createEventNames: Create unique event names for each attribute of an event...

In novasmedley/gbmSpm: Find predictive sequential patterns for clinical glioblastoma patients

Description

Event names serve as an unique event in SPM. This will merge agent and agent_detail into a new column, eventName Here, each attribute of an event type is stated in the event name. Events with continuous values will first discretized. (e.g., "tumorINCR", tumor volume is the event from agent column, and INCR is the attribute converted from agent_detail column.)

Usage

createEventNames(event, tType, removeChemo)

Arguments

tType	char, shortcut for type of tumor volume information
event:	dataframe, all events across all patients, each row is an event, returned from 'getData' in 'getData.R'
removeChemo:	bool, remove chemo event types

Details

event contains events as rows and at least the following columns:

• iois patient id, char

• agent event type, char

• agent_detail event attribute, char

• startdate event start date in the format 'YYYY-MM-DD', char

• enddate event end date in the format 'YYYY-MM-DD', char

• eventID event id

• eventName distinct names for an event (e.g., mentalStatus0: agent is mental status, agent_detail is 0)

Value

event: dataframe, cleaned and formated information that is ammendable to SPM

Examples

data("fake_data")
events <- fake_data$events
events$startdate <- as.Date(as.character(events$startdate), format='%Y-%m-%d')
events$enddate <- as.Date(as.character(events$enddate), format='%Y-%m-%d')

cleaned <- removeData(events)
cleaned <- resetEventIDsToDays(cleaned)
cleaned <- removePreRadiation(cleaned)

cleaned <- createEventNames(event=cleaned,
                            tType='r',
                            removeChemo=T)
                            

novasmedley/gbmSpm documentation built on May 17, 2019, 10:39 a.m.