fitPlp: fitPlp

Description Usage Arguments Details Value

View source: R/Fit.R

Description

Train various models using a default parameter gird search or user specified parameters

Usage

1
2
3
4
5
6
7
8
9
fitPlp(
  population,
  data,
  modelSettings,
  cohortId,
  outcomeId,
  minCovariateFraction = 0.001,
  normalizeData = T
)

Arguments

population

The population created using createStudyPopulation() who will have their risks predicted

data

An object of type plpData - the patient level prediction data extracted from the CDM.

modelSettings

An object of class modelSettings created using one of the function:

  • logisticRegressionModel() A lasso logistic regression model

  • GBMclassifier() A gradient boosting machine

  • RFclassifier() A random forest model

  • GLMclassifier () A generalised linear model

  • KNNclassifier() A KNN model

cohortId

Id of study cohort

outcomeId

Id of outcome cohort

minCovariateFraction

The minimum fraction of the target popualtion who have a variable for it to be included in the model training

normalizeData

Whether to normalise the data before model fitting

Details

The user can define the machine learning model to train (regularised logistic regression, random forest, gradient boosting machine, neural network and )

Value

An object of class plpModel containing:

model

The trained prediction model

modelLoc

The path to where the model is saved (if saved)

trainAuc

The AUC obtained on the training set

trainCalibration

The calibration obtained on the training set

modelSettings

A list specifiying the model, preprocessing, outcomeId and cohortId

metaData

The model meta data

trainingTime

The time taken to train the classifier


ted9219/CoDImputationHeart documentation built on Sept. 15, 2020, 11:30 a.m.