def t_test(name):
# if name == 'c20ng':
# return
dresults = experiment.read_csv(experiment.csv_path(name, "dag", "compare"))
tresults = experiment.read_csv(experiment.csv_path(name, "tree", "compare"))
dtst = [float(r["tst_llh"]) for r in dresults]
ttst = [float(r["tst_llh"]) for r in tresults]
dsize = [int(r["num_nodes"]) for r in dresults]
tsize = [int(r["num_nodes"]) for r in tresults]
dtime = [float(r["time"]) for r in dresults]
ttime = [float(r["time"]) for r in tresults]
print (name + " ")[:8], "\t%.4f" % np.mean(dtst), "\t%.4f" % np.mean(ttst), "\t", np.mean(dtst) > np.mean(
ttst
), "\t\t", "%6d" % int(np.mean(dsize)), "%7d" % int(np.mean(tsize)), "\t", "%.4f" % (
np.mean(dsize) / np.mean(tsize)
), "\t%8.2f" % np.mean(
dtime
), " %8.2f" % np.mean(
ttime
), np.mean(
dtime
) / np.mean(
ttime
),
from scipy import stats
print "\t", stats.ttest_ind(dtst, ttst, equal_var=False)[1] < 0.05
def best_grid_point(name, structure, dirname):
bp = experiment.csv_path(name, structure, dirname)
rows = experiment.read_csv(bp)
return best_row(rows)
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()