def run_training(head_host, head_port, debug_out=None):
"""Main worker training routine (creates the Seq2SeqTrainingService and connects it to the
head.
@param head_host: hostname of the head
@param head_port: head port number
@param debug_out: path to the debugging output file (debug output discarded if None)
"""
# setup debugging output, if applicable
if debug_out is not None:
set_debug_stream(file_stream(debug_out, mode='w'))
# start the server (in the background)
log_info('Creating training server...')
server = ThreadPoolServer(service=Seq2SeqTrainingService, nbThreads=1)
server_thread = Thread(target=server.start)
server_thread.start()
my_host = socket.getfqdn()
log_info('Worker server created at %s:%d. Connecting to head at %s:%d...' %
(my_host, server.port, head_host, head_port))
# notify main about this server
conn = connect(head_host, head_port, config={'allow_pickle': True})
conn.root.register_worker(my_host, server.port)
conn.close()
log_info('Worker is registered with the head.')
# now serve until we're killed (the server thread will continue to run)
server_thread.join()
def percrank_train(args):
opts, files = getopt(args, 'c:d:s:j:w:e:r:')
candgen_model = None
train_size = 1.0
parallel = False
jobs_number = 0
work_dir = None
experiment_id = None
for opt, arg in opts:
if opt == '-d':
set_debug_stream(file_stream(arg, mode='w'))
elif opt == '-s':
train_size = float(arg)
elif opt == '-c':
candgen_model = arg
elif opt == '-j':
parallel = True
jobs_number = int(arg)
elif opt == '-w':
work_dir = arg
elif opt == '-e':
experiment_id = arg
elif opt == '-r' and arg:
rnd.seed(arg)
if len(files) != 4:
sys.exit(__doc__)
fname_rank_config, fname_train_das, fname_train_ttrees, fname_rank_model = files
log_info('Training perceptron ranker...')
rank_config = Config(fname_rank_config)
if candgen_model:
rank_config['candgen_model'] = candgen_model
if rank_config.get('nn'):
from tgen.rank_nn import SimpleNNRanker, EmbNNRanker
if rank_config['nn'] in ['emb', 'emb_trees', 'emb_prev']:
ranker_class = EmbNNRanker
else:
ranker_class = SimpleNNRanker
else:
ranker_class = PerceptronRanker
log_info('Using %s for ranking' % ranker_class.__name__)
if not parallel:
ranker = ranker_class(rank_config)
else:
rank_config['jobs_number'] = jobs_number
if work_dir is None:
work_dir, _ = os.path.split(fname_rank_config)
ranker = ParallelRanker(rank_config, work_dir, experiment_id,
ranker_class)
ranker.train(fname_train_das, fname_train_ttrees, data_portion=train_size)
# avoid the "maximum recursion depth exceeded" error
sys.setrecursionlimit(100000)
ranker.save_to_file(fname_rank_model)
def percrank_train(args):
opts, files = getopt(args, 'c:d:s:j:w:e:r:')
candgen_model = None
train_size = 1.0
parallel = False
jobs_number = 0
work_dir = None
experiment_id = None
for opt, arg in opts:
if opt == '-d':
set_debug_stream(file_stream(arg, mode='w'))
elif opt == '-s':
train_size = float(arg)
elif opt == '-c':
candgen_model = arg
elif opt == '-j':
parallel = True
jobs_number = int(arg)
elif opt == '-w':
work_dir = arg
elif opt == '-e':
experiment_id = arg
elif opt == '-r' and arg:
rnd.seed(arg)
if len(files) != 4:
sys.exit(__doc__)
fname_rank_config, fname_train_das, fname_train_ttrees, fname_rank_model = files
log_info('Training perceptron ranker...')
rank_config = Config(fname_rank_config)
if candgen_model:
rank_config['candgen_model'] = candgen_model
if rank_config.get('nn'):
from tgen.rank_nn import SimpleNNRanker, EmbNNRanker
if rank_config['nn'] in ['emb', 'emb_trees', 'emb_prev']:
ranker_class = EmbNNRanker
else:
ranker_class = SimpleNNRanker
else:
ranker_class = PerceptronRanker
log_info('Using %s for ranking' % ranker_class.__name__)
if not parallel:
ranker = ranker_class(rank_config)
else:
rank_config['jobs_number'] = jobs_number
if work_dir is None:
work_dir, _ = os.path.split(fname_rank_config)
ranker = ParallelRanker(rank_config, work_dir, experiment_id, ranker_class)
ranker.train(fname_train_das, fname_train_ttrees, data_portion=train_size)
# avoid the "maximum recursion depth exceeded" error
sys.setrecursionlimit(100000)
ranker.save_to_file(fname_rank_model)
def seq2seq_train(args):
ap = ArgumentParser(prog=' '.join(sys.argv[0:2]))
ap.add_argument('-s', '--train-size', type=float,
help='Portion of the training data to use (default: 1.0)', default=1.0)
ap.add_argument('-d', '--debug-logfile', type=str, help='Debug output file name')
ap.add_argument('-j', '--jobs', type=int, help='Number of parallel jobs to use')
ap.add_argument('-w', '--work-dir', type=str, help='Main working directory for parallel jobs')
ap.add_argument('-e', '--experiment-id', type=str,
help='Experiment ID for parallel jobs (used as job name prefix)')
ap.add_argument('-r', '--random-seed', type=str,
help='Initial random seed (used as string).')
ap.add_argument('-c', '--context-file', type=str,
help='Input ttree/text file with context utterances')
ap.add_argument('-v', '--valid-data', type=str,
help='Validation data paths (2-3 comma-separated files: DAs, trees/sentences, contexts)')
ap.add_argument('-l', '--lexic-data', type=str,
help='Lexicalization data paths (1-2 comma-separated files: surface forms,' +
'training lexic. instructions)')
ap.add_argument('-t', '--tb-summary-dir', '--tensorboard-summary-dir', '--tensorboard', type=str,
help='Directory where Tensorboard summaries are saved during training')
ap.add_argument('seq2seq_config_file', type=str, help='Seq2Seq generator configuration file')
ap.add_argument('da_train_file', type=str, help='Input training DAs')
ap.add_argument('tree_train_file', type=str, help='Input training trees/sentences')
ap.add_argument('seq2seq_model_file', type=str,
help='File name where to save the trained Seq2Seq generator model')
args = ap.parse_args(args)
if args.debug_logfile:
set_debug_stream(file_stream(args.debug_logfile, mode='w'))
if args.random_seed:
rnd.seed(args.random_seed)
log_info('Training sequence-to-sequence generator...')
config = Config(args.seq2seq_config_file)
if args.tb_summary_dir: # override Tensorboard setting
config['tb_summary_dir'] = args.tb_summary_dir
if args.jobs: # parallelize when training
config['jobs_number'] = args.jobs
if not args.work_dir:
work_dir, _ = os.path.split(args.seq2seq_config_file)
generator = ParallelSeq2SeqTraining(config, args.work_dir or work_dir, args.experiment_id)
else: # just a single training instance
generator = Seq2SeqGen(config)
generator.train(args.da_train_file, args.tree_train_file,
data_portion=args.train_size, context_file=args.context_file,
validation_files=args.valid_data, lexic_files=args.lexic_data)
sys.setrecursionlimit(100000)
generator.save_to_file(args.seq2seq_model_file)
def seq2seq_train(args):
ap = ArgumentParser(prog=' '.join(sys.argv[0:2]))
ap.add_argument('-s', '--train-size', type=float,
help='Portion of the training data to use (default: 1.0)', default=1.0)
ap.add_argument('-d', '--debug-logfile', type=str, help='Debug output file name')
ap.add_argument('-j', '--jobs', type=int, help='Number of parallel jobs to use')
ap.add_argument('-w', '--work-dir', type=str, help='Main working directory for parallel jobs')
ap.add_argument('-e', '--experiment-id', type=str,
help='Experiment ID for parallel jobs (used as job name prefix)')
ap.add_argument('-r', '--random-seed', type=str,
help='Initial random seed (used as string).')
ap.add_argument('-c', '--context-file', type=str,
help='Input ttree/text file with context utterances')
ap.add_argument('-v', '--valid-data', type=str,
help='Validation data paths (2-3 comma-separated files: DAs, trees/sentences, contexts)')
ap.add_argument('-l', '--lexic-data', type=str,
help='Lexicalization data paths (1-2 comma-separated files: surface forms,' +
'training lexic. instructions)')
ap.add_argument('-t', '--tb-summary-dir', '--tensorboard-summary-dir', '--tensorboard', type=str,
help='Directory where Tensorboard summaries are saved during training')
ap.add_argument('seq2seq_config_file', type=str, help='Seq2Seq generator configuration file')
ap.add_argument('da_train_file', type=str, help='Input training DAs')
ap.add_argument('tree_train_file', type=str, help='Input training trees/sentences')
ap.add_argument('seq2seq_model_file', type=str,
help='File name where to save the trained Seq2Seq generator model')
args = ap.parse_args(args)
if args.debug_logfile:
set_debug_stream(file_stream(args.debug_logfile, mode='w'))
if args.random_seed:
rnd.seed(args.random_seed)
log_info('Training sequence-to-sequence generator...')
config = Config(args.seq2seq_config_file)
if args.tb_summary_dir: # override Tensorboard setting
config['tb_summary_dir'] = args.tb_summary_dir
if args.jobs: # parallelize when training
config['jobs_number'] = args.jobs
if not args.work_dir:
work_dir, _ = os.path.split(args.seq2seq_config_file)
generator = ParallelSeq2SeqTraining(config, args.work_dir or work_dir, args.experiment_id)
else: # just a single training instance
generator = Seq2SeqGen(config)
generator.train(args.da_train_file, args.tree_train_file,
data_portion=args.train_size, context_file=args.context_file,
validation_files=args.valid_data, lexic_files=args.lexic_data)
sys.setrecursionlimit(100000)
generator.save_to_file(args.seq2seq_model_file)
def percrank_train(args):
opts, files = getopt(args, 'c:d:s:j:w:e:')
candgen_model = None
train_size = 1.0
parallel = False
jobs_number = 0
work_dir = None
experiment_id = None
for opt, arg in opts:
if opt == '-d':
set_debug_stream(file_stream(arg, mode='w'))
elif opt == '-s':
train_size = float(arg)
elif opt == '-c':
candgen_model = arg
elif opt == '-j':
parallel = True
jobs_number = int(arg)
elif opt == '-w':
work_dir = arg
elif opt == '-e':
experiment_id = arg
if len(files) != 4:
sys.exit(__doc__)
fname_rank_config, fname_train_das, fname_train_ttrees, fname_rank_model = files
log_info('Training perceptron ranker...')
rank_config = Config(fname_rank_config)
if candgen_model:
rank_config['candgen_model'] = candgen_model
if rank_config.get('nn'):
if rank_config['nn'] == 'emb':
ranker_class = EmbNNRanker
else:
ranker_class = SimpleNNRanker
else:
ranker_class = PerceptronRanker
if not parallel:
ranker = ranker_class(rank_config)
else:
rank_config['jobs_number'] = jobs_number
if work_dir is None:
work_dir, _ = os.path.split(fname_rank_config)
ranker = ParallelRanker(rank_config, work_dir, experiment_id, ranker_class)
ranker.train(fname_train_das, fname_train_ttrees, data_portion=train_size)
ranker.save_to_file(fname_rank_model)
def seq2seq_train(args):
ap = ArgumentParser()
ap.add_argument('-s', '--train-size', type=float,
help='Portion of the training data to use (default: 1.0)', default=1.0)
ap.add_argument('-d', '--debug-logfile', type=str, help='Debug output file name')
ap.add_argument('-j', '--jobs', type=int, help='Number of parallel jobs to use')
ap.add_argument('-w', '--work-dir', type=str, help='Main working for parallel jobs')
ap.add_argument('-e', '--experiment-id', type=str,
help='Experiment ID for parallel jobs (used as job name prefix)')
ap.add_argument('-r', '--random-seed', type=str,
help='Initial random seed (used as string).')
ap.add_argument('-c', '--context-file', type=str,
help='Input ttree/text file with context utterances')
ap.add_argument('-v', '--valid-data', type=str,
help='Validation data paths (2-3 comma-separated files: DAs, trees/sentences, contexts)')
ap.add_argument('seq2seq_config_file', type=str, help='Seq2Seq generator configuration file')
ap.add_argument('da_train_file', type=str, help='Input training DAs')
ap.add_argument('tree_train_file', type=str, help='Input training trees/sentences')
ap.add_argument('seq2seq_model_file', type=str,
help='File name where to save the trained Seq2Seq generator model')
args = ap.parse_args(args)
if args.debug_logfile:
set_debug_stream(file_stream(args.debug_logfile, mode='w'))
if args.random_seed:
rnd.seed(rnd.seed(args.random_seed))
log_info('Training sequence-to-sequence generator...')
config = Config(args.seq2seq_config_file)
if args.jobs:
config['jobs_number'] = args.jobs
if not args.work_dir:
work_dir, _ = os.path.split(args.seq2seq_config_file)
generator = ParallelSeq2SeqTraining(config, args.work_dir or work_dir, args.experiment_id)
else:
generator = Seq2SeqGen(config)
generator.train(args.da_train_file, args.tree_train_file,
data_portion=args.train_size, context_file=args.context_file,
validation_files=args.valid_data)
sys.setrecursionlimit(100000)
generator.save_to_file(args.seq2seq_model_file)
def candgen_train(args):
opts, files = getopt(args, 'p:lnc:sd:t:')
prune_threshold = 1
parent_lemmas = False
node_limits = False
comp_type = None
comp_limit = None
comp_slots = False
tree_classif = False
for opt, arg in opts:
if opt == '-p':
prune_threshold = int(arg)
elif opt == '-d':
set_debug_stream(file_stream(arg, mode='w'))
elif opt == '-l':
parent_lemmas = True
elif opt == '-n':
node_limits = True
elif opt == '-c':
comp_type = arg
if ':' in comp_type:
comp_type, comp_limit = comp_type.split(':', 1)
comp_limit = int(comp_limit)
elif opt == '-t':
tree_classif = Config(arg)
elif opt == '-s':
comp_slots = True
if len(files) != 3:
sys.exit("Invalid arguments.\n" + __doc__)
fname_da_train, fname_ttrees_train, fname_cand_model = files
log_info('Training candidate generator...')
candgen = RandomCandidateGenerator({
'prune_threshold': prune_threshold,
'parent_lemmas': parent_lemmas,
'node_limits': node_limits,
'compatible_dais_type': comp_type,
'compatible_dais_limit': comp_limit,
'compatible_slots': comp_slots,
'tree_classif': tree_classif
})
candgen.train(fname_da_train, fname_ttrees_train)
candgen.save_to_file(fname_cand_model)
def candgen_train(args):
opts, files = getopt(args, 'p:lnc:sd:t:')
prune_threshold = 1
parent_lemmas = False
node_limits = False
comp_type = None
comp_limit = None
comp_slots = False
tree_classif = False
for opt, arg in opts:
if opt == '-p':
prune_threshold = int(arg)
elif opt == '-d':
set_debug_stream(file_stream(arg, mode='w'))
elif opt == '-l':
parent_lemmas = True
elif opt == '-n':
node_limits = True
elif opt == '-c':
comp_type = arg
if ':' in comp_type:
comp_type, comp_limit = comp_type.split(':', 1)
comp_limit = int(comp_limit)
elif opt == '-t':
tree_classif = Config(arg)
elif opt == '-s':
comp_slots = True
if len(files) != 3:
sys.exit("Invalid arguments.\n" + __doc__)
fname_da_train, fname_ttrees_train, fname_cand_model = files
log_info('Training candidate generator...')
candgen = RandomCandidateGenerator({'prune_threshold': prune_threshold,
'parent_lemmas': parent_lemmas,
'node_limits': node_limits,
'compatible_dais_type': comp_type,
'compatible_dais_limit': comp_limit,
'compatible_slots': comp_slots,
'tree_classif': tree_classif})
candgen.train(fname_da_train, fname_ttrees_train)
candgen.save_to_file(fname_cand_model)
def seq2seq_gen(args):
"""Sequence-to-sequence generation"""
def write_trees_or_tokens(output_file, das, gen_trees, base_doc, language,
selector):
"""Decide to write t-trees or tokens based on the output file name."""
if output_file.endswith('.txt'):
gen_toks = [t.to_tok_list() for t in gen_trees]
postprocess_tokens(gen_toks, das)
write_tokens(gen_toks, output_file)
else:
write_ttrees(
create_ttree_doc(gen_trees, base_doc, language, selector),
output_file)
ap = ArgumentParser(prog=' '.join(sys.argv[0:2]))
ap.add_argument('-e',
'--eval-file',
type=str,
help='A ttree/text file for evaluation')
ap.add_argument(
'-a',
'--abstr-file',
type=str,
help=
'Lexicalization file (a.k.a. abstraction instructions, for postprocessing)'
)
ap.add_argument('-r',
'--ref-selector',
type=str,
default='',
help='Selector for reference trees in the evaluation file')
ap.add_argument(
'-t',
'--target-selector',
type=str,
default='',
help='Target selector for generated trees in the output file')
ap.add_argument('-d',
'--debug-logfile',
type=str,
help='Debug output file name')
ap.add_argument('-w',
'--output-file',
type=str,
help='Output tree/text file')
ap.add_argument('-D',
'--delex-output-file',
type=str,
help='Output file for trees/text before lexicalization')
ap.add_argument('-b',
'--beam-size',
type=int,
help='Override beam size for beam search decoding')
ap.add_argument('-c',
'--context-file',
type=str,
help='Input ttree/text file with context utterances')
ap.add_argument('seq2seq_model_file',
type=str,
help='Trained Seq2Seq generator model')
ap.add_argument('da_test_file', type=str, help='Input DAs for generation')
args = ap.parse_args(args)
if args.debug_logfile:
set_debug_stream(file_stream(args.debug_logfile, mode='w'))
# load the generator
tgen = Seq2SeqBase.load_from_file(args.seq2seq_model_file)
if args.beam_size is not None:
tgen.beam_size = args.beam_size
# read input files (DAs, contexts)
das = read_das(args.da_test_file)
if args.context_file:
if not tgen.use_context and not tgen.context_bleu_weight:
log_warn(
'Generator is not trained to use context, ignoring context input file.'
)
else:
if args.context_file.endswith('.txt'):
contexts = read_tokens(args.context_file)
else:
contexts = tokens_from_doc(read_ttrees(args.context_file),
tgen.language, tgen.selector)
das = [(context, da) for context, da in zip(contexts, das)]
elif tgen.use_context or tgen.context_bleu_weight:
log_warn('Generator is trained to use context. ' +
'Using empty contexts, expect lower performance.')
das = [([], da) for da in das]
# generate
log_info('Generating...')
gen_trees = []
for num, da in enumerate(das, start=1):
log_debug("\n\nTREE No. %03d" % num)
gen_trees.append(tgen.generate_tree(da))
if num % 100 == 0:
log_info("Generated tree %d" % num)
log_info(tgen.get_slot_err_stats())
if args.delex_output_file is not None:
log_info('Writing delex output...')
write_trees_or_tokens(args.delex_output_file, das, gen_trees, None,
tgen.language, args.target_selector
or tgen.selector)
# evaluate the generated trees against golden trees (delexicalized)
eval_doc = None
if args.eval_file and not args.eval_file.endswith('.txt'):
eval_doc = read_ttrees(args.eval_file)
evaler = Evaluator()
evaler.process_eval_doc(eval_doc, gen_trees, tgen.language,
args.ref_selector, args.target_selector
or tgen.selector)
# lexicalize, if required
if args.abstr_file and tgen.lexicalizer:
log_info('Lexicalizing...')
tgen.lexicalize(gen_trees, args.abstr_file)
# we won't need contexts anymore, but we do need DAs
if tgen.use_context or tgen.context_bleu_weight:
das = [da for _, da in das]
# evaluate the generated & lexicalized tokens (F1 and BLEU scores)
if args.eval_file and args.eval_file.endswith('.txt'):
eval_tokens(das, read_tokens(args.eval_file, ref_mode=True),
[t.to_tok_list() for t in gen_trees])
# write output .yaml.gz or .txt
if args.output_file is not None:
log_info('Writing output...')
write_trees_or_tokens(args.output_file, das, gen_trees, eval_doc,
tgen.language, args.target_selector
or tgen.selector)
def asearch_gen(args):
"""A*search generation"""
from pytreex.core.document import Document
opts, files = getopt(args, 'e:d:w:c:s:')
eval_file = None
fname_ttrees_out = None
cfg_file = None
eval_selector = ''
for opt, arg in opts:
if opt == '-e':
eval_file = arg
elif opt == '-s':
eval_selector = arg
elif opt == '-d':
set_debug_stream(file_stream(arg, mode='w'))
elif opt == '-w':
fname_ttrees_out = arg
elif opt == '-c':
cfg_file = arg
if len(files) != 3:
sys.exit('Invalid arguments.\n' + __doc__)
fname_cand_model, fname_rank_model, fname_da_test = files
log_info('Initializing...')
candgen = RandomCandidateGenerator.load_from_file(fname_cand_model)
ranker = PerceptronRanker.load_from_file(fname_rank_model)
cfg = Config(cfg_file) if cfg_file else {}
cfg.update({'candgen': candgen, 'ranker': ranker})
tgen = ASearchPlanner(cfg)
log_info('Generating...')
das = read_das(fname_da_test)
if eval_file is None:
gen_doc = Document()
else:
eval_doc = read_ttrees(eval_file)
if eval_selector == tgen.selector:
gen_doc = Document()
else:
gen_doc = eval_doc
# generate and evaluate
if eval_file is not None:
# generate + analyze open&close lists
lists_analyzer = ASearchListsAnalyzer()
for num, (da, gold_tree) in enumerate(zip(
das, trees_from_doc(eval_doc, tgen.language, eval_selector)),
start=1):
log_debug("\n\nTREE No. %03d" % num)
gen_tree = tgen.generate_tree(da, gen_doc)
lists_analyzer.append(gold_tree, tgen.open_list, tgen.close_list)
if gen_tree != gold_tree:
log_debug("\nDIFFING TREES:\n" +
tgen.ranker.diffing_trees_with_scores(
da, gold_tree, gen_tree) + "\n")
log_info('Gold tree BEST: %.4f, on CLOSE: %.4f, on ANY list: %4f' %
lists_analyzer.stats())
# evaluate the generated trees against golden trees
eval_ttrees = ttrees_from_doc(eval_doc, tgen.language, eval_selector)
gen_ttrees = ttrees_from_doc(gen_doc, tgen.language, tgen.selector)
log_info('Evaluating...')
evaler = Evaluator()
for eval_bundle, eval_ttree, gen_ttree, da in zip(
eval_doc.bundles, eval_ttrees, gen_ttrees, das):
# add some stats about the tree directly into the output file
add_bundle_text(
eval_bundle, tgen.language, tgen.selector + 'Xscore',
"P: %.4f R: %.4f F1: %.4f" %
p_r_f1_from_counts(*corr_pred_gold(eval_ttree, gen_ttree)))
# collect overall stats
evaler.append(eval_ttree, gen_ttree,
ranker.score(TreeData.from_ttree(eval_ttree), da),
ranker.score(TreeData.from_ttree(gen_ttree), da))
# print overall stats
log_info("NODE precision: %.4f, Recall: %.4f, F1: %.4f" %
evaler.p_r_f1())
log_info("DEP precision: %.4f, Recall: %.4f, F1: %.4f" %
evaler.p_r_f1(EvalTypes.DEP))
log_info("Tree size stats:\n * GOLD %s\n * PRED %s\n * DIFF %s" %
evaler.size_stats())
log_info("Score stats:\n * GOLD %s\n * PRED %s\n * DIFF %s" %
evaler.score_stats())
log_info(
"Common subtree stats:\n -- SIZE: %s\n -- ΔGLD: %s\n -- ΔPRD: %s" %
evaler.common_substruct_stats())
# just generate
else:
for da in das:
tgen.generate_tree(da, gen_doc)
# write output
if fname_ttrees_out is not None:
log_info('Writing output...')
write_ttrees(gen_doc, fname_ttrees_out)
def seq2seq_gen(args):
"""Sequence-to-sequence generation"""
ap = ArgumentParser()
ap.add_argument('-e', '--eval-file', type=str, help='A ttree/text file for evaluation')
ap.add_argument('-a', '--abstr-file', type=str,
help='Lexicalization file (a.k.a. abstraction instructions, for postprocessing)')
ap.add_argument('-r', '--ref-selector', type=str, default='',
help='Selector for reference trees in the evaluation file')
ap.add_argument('-t', '--target-selector', type=str, default='',
help='Target selector for generated trees in the output file')
ap.add_argument('-d', '--debug-logfile', type=str, help='Debug output file name')
ap.add_argument('-w', '--output-file', type=str, help='Output tree/text file')
ap.add_argument('-b', '--beam-size', type=int,
help='Override beam size for beam search decoding')
ap.add_argument('-c', '--context-file', type=str,
help='Input ttree/text file with context utterances')
ap.add_argument('seq2seq_model_file', type=str, help='Trained Seq2Seq generator model')
ap.add_argument('da_test_file', type=str, help='Input DAs for generation')
args = ap.parse_args(args)
if args.debug_logfile:
set_debug_stream(file_stream(args.debug_logfile, mode='w'))
# load the generator
tgen = Seq2SeqBase.load_from_file(args.seq2seq_model_file)
if args.beam_size is not None:
tgen.beam_size = args.beam_size
# read input files
das = read_das(args.da_test_file)
if args.context_file:
if not tgen.use_context and not tgen.context_bleu_weight:
log_warn('Generator is not trained to use context, ignoring context input file.')
else:
if args.context_file.endswith('.txt'):
contexts = read_tokens(args.context_file)
else:
contexts = tokens_from_doc(read_ttrees(args.context_file),
tgen.language, tgen.selector)
das = [(context, da) for context, da in zip(contexts, das)]
# generate
log_info('Generating...')
gen_trees = []
for num, da in enumerate(das, start=1):
log_debug("\n\nTREE No. %03d" % num)
gen_trees.append(tgen.generate_tree(da))
log_info(tgen.get_slot_err_stats())
# evaluate the generated trees against golden trees (delexicalized)
eval_doc = None
if args.eval_file and not args.eval_file.endswith('.txt'):
eval_doc = read_ttrees(args.eval_file)
evaler = Evaluator()
evaler.process_eval_doc(eval_doc, gen_trees, tgen.language, args.ref_selector,
args.target_selector or tgen.selector)
# lexicalize, if required
if args.abstr_file and tgen.lexicalizer:
log_info('Lexicalizing...')
tgen.lexicalize(gen_trees, args.abstr_file)
# evaluate the generated & lexicalized tokens (F1 and BLEU scores)
if args.eval_file and args.eval_file.endswith('.txt'):
eval_tokens(das, read_tokens(args.eval_file, ref_mode=True), gen_trees)
# write output .yaml.gz or .txt
if args.output_file is not None:
log_info('Writing output...')
if args.output_file.endswith('.txt'):
write_tokens(gen_trees, args.output_file)
else:
write_ttrees(create_ttree_doc(gen_trees, eval_doc, tgen.language,
args.target_selector or tgen.selector),
args.output_file)
def seq2seq_gen(args):
"""Sequence-to-sequence generation"""
ap = ArgumentParser(prog=' '.join(sys.argv[0:2]))
ap.add_argument('-e', '--eval-file', type=str, help='A ttree/text file for evaluation')
ap.add_argument('-a', '--abstr-file', type=str,
help='Lexicalization file (a.k.a. abstraction instructions, for postprocessing)')
ap.add_argument('-r', '--ref-selector', type=str, default='',
help='Selector for reference trees in the evaluation file')
ap.add_argument('-t', '--target-selector', type=str, default='',
help='Target selector for generated trees in the output file')
ap.add_argument('-d', '--debug-logfile', type=str, help='Debug output file name')
ap.add_argument('-w', '--output-file', type=str, help='Output tree/text file')
ap.add_argument('-b', '--beam-size', type=int,
help='Override beam size for beam search decoding')
ap.add_argument('-c', '--context-file', type=str,
help='Input ttree/text file with context utterances')
ap.add_argument('seq2seq_model_file', type=str, help='Trained Seq2Seq generator model')
ap.add_argument('da_test_file', type=str, help='Input DAs for generation')
args = ap.parse_args(args)
if args.debug_logfile:
set_debug_stream(file_stream(args.debug_logfile, mode='w'))
# load the generator
tgen = Seq2SeqBase.load_from_file(args.seq2seq_model_file)
if args.beam_size is not None:
tgen.beam_size = args.beam_size
# read input files (DAs, contexts)
das = read_das(args.da_test_file)
if args.context_file:
if not tgen.use_context and not tgen.context_bleu_weight:
log_warn('Generator is not trained to use context, ignoring context input file.')
else:
if args.context_file.endswith('.txt'):
contexts = read_tokens(args.context_file)
else:
contexts = tokens_from_doc(read_ttrees(args.context_file),
tgen.language, tgen.selector)
das = [(context, da) for context, da in zip(contexts, das)]
elif tgen.use_context or tgen.context_bleu_weight:
log_warn('Generator is trained to use context. ' +
'Using empty contexts, expect lower performance.')
das = [([], da) for da in das]
# generate
log_info('Generating...')
gen_trees = []
for num, da in enumerate(das, start=1):
log_debug("\n\nTREE No. %03d" % num)
gen_trees.append(tgen.generate_tree(da))
if num % 100 == 0:
log_info("Generated tree %d" % num)
log_info(tgen.get_slot_err_stats())
# evaluate the generated trees against golden trees (delexicalized)
eval_doc = None
if args.eval_file and not args.eval_file.endswith('.txt'):
eval_doc = read_ttrees(args.eval_file)
evaler = Evaluator()
evaler.process_eval_doc(eval_doc, gen_trees, tgen.language, args.ref_selector,
args.target_selector or tgen.selector)
# lexicalize, if required
if args.abstr_file and tgen.lexicalizer:
log_info('Lexicalizing...')
tgen.lexicalize(gen_trees, args.abstr_file)
# we won't need contexts anymore, but we do need DAs
if tgen.use_context or tgen.context_bleu_weight:
das = [da for _, da in das]
# evaluate the generated & lexicalized tokens (F1 and BLEU scores)
if args.eval_file and args.eval_file.endswith('.txt'):
eval_tokens(das, read_tokens(args.eval_file, ref_mode=True),
[t.to_tok_list() for t in gen_trees])
# write output .yaml.gz or .txt
if args.output_file is not None:
log_info('Writing output...')
if args.output_file.endswith('.txt'):
gen_toks = [t.to_tok_list() for t in gen_trees]
postprocess_tokens(gen_toks, das)
write_tokens(gen_toks, args.output_file)
else:
write_ttrees(create_ttree_doc(gen_trees, eval_doc, tgen.language,
args.target_selector or tgen.selector),
args.output_file)
def asearch_gen(args):
"""A*search generation"""
from pytreex.core.document import Document
opts, files = getopt(args, 'e:d:w:c:s:')
eval_file = None
fname_ttrees_out = None
cfg_file = None
eval_selector = ''
for opt, arg in opts:
if opt == '-e':
eval_file = arg
elif opt == '-s':
eval_selector = arg
elif opt == '-d':
set_debug_stream(file_stream(arg, mode='w'))
elif opt == '-w':
fname_ttrees_out = arg
elif opt == '-c':
cfg_file = arg
if len(files) != 3:
sys.exit('Invalid arguments.\n' + __doc__)
fname_cand_model, fname_rank_model, fname_da_test = files
log_info('Initializing...')
candgen = RandomCandidateGenerator.load_from_file(fname_cand_model)
ranker = PerceptronRanker.load_from_file(fname_rank_model)
cfg = Config(cfg_file) if cfg_file else {}
cfg.update({'candgen': candgen, 'ranker': ranker})
tgen = ASearchPlanner(cfg)
log_info('Generating...')
das = read_das(fname_da_test)
if eval_file is None:
gen_doc = Document()
else:
eval_doc = read_ttrees(eval_file)
if eval_selector == tgen.selector:
gen_doc = Document()
else:
gen_doc = eval_doc
# generate and evaluate
if eval_file is not None:
# generate + analyze open&close lists
lists_analyzer = ASearchListsAnalyzer()
for num, (da, gold_tree) in enumerate(zip(das,
trees_from_doc(eval_doc, tgen.language, eval_selector)),
start=1):
log_debug("\n\nTREE No. %03d" % num)
gen_tree = tgen.generate_tree(da, gen_doc)
lists_analyzer.append(gold_tree, tgen.open_list, tgen.close_list)
if gen_tree != gold_tree:
log_debug("\nDIFFING TREES:\n" + tgen.ranker.diffing_trees_with_scores(da, gold_tree, gen_tree) + "\n")
log_info('Gold tree BEST: %.4f, on CLOSE: %.4f, on ANY list: %4f' % lists_analyzer.stats())
# evaluate the generated trees against golden trees
eval_ttrees = ttrees_from_doc(eval_doc, tgen.language, eval_selector)
gen_ttrees = ttrees_from_doc(gen_doc, tgen.language, tgen.selector)
log_info('Evaluating...')
evaler = Evaluator()
for eval_bundle, eval_ttree, gen_ttree, da in zip(eval_doc.bundles, eval_ttrees, gen_ttrees, das):
# add some stats about the tree directly into the output file
add_bundle_text(eval_bundle, tgen.language, tgen.selector + 'Xscore',
"P: %.4f R: %.4f F1: %.4f" % p_r_f1_from_counts(*corr_pred_gold(eval_ttree, gen_ttree)))
# collect overall stats
evaler.append(eval_ttree,
gen_ttree,
ranker.score(TreeData.from_ttree(eval_ttree), da),
ranker.score(TreeData.from_ttree(gen_ttree), da))
# print overall stats
log_info("NODE precision: %.4f, Recall: %.4f, F1: %.4f" % evaler.p_r_f1())
log_info("DEP precision: %.4f, Recall: %.4f, F1: %.4f" % evaler.p_r_f1(EvalTypes.DEP))
log_info("Tree size stats:\n * GOLD %s\n * PRED %s\n * DIFF %s" % evaler.size_stats())
log_info("Score stats:\n * GOLD %s\n * PRED %s\n * DIFF %s" % evaler.score_stats())
log_info("Common subtree stats:\n -- SIZE: %s\n -- ΔGLD: %s\n -- ΔPRD: %s" %
evaler.common_substruct_stats())
# just generate
else:
for da in das:
tgen.generate_tree(da, gen_doc)
# write output
if fname_ttrees_out is not None:
log_info('Writing output...')
write_ttrees(gen_doc, fname_ttrees_out)
def seq2seq_gen(args):
"""Sequence-to-sequence generation"""
ap = ArgumentParser()
ap.add_argument('-e', '--eval-file', type=str, help='A ttree/text file for evaluation')
ap.add_argument('-a', '--abstr-file', type=str,
help='Lexicalization file (a.k.a. abstraction instsructions, for tokens only)')
ap.add_argument('-r', '--ref-selector', type=str, default='',
help='Selector for reference trees in the evaluation file')
ap.add_argument('-t', '--target-selector', type=str, default='',
help='Target selector for generated trees in the output file')
ap.add_argument('-d', '--debug-logfile', type=str, help='Debug output file name')
ap.add_argument('-w', '--output-file', type=str, help='Output tree/text file')
ap.add_argument('-b', '--beam-size', type=int,
help='Override beam size for beam search decoding')
ap.add_argument('-c', '--context-file', type=str,
help='Input ttree/text file with context utterances')
ap.add_argument('seq2seq_model_file', type=str, help='Trained Seq2Seq generator model')
ap.add_argument('da_test_file', type=str, help='Input DAs for generation')
args = ap.parse_args(args)
if args.debug_logfile:
set_debug_stream(file_stream(args.debug_logfile, mode='w'))
# load the generator
tgen = Seq2SeqBase.load_from_file(args.seq2seq_model_file)
if args.beam_size is not None:
tgen.beam_size = args.beam_size
# read input files
das = read_das(args.da_test_file)
if args.context_file:
if not tgen.use_context and not tgen.context_bleu_weight:
log_warn('Generator is not trained to use context, ignoring context input file.')
else:
if args.context_file.endswith('.txt'):
contexts = read_tokens(args.context_file)
else:
contexts = tokens_from_doc(read_ttrees(args.context_file),
tgen.language, tgen.selector)
das = [(context, da) for context, da in zip(contexts, das)]
# prepare evaluation
if args.eval_file is None or args.eval_file.endswith('.txt'): # just tokens
gen_doc = []
else: # Trees: depending on PyTreex
from pytreex.core.document import Document
eval_doc = read_ttrees(args.eval_file)
if args.ref_selector == args.target_selector:
gen_doc = Document()
else:
gen_doc = eval_doc
if args.eval_file:
tgen.init_slot_err_stats()
# generate
log_info('Generating...')
tgen.selector = args.target_selector # override target selector for generation
for num, da in enumerate(das, start=1):
log_debug("\n\nTREE No. %03d" % num)
tgen.generate_tree(da, gen_doc)
# evaluate
if args.eval_file is not None:
log_info(tgen.get_slot_err_stats())
# evaluate the generated tokens (F1 and BLEU scores)
if args.eval_file.endswith('.txt'):
lexicalize_tokens(gen_doc, lexicalization_from_doc(args.abstr_file))
eval_tokens(das, read_tokens(args.eval_file, ref_mode=True), gen_doc)
# evaluate the generated trees against golden trees
else:
eval_trees(das,
ttrees_from_doc(eval_doc, tgen.language, args.ref_selector),
ttrees_from_doc(gen_doc, tgen.language, args.target_selector),
eval_doc, tgen.language, tgen.selector)
# write output .yaml.gz or .txt
if args.output_file is not None:
log_info('Writing output...')
if args.output_file.endswith('.txt'):
write_tokens(gen_doc, args.output_file)
else:
write_ttrees(gen_doc, args.output_file)
def main():
ap = ArgumentParser()
ap.add_argument('-d',
'--debug-output',
help='Path to debugging output file',
type=str)
subp = ap.add_subparsers()
ap_train = subp.add_parser('train', help='Train a new rating predictor')
ap_train.add_argument('-p',
'--training-portion',
type=float,
help='Part of data used for traing',
default=1.0)
ap_train.add_argument('-r',
'--random-seed',
type=str,
help='String to use as a random seed',
default=None)
ap_train.add_argument('-v',
'--valid-data',
type=str,
help='Path to validation data file',
default=None)
ap_train.add_argument(
'-t',
'--tensorboard-dir-id',
default=None,
help='Colon-separated path_to_tensorboard_logdir:run_id')
ap_train.add_argument('config_file',
type=str,
help='Path to the configuration file')
ap_train.add_argument('train_data',
type=str,
help='Path to the training data TSV file')
ap_train.add_argument('model_file',
type=str,
help='Path where to store the predictor model')
ap_test = subp.add_parser('test',
help='Test a trained predictor on given data')
ap_test.add_argument(
'-w',
'--write-outputs',
type=str,
help='Path to a prediction output file (not written when empty)',
default=None)
ap_test.add_argument('model_file',
type=str,
help='Path to a trained predictor model')
ap_test.add_argument('test_data',
type=str,
help='Path to the test data TSV file')
ap_interactive = subp.add_parser('interactive',
help='Interactive test session')
ap_interactive.add_argument('model_file',
type=str,
help='Path to a trained predictor model')
args = ap.parse_args()
if args.debug_output:
ds = file_stream(args.debug_output, mode='w')
set_debug_stream(ds)
if hasattr(args, 'train_data'):
train(args)
elif hasattr(args, 'test_data'):
test(args)
else:
interactive(args)
