Sotera/webpageclassifier
Categorizes a website given URL into one of blog|wiki|news|forum|classified|shopping|undecided.
Jupyter NotebookApache-2.0
Issues
- 0
error while executing script
#21 opened - 1
Throws ValueError: Unicode... on some websites
#20 opened by ctwardy - 6
ERROR on craigslist.com
#4 opened by ctwardy - 1
Finish integrating ERROR category into scores
#14 opened by ctwardy - 0
Drop bleach/reload from _score_url()
#18 opened by ctwardy - 1
Confusion Matrix labels are wrong
#15 opened by ctwardy - 0
Simplify the JPL_Classifier
#16 opened by ctwardy - 0
Goldwords files fail on Cyrillic text.
#17 opened by ctwardy - 1
Include errors in results
#12 opened by ctwardy - 3
- 0
Save HTML to file for faster retesting.
#9 opened by ctwardy - 1
Improve blog detection
#8 opened by ctwardy - 0
Add to web app
#7 opened by ctwardy - 1
Always calculate all 4 cosine scores.
#5 opened by ctwardy - 1
forum class_list always blank
#2 opened by ctwardy - 2
Improve results
#3 opened by ctwardy - 0
Handle redirect loops
#1 opened by ctwardy