--train_bootstraps_ns

Switch

--train_bootstraps_ns N [N2 ...]

Description

Sample sizes to use when doing bootstrapped training with --train_bootstraps.

Argument and Default Value

One or more integers. Default: None.

Details

Verified end-to-end: with --train_bootstraps 3 --train_bootstraps_ns 20 40, ran 3 resamples at sample size 20, then 3 more at sample size 40 (printing Sample Size: 20, bs resample num: 1/2/3 then the same for 40) — useful for building a learning curve of model performance vs. training set size.

Other Switches

Required Switches:

• --train_regression

• --train_bootstraps

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$1to3gram$msgs$user_id$0_05' \
--outcome_table blog_outcomes --outcomes age --train_regression --train_bootstraps 3 \
--train_bootstraps_ns 500 1000 --save_model --picklefile ./boot_test.pickle