wpd_threshold: chooses threshold for a harmony table

In Sayani07/gravitas: Explore Probability Distributions for Bivariate Temporal Granularities

chooses threshold for a harmony table

Description

chooses threshold for a harmony table

Usage

wpd_threshold(
  .data,
  harmony_tbl = NULL,
  response = NULL,
  quantile_prob = seq(0.01, 0.99, 0.01),
  dist_ordered = TRUE,
  lambda = 0.67,
  nperm = 20,
  use_perm = TRUE,
  probs = c(0.9, 0.95, 0.99),
  nsamp = 100,
  create_harmony_data = TRUE
)

Arguments

.data	a tsibble or data with already computed categories
harmony_tbl	A tibble containing one or more hamronies with facet_variable, x_variable, facet_levels and x_levels
response	the response variable
quantile_prob	numeric vector of probabilities with value #'in [0,1] whose sample quantiles are wanted. Default is set to #' "decile" plot
dist_ordered	if categories are ordered
lambda	value of tuning parameter for computing weighted
nperm	number of permutations for normalization
use_perm	should permutation approach for normalization be used
probs	threshold probability
nsamp	number of samples considered to compute threshold
create_harmony_data	a logical value indicating if data corresponding to harmonies to be created or not

Examples

library(parallel)
library(dplyr)
library(tidyr)
sm <- smart_meter10 %>%
  filter(customer_id %in% c("10017936"))
harmonies <- sm %>%
  harmony(
    ugran = "month",
    filter_in = "wknd_wday",
    filter_out = c("hhour", "fortnight")
  )
#all_harmony <- wpd_threshold(sm,
  #harmony_tbl = harmonies,
  #response = general_supply_kwh, nsamp = 3
#)

Sayani07/gravitas documentation built on June 18, 2022, 2:40 a.m.