def main():
usage = "%prog <out-file>"
parser = OptionParser(usage=usage)
parser.add_option("-n",
"--no-names",
dest="no_names",
action="store_true",
help="obscure names of the chord sequences")
options, arguments = parser.parse_args()
if len(arguments) == 0:
print >> sys.stderr, "You must specify an output file as the first argument"
sys.exit(1)
filename = arguments[0]
# Get songs that have multiple annotations
songs = Song.objects.annotate(seqs=Count('chordsequence')).filter(
seqs__gte=2)
# Create db mirrors of all the sequences
sequences = []
pairs = []
for song in songs:
if song.chordsequence_set.count() > 2:
print >>sys.stderr, "%s has more than 2 alternative annotations" % \
song.string_name
seqs = song.chordsequence_set.all()
# Add a record of the pairing
pairs.append((seqs[0].id, seqs[1].id))
# Add the mirrored version of the sequence
for seq in seqs:
sequences.append(seq.mirror)
if options.no_names:
for seq in sequences:
# Obscure the sequence's name
seq.name = "sequence-%d" % seq.id
consdata = ConsistencyData(sequences, pairs)
consdata.save(filename)
print "Output %d sequences with multiple annotations" % songs.count()
def main():
usage = "%prog <out-file>"
parser = OptionParser(usage=usage)
parser.add_option("-n", "--no-names", dest="no_names", action="store_true", help="obscure names of the chord sequences")
options, arguments = parser.parse_args()
if len(arguments) == 0:
print >>sys.stderr, "You must specify an output file as the first argument"
sys.exit(1)
filename = arguments[0]
# Get songs that have multiple annotations
songs = Song.objects.annotate(seqs=Count('chordsequence')).filter(seqs__gte=2)
# Create db mirrors of all the sequences
sequences = []
pairs = []
for song in songs:
if song.chordsequence_set.count() > 2:
print >>sys.stderr, "%s has more than 2 alternative annotations" % \
song.string_name
seqs = song.chordsequence_set.all()
# Add a record of the pairing
pairs.append((seqs[0].id, seqs[1].id))
# Add the mirrored version of the sequence
for seq in seqs:
sequences.append(seq.mirror)
if options.no_names:
for seq in sequences:
# Obscure the sequence's name
seq.name = "sequence-%d" % seq.id
consdata = ConsistencyData(sequences, pairs)
consdata.save(filename)
print "Output %d sequences with multiple annotations" % songs.count()
def main():
usage = "%prog [options] <consistency-data>"
description = "Evaluates annotator consistency."
parser = OptionParser(usage=usage, description=description)
parser.add_option("-m", "--metric", dest="metric", action="store",
help="semantics distance metric to use. Use '-m help' for a list of "\
"available metrics")
parser.add_option("--mopt", "--metric-options", dest="mopts",
action="append",
help="options to pass to the semantics metric. Use with '--mopt help' "\
"with -m to see available options")
parser.add_option("-f", "--f-score", dest="f_score", action="store_true",
help="outputs recall, precision and f-score for an f-score-based "\
"metric. Just uses the same metric 3 times with output=recall, "\
"etc. Will only work with appropriate metrics")
options, arguments = parser.parse_args()
grammar = get_grammar()
if options.metric is not None:
use_metric = True
if options.f_score:
# Special case: get 3 metrics
metrics = []
opts = options.mopts or []
for opt in [ "output=precision", "output=recall", "output=f" ]:
metrics.append(command_line_metric(formalism, options.metric,
opts+[opt]))
print "Evaluating precision, recall and f-score on %s" % metrics[0].name
else:
# Get a metric according to the options
metrics = [command_line_metric(formalism, options.metric, options.mopts)]
print "Evaluating using metric: %s" % metrics[0].name
else:
use_metric = False
if len(arguments) < 1:
print >>sys.stderr, "Specify a consistency data file"
sys.exit(1)
filename = arguments[0]
consdata = ConsistencyData.from_file(filename)
# Count up matching annotations
matches = 0
chords = 0
for ann1,ann2 in consdata:
for chord1,chord2 in zip(ann1,ann2):
chords += 1
if chord1.category == chord2.category:
matches += 1
# Count matching coordination points
rean_coords = sum(sum(
[1 for crd in seq if crd.treeinfo.coord_unresolved])
for seq,gs in consdata) + \
sum(sum(
[1 for crd in seq if crd.treeinfo.coord_resolved])
for seq,gs in consdata)
gold_coords = sum(sum(
[1 for crd in gs if crd.treeinfo.coord_unresolved])
for seq,gs in consdata) + \
sum(sum(
[1 for crd in gs if crd.treeinfo.coord_resolved])
for seq,gs in consdata)
match_coords = sum(sum(
[1 for crdr,crdg in zip(seq,gs) if
crdr.treeinfo.coord_unresolved
and crdg.treeinfo.coord_unresolved])
for seq,gs in consdata) + \
sum(sum(
[1 for crdr,crdg in zip(seq,gs) if
crdr.treeinfo.coord_resolved
and crdg.treeinfo.coord_resolved])
for seq,gs in consdata)
# Compute precision, recall and f-score from this
precision = 100.0 * (matches + match_coords) / (chords + rean_coords)
recall = 100.0 * (matches + match_coords) / (chords + gold_coords)
fscore = 2.0 * precision * recall / (precision+recall)
print "%d chords" % chords
print "\nCategory and coordination accuracy:"
print "Precision: %.2f" % precision
print "Recall: %.2f" % recall
print "F-score: %.2f" % fscore
if use_metric:
print
def _parse_seq(seq):
# Parse the annotations to get a semantics
try:
gold_parses = parse_sequence_with_annotations(
DbInput.from_sequence(seq),
grammar=grammar,
allow_subparses=False)
# Got a result: return its semantics
return gold_parses[0].semantics
except ParseError, err:
# Could not parse annotated sequence
print >>sys.stderr, "Could not parse sequence '%s': %s" % \
(seq.string_name, err)
return
# Prepare pairs of gold-standard parse results from the two annotations
sem_pairs = [
(_parse_seq(ann1), _parse_seq(ann2)) for (ann1,ann2) in consdata
]
# Compute the distance using the metrics
for metric in metrics:
distance = metric.total_distance(sem_pairs)
print "%s: %s" % (metric.identifier.capitalize(),
metric.format_distance(distance))
def main():
usage = "%prog [options] <consistency-data>"
description = "Evaluates annotator consistency."
parser = OptionParser(usage=usage, description=description)
parser.add_option("-m", "--metric", dest="metric", action="store",
help="semantics distance metric to use. Use '-m help' for a list of "\
"available metrics")
parser.add_option("--mopt", "--metric-options", dest="mopts",
action="append",
help="options to pass to the semantics metric. Use with '--mopt help' "\
"with -m to see available options")
parser.add_option("-f", "--f-score", dest="f_score", action="store_true",
help="outputs recall, precision and f-score for an f-score-based "\
"metric. Just uses the same metric 3 times with output=recall, "\
"etc. Will only work with appropriate metrics")
options, arguments = parser.parse_args()
grammar = get_grammar()
if options.metric is not None:
use_metric = True
if options.f_score:
# Special case: get 3 metrics
metrics = []
opts = options.mopts or []
for opt in ["output=precision", "output=recall", "output=f"]:
metrics.append(
command_line_metric(formalism, options.metric,
opts + [opt]))
print "Evaluating precision, recall and f-score on %s" % metrics[
0].name
else:
# Get a metric according to the options
metrics = [
command_line_metric(formalism, options.metric, options.mopts)
]
print "Evaluating using metric: %s" % metrics[0].name
else:
use_metric = False
if len(arguments) < 1:
print >> sys.stderr, "Specify a consistency data file"
sys.exit(1)
filename = arguments[0]
consdata = ConsistencyData.from_file(filename)
# Count up matching annotations
matches = 0
chords = 0
for ann1, ann2 in consdata:
for chord1, chord2 in zip(ann1, ann2):
chords += 1
if chord1.category == chord2.category:
matches += 1
# Count matching coordination points
rean_coords = sum(sum(
[1 for crd in seq if crd.treeinfo.coord_unresolved])
for seq,gs in consdata) + \
sum(sum(
[1 for crd in seq if crd.treeinfo.coord_resolved])
for seq,gs in consdata)
gold_coords = sum(sum(
[1 for crd in gs if crd.treeinfo.coord_unresolved])
for seq,gs in consdata) + \
sum(sum(
[1 for crd in gs if crd.treeinfo.coord_resolved])
for seq,gs in consdata)
match_coords = sum(sum(
[1 for crdr,crdg in zip(seq,gs) if
crdr.treeinfo.coord_unresolved
and crdg.treeinfo.coord_unresolved])
for seq,gs in consdata) + \
sum(sum(
[1 for crdr,crdg in zip(seq,gs) if
crdr.treeinfo.coord_resolved
and crdg.treeinfo.coord_resolved])
for seq,gs in consdata)
# Compute precision, recall and f-score from this
precision = 100.0 * (matches + match_coords) / (chords + rean_coords)
recall = 100.0 * (matches + match_coords) / (chords + gold_coords)
fscore = 2.0 * precision * recall / (precision + recall)
print "%d chords" % chords
print "\nCategory and coordination accuracy:"
print "Precision: %.2f" % precision
print "Recall: %.2f" % recall
print "F-score: %.2f" % fscore
if use_metric:
print
def _parse_seq(seq):
# Parse the annotations to get a semantics
try:
gold_parses = parse_sequence_with_annotations(
DbInput.from_sequence(seq),
grammar=grammar,
allow_subparses=False)
# Got a result: return its semantics
return gold_parses[0].semantics
except ParseError, err:
# Could not parse annotated sequence
print >>sys.stderr, "Could not parse sequence '%s': %s" % \
(seq.string_name, err)
return
# Prepare pairs of gold-standard parse results from the two annotations
sem_pairs = [(_parse_seq(ann1), _parse_seq(ann2))
for (ann1, ann2) in consdata]
# Compute the distance using the metrics
for metric in metrics:
distance = metric.total_distance(sem_pairs)
print "%s: %s" % (metric.identifier.capitalize(),
metric.format_distance(distance))