fn_conf_mat: Creates confusion matrix and its related measures

In scorecardModelUtils: Credit Scorecard Modelling Utils

Description

The function takes the base dataframe with observed/actual and predicted columns. The actual/predicted class preferably should be binary and if not, it will be considered as event vs rest. It computes the performance measures like accuracy, precision, recall, sensitivity, specificity and f1 score.

Usage

fn_conf_mat(base, observed_col, predicted_col, event)

Arguments

base	input dataframe
observed_col	column / field name of the observed event
predicted_col	column / field name of the predicted event
event	the event class, to be passed as string

Value

An object of class "fn_conf_mat" is a list containing the following components:

confusion_mat	confusion matrix as a table
accuracy	accuracy measure
precision	precision measure
recall	recall measure
sensitivity	sensitivity measure
specificity	specificity measure
f1_score	F1 score

Author(s)

Arya Poddar <[e-mail]>

Examples

data <- iris
data$Species <- as.character(data$Species)
suppressWarnings(RNGversion('3.5.0'))
set.seed(11)
data$Y <- sample(0:1,size=nrow(data),replace=TRUE)
data$Y_pred <- sample(0:1,size=nrow(data),replace=TRUE)
fn_conf_mat_list <- fn_conf_mat(base = data,observed_col = "Y",predicted_col = "Y_pred",event = 1)
fn_conf_mat_list$confusion_mat
fn_conf_mat_list$accuracy
fn_conf_mat_list$precision
fn_conf_mat_list$recall
fn_conf_mat_list$sensitivity
fn_conf_mat_list$specificity
fn_conf_mat_list$f1_score

scorecardModelUtils documentation built on May 2, 2019, 9:59 a.m.