split_input_data: Function to split an input data frame into training and...

In skgrange/normalweatherr: An R package to conduct meteorological/weather normalisation on air quality data

Description

Use set.seed to ensure the splitting of the training and testing sets is reproducible.

Usage

split_input_data(df, fraction = 0.8)

Arguments

df	Data frame containing date and value variables. df will usually be prepared with add_date_variables.
fraction	Fraction of observations to form the training set. Default is 0.8 for an 80/20 % split for training and testing sets.

Value

A named list containing two data frames: training and testing with the class normalweatherr_data.

Author(s)

Stuart K. Grange

See Also

set.seed, add_date_variables, calculate_model, normalise_for_meteorology

Examples

## Not run: 

# Make modelling reproducible
set.seed(123)

# Prepare data for modelling
list_input_data <- split_input_data(data_swiss_daily)


## End(Not run)

skgrange/normalweatherr documentation built on May 23, 2019, 9:34 a.m.