def plotfeats(dict_train_features, mask=arange(10) + 8):
for feat_index, feat in enumerate(mask):
plt.figure(figsize=(10, 10))
for i in arange(len(classes())):
sns.distplot(dict_train_features[i][:, feat],
label='Histogram for {} of feature {}'.format(
classes()[i],
featuresnames()[feat]))
plt.legend()
plt.grid(True)
for d, c in enumerate(mask):
plt.figure(figsize=(10, 10))
for i in arange(len(classes())):
plt.subplot(len(classes()), 1, i + 1)
plt.ylim(0, 1)
feature = dict_train_features[i].transpose()[c]
plt.stem(feature,
markerfmt='C3.',
basefmt='C9-',
use_line_collection=True)
if i == 0:
plt.title(featuresnames()[c] + ' coefficients')
plt.ylabel(classes()[i])
plt.grid(True)
plt.show()
def print_features(featurelst):
print('\n\nSelected matrix:')
print([featuresnames()[i] for i in featurelst['selectedcolumns']])
print(featurelst['featurematrix'])
print('\nfeature scores:')
print(featuresnames())
print(featurelst['scores'])
print('\nselected features')
print([featuresnames()[i] for i in featurelst['selectedcolumns']])
def plotfeature(feat, i=-1):
plt.figure(figsize=(18, 4))
plt.subplot(1, 1, 1)
plt.stem(feat, use_line_collection=True)
if i != -1:
plt.ylabel(featuresnames()[i] + ' coefficients')
plt.title(featuresnames()[i] + ' coefficients {}'.format(classes()[i]))
plt.grid(True)
plt.show()
def plotfeats_per_class(dict_train_features):
for c in arange(len(classes())):
plt.figure(figsize=(10, 10))
for i in arange(len(featuresnames())):
plt.subplot(len(featuresnames()), 1, i + 1)
plt.ylim(0, 1)
feature = dict_train_features[c].transpose()[i]
plt.stem(feature, use_line_collection=True)
if i == 0:
plt.title(classes()[c] + ' coefficients')
plt.ylabel(featuresnames()[i])
plt.grid(True)
plt.show()
def traintest(path):
dict_features = trainingloop.getdicttrainfeatures(
path) # compute train features
classes = user_interface.classes()
test_size = user_interface.test_size()
X = [dict_features[c] for c in classes]
y = [np.ones(X[i].shape[0], ) * i for i in np.arange(len(classes))] # keys
y_mc = np.concatenate((y[0], y[1], y[2]), axis=0)
X_mc = np.concatenate((X[0], X[1], X[2]), axis=0)
X_train, X_test, y_train, y_test = train_test_split(X_mc,
y_mc,
test_size=test_size)
dict_train_feats = {'NoFX': [], 'Distortion': [], 'Tremolo': []}
dict_test_feats = {'NoFX': [], 'Distortion': [], 'Tremolo': []}
n_features = len(user_interface.featuresnames())
for c in np.arange(len(classes)):
condition = np.mod(y_train, 3) == c
n_train = len(y_train[condition])
train_feats = np.zeros((n_train, n_features))
k = 0
for i in np.arange(len(y_train)):
if y_train[i] == c:
train_feats[k, :] = X_train[i, :]
k = k + 1
dict_train_feats[classes[c]] = train_feats
for c in np.arange(len(classes)):
condition = np.mod(y_test, 3) == c
n_test = len(y_test[condition])
test_feats = np.zeros((n_test, n_features))
k = 0
for i in np.arange(len(y_test)):
if y_test[i] == c:
test_feats[k, :] = X_test[i, :]
k = k + 1
dict_test_feats[classes[c]] = test_feats
savetraindata.save_datasets(dict_train_feats, dict_test_feats)
return dict_train_feats, dict_test_feats
def train():
path = pathlib.Path(__file__).parent.absolute()
classes = user_interface.classes()
if user_interface.generate_datasets():
main_traintest.traintest(path)
dict_train_features = {'NoFX': [], 'Distortion': [], 'Tremolo': []}
for c in classes:
dict_train_features[c] = dataloader.dict_train_features(c)
else:
dict_train_features = trainingloop.getdicttrainfeatures(
path) # compute train features
X_train = [dict_train_features[c] for c in classes]
y_train = [
np.ones(X_train[i].shape[0], ) * i
for i in np.arange(len(user_interface.classes()))
] # keys
feat_max = np.max(np.concatenate((X_train[0], X_train[1], X_train[2]),
axis=0),
axis=0)
feat_min = np.min(np.concatenate((X_train[0], X_train[1], X_train[2]),
axis=0),
axis=0)
X_train_normalized = [(X_train[c] - feat_min) / (feat_max - feat_min)
for c in np.arange(len(user_interface.classes()))
] # normalized matrix
X_train_mc_normalized = np.concatenate(
(X_train_normalized[0], X_train_normalized[1], X_train_normalized[2]),
axis=0)
y_train_mc = np.concatenate((y_train[0], y_train[1], y_train[2]), axis=0)
featurelst = featureselection.getfeaturelist(
X_train_mc_normalized, y_train_mc) # feature selection
if user_interface.do_plot():
plotfeatures.plotfeats(X_train_normalized,
mask=np.arange(10) + 7) # plot train features
else:
plotselected.plotsel(X_train_normalized, featurelst['selectedcolumns'])
savetraindata.savedata(dict_train_features, featurelst, feat_max,
feat_min) # save data
print('All features')
print(user_interface.featuresnames())
print_feature_sel.print_features(featurelst)
return True
def getdicttrainfeatures(path):
dict_train_features = {'NoFX': [], 'Distortion': [], 'Tremolo': []}
fullpath = str(path) + '/environment/databases/train/{}'
for c in user_interface.classes(): # loops over classes
n_features = len(user_interface.featuresnames())
train_root = fullpath.format(c)
class_train_files = [
f for f in os.listdir(train_root) if f.endswith('.wav')
]
n_train = len(class_train_files)
train_features = np.zeros((n_train, n_features))
for index, f in enumerate(
class_train_files): # loops over all the files of the class
audio, fs = librosa.load(os.path.join(train_root, f), sr=None)
train_features[index, :] = features.getfeatures(audio)
dict_train_features[c] = train_features
return dict_train_features