def evaluate(gold_file, pred_file):
"""Evaluate using official CoNLL-X evaluation script (Yuval Krymolowski)
Args:
gold_file(str): The gold conllx file
pred_file(str): The pred conllx file
Returns:
"""
gold_file = get_resource(gold_file)
fixed_pred_file = tempfile.NamedTemporaryFile().name
copy_cols(gold_file, pred_file, fixed_pred_file, keep_comments=False)
if gold_file.endswith('.conllu'):
fixed_gold_file = tempfile.NamedTemporaryFile().name
copy_cols(gold_file, gold_file, fixed_gold_file, keep_comments=False)
gold_file = fixed_gold_file
exitcode, out, err = get_exitcode_stdout_stderr(
f'perl {CONLLX_EVAL} -q -b -g {gold_file} -s {fixed_pred_file}')
if exitcode:
raise RuntimeError(
f'eval.pl exited with error code {exitcode} and error message {err} and output {out}.'
)
lines = out.split('\n')[-4:]
las = int(lines[0].split()[3]) / int(lines[0].split()[5])
uas = int(lines[1].split()[3]) / int(lines[1].split()[5])
return uas, las
def ensure_python_points_to_python2():
exitcode, out, version = get_exitcode_stdout_stderr('python --version')
if not version:
version = out
if not version.startswith('Python 2'):
raise EnvironmentError(
f'Your python command needs to be Python2, not {version.strip()}. Try:\n\n\t'
'ln -sf "$(which python2)" "$(which python)"')
def run_perl(script, src, dst=None):
os.environ['PERL5LIB'] = f''
exitcode, out, err = get_exitcode_stdout_stderr(
f'perl -I{os.path.expanduser("~/.local/lib/perl5")} {script} {src}')
if exitcode:
# cpanm -l ~/.local namespace::autoclean
# cpanm -l ~/.local Moose
# cpanm -l ~/.local MooseX::SemiAffordanceAccessor module
raise RuntimeError(err)
with open(dst, 'w') as ofile:
ofile.write(out)
return dst
def run_perl(script, src, dst=None):
if not dst:
dst = tempfile.NamedTemporaryFile().name
exitcode, out, err = get_exitcode_stdout_stderr(
f'perl -I{os.path.expanduser("~/.local/lib/perl5")} {script} {src}')
if exitcode:
# cpanm -l ~/.local namespace::autoclean
# cpanm -l ~/.local Moose
# cpanm -l ~/.local MooseX::SemiAffordanceAccessor module
raise RuntimeError(err)
with open(dst, 'w') as ofile:
ofile.write(out)
return dst
def convert_to_stanford_dependency_330(src, dst):
cprint(
f'Converting {os.path.basename(src)} to {os.path.basename(dst)} using Stanford Parser Version 3.3.0. '
f'It might take a while [blink][yellow]...[/yellow][/blink]')
sp_home = 'https://nlp.stanford.edu/software/stanford-parser-full-2013-11-12.zip'
sp_home = get_resource(sp_home)
# jar_path = get_resource(f'{sp_home}#stanford-parser.jar')
code, out, err = get_exitcode_stdout_stderr(
f'java -cp {sp_home}/* edu.stanford.nlp.trees.international.pennchinese.ChineseGrammaticalStructure '
f'-basic -keepPunct -conllx '
f'-treeFile {src}')
with open(dst, 'w') as f:
f.write(out)
if code:
raise RuntimeError(
f'Conversion failed with code {code} for {src}. The err message is:\n {err}\n'
f'Do you have java installed? Do you have enough memory?')
def convert_to_dependency(src,
dst,
language='zh',
version='3.3.0',
conllx=True,
ud=False):
cprint(
f'Converting {os.path.basename(src)} to {os.path.basename(dst)} using Stanford Parser Version {version}. '
f'It might take a while [blink][yellow]...[/yellow][/blink]')
if version == '3.3.0':
sp_home = 'https://nlp.stanford.edu/software/stanford-parser-full-2013-11-12.zip'
elif version == '4.2.0':
sp_home = 'https://nlp.stanford.edu/software/stanford-parser-4.2.0.zip'
else:
raise ValueError(f'Unsupported version {version}')
sp_home = get_resource(sp_home)
# jar_path = get_resource(f'{sp_home}#stanford-parser.jar')
if ud:
jclass = 'edu.stanford.nlp.trees.international.pennchinese.UniversalChineseGrammaticalStructure' if language == 'zh' \
else 'edu.stanford.nlp.trees.ud.UniversalDependenciesConverter'
else:
jclass = 'edu.stanford.nlp.trees.international.pennchinese.ChineseGrammaticalStructure' if language == 'zh' \
else 'edu.stanford.nlp.trees.EnglishGrammaticalStructure'
cmd = f'java -cp {sp_home}/* {jclass} ' \
f'-treeFile {src}'
if conllx:
cmd += ' -conllx'
if not ud:
cmd += f' -basic -keepPunct'
code, out, err = get_exitcode_stdout_stderr(cmd)
with open(dst, 'w') as f:
f.write(out)
if code:
raise RuntimeError(
f'Conversion failed with code {code} for {src}. The err message is:\n {err}\n'
f'Do you have java installed? Do you have enough memory?')