Commit 177ccf08 authored by Paul McCarthy's avatar Paul McCarthy 🚵
Browse files

RF: Change binarised ICD10 column naming convention to be a bit more

standardised - I can't foresee the instance field being used in the
original biobank data.
parent 7aeb111e
Variable Process
40001 binariseCategorical(acrossInstances=True, nameFormat='{vid}{value}-{visit}.0')
40002 binariseCategorical(acrossInstances=True, nameFormat='{vid}{value}-{visit}.0')
40006 binariseCategorical(acrossInstances=True, nameFormat='{vid}{value}-{visit}.0')
41202 binariseCategorical(acrossInstances=True, nameFormat='{vid}{value}-{visit}.0')
41204 binariseCategorical(acrossInstances=True, nameFormat='{vid}{value}-{visit}.0')
40001 binariseCategorical(acrossInstances=True, nameFormat='{vid}-{visit}.{value}')
40002 binariseCategorical(acrossInstances=True, nameFormat='{vid}-{visit}.{value}')
40006 binariseCategorical(acrossInstances=True, nameFormat='{vid}-{visit}.{value}')
41202 binariseCategorical(acrossInstances=True, nameFormat='{vid}-{visit}.{value}')
41204 binariseCategorical(acrossInstances=True, nameFormat='{vid}-{visit}.{value}')
all_independent removeIfSparse(minpres=51, maxcat=0.99)
all removeIfRedundant(0.99, 0.2)
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment