def mutate(genotype, num_rows, num_cols, arr, constraints, mut_rate=0.15):
segments = find_segments(genotype)
r = random()
if r < 0.45 and max(segments) >= constraints[0]:
v_from, v_to = merge_2_similar_segments(arr, segments, num_rows,
num_cols)
seg_1, seg_2 = segments[v_from], segments[v_to]
if seg_1 != seg_2:
# Set all seg 2 pixels to seg 1
segment_indices = np.flatnonzero(segments == seg_2)
segments[segment_indices] = seg_1
genotype = segment_mst(arr, segments, seg_1, np.array(genotype),
num_rows, num_cols, 0)
elif r < 0.9 and max(segments) < constraints[1]:
start = time.time()
if random() < 0.5:
segment_id = get_worst_segment(arr, segments, num_rows, num_cols)
else:
segment_id = np.random.choice(segments)
genotype = segment_mst(arr, segments, segment_id, np.array(genotype),
num_rows, num_cols, 1)
else:
rand_i = randint(0, len(genotype) - 1)
mutate_random_edge(rand_i, num_rows, num_cols)
return genotype
def __init__(self, arr, genotype=None):
self.rows = arr.shape[0]
self.cols = arr.shape[1]
# Generate initial phenotype
if genotype is None:
self.genotype = mst(arr, self.rows, self.cols)
else:
self.genotype = genotype
self.segments = find_segments(self.genotype)
self.edge_value = edge_value(arr, self.segments, self.rows, self.cols)
self.connectivity = connectivity(arr, self.segments, self.rows,
self.cols)
self.deviation = overall_deviation(arr, self.segments, self.cols)
self.fitness = 10 * self.edge_value - 8500 * self.connectivity - 2 * self.deviation
def __init__(self, arr, genotype=None):
self.rows = arr.shape[0]
self.cols = arr.shape[1]
# Generate initial phenotype
if genotype is None:
self.genotype = mst(arr, self.rows, self.cols)
else:
self.genotype = genotype
self.segments = find_segments(self.genotype)
self.num_segments = max(self.segments) + 1
self.edge_value = -edge_value(arr, self.segments, self.rows,
self.cols) # negative to minimize
self.connectivity = connectivity(arr, self.segments, self.rows,
self.cols)
self.deviation = overall_deviation(arr, self.segments, self.cols)
def process(wav_file, outfile, csv_file=None, bpm=None, tol=0.35,
ssm_read_pk=False, read_pk=False, rho=2, is_ismir=False,
tonnetz=False, sonify=False):
"""Main process to find the patterns in a polyphonic audio file.
Parameters
----------
wav_file : str
Path to the wav file to be analyzed.
csv_file : str
Path to the csv containing the midi_score of the input audio file
(needed to produce a result that can be read for JKU dataset).
outfile : str
Path to file to save the results.
bpm : int
Beats per minute of the piece. If None, bpms are read from the JKU.
tol : float
Tolerance to find the segments in the SSM.
ssm_read_pk : bool
Whether to read the SSM from a pickle file.
read_pk : bool
Whether to read the segments from a pickle file.
rho : int
Positive integer to compute the score of the segments.
is_ismir : bool
Produce the plots that appear on the ISMIR paper.
tonnetz : bool
Whether to use Tonnetz or Chromas.
sonify : bool
Whether to sonify the patterns or not.
"""
# Get the correct bpm if needed
if bpm is None:
bpm = get_bpm(wav_file)
# Algorithm parameters
min_notes = 8
max_diff_notes = 4
h = bpm / 60. / 8. # Hop size /8 works better than /4, but it takes longer
# to process
# Obtain the Self Similarity Matrix
X = compute_ssm(wav_file, h, ssm_read_pk, is_ismir, tonnetz)
# Read CSV file
if csv_file is not None:
logging.info("Reading the CSV file for MIDI pitches...")
midi_score = utils.read_csv(csv_file)
patterns = []
csv_patterns = []
while patterns == [] or csv_patterns == []:
# Find the segments inside the self similarity matrix
logging.info("Finding segments in the self-similarity matrix...")
max_diff = int(max_diff_notes / float(h))
min_dur = int(np.ceil(min_notes / float(h)))
#print min_dur, min_notes, h, max_diff
if not read_pk:
segments = []
while segments == []:
logging.info("\ttrying tolerance %.2f" % tol)
segments = utils.find_segments(X, min_dur, th=tol, rho=rho)
tol -= 0.05
utils.write_cPickle(wav_file + "-audio.pk", segments)
else:
segments = utils.read_cPickle(wav_file + "-audio.pk")
# Obtain the patterns from the segments and split them if needed
logging.info("Obtaining the patterns from the segments...")
patterns = obtain_patterns(segments, max_diff)
# Decrease tolerance in case we couldn't find any patterns
tol -= 0.05
# Get the csv patterns if they exist
if csv_file is not None:
csv_patterns = patterns_to_csv(patterns, midi_score, h)
else:
csv_patterns = [0]
# Sonify patterns if needed
if sonify:
logging.info("Sonifying Patterns...")
utils.sonify_patterns(wav_file, patterns, h)
# Formatting csv patterns and save results
if csv_file is not None:
logging.info("Writting results into %s" % outfile)
utils.save_results(csv_patterns, outfile=outfile)
else:
# If not csv, just print the results on the screen
print_patterns(patterns, h)
if is_ismir:
ismir.plot_segments(X, segments)
# Alright, we're done :D
logging.info("Algorithm finished.")