residual_outliers: Identify outlying yields

In jillianderson8/cydr: An R Package for Cleaning Agricultural Yield Data

Description

Adds a column called cydr_ResidualError to a dataframe to identify observations associated with outlying yields.

Will identify all observations with yields greater than sd standard deviations away from the mean. If remove is TRUE all observations associated with a residual error will be removed from the dataframe.

Usage

residual_outliers(data, remove=FALSE, type="both", sd=2)

Arguments

data	a dataframe, standardized and outputted from AgLeader.
remove	a boolean. Defaults to FALSE. Indicates whether to remove identified errors.
type	one of "high", "low", or "both". Indicates which types of data to identify as erroneous "high" will identify, high yields, "low" will identify low speeds, and "both" will identify high and low speeds.
sd	a number >= 0. Defaults to 2. Used as the standard deviation threshold for error identification.

Value

A dataframe with an added column called cydr_ResidualError. This column will be set to TRUE if an observation is deemed erroneous.

If remove = TRUE all observations cydr identifies as erroneous are removed from the returned dataframe.

See Also

Other core functions: narrow_passes, pass_end_turns, speed

Examples

residual_outliers(data)
residual_outliers(data, TRUE)
residual_outliers(data, TRUE, type="low", sd=3)

jillianderson8/cydr documentation built on May 19, 2019, 10:31 a.m.