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 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)
#!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# Simple statistics about types of inner nodes and leaves
# in the training data.
#
from tgen.futil import read_ttrees, ttrees_from_doc
import sys
import codecs
if len(sys.argv[1:]) != 1:
sys.exit('Usage: python leaf_stats.py <file.pickle>')
stats = {}
for ttree in ttrees_from_doc(read_ttrees(sys.argv[1]), 'en', ''):
for tnode in ttree.get_descendants():
node_id = (tnode.t_lemma, tnode.formeme)
if node_id not in stats:
stats[node_id] = {'leaf': 0, 'int': 0}
if tnode.get_children():
stats[node_id]['int'] += 1
else:
stats[node_id]['leaf'] += 1
out = codecs.getwriter('UTF-8')(sys.stdout)
for node_id, val in stats.iteritems():
print >> out, node_id, "\t", val['int'], "\t", val['leaf']
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)