combineFeatureVectors: This function combines all of the desired feature types into...

In OHDSI/Aphrodite: Automated PHenotype Routine for Observational Definition Identification Training and Evaluation (APHRODITE) - Phenotype building tool using Fuzzy labels

Description

This function combines all of the desired feature types into one single feature vector. This feature vector is ready to be used for training

Usage

combineFeatureVectors(flags, cases_pids, controls_pids, featureVector,
  outcomeNameS)

Arguments

flags	The R dataframe that contains all feature/model flags specified in settings.R.
cases_pids	List of patient_id's considered cases (for labeling purposes)
controls_pids	List of patient_id's considered controls (for labeling purposes)
featureVector	List of flattened feature vectors returned by buildFeatureVector function.
outcomeNameS	String description of the outcome for which the model is being built [Not actually needed]

Details

This function builds a feature vector by concatenating all of the available datasets. If binary features are specified in the settings, this conversion is made. The cases_pids and control_pids are patient_id's used for the labeling of the testing and training sets.

Value

fv_all - The combined feature vector (n patients x n features). The columns are: pid column, predictorNames, outcomeName

Examples

## Not run: 

 fv_full_data <- combineFeatureVectors(flag, cases, controls, fv_all, outcomeName)


## End(Not run)

OHDSI/Aphrodite documentation built on Sept. 18, 2020, 10:26 p.m.