Add implementation of Cramer's V #52
Comments
willb
pushed a commit
that referenced
this issue
May 6, 2016
Closes issue #52. Closes #56 and squashes the following commits: * 7f54e3a Provide implementation of Cramer's V. Closes issue #52. * 87788ff Remove leftover commented-out line * 495a247 Move divide outside of loop. Yay distributive law! * 0ab8919 Address Erik's suggestions * cb60324 Replace redundant counting code with a function * 0ab8ea1 Use required seed instead of optional RNG to make Scala 2.11 happy * c4d7af5 Address some of Erik's comments * c2f0579 Update Cramer's V permutation test name, test docs, move cross product to utils, and add extra guard to Cramer's V. * 9345c59 Use values instead of zipping * efacb4c Updated tests, should have been in earlier commit * 034351c Use Random.nextLong instead of -1 for the default seed * 3cd0bdd pValueEstimate should return probability of higher association, not less Signed-off-by: William Benton <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Cramer's V is a measure of association between nominal (categorical) variables. Useful for feature selection, comparing clusterings, potentially evaluating splits in Decision Trees trained on purely categorical data, etc.
The text was updated successfully, but these errors were encountered: