From e3f7237ffcb19f19db3b68777b5a94b89e07f66a Mon Sep 17 00:00:00 2001 From: ziejd2 Date: Thu, 13 Sep 2018 23:59:20 -0500 Subject: New parameter learning options The main change here is in the parameter learning methods. The parameters that are learned at first (i.e., if there is no evidence) are the distributions that are found directly in the data. I had to create or significantly modify several BNT files for this. If there is evidence, the parameters are learned using a Dirichlet prior. This only required a couple of small changes to the BNW parameter learning files. --- sourcecodes/kfold_cv.php | 150 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 150 insertions(+) create mode 100644 sourcecodes/kfold_cv.php (limited to 'sourcecodes/kfold_cv.php') diff --git a/sourcecodes/kfold_cv.php b/sourcecodes/kfold_cv.php new file mode 100644 index 00000000..6cae9538 --- /dev/null +++ b/sourcecodes/kfold_cv.php @@ -0,0 +1,150 @@ + + + + + + +
+ + + + + +
+ Enter the name of variable and number of folds below to validate predictions of that variable.
+
+
+ To perform cross-validation, enter the name of the variable
that you want to test the predictions of and the number
of folds that the data should be separated into below.
+
+