run_apriori_w_sample_names {RareComb}

Generate frequent items along with the names of supporting observations using the apriori algorithm

Description

This function takes in a factorized Boolean matrix and generate frequent item sets that meet all the user provided criteria provided by the calling function. This function includes in it's output the identifiers of observations that support each significant combination.

Usage

run_apriori_w_sample_names(
  apriori_input_df,
  combo_length,
  support_threshold,
  input_colname_list,
  input_sample_list,
  confidence_threshold = confidence_threshold,
  include_output_ind = include_output_ind,
  output_colname_list = output_colname_list
)

Arguments

apriori_input_df

An input factorized Boolean dataframe with multiple input and outcome variables

combo_length

The length of the combinations specified by the user

support_threshold

Minimum support value calculated based on the minimum absolute observed frequency threshold specified by the user

input_colname_list

A list of column names that identify the input variables

input_sample_list

A list of row names that identify the samples/observations

confidence_threshold

Minimum confidence threshold specified by the user

include_output_ind

Specifies if the outcome variables must also be made part of the analysis using the algorithm

output_colname_list

A list of column names that identify the outcome variables

Details

This is a function leveraged by few of the four main methods available to the users.

Value

A list of frequent item sets that meet all the constraints supplied to the apriori algorithm

Author(s)

Vijay Kumar Pounraja