CourseNatural Language Processing: The Complete Course · Module 5: Evaluation, Sentiment and Topics · part 37 of 73
Part 37 · Module 5: Evaluation, Sentiment and Topics

Lab: An evaluation report and Rosa's Monday report

77 min read·14 Oct 2026
Module 5 · Lab · About 75 minutes · Needs: lessons 1 to 4 of this module, and the Module 4 lab (or its cells, pasted here)

What you are building

SETTLED FROM FOUR LESSONS inbox/evaluate.py inbox/abstain.py inbox/sentiment.py inbox/topics.py WHAT ROSA GETS intent v1 evaluation macro F1 0.562 (0.417 to 0.677) Monday report aspects and topics by week both written to reports/, 66 tests passing
The lab settles four project files (blue) and uses them to write two reports for Rosa (green): one on the intent model, one on unhappy customers.

It is Monday 5 October 2026, project week 5, and Rosa wants two things. First, one honest page on the intent model the Module 4 lab saved: per class, per language, with an interval around each score, and a rule for when it should pass a message to Ines. Second, her Monday report: what customers are unhappy about, and whether it is getting worse.

The four lessons appended parts to four files. This lab settles each one, writes the tests once, scores version 1 through inbox.classify.predict, and writes both reports to reports/ for the last week in the export, 24 to 30 August.

Open a new Colab notebook, call it module-05-lab.ipynb, and run each cell in order.

The rest of this part opens with an account

Signing up is free and takes one email. Nothing to pay, and nothing renews.