Performance of a single model
Now that you have the binary vectors for the actual and predicted values of the model, you can calculate many commonly used binary classification metrics. In this exercise you will focus on:
- accuracy: rate of correctly predicted values relative to all predictions.
- precision: portion of predictions that the model correctly predicted as TRUE.
- recall: portion of actual TRUE values that the model correctly recovered.
Questo esercizio fa parte del corso
Machine Learning in the Tidyverse
Istruzioni dell'esercizio
- Use
table()to compare thevalidate_actualandvalidate_predictedvalues for the example model and validate data frame. - Calculate the accuracy.
- Calculate the precision.
- Calculate the recall.
Esercizio pratico interattivo
Prova a risolvere questo esercizio completando il codice di esempio.
library(Metrics)
# Compare the actual & predicted performance visually using a table
table(___, ___)
# Calculate the accuracy
accuracy(___, ___)
# Calculate the precision
precision(___, ___)
# Calculate the recall
recall(___, ___)