summer 2021 cse 6040 midterm 1 problem PDF

Preview

Summary

problem XX of midterm 1 for gatech cse 6040...

Description

Problem 21: Caption Contest Version 1.4b This problem is a data mining task that exercises basic da exercises, numbered 0-4. These depend on one another a Exercises 0 (1 point), 1 (3 points), 2 (2 points), and 3 ( credit. Exercise 4 (2 points) depends on successful complet Pro-tips. If your program behavior seem strange, try resetting t If you mess up this notebook or just want to start from get a fresh, original copy of this notebook. (Resetting intend to keep or reuse them!) If you generate excessive output (e.g., from an ill-plac Clear Notebook Output to get a clean copy. The the notebook to clean.xxx.ipynb. Since the autog accordingly. Good luck!

Background Every week, the New Yorker magazine runs a cartoon cap their ideas. For example, run the following code cell to see a cartoon In [1]: from problem_utils import get_path, displa display_image(get_path("toast/image.png")) Out[1]:

You should see a picture of a piece of bread, wearing a bo The data. The New Yorker allows readers to vote on the s will serve as your dataset. (These data are just the caption The data are stored in a JSON file, which Python can easi the first four captions: In [2]: import json with open(get_path('toast/captions.json'), captions_json = json.load(fp) print(f"==> The dataset contains {len(capt captions_json[:4] ==> The dataset contains 2458 captions. Th Out[2]: [{'target_id': 0, 'primary_type': 'text', 'primary_description': 'I told you not t {'target_id': 1, 'primary_type': 'text', 'primary_description': 'Well that explai {'target_id': 2, 'primary_type': 'text', 'primary_description': "The dairy-free v {'target_id': 3, 'primary_type': 'text', 'primary_description': 'Repeatedly, chee Observe that the variable holding this caption data, capt caption text itself is a string value associated with the pri

Your task: Data mining the caption There are a lot of submissions (even more than the 2,400+...