def main():
name = 'Aly & Fila - Future Sound of Egypt 338 '
print name
csv_file = os.path.join('.', 'data',
name + experiment.plugin_suffix + '.csv')
cue_file = os.path.join('.', 'data', name + '.cue')
sim_file = os.path.join('.', 'data',
name + experiment.plugin_suffix + '.sim')
timestamps, data = experiment.read_csv(csv_file)
info = experiment.read_cue(cue_file)
has_intro = 'intro' in info[0]['TITLE'].strip().lower()
has_outro = 'outro' in info[-1]['TITLE'].strip().lower()
with open(sim_file, 'rb') as f:
(self_sim, factor) = cPickle.load(f)
filtered, novelty = tools.init_borders2(self_sim)
sec_per_row = timestamps[-1] / self_sim.shape[0]
#filtered = [x * sec_per_row for x in filtered]
filtered = tools.detect_track_borders(data,
timestamps[-1],
len(info),
self_sim=self_sim,
factor=factor,
has_intro=has_intro,
has_outro=has_outro)
#make_average(data, factor, [int(x / sec_per_row) for x in filtered])
#for i in range(len(info)):
# print '%d.\t%.2f\t%.2f: %f' % (i, info[i]['INDEX'], filtered[i], filtered[i] - info[i]['INDEX'])
#print filtered
#print [x['INDEX'] for x in info]
#print experiment.get_diff(info, filtered)
data = data.transpose((1, 0))
draw_spectrum(data, timestamps, 1)
#draw_selfsim(self_sim, timestamps)
vlines([datetime.datetime.fromtimestamp(x) for x in filtered],
0,
24,
color='k',
linewidths=[1] * len(filtered),
alpha=1.0)
vlines([datetime.datetime.fromtimestamp(x['INDEX']) for x in info],
24,
48,
color='y',
linewidths=[1] * len(info),
alpha=1.0)
#savefig('fig.pdf', bbox_inches='tight')
tracks = [(x['PERFORMER'], x['TITLE']) for x in info]
export_cue(name, tracks, filtered)
# borders2, novelty = tools.init_borders2(self_sim)
# plt.figure(2)
# plt.plot(novelty)
# print borders2
#draw_spectrum(data2, timestamps, 2)
# plt.figure(2)
# plt.plot(data2)
# plt.figure(3)
# plt.matshow(areas, fignum=3)
# _, axs = plt.subplots(5, 1, sharex=True)
# tss = [datetime.datetime.fromtimestamp(x) for x in timestamps]
# for i in range(len(centroids)):
# axs[i].plot(centroids[i])
# axs[4].plot(flux)
# plt.figure(4)
# plt.matshow(self_sim, fignum=4)
show()
def main():
name = 'Aly & Fila - Future Sound of Egypt 338 '
print name
csv_file = os.path.join('.', 'data', name + experiment.plugin_suffix + '.csv')
cue_file = os.path.join('.', 'data', name + '.cue')
sim_file = os.path.join('.', 'data', name + experiment.plugin_suffix + '.sim')
timestamps, data = experiment.read_csv(csv_file)
info = experiment.read_cue(cue_file)
has_intro = 'intro' in info[0]['TITLE'].strip().lower()
has_outro = 'outro' in info[-1]['TITLE'].strip().lower()
with open(sim_file, 'rb') as f:
(self_sim, factor) = cPickle.load(f)
filtered, novelty = tools.init_borders2(self_sim)
sec_per_row = timestamps[-1] / self_sim.shape[0]
#filtered = [x * sec_per_row for x in filtered]
filtered = tools.detect_track_borders(data,
timestamps[-1],
len(info),
self_sim=self_sim,
factor=factor,
has_intro=has_intro,
has_outro=has_outro)
#make_average(data, factor, [int(x / sec_per_row) for x in filtered])
#for i in range(len(info)):
# print '%d.\t%.2f\t%.2f: %f' % (i, info[i]['INDEX'], filtered[i], filtered[i] - info[i]['INDEX'])
#print filtered
#print [x['INDEX'] for x in info]
#print experiment.get_diff(info, filtered)
data = data.transpose((1, 0))
draw_spectrum(data, timestamps, 1)
#draw_selfsim(self_sim, timestamps)
vlines([datetime.datetime.fromtimestamp(x) for x in filtered], 0, 24, color='k', linewidths=[1]*len(filtered), alpha=1.0)
vlines([datetime.datetime.fromtimestamp(x['INDEX']) for x in info], 24, 48, color='y', linewidths=[1]*len(info), alpha=1.0)
#savefig('fig.pdf', bbox_inches='tight')
tracks = [(x['PERFORMER'], x['TITLE']) for x in info]
export_cue(name, tracks, filtered)
# borders2, novelty = tools.init_borders2(self_sim)
# plt.figure(2)
# plt.plot(novelty)
# print borders2
#draw_spectrum(data2, timestamps, 2)
# plt.figure(2)
# plt.plot(data2)
# plt.figure(3)
# plt.matshow(areas, fignum=3)
# _, axs = plt.subplots(5, 1, sharex=True)
# tss = [datetime.datetime.fromtimestamp(x) for x in timestamps]
# for i in range(len(centroids)):
# axs[i].plot(centroids[i])
# axs[4].plot(flux)
# plt.figure(4)
# plt.matshow(self_sim, fignum=4)
show()
def main():
data_dir = os.path.join(".", "temp_data")
mp3_files = [f for f in os.listdir(data_dir) if os.path.isfile(os.path.join(data_dir, f)) and f.endswith(".mp3")]
result = []
nc = tools.NoveltyCalculator()
with open(os.path.join("logs", "test.log"), "wb") as log:
for mp3 in mp3_files:
name = mp3[:-4]
cue = os.path.join(data_dir, name + ".cue")
info = None
if os.path.isfile(cue):
info = read_cue(cue)
else:
print "No cue file for %s, skipping" % mp3
if info:
has_intro = "intro" in info[0]["TITLE"].strip().lower()
has_outro = "outro" in info[-1]["TITLE"].strip().lower()
# has_intro = False
# has_outro = False
csv_file = os.path.join(data_dir, name + plugin_suffix + ".csv")
npz_file = os.path.join(data_dir, name + plugin_suffix + ".npz")
self_sim_file = os.path.join(data_dir, name + plugin_suffix + ".sim.npz")
if not os.path.isfile(csv_file) and not os.path.isfile(npz_file):
extract_features(os.path.join(data_dir, mp3))
if os.path.isfile(npz_file):
saved = numpy.load(npz_file)
timestamps = saved["timestamps"]
data = saved["data"]
elif os.path.isfile(csv_file):
(timestamps, data) = read_csv(csv_file)
replace_csv(timestamps, data, csv_file, npz_file)
if timestamps is not None and data is not None:
if os.path.isfile(self_sim_file):
saved = numpy.load(self_sim_file)
self_sim = saved["self_sim"]
factor = saved["factor"]
borders = tools.detect_track_borders(
data,
timestamps[-1],
len(info),
nc,
self_sim=self_sim,
factor=factor,
has_intro=has_intro,
has_outro=has_outro,
)
else:
borders = tools.detect_track_borders(
data,
timestamps[-1],
len(info),
nc,
sim_file=self_sim_file,
has_intro=has_intro,
has_outro=has_outro,
)
if len(borders) < len(info):
print len(borders), len(info)
true_borders = [c["INDEX"] for c in info]
true_borders.append(borders[-1])
expected_intervals, expected_labels = create_labeled_intervals(true_borders)
actual_intervals, actual_labels = create_labeled_intervals(borders)
validate_structure(expected_intervals, expected_labels, actual_intervals, actual_labels)
precision, recall, f_measure = pairwise(
expected_intervals, expected_labels, actual_intervals, actual_labels, frame_size=1
)
actual_to_expected, expected_to_actual = deviation(expected_intervals, actual_intervals)
avg_diff, max_diff = get_diff(info, borders)
result.append(
{"name": mp3, "info": info, "borders": borders, "avg_diff": avg_diff, "max_diff": max_diff}
)
print "%s\t%.3f\t%.3f\t\t%.4f\t%.4f\t%.4f\t\t%.4f\t%.4f" % (
mp3,
avg_diff,
max_diff,
precision,
recall,
f_measure,
actual_to_expected,
expected_to_actual,
)
log.write(
"%s\t%f\t%f\t%f\t%f\t%f\t%f\t%f\t%s\r\n"
% (
mp3,
avg_diff,
max_diff,
precision,
recall,
f_measure,
actual_to_expected,
expected_to_actual,
borders,
)
)
print_results(sorted(result, key=lambda x: x["name"]), log)
def main():
data_dir = os.path.join('.', 'temp_data')
mp3_files = [
f for f in os.listdir(data_dir)
if os.path.isfile(os.path.join(data_dir, f)) and f.endswith('.mp3')
]
result = []
nc = tools.NoveltyCalculator()
with open(os.path.join('logs', 'test.log'), 'wb') as log:
for mp3 in mp3_files:
name = mp3[:-4]
cue = os.path.join(data_dir, name + '.cue')
info = None
if os.path.isfile(cue):
info = read_cue(cue)
else:
print 'No cue file for %s, skipping' % mp3
if info:
has_intro = 'intro' in info[0]['TITLE'].strip().lower()
has_outro = 'outro' in info[-1]['TITLE'].strip().lower()
#has_intro = False
#has_outro = False
csv_file = os.path.join(data_dir,
name + plugin_suffix + '.csv')
npz_file = os.path.join(data_dir,
name + plugin_suffix + '.npz')
self_sim_file = os.path.join(data_dir,
name + plugin_suffix + '.sim.npz')
if not os.path.isfile(csv_file) and not os.path.isfile(
npz_file):
extract_features(os.path.join(data_dir, mp3))
if os.path.isfile(npz_file):
saved = numpy.load(npz_file)
timestamps = saved['timestamps']
data = saved['data']
elif os.path.isfile(csv_file):
(timestamps, data) = read_csv(csv_file)
replace_csv(timestamps, data, csv_file, npz_file)
if timestamps is not None and data is not None:
if os.path.isfile(self_sim_file):
saved = numpy.load(self_sim_file)
self_sim = saved['self_sim']
factor = saved['factor']
borders = tools.detect_track_borders(
data,
timestamps[-1],
len(info),
nc,
self_sim=self_sim,
factor=factor,
has_intro=has_intro,
has_outro=has_outro)
else:
borders = tools.detect_track_borders(
data,
timestamps[-1],
len(info),
nc,
sim_file=self_sim_file,
has_intro=has_intro,
has_outro=has_outro)
if len(borders) < len(info):
print len(borders), len(info)
true_borders = [c['INDEX'] for c in info]
true_borders.append(borders[-1])
expected_intervals, expected_labels = create_labeled_intervals(
true_borders)
actual_intervals, actual_labels = create_labeled_intervals(
borders)
validate_structure(expected_intervals, expected_labels,
actual_intervals, actual_labels)
precision, recall, f_measure = \
pairwise(expected_intervals, expected_labels, actual_intervals, actual_labels, frame_size=1)
actual_to_expected, expected_to_actual = deviation(
expected_intervals, actual_intervals)
avg_diff, max_diff = get_diff(info, borders)
result.append({
'name': mp3,
'info': info,
'borders': borders,
'avg_diff': avg_diff,
'max_diff': max_diff
})
print '%s\t%.3f\t%.3f\t\t%.4f\t%.4f\t%.4f\t\t%.4f\t%.4f' % \
(mp3, avg_diff, max_diff, precision, recall, f_measure, actual_to_expected, expected_to_actual)
log.write(
'%s\t%f\t%f\t%f\t%f\t%f\t%f\t%f\t%s\r\n' %
(mp3, avg_diff, max_diff, precision, recall, f_measure,
actual_to_expected, expected_to_actual, borders))
print_results(sorted(result, key=lambda x: x['name']), log)
