagher/timeternR: A Pipeline to Analyze and Compare Infectious Disease Epidemics

Description

pulling out data points from curves that are ranked highest based on quantile function.

Usage

top_curves_to_points(
  x,
  alpha,
  tidy_dm,
  quantile_func = distance_depth_function,
  x_names_df = NULL,
  ...
)

Arguments

x	list or grouped_df containing curves, with index ordering associated with the x_names_df and rownames of tidy_dm
alpha	the proportion of curves to be removed before presenting all the points together. Takes value in [0, 1.0].
tidy_dm	a tidy_dist_mat distance matrix
quantile_func	function to calculate quantiles via the distance_matrix, we now expect this function to handle tidy_dist_mat objects and have a parameter called df_out which we can set as true. See distance_depth_function.tidy_dist_mat for an example.
x_names_df	Only used when x is a list. Group structure associated with the ordering of the items in the list x. Assume the naming structure for tidy_dm is the same as this data frame (can have different ordering).
...	additional parameters to be passed to the quantile_func. Please also see details for more information.

Details

See top_curves_to_points.list and top_curves_to_points.grouped_df for more details and commentary on expected parameters. top_curves_to_points.list requires an additional parameter - x_names_df.

Value

data frame from curves of the top values associated with the quantile_func

Examples

library(dplyr)
set.seed(1)
random_data_list <- lapply(1:5, function(x){data.frame(matrix(rnorm(10),
                                                              ncol = 2))})

dist_mat <- dist_matrix_innersq_direction(random_data_list,
                                position = 1:2,
                                verbose = FALSE)

combined_points_list <- quantile_curves_to_points(random_data_list,
                                               alpha = .2,
                                               dist_mat)

random_data_grouped <- random_data_list %>%
  do.call(rbind, .) %>%
  mutate(id = rep(1:5, each = 5)) %>%
  group_by(id)

combined_points_grouped <- quantile_curves_to_points(random_data_grouped,
                                                  alpha = .2,
                                                  dist_mat)

skgallagher/timeternR documentation built on Sept. 16, 2021, 7:21 p.m.