def get_training_data(window_size_ms, train_time_sec=30):
#loop until empty input is detected
X = []
y = []
print "Training time for each key is {} seconds".format(train_time_sec)
i = 0
while True:
s = raw_input('Press <enter> to begin training key {} or q-<enter> to quit'.format(i))
if s: break
j = 0
while j < train_time_sec:
j += (window_size_ms / float(1000))
freq_spect = read_spectral_data_for_time(window_size_ms)
X.append(freq_spect)
y.append([i])
#increment key counter
i += 1
mb = MultiLabelBinarizer()
y = mb.fit_transform(y)
X = np.asarray(X)
y = np.asarray(y)
return X, y
def listen(clf, mb, window_size_ms): while True: freq_spect = read_spectral_data_for_time(window_size_ms) _label = clf.predict([freq_spect]) current_notes = mb.inverse_transform(_label)[0] for note in current_notes: note_buffer.put(note) print str(current_notes)
def single_key_experiment(window_size_ms, clf, train_time_sec):
#loop until empty input is detected
X = []
y = []
while True:
#the key I will press
key = raw_input('Label num:')
if not key: break
i = 0
while i < train_time_sec:
i += (window_size_ms / float(1000))
freq_spect = read_spectral_data_for_time(window_size_ms)
X.append(freq_spect)
y.append(key)
clf.fit(X, y)
while True:
freq_spect = read_spectral_data_for_time(window_size_ms)
_label = clf.predict([freq_spect])
print 'Predicting class {}'.format(_label[0])
def train(window_size_ms, train_time_sec=30, clf = OneVsRestClassifier(DecisionTreeClassifier()), n_keys=2):
#loop until empty input is detected
X = []
y = []
labels = [(i,) for i in range(n_keys+1)]
mb = MultiLabelBinarizer()
labels = mb.fit_transform(labels)
print "Training time for each key is {} seconds".format(train_time_sec)
for label_num, label in enumerate(labels):
raw_input('Press <enter> to begin training key {}'.format(label_num))
i = 0
while i < train_time_sec:
i += (window_size_ms / float(1000))
freq_spect = read_spectral_data_for_time(window_size_ms)
X.append(freq_spect)
y.append(label)
X = np.asarray(X)
y = np.asarray(y)
clf.fit(X, y)
return (clf, mb)
