1
62%
master: 61%

Ran 14 May 2018 07:54PM UTC

Files 206

Run time 11s

Badge

Embed ▾

Committed 14 May 2018 07:29PM UTC coverage: 58.549% (+0.1%) from 58.432%

Job # TERM=dumb

Build Type

push

travis-ci

Committed by

aecio

Commit Message

Implement dedup classifier as online learning and crawl simulation

Changes:
- Improved training data deduplication classifier using
duplicate page grouping with union find algorithm
- Implemented learning for the deduplication classifier using
the online learning framework
- Improve crawl simulation and added coverage metrics using
an duplication 'oracle'
TODO:
- Finish implementation of ProbabilisticExactDupDetector
- Finish configuration on adaptive rate for online learning

Coverage Stats

7246 of 12376 relevant lines covered (58.55%)

0.59 hits per line

ViDA-NYU / ache / 765 / 1
62%
master: 61%

README BADGES
x

Markdown

Textile

RDoc

HTML

Rst

Source Files on job 765.1 (TERM=dumb)

ViDA-NYU / ache / 765 / 1 62% master: 61%

README BADGES x

Markdown

Textile

RDoc

HTML

Rst

Source Files on job 765.1 (TERM=dumb)

ViDA-NYU / ache / 765 / 1
62%
master: 61%

README BADGES
x