def train_one_vs_all_models(person_id):
prob_classifiers = []
#score_person = 4
test_person = person_id
person_ids = set(xrange(1, 48))
#person_ids.remove(score_person)
person_ids.remove(test_person)
for number in xrange(10):
# create the training data
training_vectors, training_labels = [], []
for person_id in person_ids:
vectors, labels = get_labelled_number_data_for_person(person_id)
labels = [int(label == number) for label in labels]
training_vectors += vectors
training_labels += labels
# get the scoring data
#score_vectors, score_labels = get_labelled_number_data_for_person(score_person)
#score_labels = [int(label == number) for label in score_labels]
classifier = train_with_data(training_vectors, training_labels)
#scores = classifier.decision_function(score_vectors)
scores = classifier.decision_function(training_vectors)
#yes_scores = [scores[index] for index in xrange(len(scores)) if score_labels[index] == 1]
#no_scores = [scores[index] for index in xrange(len(scores)) if score_labels[index] == 0]
yes_scores = [scores[index] for index in xrange(len(scores)) if training_labels[index] == 1]
no_scores = [scores[index] for index in xrange(len(scores)) if training_labels[index] == 0]
curve_data = get_curve_params(yes_scores, no_scores)
prob_classifiers.append(ProbabilisticSVM(classifier, curve_data))
# now let's hit up the classifiers with the test data
test_vectors, test_labels = get_labelled_number_data_for_person(test_person)
hits = 0
for vector, label in zip(test_vectors, test_labels):
probabilities = []
for index, classifier in enumerate(prob_classifiers):
probabilities.append((classifier.get_probability(vector), index))
probabilities.sort(reverse=True)
hit = probabilities[0][1] == label
if hit:
hits += 1
print 100 * (hits / float(len(test_labels))), '%'
return hits, len(test_labels)
from sound_recorder import get_raw_wav_data
from yes_no_test import get_labelled_yn_data_for_person
from predictor import train_with_data
from vectoriser import get_normalised_vector
#1 - train classifier
training_vectors, training_labels = [], []
for person_index in xrange(1, 38):
vectors, labels = get_labelled_yn_data_for_person(person_index)
training_vectors += vectors
training_labels += labels
print 'training...'
classifier = train_with_data(training_vectors, training_labels)
while True:
#2 - get raw data
sample_rate, data = get_raw_wav_data()
#3 vectorise data
vector = get_normalised_vector(sample_rate, data)
#4 test data
prediction = classifier.predict(vector)[0]
print '\n\n\n\n\n'
if prediction == 1:
print 'yes'
else:
print 'no'
print '\n\n\n\n\n'
