Learn R Programming

timetk (version 2.6.1)

ts_clean_vec: Replace Outliers & Missing Values in a Time Series

Description

This is mainly a wrapper for the outlier cleaning function, tsclean(), from the forecast R package. The ts_clean_vec() function includes arguments for applying seasonality to numeric vector (non-ts) via the period argument.

Usage

ts_clean_vec(x, period = 1, lambda = NULL)

Arguments

x

A numeric vector.

period

A seasonal period to use during the transformation. If period = 1, seasonality is not included and supsmu() is used to fit a trend. If period > 1, a robust STL decomposition is first performed and a linear interpolation is applied to the seasonally adjusted data.

lambda

A box cox transformation parameter. If set to "auto", performs automated lambda selection.

Details

Cleaning Outliers

  1. Non-Seasonal (period = 1): Uses stats::supsmu()

  2. Seasonal (period > 1): Uses forecast::mstl() with robust = TRUE (robust STL decomposition) for seasonal series.

To estimate missing values and outlier replacements, linear interpolation is used on the (possibly seasonally adjusted) series. See forecast::tsoutliers() for the outlier detection method.

Box Cox Transformation

In many circumstances, a Box Cox transformation can help. Especially if the series is multiplicative meaning the variance grows exponentially. A Box Cox transformation can be automated by setting lambda = "auto" or can be specified by setting lambda = numeric value.

References

See Also

Examples

Run this code
# NOT RUN {
library(dplyr)
library(timetk)


# --- VECTOR ----

values <- c(1,2,3, 4*2, 5,6,7, NA, 9,10,11, 12*2)
values

# Linear interpolation + Outlier Cleansing
ts_clean_vec(values, period = 1, lambda = NULL)

# Seasonal Interpolation: set period = 4
ts_clean_vec(values, period = 4, lambda = NULL)

# Seasonal Interpolation with Box Cox Transformation (internal)
ts_clean_vec(values, period = 4, lambda = "auto")


# }

Run the code above in your browser using DataLab