script(steps=[get_abs,
core_nlp,
lemma_trees,
ext_vars,
offsets,
prep_vars,
prune_vars,
tag_trees,
ext_rels,
arts2csv,
vars2csv,
rels2csv],
optional=[get_inp,
remove_server,
start_server,
stop_server,
add_cit,
add_meta,
clean,
clean_cache,
report,
tag_trees,
setup_server,
toneo,
ppgraph],
default_cfg_fnames=[
getenv('MEGAMOUTH_HOME') + '/scripts/megamouth.ini',
getenv('MEGAMOUTH_HOME') + '/scripts/abs/megamouth-abs.ini',
getenv('MEGAMOUTH_HOME') + '/scripts/abs/elsevier/megamouth-abs-elsevier-6.ini',
getenv('MEGAMOUTH_HOME') + '/scripts/local.ini'])
def bibtex(records_dir, bib_dir, resume=False):
lookup_bibtex(records_dir, bib_dir, resume=resume)
@docstring(rank_results)
def rank(results_file):
rank_results(results_file)
@arg("--max-n-records", type=int)
@docstring(results_to_html)
def html(search_results_file, records_dir, results_file,
max_n_records=None):
results_to_html(search_results_file, records_dir, results_file,
max_n_records)
# -----------------------------------------------------------------------------
# Optional steps
# -----------------------------------------------------------------------------
@arg("--max-n", type=int)
@docstring(get_terms)
def terms(csv_file, results_file, max_n=None):
get_terms(csv_file, results_file, max_n)
script(steps=[search, bibtex, rank, html],
optional=[terms, clean],
default_cfg_fnames=['nature-corpus.ini'])
#!/usr/bin/env python
"""
process full-text corpus, segment Plos, part 1
"""
from os import getenv
from baleen.pipeline import script
from baleen.steps import *
from megamouth.steps import get_full, get_inp
script(steps=[
get_full, core_nlp, lemma_trees, ext_vars, offsets, prep_vars, prune_vars,
tag_trees, ext_rels, arts2csv, vars2csv, rels2csv
],
optional=[
get_inp, remove_server, start_server, stop_server, add_cit,
add_meta, clean, clean_cache, report, tag_trees, setup_server,
toneo, ppgraph
],
default_cfg_fnames=[
getenv('MEGAMOUTH_HOME') + '/scripts/megamouth.ini',
getenv('MEGAMOUTH_HOME') + '/scripts/full/megamouth-full.ini',
getenv('MEGAMOUTH_HOME') +
'/scripts/full/plos/megamouth-full-plos-1.ini',
getenv('MEGAMOUTH_HOME') + '/scripts/local.ini'
])
#!/usr/bin/env python
"""
process all fulltracts
"""
from os import getenv
from baleen.pipeline import script
from baleen.steps import *
from megamouth.steps import clean_all
script(steps=[uniq, setup_server, multi_toneo, ppgraph],
optional=[start_server, stop_server, report, clean, clean_cache],
default_cfg_fnames=[
getenv('MEGAMOUTH_HOME') + '/scripts/megamouth.ini',
getenv('MEGAMOUTH_HOME') + '/scripts/full/megamouth-full.ini',
getenv('MEGAMOUTH_HOME') + '/scripts/local.ini'
])
"""
pipeline for extracting variables from text
"""
from baleen.pipeline import script
from baleen.steps import *
script(
steps=[core_nlp,
lemma_trees,
ext_vars,
offsets,
prep_vars,
prune_vars,
tocsv,
setup_server,
toneo,
ppgraph,
tag_trees,
ext_rels,
add_rels,
add_cit,
add_meta],
optional=[remove_server,
start_server,
stop_server,
clean,
clean_cache,
report])
#!/usr/bin/env python
"""
process all fulltracts
"""
from os import getenv
from baleen.pipeline import script
from baleen.steps import *
from megamouth.steps import clean_all
script(steps=[
uniq,
setup_server,
multi_toneo,
ppgraph],
optional=[
start_server,
stop_server,
report,
clean,
clean_cache],
default_cfg_fnames=[
getenv('MEGAMOUTH_HOME') + '/scripts/megamouth.ini',
getenv('MEGAMOUTH_HOME') + '/scripts/full/megamouth-full.ini',
getenv('MEGAMOUTH_HOME') + '/scripts/local.ini'])
"""
run processes to create Nature full corpus
"""
from baleen.pipeline import script
from baleen.steps import core_nlp, lemma_trees, ext_vars, \
offsets, prep_vars, prune_vars
from nature.steps import download, ext_full, soa, tocsv, toneo, ppgraph, \
setupserver, startserver, stopserver, vertical
script(steps=[download,
ext_full,
soa,
core_nlp,
lemma_trees,
ext_vars,
offsets,
prep_vars,
prune_vars,
tocsv,
toneo,
ppgraph],
optional=[
setupserver,
startserver,
stopserver,
vertical],
default_cfg_fnames=['nature-corpus.ini', 'local.ini'],
default_section='FULL')
"""
from baleen.pipeline import script
from baleen.steps import split_sent, parse_sent, lemma_trees, ext_vars, \
offsets, prep_vars, prune_vars
from nature.steps import ext_abs, ext_sent, brat, soa, tocsv, toneo, ppgraph, \
setupserver, startserver, stopserver, vertical
script(steps=[ext_abs,
soa,
split_sent,
ext_sent,
parse_sent,
lemma_trees,
ext_vars,
offsets,
prep_vars,
prune_vars,
tocsv,
toneo,
ppgraph],
optional=[
setupserver,
startserver,
stopserver,
vertical,
brat],
default_cfg_fnames=['nature-corpus.ini', 'local.ini'],
default_section='ABSTRACTS')
