def main():
usage = "%prog [options] <seq-file> <index>"
description = "Outputs the key associated with each chord of a sequence "\
"from an annotated corpus"
parser = OptionParser(usage=usage, description=description)
options, arguments = parser.parse_args()
if len(arguments) < 2:
print "You must specify a sequence file and index"
sys.exit(1)
index = int(arguments[1])
# Get the chord sequence
seq = SequenceIndex.from_file(arguments[0]).sequence_by_index(index)
print keys_for_sequence(seq)
def train(data, name, logger=None, options={}, chord_data=None):
"""
Initializes and trains an HMM in a supervised fashion using the given
training data.
"""
if len(data) == 0:
raise ModelTrainError, "empty training data set"
# Prepare a dummy logger if none was given
if logger is None:
logger = create_dummy_logger()
# Process the options dict
options = HPChordLabeler.process_training_options(options)
# Work out what kind of input data we've got
# It should be a bulk input type: check what type the first input is
input_type = detect_input_type(data[0], allowed=['segmidi', 'db-annotated'])
logger.info(">>> Beginning training of HP chord labeler model '%s'" % name)
# If we got midi tagger training data, it may include chord data as well
if isinstance(data, MidiTaggerTrainingBulkInput) and \
data.chords is not None:
if chord_data is None:
# Use the chord data in the input data
logger.info("Midi training data; chord corpus data available")
chord_inputs = data.chords
else:
# Use the chord data that was given explicitly
chord_inputs = chord_data
midi_inputs = data
elif isinstance(data, DbBulkInput):
logger.info("Only chord corpus training data")
# This was only chord input, no midi data
chord_inputs = data
midi_inputs = None
else:
chord_inputs = chord_data
# Presumably this is another form of midi training data
midi_inputs = data
logger.info("Midi training data; no chord data was included")
# Get the chord vocab from the options
logger.info("Model chord vocabulary: %s" % options['vocab'])
vocab, vocab_mapping = CHORD_VOCABS[options['vocab']]
# Initialize a model according to the chord types
logger.info("Initializing emission distributions to favour chord "\
"notes with chord probability %s" % (options['chordprob']))
model = HPChordLabeler.initialize_chords(options['chordprob'], \
options['maxnotes'], vocab, \
vocab_mapping, name=name)
# If we have chord training data, use this to train the transition dist
if chord_inputs is not None:
logger.info("Training using chord data")
# Construct the trees implicit in the annotations to get the
# key of every chord
logger.info("Preparing key data for annotated chord sequences")
input_keys = [keys_for_sequence(dbinput) for dbinput in chord_inputs]
# Run the supervised training of the transition distribution
logger.info("Training transition distribution on chord sequences")
model.train_transition_distribution(chord_inputs, input_keys)
if midi_inputs is not None:
logger.info("Training using midi data")
# Preprocess the midi inputs so they're ready for the model training
emissions = [midi_to_emission_stream(seq,
remove_empty=False)[0] \
for seq in midi_inputs]
# Use the midi data to train emission number dist
logger.info("Training emission number distribution")
model.train_emission_number_distribution(emissions)
####### EM unsupervised training on the midi data
# Pull out the options to pass to the trainer
# These are a subset of the model training options
bw_opt_names = [opt.name for opt in HPBaumWelchTrainer.OPTIONS]
bw_opts = dict([(name,val) for (name,val) in options.items() \
if name in bw_opt_names])
# Create a Baum-Welch trainer
trainer = HPBaumWelchTrainer(model, bw_opts)
# Do the Baum-Welch training
model = trainer.train(emissions, logger=logger)
logger.info("Training complete")
return model
