Learn R Programming

emil (version 2.2.10)

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

32

Version

2.2.10

License

GPL (>= 2)

Issues

0

Pull Requests

0

Stars

5

Forks

0

Maintainer

Christofer Backlin

Last Published

July 30th, 2018

Functions in emil (2.2.10)

factor_to_logical

Convert factors to logicals
fit_rpart

Fit a decision tree
get_tuning

Extract parameter tuning statistics
image.resample

Visualize resampling scheme
notify_once

Print a warning message if not printed earlier
%>%

Pipe operator
fit_glmnet

Fit elastic net, LASSO or ridge regression model
pre_log_message

Print log message during pre-processing
fit

Fit a model
fit_lda

Fit linear discriminant
indent

Increase indentation
fit_caret

Fit a model using the caret package
index_fit

Convert a fold to row indexes of fittdng or test set
mode

Get the most common value
modeling_procedure

Setup a modeling procedure
pre_pamr

PAMR adapted dataset pre-processing
fit_lm

Fit a linear model fitted with ordinary least squares
pvalue.cuminc

Extract p-value from a cumulative incidence estimation
fit_naive_bayes

Fit a naive Bayes classifier
pvalue.survdiff

Extracts p-value from a logrank test
get_importance

Feature (variable) importance of a fitted model
pre_impute_df

Impute a data frame
get_performance

Extract prediction performance
pre_impute_knn

Nearest neighbors imputation
predict_naive_bayes

Predict using naive Bayes model
predict_rpart

Predict using a fitted decision tree
predict_pamr

Prediction using nearest shrunken centroids.
predict_svm

Predict using support vector machine
emil

Introduction to the emil package
as.modeling_procedure

Coerce to modeling procedure
dichotomize

Dichotomize time-to-event data
importance_randomForest

Feature importance of random forest.
fit_pamr

Fit nearest shrunken centroids model.
error_fun

Performance estimation functions
fit_svm

Fit a support vector machine
get_color

Get color palettes
select

emil and dplyr integration
subresample

Generate resampling subschemes
list_method

List all available methods
log_message

Print a timestamped and indented log message
predict_caret

Predict using a caret method
evaluate

Evaluate a modeling procedure
fit_qda

Fit quadratic discriminant.
impute

Regular imputation
nice_box

Plots a box around a plot
predict_cforest

Predict with conditional inference forest
get_prediction

Extract predictions from modeling results
extension

Extending the emil framework with user-defined methods
fit_cforest

Fit conditional inference forest
get_response

Extract the response from a data set
is_multi_procedure

Detect if modeling results contains multiple procedures
fit_coxph

Fit Cox proportional hazards model
learning_curve

Learning curve analysis
nice_require

Load a package and offer to install if missing
na_index

Support function for identifying missing values
subtree

Extract a subset of a tree of nested lists
importance_glmnet

Feature importance extractor for elastic net models
pre_process

Data preprocessing
name_procedure

Get names for modeling procedures
trivial_error_rate

Calculate the trivial error rate
predict.model

Predict the response of unknown observations
predict_qda

Prediction using already trained classifier.
predict_randomForest

Prediction using random forest.
pre_factor_to_logical

Convert factors to logical columns
pre_impute

Basic imputation
importance_pamr

Feature importance of nearest shrunken centroids.
is_constant

Check if an object contains more than one unique value
is_blank

Wrapper for several methods to test if a variable is empty
neg_gmpa

Negative geometric mean of class specific predictive accuracy
nice_axis

Plots an axis the way an axis should be plotted.
predict_lda

Prediction using already trained prediction model
plot.learning_curve

Plot results from learning curve analysis
predict_lm

Prediction using linear model
plot_Surv

Plot Surv vector [DEPRECATED]
resample

Resampling schemes
predict_coxph

Predict using Cox proportional hazards model
roc_curve

Calculate ROC curves
print.preprocessed_data

Print method for pre-processed data
vlines

Add vertical or horizontal lines to a plot
predict_glmnet

Predict using generalized linear model with elastic net regularization
pvalue

Extraction of p-value from a statistical test
weighted_error_rate

Weighted error rate
pvalue.coxph

Extract p-value from a Cox proportional hazards model
pvalue.crr

Extracts p-value from a competing risk model
tune

Tune parameters of modeling procedures
validate_data

Validate a pre-processed data set
fill

Replace values with something else
fit_randomForest

Fit random forest.