qurator-spk/page2tsv
1
0
Fork 0
mirror of https://github.com/qurator-spk/page2tsv.git synced 2025-06-15 22:39:54 +02:00
Code Issues Releases Wiki Activity

try to infer correct line ordering ...

Browse source
This commit is contained in:
Kai Labusch 2020-03-09 13:44:16 +01:00
parent 7bf9cfa5de
commit abdabbac4f
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
cli.py
View file

@ -203,8 +203,8 @@ def page2tsv(page_xml_file, tsv_out_file, image_url, ner_rest_endpoint, noproxy,
tsv = pd.DataFrame(tsv, columns=['rid', 'line', 'hcenter'] + out_columns)
vlinecenter = pd.DataFrame(tsv[['line', 'top']].groupby('line', sort=False).mean().top +
(tsv[['line', 'bottom']].groupby('line').mean().bottom -
tsv[['line', 'top']].groupby('line').mean().top) / 2, columns=['vlinecenter'])
(tsv[['line', 'bottom']].groupby('line', sort=False).mean().bottom -
tsv[['line', 'top']].groupby('line', sort=False).mean().top) / 2, columns=['vlinecenter'])
tsv = tsv.merge(vlinecenter, left_on='line', right_index=True)