August 17, 2022
View253c56fc

- All references to runTest and runTests in examples and vignette converted to crossValidate. End users should always use crossValidate from now on. - Minor fixes to code mistakes. - Performance tuning of training method parameters chosen within feature selection is now faithfully used in the model training.

Dario Strbenac authored on 17/08/2022 13:55:15
August 14, 2022
Viewd37fb9c5

- Classifiers and feature selection functions no longer have multiple signaures and are private. - prepareData function to filter and subset input data using common ways, such as missingness and variability. - The variable renaming and storage in Original Feature and Renamed Feature reverted back to column metadata and assay / feature colums. - sampleInfo now reverted back to clinical.

Dario Strbenac authored on 14/08/2022 23:45:28
August 9, 2022
View8fe7aeff

Update utilities.R

Ellis Patrick authored on 09/08/2022 08:21:20 • GitHub committed on 09/08/2022 08:21:20
August 2, 2022
Viewb964ca82

Update utilities.R

Ellis Patrick authored on 02/08/2022 05:05:50 • GitHub committed on 02/08/2022 05:05:50
Viewcf84dedb

Merge branch 'master' of https://github.com/SydneyBioX/ClassifyR

Dario Strbenac authored on 02/08/2022 04:00:15
Viewedf8416b

Fix for function not found if SnowParam parallelisation used.

Dario Strbenac authored on 02/08/2022 04:00:10
Vieweb01afff

Update utilities.R

Ellis Patrick authored on 02/08/2022 02:47:02 • GitHub committed on 02/08/2022 02:47:02
July 22, 2022
View42b55d21

- Recently added assayName parameter removed from crossValidate (use characteristicsLabel instead). - All references to outcomes now use outcome instead.

Dario Strbenac authored on 22/07/2022 12:00:33
Viewb0380c0c

- crossVaildate now allows input of assay name for a single data table. - References to data set have been replaced by assay to remove ambiguity.

Dario Strbenac authored on 22/07/2022 10:30:06
July 15, 2022
View971b749e

- calcPerformance gains a Sample C-index option to calculate a C-index for each individual. - .splitDataAndOutcomes fix for survival object creation.

Dario Strbenac authored on 15/07/2022 06:00:02
July 13, 2022
Viewf68ea112

- Variable importance updated for new feature and dataset safe renaming. - Documentation of ranking functions updated to explain that they now return indices, not identifiers. - Ensemble feature selection in .doSelection fixes for newer format of runTest parameters. - crossValidate updated for safe renaming.

Dario Strbenac authored on 13/07/2022 11:30:39
July 12, 2022
View00cff98e

- Data sets and feature names are converted into safe names such as Dataset1 and Feature1 for use inside of feature selection and classification functions. ClasifyResult class gains a featuresInfo slot which stores original identifiers as well as sanitised ones. - elasticNetPreval defunct parameter set removed.

Dario Strbenac authored on 12/07/2022 14:35:03
June 30, 2022
View545a691d

Parameter tuning in .doTrain fixed. - drop FALSE added to crossValidate.

Dario Strbenac authored on 30/06/2022 03:50:02
Viewfba7d4b4

- Data table splitting made robust to single predictor input.

Dario Strbenac authored on 30/06/2022 01:57:51
View6f308f8b

- Check for nFeatures too large also added to runTest and runTests. - Check for undesired replicates added to all cross-validation entry points.

Dario Strbenac authored on 30/06/2022 01:06:08