def weight_files(inst_fns, out_fns, weight_func=entropy_weight,
descriptor=None, n=None, binary=False):
"""
Weight corpus instance files
@param inst_fns: list of corpus instance filenames
@param out_fns: list of filenames containing Timbl output
@keyword weight_func: weighting fuction
@keyword descriptor: a Descriptor instance, required if corpus instances
are loaded in text format
@keyword n: limit merging to the first n files
"""
for inst_fname, out_fname in zip(inst_fns, out_fns)[:n]:
corpus_inst = CorpusInst()
if binary:
corpus_inst.loadbin(inst_fname)
else:
corpus_inst.loadtxt(inst_fname, descriptor.dtype)
timbl_out = parse_timbl_output(open(out_fname))
weight_corpus(corpus_inst, timbl_out, weight_func)
log.info("saving weighted corpus instances to {0}".format(inst_fname))
corpus_inst.save()
def test_weight_corpus(self):
st = create_setting()
corpus_inst = CorpusInst()
inst_fname = st.dev_inst_fns[0]
corpus_inst.loadtxt(inst_fname, st.descriptor.dtype)
graph_inst = corpus_inst[0]
# clear predicted weights field
graph_inst["pred_weight"] = 0.0
# backup original for comparison later on
weight_before = graph_inst["pred_weight"].copy()
out_fname = st.dev_clas_fns[0]
timbl_out = parse_timbl_output(open(out_fname))
weight_corpus(corpus_inst, timbl_out, entropy_weight)
# check that at least one weight is different (i.e. not 0.0)
self.assertTrue(any(graph_inst["pred_weight"] != weight_before))
def test_weight_corpus(self):
st = create_setting()
corpus_inst = CorpusInst()
inst_fname = st.dev_inst_fns[0]
corpus_inst.loadtxt(inst_fname, st.descriptor.dtype)
graph_inst = corpus_inst[0]
# clear predicted weights field
graph_inst["pred_weight"] = 0.0
# backup original for comparison later on
weight_before = graph_inst["pred_weight"].copy()
out_fname = st.dev_clas_fns[0]
timbl_out = parse_timbl_output(open(out_fname))
weight_corpus(corpus_inst, timbl_out, entropy_weight)
# check that at least one weight is different (i.e. not 0.0)
self.assertTrue(any(graph_inst["pred_weight"] != weight_before))
def exp_dev_fast(setting):
"""
perform a fast alignment experiment on development data
Weighting, matching and merging takes place per test corpus without
writing intermediary results to a file.
"""
assert setting.develop and not setting.validate
exp_init(setting)
create_parts(setting)
# It's impossible to do extraction one corpus a time, because in order to
# classify a test corpus you need instances for all the other training
# corpora! Moreover, since Timbl classification is file-based, we need to
# write the corpus instance files to disk. These files can be huge and
# keeping all of them in memory seems to offer little benefit.
extract(setting)
sample(setting)
# Timbl writes its output to a file, which then needs to be parsed in
# order to insert the class predictions and weights into the corpus
# instances. That means there is no advantage to doing classification
# one corpus a time.
classify(setting)
log.info("\n" + header("WEIGHT/MATCH/MERGE STEP"))
# reset evaluator
if setting.evaluate:
setting.evaluator.__init__()
scope = zip(setting.dev_inst_fns, setting.dev_clas_fns, setting.dev_true_fns)[: setting.n]
for inst_fname, out_fname, true_fname in scope:
log.info("reading corpus instances {0}".format(inst_fname))
corpus_inst = CorpusInst()
corpus_inst.loadtxt(inst_fname, setting.descriptor.dtype)
if setting.weight:
log.info("reading classifier output {0}".format(out_fname))
timbl_out = parse_timbl_output(open(out_fname))
log.info("weighting...")
weight_corpus(corpus_inst, timbl_out, setting.weight_func)
if setting.match:
log.info("matching...")
match_corpus(corpus_inst, setting.matcher)
if setting.merge:
log.info("reading true corpus {0}".format(true_fname))
true_corpus = ParallelGraphCorpus(inf=true_fname, graph_loading=LOAD_NONE)
log.info("merging...")
pred_corpus = merge_corpus(corpus_inst, true_corpus, setting.merger)
if setting.evaluate:
name = os.path.basename(true_fname).split("_")[0]
setting.evaluator.add(true_corpus, pred_corpus, name)
if setting.evaluate:
log.info("evaluting...")
setting.evaluator.run_eval()
log.info("saving evaluation {0}".format(setting.dev_eval_fname))
makedirs(setting.eval_dir)
setting.evaluator.write(setting.dev_eval_fname)
exp_exit(setting)
def exp_dev_fast(setting):
"""
perform a fast alignment experiment on development data
Weighting, matching and merging takes place per test corpus without
writing intermediary results to a file.
"""
assert setting.develop and not setting.validate
exp_init(setting)
create_parts(setting)
# It's impossible to do extraction one corpus a time, because in order to
# classify a test corpus you need instances for all the other training
# corpora! Moreover, since Timbl classification is file-based, we need to
# write the corpus instance files to disk. These files can be huge and
# keeping all of them in memory seems to offer little benefit.
extract(setting)
sample(setting)
# Timbl writes its output to a file, which then needs to be parsed in
# order to insert the class predictions and weights into the corpus
# instances. That means there is no advantage to doing classification
# one corpus a time.
classify(setting)
log.info("\n" + header("WEIGHT/MATCH/MERGE STEP"))
# reset evaluator
if setting.evaluate: setting.evaluator.__init__()
scope = zip(setting.dev_inst_fns, setting.dev_clas_fns,
setting.dev_true_fns)[:setting.n]
for inst_fname, out_fname, true_fname in scope:
log.info("reading corpus instances {0}".format(inst_fname))
corpus_inst = CorpusInst()
corpus_inst.loadtxt(inst_fname, setting.descriptor.dtype)
if setting.weight:
log.info("reading classifier output {0}".format(out_fname))
timbl_out = parse_timbl_output(open(out_fname))
log.info("weighting...")
weight_corpus(corpus_inst, timbl_out, setting.weight_func)
if setting.match:
log.info("matching...")
match_corpus(corpus_inst, setting.matcher)
if setting.merge:
log.info("reading true corpus {0}".format(true_fname))
true_corpus = ParallelGraphCorpus(inf=true_fname,
graph_loading=LOAD_NONE)
log.info("merging...")
pred_corpus = merge_corpus(corpus_inst, true_corpus,
setting.merger)
if setting.evaluate:
name = os.path.basename(true_fname).split("_")[0]
setting.evaluator.add(true_corpus, pred_corpus, name)
if setting.evaluate:
log.info("evaluting...")
setting.evaluator.run_eval()
log.info("saving evaluation {0}".format(setting.dev_eval_fname))
makedirs(setting.eval_dir)
setting.evaluator.write(setting.dev_eval_fname)
exp_exit(setting)