AMS: Generate Approximate Median Significance (AMS) function for...

In hsansford1/higgsboson:

Description

Generates an AMS function with threshold ('theta') of a logistic regression model as input. Useful for tuning threshold as a second stage to fitting logistic regression model.

Usage

AMS(f, valid_set, valid_y, valid_weights)

Arguments

f	Weighted logistic regression model (output of caret::train).
valid_set	Validation data set for model 'f'.
valid_y	Binary labels of validation data (0/1).
valid_weights	Weights of validation data.

Value

Function with one input 'theta', that returns AMS of validation set using model 'f' with threshold 'theta'.

hsansford1/higgsboson documentation built on Jan. 22, 2022, 4:34 a.m.