improve_kmeans_labels_variable: improve_kmeans_labels_variable

In 1Edtrujillo1/udeploy: Back-end & Front-end functions

Description

Improve the dataset labels based on a balanced grouped sum of a particular variable.

Usage

improve_kmeans_labels_variable(
  df,
  id,
  label,
  var_model,
  split_type = c("mean_split", "range_split")
)

Arguments

df	dataset to change labels.
id	dataset id variable
label	k-means label variable
var_model	reference variable to balance
split_type	type of label modification.

Details

1. Get the grouped sum of var_model by the created k-mean label variable.

2. Calculate the population mean and standard deviation from 1. as parameters to modify the label

3. create the value_check as the constant values as comparation reference where the user will select based on the parameter split_type

4. With help of the function split_lower_upper_df we obtain the labels under and upper the constant values on 3.

5. Apply the subfunction modify_labels_variable_df

Value

This function modify the label variable of the df based on split_type:

• If split_type == "mean_split", change the labels where are upper the the mean of 1. to the lower ones, to balance the grouped sum var_model by the label

• If split_type == "range_split", change the labels out of the range population mean +- 1 standard deviation of 1.. Channging equally to the previous option.

Note

This function is used to improve the k-means labels based on a particular variable.

Author(s)

Eduardo Trujillo

1Edtrujillo1/udeploy documentation built on July 13, 2021, 9:12 p.m.