def train_from_file(self, conll_file, verbose=False):
"""
Train MaltParser from a file
:param conll_file: str for the filename of the training input data
:type conll_file: str
"""
# If conll_file is a ZipFilePathPointer,
# then we need to do some extra massaging
if isinstance(conll_file, ZipFilePathPointer):
with tempfile.NamedTemporaryFile(prefix='malt_train.conll.',
dir=self.working_dir,
mode='w',
delete=False) as input_file:
with conll_file.open() as conll_input_file:
conll_str = conll_input_file.read()
input_file.write(text_type(conll_str))
return self.train_from_file(input_file.name, verbose=verbose)
# Generate command to run maltparser.
cmd = self.generate_malt_command(conll_file, mode="learn")
ret = self._execute(cmd, verbose)
if ret != 0:
raise Exception("MaltParser training (%s) failed with exit "
"code %d" % (' '.join(cmd), ret))
self._trained = True
def parse_tagged_sents(self, sentences, verbose=False, top_relation_label='null'):
"""
Use MaltParser to parse multiple POS tagged sentences. Takes multiple
sentences where each sentence is a list of (word, tag) tuples.
The sentences must have already been tokenized and tagged.
:param sentences: Input sentences to parse
:type sentence: list(list(tuple(str, str)))
:return: iter(iter(``DependencyGraph``)) the dependency graph
representation of each sentence
"""
if not self._trained:
raise Exception("Parser has not been trained. Call train() first.")
with tempfile.NamedTemporaryFile(prefix='malt_input.conll.',
dir=self.working_dir, mode='w', delete=False) as input_file:
with tempfile.NamedTemporaryFile(prefix='malt_output.conll.',
dir=self.working_dir, mode='w', delete=False) as output_file:
# Convert list of sentences to CONLL format.
for line in taggedsents_to_conll(sentences):
input_file.write(text_type(line))
input_file.close()
# Generate command to run maltparser.
cmd =self.generate_malt_command(input_file.name,
output_file.name, mode="parse")
# This is a maltparser quirk, it needs to be run
# where the model file is. otherwise it goes into an awkward
# missing .jars or strange -w working_dir problem.
_current_path = os.getcwd() # Remembers the current path.
try: # Change to modelfile path
os.chdir(os.path.split(self.model)[0])
except:
pass
ret = self._execute(cmd, verbose) # Run command.
os.chdir(_current_path) # Change back to current path.
if ret is not 0:
raise Exception("MaltParser parsing (%s) failed with exit "
"code %d" % (' '.join(cmd), ret))
# Must return iter(iter(Tree))
with open(output_file.name) as infile:
for tree_str in infile.read().split('\n\n'):
yield(iter([DependencyGraph(tree_str, top_relation_label=top_relation_label)]))
os.remove(input_file.name)
os.remove(output_file.name)
def parse_tagged_sents(self, sentences, verbose=False, top_relation_label='null'):
"""
Use MaltParser to parse multiple POS tagged sentences. Takes multiple
sentences where each sentence is a list of (word, tag) tuples.
The sentences must have already been tokenized and tagged.
:param sentences: Input sentences to parse
:type sentence: list(list(tuple(str, str)))
:return: iter(iter(``DependencyGraph``)) the dependency graph
representation of each sentence
"""
if not self._trained:
raise Exception("Parser has not been trained. Call train() first.")
with tempfile.NamedTemporaryFile(prefix='malt_input.conll.',
dir=self.working_dir, mode='w', delete=False) as input_file:
with tempfile.NamedTemporaryFile(prefix='malt_output.conll.',
dir=self.working_dir, mode='w', delete=False) as output_file:
# Convert list of sentences to CONLL format.
for line in taggedsents_to_conll(sentences):
input_file.write(text_type(line))
input_file.close()
# Generate command to run maltparser.
cmd =self.generate_malt_command(input_file.name,
output_file.name, mode="parse")
# This is a maltparser quirk, it needs to be run
# where the model file is. otherwise it goes into an awkward
# missing .jars or strange -w working_dir problem.
_current_path = os.getcwd() # Remembers the current path.
try: # Change to modelfile path
os.chdir(os.path.split(self.model)[0])
except:
pass
ret = self._execute(cmd, verbose) # Run command.
os.chdir(_current_path) # Change back to current path.
if ret is not 0:
raise Exception("MaltParser parsing (%s) failed with exit "
"code %d" % (' '.join(cmd), ret))
# Must return iter(iter(Tree))
with open(output_file.name) as infile:
for tree_str in infile.read().split('\n\n'):
yield(iter([DependencyGraph(tree_str, top_relation_label=top_relation_label)]))
os.remove(input_file.name)
os.remove(output_file.name)
def train(self, depgraphs, verbose=False):
"""
Train MaltParser from a list of ``DependencyGraph`` objects
:param depgraphs: list of ``DependencyGraph`` objects for training input data
:type depgraphs: DependencyGraph
"""
# Write the conll_str to malt_train.conll file in /tmp/
with tempfile.NamedTemporaryFile(prefix='malt_train.conll.',
dir=self.working_dir, mode='w', delete=False) as input_file:
input_str = ('\n'.join(dg.to_conll(10) for dg in depgraphs))
input_file.write(text_type(input_str))
# Trains the model with the malt_train.conll
self.train_from_file(input_file.name, verbose=verbose)
# Removes the malt_train.conll once training finishes.
os.remove(input_file.name)
def train(self, depgraphs, verbose=False):
"""
Train MaltParser from a list of ``DependencyGraph`` objects
:param depgraphs: list of ``DependencyGraph`` objects for training input data
:type depgraphs: DependencyGraph
"""
# Write the conll_str to malt_train.conll file in /tmp/
with tempfile.NamedTemporaryFile(prefix='malt_train.conll.',
dir=self.working_dir, mode='w', delete=False) as input_file:
input_str = ('\n'.join(dg.to_conll(10) for dg in depgraphs))
input_file.write(text_type(input_str))
# Trains the model with the malt_train.conll
self.train_from_file(input_file.name, verbose=verbose)
# Removes the malt_train.conll once training finishes.
os.remove(input_file.name)
def train_from_file(self, conll_file, verbose=False):
"""
Train MaltParser from a file
:param conll_file: str for the filename of the training input data
:type conll_file: str
"""
# If conll_file is a ZipFilePathPointer,
# then we need to do some extra massaging
if isinstance(conll_file, ZipFilePathPointer):
with tempfile.NamedTemporaryFile(prefix='malt_train.conll.',
dir=self.working_dir, mode='w', delete=False) as input_file:
with conll_file.open() as conll_input_file:
conll_str = conll_input_file.read()
input_file.write(text_type(conll_str))
return self.train_from_file(input_file.name, verbose=verbose)
# Generate command to run maltparser.
cmd =self.generate_malt_command(conll_file, mode="learn")
ret = self._execute(cmd, verbose)
if ret != 0:
raise Exception("MaltParser training (%s) failed with exit "
"code %d" % (' '.join(cmd), ret))
self._trained = True
