explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-24 00:46:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Edits to align_raw script, for use in prepare_treebank

Browse Source
This commit is contained in:
Matthew Honnibal 2015-05-27 04:23:31 +02:00
parent 4010b9b6d9
commit 732fa7709a
1 changed files with 7 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
spacy/munge/align_raw.py
View File

@ -183,13 +183,15 @@ def get_sections(odc_dir, ptb_dir, out_dir):
yield odc_loc, ptb_sec, out_loc
def align_section(raw_paragraphs, ptb_files):
aligned = get_alignment(raw_paragraphs, ptb_files)
return [(fn, group_into_paras(sents))
for fn, sents in group_into_files(aligned)]
def do_wsj(odc_dir, ptb_dir, out_dir):
for odc_loc, ptb_sec_dir, out_loc in get_sections(odc_dir, ptb_dir, out_dir):
raw_paragraphs = read_odc(odc_loc)
ptb_files = read_ptb_sec(ptb_sec_dir)
aligned = get_alignment(raw_paragraphs, ptb_files)
files = [(fn, group_into_paras(sents))
for fn, sents in group_into_files(aligned)]
files = align_section(read_odc(odc_loc), read_ptb_sec(ptb_sec_dir))
with open(out_loc, 'w') as file_:
json.dump(files, file_)