def _cut_valid_data(self):
"""Put aside part of the training set for validation."""
train_size = len(self.train_trees)
# we have multiple references
if self.multiple_refs:
num_refs, refs_stored = self._check_multiple_ref_type(train_size)
# data stored "serially" (all different instances next to each other, then again in the
# same order)
if refs_stored == 'serial':
train_tree_chunks = [
chunk
for chunk in chunk_list(self.train_trees, train_size /
num_refs)
]
train_da_chunks = [
chunk for chunk in chunk_list(self.train_das, train_size /
num_refs)
]
self.valid_trees = [[
chunk[i] for chunk in train_tree_chunks
] for i in xrange(train_size / num_refs -
self.validation_size, train_size / num_refs)]
self.valid_das = train_da_chunks[0][-self.validation_size:]
self.train_trees = sum([
chunk[:-self.validation_size]
for chunk in train_tree_chunks
], [])
self.train_das = sum([
chunk[:-self.validation_size] for chunk in train_da_chunks
], [])
# data stored in "parallel" (all synonymous instances next to each other)
else:
self.valid_trees = [
chunk for chunk in chunk_list(
self.train_trees[-self.validation_size *
num_refs:], num_refs)
]
self.valid_das = self.train_das[-self.validation_size *
num_refs::num_refs]
self.train_trees = self.train_trees[:-self.validation_size *
num_refs]
self.train_das = self.train_das[:-self.validation_size *
num_refs]
# single validation reference
else:
# make "reference lists" of length 1 to accommodate for functions working
# with multiple references
self.valid_trees = [
[tree] for tree in self.train_trees[-self.validation_size:]
]
self.valid_das = self.train_das[-self.validation_size:]
self.train_trees = self.train_trees[:-self.validation_size]
self.train_das = self.train_das[:-self.validation_size]
def _load_valid_data(self, valid_data_paths):
"""Load validation data from separate files (comma-separated list of files with DAs, trees,
and optionally contexts is expected)."""
# parse validation data file specification
valid_data_paths = valid_data_paths.split(',')
if len(
valid_data_paths
) == 3: # with contexts (this does not determine if they're used)
valid_das_file, valid_trees_file, valid_context_file = valid_data_paths
else:
valid_das_file, valid_trees_file = valid_data_paths
# load the validation data
log_info('Reading DAs from ' + valid_das_file + '...')
self.valid_das = read_das(valid_das_file)
self.valid_trees = self._load_trees(valid_trees_file,
selector=self.ref_selectors)
if self.use_context:
self.valid_das = self._load_contexts(self.valid_das,
valid_context_file)
# reorder validation data for multiple references (see also _cut_valid_data)
valid_size = len(self.valid_trees)
if self.multiple_refs:
num_refs, refs_stored = self._check_multiple_ref_type(valid_size)
# serial: different instances next to each other, then synonymous in the same order
if refs_stored == 'serial':
valid_tree_chunks = [
chunk
for chunk in chunk_list(self.valid_trees, valid_size /
num_refs)
]
self.valid_trees = [[chunk[i] for chunk in valid_tree_chunks]
for i in xrange(valid_size / num_refs)]
if len(self.valid_das) > len(self.valid_trees):
self.valid_das = self.valid_das[0:valid_size / num_refs]
# parallel: synonymous instances next to each other
elif refs_stored == 'parallel':
self.valid_trees = [
chunk for chunk in chunk_list(self.valid_trees, num_refs)
]
if len(self.valid_das) > len(self.valid_trees):
self.valid_das = self.valid_das[::num_refs]
# no multiple references; make lists of size 1 to simplify working with the data
else:
self.valid_trees = [[tree] for tree in self.valid_trees]
def sample_gen(args):
from pytreex.core.document import Document
opts, files = getopt(args, 'r:n:o:w:')
num_to_generate = 1
oracle_eval_file = None
fname_ttrees_out = None
for opt, arg in opts:
if opt == '-n':
num_to_generate = int(arg)
elif opt == '-o':
oracle_eval_file = arg
elif opt == '-w':
fname_ttrees_out = arg
if len(files) != 2:
sys.exit(__doc__)
fname_cand_model, fname_da_test = files
# load model
log_info('Initializing...')
candgen = RandomCandidateGenerator.load_from_file(fname_cand_model)
ranker = candgen
tgen = SamplingPlanner({'candgen': candgen, 'ranker': ranker})
# generate
log_info('Generating...')
gen_doc = Document()
das = read_das(fname_da_test)
for da in das:
for _ in xrange(num_to_generate): # repeat generation n times
tgen.generate_tree(da, gen_doc)
# evaluate if needed
if oracle_eval_file is not None:
log_info('Evaluating oracle F1...')
log_info('Loading gold data from ' + oracle_eval_file)
gold_trees = ttrees_from_doc(read_ttrees(oracle_eval_file), tgen.language, tgen.selector)
gen_trees = ttrees_from_doc(gen_doc, tgen.language, tgen.selector)
log_info('Gold data loaded.')
correct, predicted, gold = 0, 0, 0
for gold_tree, gen_trees in zip(gold_trees, chunk_list(gen_trees, num_to_generate)):
# find best of predicted trees (in terms of F1)
_, tc, tp, tg = max([(f1_from_counts(c, p, g), c, p, g) for c, p, g
in map(lambda gen_tree: corr_pred_gold(gold_tree, gen_tree),
gen_trees)],
key=lambda x: x[0])
correct += tc
predicted += tp
gold += tg
# evaluate oracle F1
log_info("Oracle Precision: %.6f, Recall: %.6f, F1: %.6f" % p_r_f1_from_counts(correct, predicted, gold))
# write output
if fname_ttrees_out is not None:
log_info('Writing output...')
write_ttrees(gen_doc, fname_ttrees_out)
def sample_gen(args):
from pytreex.core.document import Document
opts, files = getopt(args, 'r:n:o:w:')
num_to_generate = 1
oracle_eval_file = None
fname_ttrees_out = None
for opt, arg in opts:
if opt == '-n':
num_to_generate = int(arg)
elif opt == '-o':
oracle_eval_file = arg
elif opt == '-w':
fname_ttrees_out = arg
if len(files) != 2:
sys.exit(__doc__)
fname_cand_model, fname_da_test = files
# load model
log_info('Initializing...')
candgen = RandomCandidateGenerator.load_from_file(fname_cand_model)
ranker = candgen
tgen = SamplingPlanner({'candgen': candgen, 'ranker': ranker})
# generate
log_info('Generating...')
gen_doc = Document()
das = read_das(fname_da_test)
for da in das:
for _ in xrange(num_to_generate): # repeat generation n times
tgen.generate_tree(da, gen_doc)
# evaluate if needed
if oracle_eval_file is not None:
log_info('Evaluating oracle F1...')
log_info('Loading gold data from ' + oracle_eval_file)
gold_trees = ttrees_from_doc(read_ttrees(oracle_eval_file), tgen.language, tgen.selector)
gen_trees = ttrees_from_doc(gen_doc, tgen.language, tgen.selector)
log_info('Gold data loaded.')
correct, predicted, gold = 0, 0, 0
for gold_tree, gen_trees in zip(gold_trees, chunk_list(gen_trees, num_to_generate)):
# find best of predicted trees (in terms of F1)
_, tc, tp, tg = max([(f1_from_counts(c, p, g), c, p, g) for c, p, g
in map(lambda gen_tree: corr_pred_gold(gold_tree, gen_tree),
gen_trees)],
key=lambda x: x[0])
correct += tc
predicted += tp
gold += tg
# evaluate oracle F1
log_info("Oracle Precision: %.6f, Recall: %.6f, F1: %.6f" % p_r_f1_from_counts(correct, predicted, gold))
# write output
if fname_ttrees_out is not None:
log_info('Writing output...')
write_ttrees(gen_doc, fname_ttrees_out)
def _cut_valid_data(self):
"""Put aside part of the training set for validation."""
train_size = len(self.train_trees)
# we have multiple references
if self.multiple_refs:
num_refs, refs_stored = self._check_multiple_ref_type(train_size)
# data stored "serially" (all different instances next to each other, then again in the
# same order)
if refs_stored == 'serial':
train_tree_chunks = [chunk for chunk in
chunk_list(self.train_trees, train_size / num_refs)]
train_da_chunks = [chunk for chunk in
chunk_list(self.train_das, train_size / num_refs)]
self.valid_trees = [[chunk[i] for chunk in train_tree_chunks]
for i in xrange(train_size / num_refs - self.validation_size,
train_size / num_refs)]
self.valid_das = train_da_chunks[0][-self.validation_size:]
self.train_trees = sum([chunk[:-self.validation_size]
for chunk in train_tree_chunks], [])
self.train_das = sum([chunk[:-self.validation_size]
for chunk in train_da_chunks], [])
# data stored in "parallel" (all synonymous instances next to each other)
else:
self.valid_trees = [chunk for chunk in
chunk_list(self.train_trees[-self.validation_size * num_refs:],
num_refs)]
self.valid_das = self.train_das[-self.validation_size * num_refs::num_refs]
self.train_trees = self.train_trees[:-self.validation_size * num_refs]
self.train_das = self.train_das[:-self.validation_size * num_refs]
# single validation reference
else:
# make "reference lists" of length 1 to accommodate for functions working
# with multiple references
self.valid_trees = [[tree] for tree in self.train_trees[-self.validation_size:]]
self.valid_das = self.train_das[-self.validation_size:]
self.train_trees = self.train_trees[:-self.validation_size]
self.train_das = self.train_das[:-self.validation_size]
def _load_valid_data(self, valid_data_paths):
"""Load validation data from separate files (comma-separated list of files with DAs, trees,
and optionally contexts is expected)."""
# parse validation data file specification
valid_data_paths = valid_data_paths.split(',')
if len(valid_data_paths) == 3: # with contexts (this does not determine if they're used)
valid_das_file, valid_trees_file, valid_context_file = valid_data_paths
else:
valid_das_file, valid_trees_file = valid_data_paths
# load the validation data
log_info('Reading DAs from ' + valid_das_file + '...')
self.valid_das = read_das(valid_das_file)
self.valid_trees = self._load_trees(valid_trees_file, selector=self.ref_selectors)
if self.use_context:
self.valid_das = self._load_contexts(self.valid_das, valid_context_file)
# reorder validation data for multiple references (see also _cut_valid_data)
valid_size = len(self.valid_trees)
if self.multiple_refs:
num_refs, refs_stored = self._check_multiple_ref_type(valid_size)
# serial: different instances next to each other, then synonymous in the same order
if refs_stored == 'serial':
valid_tree_chunks = [chunk for chunk in
chunk_list(self.valid_trees, valid_size / num_refs)]
self.valid_trees = [[chunk[i] for chunk in valid_tree_chunks]
for i in xrange(valid_size / num_refs)]
if len(self.valid_das) > len(self.valid_trees):
self.valid_das = self.valid_das[0:valid_size / num_refs]
# parallel: synonymous instances next to each other
elif refs_stored == 'parallel':
self.valid_trees = [chunk for chunk in chunk_list(self.valid_trees, num_refs)]
if len(self.valid_das) > len(self.valid_trees):
self.valid_das = self.valid_das[::num_refs]
# no multiple references; make lists of size 1 to simplify working with the data
else:
self.valid_trees = [[tree] for tree in self.valid_trees]