filter_stationary_columns: Filter stationary columns from the data

In ing-bank/tsforecast: Time Series Forecasting Pipeline

Description

filter_stationary_columns is a function to filter columns which have only a single unique value from the data. This is done mostly before modelling, because these stationary columns contain no information that can be used to create a model.

Usage

filter_stationary_columns(data)

Arguments

data	A data.table, data.frame or tibble object containing the data to be used for modelling, from which the stationary columns need to be filtered.

Value

A tibble with only non-stationary columns.

Examples

dummy_gasprice %>% 
   filter_stationary_columns() %>% 
   colnames()
dummy_gasprice %>% 
   dplyr::filter(state == "New York") %>% 
   filter_stationary_columns() %>% 
   colnames()

ing-bank/tsforecast documentation built on Sept. 18, 2020, 9:40 a.m.