Skip to content

Commit

Permalink
nicer formatting of results
Browse files Browse the repository at this point in the history
  • Loading branch information
lopuhin committed Jul 22, 2021
1 parent bb170ce commit 7c60d68
Showing 1 changed file with 20 additions and 18 deletions.
38 changes: 20 additions & 18 deletions README.rst
Original file line number Diff line number Diff line change
Expand Up @@ -37,27 +37,29 @@ Results

Results of the initial evaluation, done in November 2019::

AutoExtract Nov 2019 F1=0.970 ± 0.005 precision=0.984 ± 0.002 recall=0.956 ± 0.010 accuracy=0.470 ± 0.037
Diffbot Nov 2019 F1=0.951 ± 0.010 precision=0.958 ± 0.009 recall=0.944 ± 0.013 accuracy=0.348 ± 0.038
boilerpipe ab3694d F1=0.860 ± 0.016 precision=0.850 ± 0.016 recall=0.870 ± 0.020 accuracy=0.006 ± 0.006
dragnet 1b65e7b F1=0.907 ± 0.014 precision=0.925 ± 0.013 recall=0.889 ± 0.019 accuracy=0.221 ± 0.030
html-text 0.5.1 F1=0.665 ± 0.015 precision=0.500 ± 0.017 recall=0.994 ± 0.001 accuracy=0.000 ± 0.000
newspaper3k 0.2.8 F1=0.912 ± 0.014 precision=0.917 ± 0.014 recall=0.906 ± 0.018 accuracy=0.260 ± 0.032
readability-lxml 0.7.1 F1=0.922 ± 0.014 precision=0.913 ± 0.014 recall=0.931 ± 0.016 accuracy=0.315 ± 0.035
xpath-text 4.4.2 F1=0.394 ± 0.020 precision=0.246 ± 0.016 recall=0.992 ± 0.001 accuracy=0.000 ± 0.000
version F1 precision recall accuracy
AutoExtract Nov 2019 0.970 ± 0.005 0.984 ± 0.002 0.956 ± 0.010 0.470 ± 0.037
Diffbot Nov 2019 0.951 ± 0.010 0.958 ± 0.009 0.944 ± 0.013 0.348 ± 0.038
boilerpipe ab3694d 0.860 ± 0.016 0.850 ± 0.016 0.870 ± 0.020 0.006 ± 0.006
dragnet 1b65e7b 0.907 ± 0.014 0.925 ± 0.013 0.889 ± 0.019 0.221 ± 0.030
html-text 0.5.1 0.665 ± 0.015 0.500 ± 0.017 0.994 ± 0.001 0.000 ± 0.000
newspaper3k 0.2.8 0.912 ± 0.014 0.917 ± 0.014 0.906 ± 0.018 0.260 ± 0.032
readability-lxml 0.7.1 0.922 ± 0.014 0.913 ± 0.014 0.931 ± 0.016 0.315 ± 0.035
xpath-text 4.4.2 0.394 ± 0.020 0.246 ± 0.016 0.992 ± 0.001 0.000 ± 0.000

Result of packages added after original evaluation::

trafilatura 0.5.1 F1=0.945 ± 0.009 precision=0.925 ± 0.011 recall=0.966 ± 0.009 accuracy=0.221 ± 0.031
go_readability bdc8717 F1=0.943 ± 0.007 precision=0.912 ± 0.009 recall=0.975 ± 0.007 accuracy=0.210 ± 0.030
readability_js Feb 2021 F1=0.887 ± 0.012 precision=0.853 ± 0.013 recall=0.924 ± 0.012 accuracy=0.149 ± 0.026
go_domdistiller 1c90a88 F1=0.927 ± 0.007 precision=0.901 ± 0.010 recall=0.956 ± 0.010 accuracy=0.066 ± 0.018
news_please 1.5.17 F1=0.911 ± 0.014 precision=0.917 ± 0.013 recall=0.906 ± 0.018 accuracy=0.249 ± 0.032
goose3 3.1.8 F1=0.887 ± 0.016 precision=0.930 ± 0.015 recall=0.847 ± 0.021 accuracy=0.227 ± 0.032
inscriptis 1.1.2 F1=0.679 ± 0.015 precision=0.517 ± 0.017 recall=0.993 ± 0.001 accuracy=0.000 ± 0.000
html2text 2020.1.16 F1=0.662 ± 0.015 precision=0.499 ± 0.017 recall=0.983 ± 0.002 accuracy=0.000 ± 0.000
justext 2.2.0 F1=0.802 ± 0.018 precision=0.858 ± 0.017 recall=0.754 ± 0.028 accuracy=0.088 ± 0.021
beautifulsoup 4.9.3 F1=0.665 ± 0.015 precision=0.499 ± 0.017 recall=0.994 ± 0.001 accuracy=0.000 ± 0.000
version F1 precision recall accuracy
trafilatura 0.5.1 0.945 ± 0.009 0.925 ± 0.011 0.966 ± 0.009 0.221 ± 0.031
go_readability bdc8717 0.943 ± 0.007 0.912 ± 0.009 0.975 ± 0.007 0.210 ± 0.030
readability_js Feb 2021 0.887 ± 0.012 0.853 ± 0.013 0.924 ± 0.012 0.149 ± 0.026
go_domdistiller 1c90a88 0.927 ± 0.007 0.901 ± 0.010 0.956 ± 0.010 0.066 ± 0.018
news_please 1.5.17 0.911 ± 0.014 0.917 ± 0.013 0.906 ± 0.018 0.249 ± 0.032
goose3 3.1.8 0.887 ± 0.016 0.930 ± 0.015 0.847 ± 0.021 0.227 ± 0.032
inscriptis 1.1.2 0.679 ± 0.015 0.517 ± 0.017 0.993 ± 0.001 0.000 ± 0.000
html2text 2020.1.16 0.662 ± 0.015 0.499 ± 0.017 0.983 ± 0.002 0.000 ± 0.000
justext 2.2.0 0.802 ± 0.018 0.858 ± 0.017 0.754 ± 0.028 0.088 ± 0.021
beautifulsoup 4.9.3 0.665 ± 0.015 0.499 ± 0.017 0.994 ± 0.001 0.000 ± 0.000

Below you can find more details about the packages and result reproduction.

Expand Down

0 comments on commit 7c60d68

Please sign in to comment.