Learn R Programming

⚠️There's a newer version (2.2.10) of this package.Take me there.

emil (version 1.1-3)

Evaluation of Modeling without Information Leakage

Description

A toolbox for designing and evaluating predictive models with resampling methods. The aim of this package is to provide a simple and efficient general framework for working with any type of prediction problem, be it classification, regression or survival analysis, that is easy to extend and adapt to your specific setting. Some commonly used methods for classification, regression and survival analysis are included.

Copy Link

Version

Install

install.packages('emil')

Monthly Downloads

18

Version

1.1-3

License

GPL (>= 2)

Maintainer

Christofer Backlin

Last Published

July 31st, 2014

Functions in emil (1.1-3)

as.outcome.Surv

Convert Surv vector to outcome vector

Fit quadratic discriminant.

emil.predict.cforest

Predict with conditional inference forest

emil.predict.glmnet

Predict using generalized linear model with elastic net regularization

emil.fit.glmnet

Fit GLM with LASSO, Ridge or elastic net regularization.

Introduction to the emil package

Regular imputation

Fit linear discriminant

Convert object to outcome vector

Wrapper for several methods to test if a variable is empty

PAMR adapted dataset pre-processing

emil.predict.pamr

Prediction using nearest shrunken centroids.

emil.predict.qda

Prediction using already trained classifier.

emil.extensions

Extending the emil framework with user-defined methods

Extracts p-value from a competing risk model

Extraction of p-value from a statistical test

Load a package and offer to install if missing

Trivial function

resample.mapply

Compare true response to resampled predictions

predict.modeling.procedure

Predict the response of unknown observations

Convert a fold to row indexes of fittdng or test set

Dimension of an outcome vector

Variable importance of a fitted model

Fit nearest shrunken centroids model.

Create a vector of outcomes

Replace values with something else

Resampling schemes

Extract a subset of a tree of nested lists

Generate resampling subschemes

Variable importance of nearest shrunken centroids.

evaluate.modeling

Performance estimation of modeling procedures

as.data.frame.outcome

Convert outcome vector to data frame

Get events on factor form

emil.fit.randomForest

Fit random forest.

emil.fit.cforest

Fit conditional inference forest

Print outcome vector

Perform modeling

emil.predict.randomForest

Prediction using random forest.

Length of an outcome vector

Extract p-value from a Cox proportional hazards model

emil.predict.lm

Prediction using linear model

Extract and organize predictions according to a resampling scheme

as.Surv.outcome

Convert outcome vector to Surv vector

Performance estimation functions

Negative geometric mean of class specific predictive accuracy

weighted.error.rate

Weighted error rate

emil.predict.lda

Prediction using already trained prediction model

Print a timestamped and indented log message

Extract p-value from a cumulative incidence estimation

Test if a directory is writable

Test if object is of class outcome

modeling.procedure

Setup a modeling procedure

p.value.survdiff

Extracts p-value from a logrank test

Check for missing values

emil.predict.caret

Predict using a caret method

Data preprocessing

as.matrix.outcome

Convert outcome vector to matrix

Plot outcome vector

Convert object to Surv vector

Return events in integer form

Fit a linear model fitted with ordinary least squares

emil.vimp.randomForest

Variable importance of random forest.

as.character.outcome

Convert outcome vector to character vector

Fit a model using the caret package

Visualize resampling scheme

Print a warning message if not printed earlier

Tune parameters of modeling procedures