--roc

Switch

--roc

Description

Computes ROC (receiver operating characteristic) curves and outputs to PDF

Argument and Default Value

None. If --output_name is not specified then output pdf will be names "ROC.pdf".

Details

Other Switches

Required Switches:

One of the classification prediction switches, e.g. --nfold_test_classifiers, --test_classifiers

Optional Switches:

--group_freq_thresh, --sparse, --output_name

Example Commands

Using the packaged dla_tutorial dataset (see Differential Language Analysis (DLA) Tutorial):

dlatkInterface.py -d dla_tutorial -t msgs -c user_id -f 'feat$1gram$msgs$user_id$16to16$0_01' \
--outcome_table blog_outcomes --outcomes is_student --combo_test_classifiers --roc --output_name ./is_student