unnormalize: Unnormalize a series using conditional moments

In PuwasalaG/conduits: CONDitional UI for Time Series normalisation

Unnormalize a series using conditional moments

Description

This function produces an unnormalized series using conditional moments.

Usage

unnormalize(data, ystar, fit_mean, fit_var)

Arguments

data	a tsibble containing all the time series which are uniquely identified by the corresponding Timestamp.
ystar	The normalized variable name
fit_mean	Model object of class "conditional_moment" returned from conditional_mean with information to append to observations.
fit_var	Model object of class "conditional_moment" returned from conditional_var with information to append to observations.

Value

A tsibble with the conditional normliased series

Examples

data <- NEON_PRIN_5min_cleaned |>
  dplyr::filter(site == "upstream") |>
  dplyr::select(Timestamp, turbidity, level, conductance, temperature) |>
  tsibble::as_tsibble(index = Timestamp)

fit_mean <- data |>
  conditional_mean(turbidity ~ s(level, k = 8) +
    s(conductance, k = 8) + s(temperature, k = 8))

fit_var <- data |>
  conditional_var(
    turbidity ~ s(level, k = 7) + s(conductance, k = 7) + s(temperature, k = 7),
    family = "Gamma",
    fit_mean = fit_mean
  )

new_ts <- data |>
  dplyr::mutate(ystar = normalize(data, turbidity, fit_mean, fit_var))

# For demonstrative purposes, declare three data points
# as missing values.
new_ts[3:5, 6] <- NA

## Not run: 
library(fable)
library(dplyr)
impute_ts <- new_ts |>
  model(ARIMA(ystar)) |>
  interpolate(new_ts) |>
  rename(y_star_impt = ystar) |>
  full_join(new_ts, by = "Timestamp")
impute_ts <- impute_ts
  mutate(y = unnormalize(impute_ts, y_star_impt, fit_mean, fit_var))

## End(Not run)

PuwasalaG/conduits documentation built on April 22, 2023, 3:40 p.m.