# Linear (dot-product) kernel that takes the average of each feature over all images
# for each business.
def mean_linear_kernel(X1, X2):
f1 = np.array([np.mean(features_by_bid[int(bid)].T, axis=1) for bid in X1[:,0]])
f2 = np.array([np.mean(features_by_bid[int(bid)].T, axis=1) for bid in X2[:,0]])
return np.dot(f1, f2.T)
def max_linear_kernel(X1, X2):
f1 = np.array([np.ndarray.max(features_by_bid[int(bid)].T, axis=1) for bid in X1[:,0]])
f2 = np.array([np.ndarray.max(features_by_bid[int(bid)].T, axis=1) for bid in X2[:,0]])
return np.dot(f1, f2.T)
if emd_matrix_prefix is not None:
emd_matrix = EMDMatrix.load(emd_matrix_prefix)
def EMD_kernel(X1, X2, gamma):
emd = emd_matrix.for_business_ids(X1[:,0], X2[:,0])
if emd is None:
raise Exception('Provided EMD matrix does not cover needed business IDs.')
# emd **= 2
emd *= -gamma
return np.exp(emd)
def accuracy_for_label(label_num):
label = shuffled_labels[:,label_num]
data = shuffled_bids.reshape(-1, 1)
params = ''
features_prefix = sys.argv[1]
fdata = FeatureData(features_prefix)
features_by_bid = {}
for f, bid in izip(fdata.features, fdata.business_ids):
if bid in features_by_bid:
features_by_bid[bid].append(f)
else:
features_by_bid[bid] = [f]
for bid in features_by_bid.keys():
features_by_bid[bid] = np.array(features_by_bid[bid])
business_ids = np.array(sorted(features_by_bid.keys())[:2])
print "bids: ", business_ids
print "recalculated:"
for bid1 in business_ids:
for bid2 in business_ids:
print "D(%d, %d): %.4f" % (bid1, bid2,
emd(features_by_bid[bid1], features_by_bid[bid2]))
print "from file:"
emd_matrix = EMDMatrix.load(sys.argv[2])
print emd_matrix.for_business_ids(business_ids, business_ids)
self.business_ids = np.load(file_prefix + '-business_ids.npy')
features_prefix = sys.argv[1]
fdata = FeatureData(features_prefix)
features_by_bid = {}
for f, bid in izip(fdata.features, fdata.business_ids):
if bid in features_by_bid:
features_by_bid[bid].append(f)
else:
features_by_bid[bid] = [f]
for bid in features_by_bid.keys():
features_by_bid[bid] = np.array(features_by_bid[bid])
business_ids = np.array(sorted(features_by_bid.keys())[:2])
print "bids: ", business_ids
print "recalculated:"
for bid1 in business_ids:
for bid2 in business_ids:
print "D(%d, %d): %.4f" % (
bid1, bid2, emd(features_by_bid[bid1], features_by_bid[bid2]))
print "from file:"
emd_matrix = EMDMatrix.load(sys.argv[2])
print emd_matrix.for_business_ids(business_ids, business_ids)
return np.dot(f1, f2.T)
def max_linear_kernel(X1, X2):
f1 = np.array([
np.ndarray.max(features_by_bid[int(bid)].T, axis=1) for bid in X1[:, 0]
])
f2 = np.array([
np.ndarray.max(features_by_bid[int(bid)].T, axis=1) for bid in X2[:, 0]
])
return np.dot(f1, f2.T)
if emd_matrix_prefix is not None:
emd_matrix = EMDMatrix.load(emd_matrix_prefix)
def EMD_kernel(X1, X2, gamma):
emd = emd_matrix.for_business_ids(X1[:, 0], X2[:, 0])
if emd is None:
raise Exception(
'Provided EMD matrix does not cover needed business IDs.')
# emd **= 2
emd *= -gamma
return np.exp(emd)
def accuracy_for_label(label_num):
