def run(self, args):
a = feature_matrix.FeatureMatrix().load(args.infile)
if args.labels is True:
print "Stored ", len(a.metadata.filename), " files"
for f in a.metadata.filename:
print f
exit()
#classe = a.metadata.filename.split("/")[-1].split(".")[0]
# verification
#print a.metadata.feature
#print a.data, a.data.shape
feature_names = a.metadata.feature.split()
feature_names.sort()
if args.features is True:
if len(feature_names) != a.data.shape[1]:
print "Feature names are inconsistent with data!"
print feature_names
print len(feature_names)
print a.data.shape
exit()
for f in feature_names:
sys.stdout.write(f)
if args.csv is True:
sys.stdout.write(",")
sys.stdout.write(" ")
print "label"
else:
for i in xrange(len(a.metadata.filename)):
for j in xrange(a.data.shape[1] - 1):
sys.stdout.write(str(a.data[i, j]))
if args.csv is True:
sys.stdout.write(",")
sys.stdout.write(" ")
sys.stdout.write(str(a.data[i, j + 1]))
sys.stdout.write(", ")
#A linha seguinte esta porquinha.
#masss (requer que o nome da classe seja o primeiro no arquivo
sys.stdout.write(
a.metadata.filename[i].split("/")[-1].split(".")[0])
print ""
def run(self, args):
a = feature_matrix.FeatureMatrix().load(args.database)
file_label_dict = self.label_list(open(args.labels, 'rb'))
# Start join process
output = ""
# Title row
output += "filename,"
for i in xrange(a.data.shape[1]):
output += "F" + str(i) + ","
output += "Class\n"
for i in xrange(len(a.metadata.filename)):
fname = a.metadata.filename[i].split('/')[-1]
output += fname + ","
for j in xrange(a.data.shape[1]):
output += str(a.data[i][j]) + ","
output += str(file_label_dict[fname]) + "\n"
print output
def run(self):
print "training model from train filelist: %s" % (
self.params['general']['train_filelist'])
m = feature_matrix.FeatureMatrix()
mf = open(self.params['general']['scratch_directory'] + "/" +
self.params['feature_aggregation']['aggregated_output'])
m = m.load(mf)
mf.close()
with open(self.params['general']['train_filelist']) as f:
linhas = f.readlines()
files = dict()
for i in xrange(len(m.metadata.filename)):
files[m.metadata.filename[i]] = i
labels = []
features = []
for i in xrange(len(linhas)):
filename = linhas[i].split("\t")[0].strip()
label = linhas[i].split("\t")[1].strip()
labels.append(label)
feat = m.data[files[filename]]
features.append(feat)
features = numpy.array(features)
files = None
input = ModelTrainerInput(features, labels)
gc.collect()
self.train(input)
def run(self, args):
o = track.FeatureTrack()
o = o.load(args.trackfile)
#print o.metadata
#print o.data
# Read label file
onsets = []
offsets = []
labels = []
with open(args.labelfile) as f:
content = f.readlines()
for line in content:
L = line.split()
#print L
onsets.append(float(L[0]))
offsets.append(float(L[1]))
L[2] = L[2].replace('_', '-')
L[2] = L[2].replace('-', '+')
labels.append(str(L[2].split('+')[0]))
#print onsets[-1], offsets[-1], labels[-1]
#exit()
final_output = None
final_filenames = []
final_filenames.append(o.metadata.filename)
if o.data.ndim == 1:
o.data.shape = (o.data.size, 1)
feats = o.metadata.feature.split()
a = numpy.array(feats)
i = a.argsort()
ofs = o.metadata.sampling_configuration.ofs
#print offsets[-1], o.data.shape, o.data.shape[0] / float(ofs)
#print i
my_features = o.metadata.feature.split()
my_features.sort()
new_features = ""
if args.mean is True:
for feat in my_features:
new_features = new_features + " " + "mean_" + feat
if args.variance is True:
for feat in my_features:
new_features = new_features + " " + "var_" + feat
if args.slope is True:
for feat in my_features:
new_features = new_features + " " + "slope_" + feat
if args.limits is True:
for feat in my_features:
new_features = new_features + " " + "max_" + feat
for feat in my_features:
new_features = new_features + " " + "argmax_" + feat
for feat in my_features:
new_features = new_features + " " + "min_" + feat
for feat in my_features:
new_features = new_features + " " + "argmin_" + feat
new_features = new_features.strip()
if args.csv is True:
sys.stdout.write(new_features.replace(' ', ','))
sys.stdout.write(',LABEL')
sys.stdout.write('\n')
#exit()
for d in xrange(len(onsets)):
out = numpy.array([])
i = a.argsort()
minN = int(onsets[d] * float(ofs))
maxN = int(offsets[d] * float(ofs))
if maxN <= (minN + 1):
maxN = minN + 2
#print minN, maxN, onsets[d], offsets[d], o.data.shape[0], ofs
if args.mean is True:
out = numpy.hstack((out, o.data[minN:maxN, :].mean(axis=0)[i]))
#print out.shape, o.data[minN:maxN,:].mean(axis=0).shape
if args.variance is True:
out = numpy.hstack((out, o.data[minN:maxN, :].var(axis=0)[i]))
if args.slope is True:
variance = o.data[minN:maxN, :].var(axis=0)[i]
lindata = numpy.zeros(variance.shape)
for i in xrange(o.data[minN:maxN, i].shape[1]):
lindata[i] = scipy.stats.linregress(o.data[minN:maxN,i],\
range(o.data[minN:maxN,:].shape[0]))[0]
out = numpy.hstack((out, lindata))
if args.csv is True:
for i in xrange(len(out)):
sys.stdout.write(str(out[i]))
sys.stdout.write(",")
sys.stdout.write(labels[d])
sys.stdout.write('\n')
if final_output is None:
final_output = out
else:
final_output = numpy.vstack((final_output, out))
p = feature_matrix.FeatureMatrix()
p.data = final_output.copy()
if args.normalize:
std_p = p.data.std(axis=0)
p.data = (p.data - p.data.mean(axis=0))/\
numpy.maximum(10**(-6), std_p)
p.metadata.sampling_configuration = o.metadata.sampling_configuration
p.metadata.feature = new_features
p.metadata.filename = final_filenames
p.save(args.outfile)
def stats(self,
feature_tracks,
mean=False,
variance=False,
delta=False,
acceleration=False,
slope=False,
limits=False,
csv=False,
normalize=False):
final_output = None
final_filenames = []
for o in feature_tracks:
#print o.metadata.feature
a = numpy.array(o.metadata.feature.split())
i = a.argsort()
final_filenames.append(o.metadata.filename)
if o.data.ndim == 1:
o.data.shape = (o.data.size, 1)
out = numpy.array([])
if delta is True:
#print "o.data shape", o.data.shape
#print "out shape ", out.shape
d = numpy.mean(delta_stat(o.data, order=1, axis=0), axis=0)[i]
#print "d shape ", d.shape
out = numpy.hstack((out, d))
if acceleration is True:
#print "o.data shape", o.data.shape
#print "out shape ", out.shape
d = numpy.mean(delta_stat(o.data, order=2, axis=0), axis=0)[i]
#print "d shape ", d.shape
out = numpy.hstack((out, d))
if mean is True:
out = numpy.hstack((out, o.data.mean(axis=0)[i]))
# print out.shape
if variance is True:
out = numpy.hstack((out, o.data.var(axis=0)[i]))
# print out.shape
if slope is True:
variance = o.data.var(axis=0)[i]
lindata = numpy.zeros(variance.shape)
for i in xrange(o.data.shape[1]):
lindata[i] = scipy.stats.linregress(o.data[:,i],\
range(o.data.shape[0]))[0]
out = numpy.hstack((out, lindata))
if limits is True:
out = numpy.hstack((out, o.data.max(axis=0)[i]))
out = numpy.hstack(
(out, o.data.argmax(axis=0)[i] / float(o.data.shape[0])))
out = numpy.hstack((out, o.data.min(axis=0)[i]))
out = numpy.hstack(
(out, o.data.argmin(axis=0)[i] / float(o.data.shape[0])))
out.shape = (1, out.size)
if csv is True:
for i in xrange(len(out) - 1):
sys.stdout.write(str(out[i]))
sys.stdout.write(",")
sys.stdout.write(str(out[-1]))
sys.stdout.write('\n')
if final_output is None:
final_output = out
else:
final_output = numpy.vstack((final_output, out))
# Dealing with feature metadata:
my_features = o.metadata.feature.split()
my_features.sort()
new_features = ""
if delta is True:
for feat in my_features:
new_features = new_features + " " + "delta_" + feat
if acceleration is True:
for feat in my_features:
new_features = new_features + " " + "accel_" + feat
if mean is True:
for feat in my_features:
new_features = new_features + " " + "mean_" + feat
if variance is True:
for feat in my_features:
new_features = new_features + " " + "var_" + feat
if slope is True:
for feat in my_features:
new_features = new_features + " " + "slope_" + feat
if limits is True:
for feat in my_features:
new_features = new_features + " " + "max_" + feat
for feat in my_features:
new_features = new_features + " " + "argmax_" + feat
for feat in my_features:
new_features = new_features + " " + "min_" + feat
for feat in my_features:
new_features = new_features + " " + "argmin_" + feat
#print new_features
p = feature_matrix.FeatureMatrix()
p.data = final_output.copy()
if normalize:
std_p = p.data.std(axis=0)
p.data = (p.data - p.data.mean(axis=0))/\
numpy.maximum(10**(-6), std_p)
p.metadata.sampling_configuration = o.metadata.sampling_configuration
p.metadata.feature = new_features
p.metadata.filename = final_filenames
return p