sporada/nlp
1
0
Fork 0
mirror of https://gitlab.ub.uni-bielefeld.de/sfb1288inf/nlp.git synced 2025-10-31 13:02:44 +00:00
Code Issues Projects Releases Wiki Activity

Codestyle

Browse Source
This commit is contained in:
Patrick Jentsch
2019-09-11 16:15:41 +02:00
parent 43717de313
commit af293d6141
2 changed files with 53 additions and 64 deletions
Download Patch File Download Diff File Expand all files Collapse all files

60
nlp
View File

@@ -18,33 +18,23 @@ from pyflow import WorkflowRunner
def parse_arguments():
parser = argparse.ArgumentParser(
description='Performs NLP of documents utilizing spaCy. The results are served as verticalized text files.'
)
parser.add_argument(
'-i',
dest='input_dir',
required=True
description=('Performs NLP of documents utilizing spaCy. The results '
'are served as verticalized text files.')
)
parser.add_argument('-i', dest='input_dir', required=True)
parser.add_argument(
'-l',
choices=['de', 'el', 'en', 'es', 'fr', 'it', 'nl', 'pt'],
dest='lang',
required=True
)
parser.add_argument(
'-o',
dest='output_dir',
required=True
)
parser.add_argument(
'--nCores',
default=min(4, multiprocessing.cpu_count()),
dest='n_cores',
help='total number of cores available',
required=False,
type=int
)
parser.add_argument('-o', dest='output_dir', required=True)
parser.add_argument('--nCores',
default=min(4, multiprocessing.cpu_count()),
dest='n_cores',
help='total number of cores available',
required=False,
type=int)
return parser.parse_args()
@@ -65,11 +55,11 @@ class NLPWorkflow(WorkflowRunner):
'''
create_output_directories_jobs = []
for index, job in enumerate(self.jobs):
cmd = 'mkdir -p "%s"' % (job['output_dir'])
cmd = 'mkdir -p "{}"'.format(job['output_dir'])
create_output_directories_jobs.append(
self.addTask(
command=cmd,
label='create_output_directories_job_-_%i' % (index)
label='create_output_directories_job_-_{}'.format(index)
)
)
@@ -84,7 +74,7 @@ class NLPWorkflow(WorkflowRunner):
max(1, int(self.n_cores / len(self.jobs)))
)
for index, job in enumerate(self.jobs):
cmd = 'spacy_nlp -l "%s" "%s" "%s"' % (
cmd = 'spacy_nlp -l "{}" "{}" "{}"'.format(
self.lang,
job['path'],
os.path.join(job['output_dir'], job['name'] + '.vrt')
@@ -92,8 +82,10 @@ class NLPWorkflow(WorkflowRunner):
nlp_jobs.append(
self.addTask(
command=cmd,
dependencies='create_output_directories_job_-_%i' % (index),
label='nlp_job_-_%i' % (index),
dependencies='create_output_directories_job_-_{}'.format(
index
),
label='nlp_job_-_{}'.format(index),
nCores=nlp_job_n_cores
)
)
@@ -104,19 +96,13 @@ def analyze_jobs(input_dir, output_dir):
for file in os.listdir(input_dir):
if os.path.isdir(os.path.join(input_dir, file)):
jobs += analyze_jobs(
os.path.join(input_dir, file),
os.path.join(output_dir, file),
)
jobs += analyze_jobs(os.path.join(input_dir, file),
os.path.join(output_dir, file))
elif file.endswith('.txt'):
jobs.append(
{
'filename': file,
'name': file.rsplit('.', 1)[0],
'output_dir': os.path.join(output_dir, file),
'path': os.path.join(input_dir, file)
}
)
jobs.append({'filename': file,
'name': file.rsplit('.', 1)[0],
'output_dir': os.path.join(output_dir, file),
'path': os.path.join(input_dir, file)})
return jobs

57
spacy_nlp
View File

@@ -7,29 +7,25 @@ import spacy
import textwrap
parser = argparse.ArgumentParser(
description='Tag a text file with spaCy and save it as a verticalized text file.'
)
parser.add_argument(
'i',
metavar='txt-sourcefile',
)
parser.add_argument(
'-l',
choices=['de', 'el', 'en', 'es', 'fr', 'it', 'nl', 'pt'],
dest='lang',
required=True
)
parser.add_argument(
'o',
metavar='vrt-destfile',
description=('Tag a text file with spaCy and save it as a verticalized '
'text file.')
)
parser.add_argument('i', metavar='txt-sourcefile')
parser.add_argument('-l',
choices=['de', 'el', 'en', 'es', 'fr', 'it', 'nl', 'pt'],
dest='lang',
required=True)
parser.add_argument('o', metavar='vrt-destfile')
args = parser.parse_args()
SPACY_MODELS = {
'de': 'de_core_news_sm', 'el': 'el_core_news_sm', 'en': 'en_core_web_sm',
'es': 'es_core_news_sm', 'fr': 'fr_core_news_sm', 'it': 'it_core_news_sm',
'nl': 'nl_core_news_sm', 'pt': 'pt_core_news_sm'
}
SPACY_MODELS = {'de': 'de_core_news_sm',
'el': 'el_core_news_sm',
'en': 'en_core_web_sm',
'es': 'es_core_news_sm',
'fr': 'fr_core_news_sm',
'it': 'it_core_news_sm',
'nl': 'nl_core_news_sm',
'pt': 'pt_core_news_sm'}
# Set the language model for spacy
nlp = spacy.load(SPACY_MODELS[args.lang])
@@ -45,9 +41,9 @@ with open(args.i) as input_file:
output_file = open(args.o, 'w+')
output_file.write(
'<?xml version="1.0" encoding="UTF-8"?>\n<corpus>\n<text id="%s">\n' % (
os.path.basename(args.i).rsplit(".", 1)[0]
)
'<?xml version="1.0" encoding="UTF-8"?>\n'
'<corpus>\n'
'<text id="{}">\n'.format(os.path.basename(args.i).rsplit(".", 1)[0])
)
for text in texts:
# Run spacy nlp over the text (partial string if above 1 million chars)
@@ -61,11 +57,18 @@ for text in texts:
# Write all information in .vrt style to the output file
# text, lemma, simple_pos, pos, ner
output_file.write(
token.text + '\t' + token.lemma_ + '\t'
+ token.pos_ + '\t' + token.tag_ + '\t'
+ (token.ent_type_ if token.ent_type_ != '' else 'NULL') + '\n'
'{}\t{}\t{}\t{}\t{}\n'.format(
token.text,
token.lemma_,
token.pos_,
token.tag_,
token.ent_type_ if token.ent_type_ != '' else 'NULL'
)
)
output_file.write('</s>\n')
output_file.write('</text>\n</corpus>')
output_file.write(
'</text>\n'
'</corpus>'
)
output_file.close()