--transform_to_feats

Switch

--transform_to_feats NAME

Description

Transforms a feature table through a fitted dimensionality-reduction model (from --fit_reducer) and writes the reduced components into a new feature table.

Argument and Default Value

A name used to build the destination table (feat$dr_<model>_<name>$<corptable>$<correl_field>). Default: None.

Details

Verified end-to-end: with --fit_reducer --model pca --n_components 5 --transform_to_feats pca_reduced, created feat$dr_pca_pca_reduced$msgs$user_id and inserted one feature row per group for each of COMPONENT_0 through COMPONENT_4, printing a row count per component as it went.

Other Switches

Required Switches:

• --fit_reducer

• --model

Optional Switches:

• --n_components

Example Commands

Using the packaged dla_tutorial dataset (see Clustering and Super Topics):

dlatkInterface.py -d dla_tutorial -t msgs -c user_id -f 'feat$1to3gram$msgs$user_id$0_05' \
--fit_reducer --model pca --n_components 5 --transform_to_feats pca_reduced