Complete the tasks in the Python Notebook in this repository. Make sure to add and push the pkl or text file of your scraped html (this is specified in the notebook)
- (Question 1) Article html stored in separate file that is committed and pushed: 1 pt
- (Question 2) Polarity score printed with an appropriate label: 1 pt
- (Question 2) Number of sentences printed: 1 pt
- (Question 3) Correct (or equivalent in the case of multiple tokens with same frequency) tokens printed: 1 pt
- (Question 4) Correct (or equivalent in the case of multiple lemmas with same frequency) lemmas printed: 1 pt
- (Question 5) Histogram shown with appropriate labelling: 1 pt
- (Question 6) Histogram shown with appropriate labelling: 1 pt
- (Question 7) Cutoff score seems appropriate given histograms: 2 pts (1/score)
- (Question 8) Summary contains a shortened version of the article (less than half the number of sentences): 1 pt
- (Question 8) Summary sentences are in the same order as they appeared in the original article: 1 pt
- (Question 9) Polarity score printed with an appropriate label: 1 pt
- (Question 9) Number of sentences printed: 1 pt
- (Question 10) Summary contains a shortened version of the article (less than half the number of sentences): 1 pt
- (Question 10) Summary sentences are in the same order as they appeared in the original article: 1 pt
- (Question 11) Polarity score printed with an appropriate label: 1 pt
- (Question 11) Number of sentences printed: 1 pt
- (Question 12) Thoughtful answer based on reported polarity scores: 1 pt
- (Question 13) Thoughtful answer based on summaries: 1 pt