add_enrich: Add extended data

In MrMaximumMax/FBCanalysis: Develop and evaluate time series data models based on fluctuation based clustering

Add extended data

Description

Add extended data from a csv file, match with Patient ID entries from a previously generated time series data list and preprocess for further analysis.

Usage

add_enrich(plist, path)

Arguments

plist	List storing patient time series data (also see function: patient_list)
path	Path where enrichment csv file is stored

Details

the extended csv file should have a column including the Patient ID. Additionally, one specifies the list in which time series data is saved. This is advantageous since the function can now do matching, i.e. determine which Patient IDs occur in both the extended dataset and time series datalist. So for a result, any Patient ID that appears in the extended dataset but does not exist in the time series datalist will be deleted from the extended dataset, as it cannot be used in any further investigation. Nonetheless, Patient IDs from the time series data that do not appear in the enrichment dataset will be added to the enrichment dataset, but each new parameter will be featureless, so added as NA value.

If one selects option 1 (leave missing values as NA), no further processing of the input occurs. The extended data set will be added to the environment as a data frame. In this situation, the NA values from the extended dataset will be included in the summary indicating, for example, that a certain cluster has a given percentage of missing values. This may also lead to some additional findings, such as that a specific parameter considerably enriches a cluster yet many data is absent. If the one selects option 2 (sample missing values), the function loops over each NA entry and selects a random value from the whole distribution for the parameter for which the data is missing. This cycle is repeated until the whole dataset has been processed and the data will be added as a data frame to the environment.

Value

Processed data as object of type data frame; Enrichment data Patient_IDs are matched with Time Series Data List Patient IDs; In case it was indicated, NA values in the enrichment data are filled up by random sampling

Examples

list <- patient_list(
"https://raw.githubusercontent.com/MrMaximumMax/FBCanalysis/master/demo/phys/data.csv",
GitHub = TRUE)
#Sampling frequency is supposed to be daily
enr <- add_enrich(list,
'https://raw.githubusercontent.com/MrMaximumMax/FBCanalysis/master/demo/enrich/enrichment.csv')

MrMaximumMax/FBCanalysis documentation built on June 23, 2022, 8:21 p.m.