Package 'spooky'

Title: Time Feature Extrapolation Using Spectral Analysis and Jack-Knife Resampling
Description: Proposes application of spectral analysis and jack-knife resampling for multivariate sequence forecasting using only base R functionality.
Authors: Giancarlo Vercellino [aut, cre]
Maintainer: Giancarlo Vercellino <[email protected]>
License: GPL-3
Version: 2.0.0
Built: 2026-09-26 10:57:39 UTC
Source: https://github.com/cran/spooky

Help Index

Spectral forecasting with jackknife resampling

Description

Automatic jack-knife of spectral analysis for time feature extrapolation

Usage

spooky(
  df,
  seq_len = NULL,
  lno = NULL,
  n_samp = 30,
  n_windows = 3,
  ci = 0.8,
  smoother = FALSE,
  dates = NULL,
  error_scale = "naive",
  error_benchmark = "naive",
  seed = 42
)

Arguments

df

Numeric or categorical time-feature data frame.
seq_len

Forecast horizon or range of horizons to search.
lno

Jackknife leave-out value or search range.
n_samp

Number of candidate configurations.
n_windows

Number of validation windows.
ci

Confidence level for prediction summaries.
smoother

Apply a moving-average smoother to numeric data.
dates

Optional Date vector matching 'df'.
error_scale

Scale used by numeric error metrics.
error_benchmark

Benchmark used by relative error metrics.
seed

Random seed.

Value

An object of class 'spooky_fit'.

Author(s)

Maintainer: Giancarlo Vercellino [email protected]

time features example: IBM and Microsoft Close Prices

Description

A data frame with with daily with daily prices for IBM and Microsoft since March 2017.

Usage

time_features

Format

A data frame with 2 columns and 1324 rows.

Source

finance.yahoo.com