IMP (version 1.1)

staticConfMatrix: Confusion Matrix for Binary Classification Models

Description

Generates confusion matrix for a specified probability threshold. Also computes the following metrics - Accuracy, True Positive Rate, False Positive Rate & Precision. Multiple models can be passed as arguments to this function

Usage

staticConfMatrix(list_models, t, reps = NULL, reps.all.unique = F)

Arguments

list_models

A list of one (or more) dataframes for each model whose performance is to be evaluated. Each dataframe should comprise of 2 columns with the first column indicating the class labels (0 or 1) and the second column providing the raw predicted probabilities

t

Probability threshold value

reps

Performance measures derived from the confusion matrix (Accuracy, TPR, FPR & Precision) are computed for a range of different probability thresholds. The "reps" argument controls the number of different probability thresholds considered (threshold range given by the sequence - seq(0,1,1/reps))

reps.all.unique

Logical; If set to True, Performance measures are computed for each unique Probability value

Value

If reps = NULL, the output will be a list with 2 components - a confusion matrix dataframe and a dataframe with the values of the computed metrics (Accuracy,TPR,FPR,Precision). If reps argument is supplied, an additional dataframe containing the metrics values for different probability thresholds is included in the output

Examples

model_1 <- glm(Species ~ Sepal.Length,data=iris,family=binomial)
model_2 <- glm(Species ~ Sepal.Width, data=iris, family = binomial)
df1 <- data.frame(model_1$y,fitted(model_1))
df2 <- data.frame(model_2$y,fitted(model_2))
staticConfMatrix(list(df1,df2),t=0.2)