Exercise

Comparing models on labeled review data

Now that you can classify sentiment in bulk, your team wants to evaluate which model is more reliable. You'll compare two models using a larger labeled dataset of reviews and measure their accuracy.

A texts list and its true_labels are pre-loaded for you.

Instructions 1/2

undefined XP

1

2

Load two pipelines (pipe_a and pipe_a) using the models "distilbert-base-uncased-finetuned-sst-2-english" and "abilfad/sentiment-binary-dicoding", respectively.
Extract the 'label' values from the predictions of both pipelines.

.css-6su6fj{-webkit-flex-shrink:0;-ms-flex-negative:0;flex-shrink:0;}Exercise

Instructions 1/2

Exercise