- 54c18ee Perl Script for processing Konvents2021 data by PeterFankhauserIDS · 3 years, 7 months ago
- 23102c9 Datasets for konvents 2021 Benchmark by PeterFankhauserIDS · 3 years, 7 months ago
- bc640f1 Datasets for publication (deduplicated via nstokens). by PeterFankhauserIDS · 3 years, 7 months ago
- 3f48b7a List of feature groups. by PeterFankhauserIDS · 3 years, 7 months ago
- b9a3cef Some quick and dirty latex table generation. by PeterFankhauserIDS · 3 years, 7 months ago
- e5ee071 extended with analysing both datasets. by PeterFankhauserIDS · 3 years, 7 months ago
- a18d535 extended with carret cross validation and some more feature analysis. by PeterFankhauserIDS · 3 years, 7 months ago
- 41425dc added independent test file idioms from wikipedia + adapted classification script by PeterFankhauserIDS · 3 years, 9 months ago
- 46e579c consistent file endings .csv for datasets by PeterFankhauserIDS · 3 years, 9 months ago
- 3f97f36 added NA treatment for dataset 1, Marc's improved axis labelling by PeterFankhauserIDS · 3 years, 9 months ago
- 67a06bd Merge changes I02169a8a,I23fa3680,Iee2355e0,Iae35113f by Marc Kupietz · 3 years, 9 months ago
- 347a039 Restore original x axis direction for tradeoff plot by Marc Kupietz · 3 years, 9 months ago
- b1b0336 Plot also Sensitivity, Balanced Accuracy and use ggplot by Marc Kupietz · 3 years, 9 months ago
- d2c893a Fscore over the full range by PeterFankhauserIDS · 3 years, 9 months ago
- 03d4ece added Fscore plot for various cutoffs by PeterFankhauserIDS · 3 years, 9 months ago
- a5b2acf Got rid of hyperparameters in # rf invocations by PeterFankhauserIDS · 3 years, 9 months ago
- 355d548 Show table with comparison of RF w/ or w/o SMOTE, cutoff by Marc Kupietz · 3 years, 9 months ago
- 201e6f3 Explicitly name factors idiom and no_idiom by Marc Kupietz · 3 years, 9 months ago
- 1be40eb Add example with cutoff again to demonstrate idiom detection potential by Marc Kupietz · 3 years, 9 months ago
- 65733b2 Make output more readable by Marc Kupietz · 3 years, 9 months ago
- 358a296 Set randon seeed on start to make results reproducible by Marc Kupietz · 3 years, 9 months ago
- 13f67ed Use consistent default parameters for randomForest training by Marc Kupietz · 3 years, 9 months ago
- ecc9c4c get rid of cutoff for consistency reasons by PeterFankhauserIDS · 3 years, 9 months ago
- c262278 Clarified data vs. reference for caret:confusion matrices. by PeterFankhauserIDS · 3 years, 9 months ago
- 7cad9b7 Added readme.txt, derekovecs_apicall_syn_nlc, and some data files by PeterFankhauserIDS · 3 years, 9 months ago
- b48fa17 2nd Dataset with proper feature names and nullvalue treatment by PeterFankhauserIDS · 3 years, 9 months ago
- ed93d2e Test by PeterFankhauserIDS · 3 years, 9 months ago
- d1f3df8 Added some comments, variable for ngramfile, cleanup feature ranking aggregation in 10fold. by PeterFankhauserIDS · 3 years, 9 months ago
- 4c8b96f Add project file to ease RStudio-git integration by Marc Kupietz · 3 years, 9 months ago
- aced270 Fix syfeatures -> syfeaturenames by Marc Kupietz · 3 years, 9 months ago
- 7049c74 Improve Sensitiviy with SMOTE by Marc Kupietz · 3 years, 9 months ago
- 0932a78 Fix input for caret::confusionMatrix by Marc Kupietz · 3 years, 9 months ago
- 631800f Fully remove incomplete idioms from data by Marc Kupietz · 3 years, 9 months ago
- c3bf350 Initial import by Marc Kupietz · 3 years, 9 months ago