def test_specific_user(self):
link = ClusterLinkage(self.user_ink_data, target_user_id='user_1')
clustered_data = link.clustered_data()
cdtw = ClassifierDTW()
cdtw.train(clustered_data)
accuracy,_,_ = cdtw.test(self.label_ink_pairs)
self.assertGreater(accuracy, 91.0)
def test_simple(self):
link = ClusterLinkage(self.user_ink_data)
clustered_data = link.clustered_data()
cdtw = ClassifierDTW()
cdtw.train(clustered_data)
accuracy,_,_ = cdtw.test(self.label_ink_pairs)
self.assertGreater(accuracy, 92.0)
def test_state_reduction(self):
cDTW = ClassifierDTW(alpha=0.5,min_cluster_size=10)
cDTW.train(self.clustered_data,center_type='medoid',
state_reduction=True)
accuracy,_,_ = cDTW.test(self.label_ink_pairs)
if VERBOSE: print accuracy, 87
self.assertGreater(accuracy, 87.0)
def test_simple(self):
km = ClusterKMeans(self.user_ink_data,algorithm='dtw')
clustered_data = km.clustered_data()
cDTW = ClassifierDTW()
cDTW.train(clustered_data, center_type='centroid')
accuracy,_,_ = cDTW.test(self.label_ink_pairs)
self.assertGreater(accuracy, 93.0)
def test_optimize(self):
km = ClusterKMeans(self.user_ink_data,algorithm='dtw')
km.optimize_cluster_num(self.label_ink_pairs, verbose=False)
clustered_data = km.clustered_data()
cDTW = ClassifierDTW()
cDTW.train(clustered_data, center_type='centroid')
accuracy,_,_ = cDTW.test(self.label_ink_pairs)
self.assertGreater(accuracy, 93.0)
def optimize_cluster_num(self, test_data, n_iter=30,
threshold=0.001, dview=None, verbose=False):
# start with 1 prototype for each label
temp_n_clusters = np.ones(len(self.labels),dtype=np.int)
cluster_info = self._partition_data(temp_n_clusters.tolist(),
dview=dview)
distmats = [distmat for _,distmat in cluster_info]
trained_prototypes = _train_all_prototypes(self.weighted_ink_data,
cluster_info,
self.labels)
curr_classifier = ClassifierDTW()
curr_classifier.trained_prototypes = trained_prototypes
(accuracy,_,_) = curr_classifier.test(test_data,dview=dview)
error_rates = [1.0 - accuracy / 100.0]
n_clusters = [temp_n_clusters.copy()]
added_labels = []
if verbose: print error_rates
# compute all candidates
candidates = []
for i in range(len(self.labels)):
partition,_ = _partition_subset((self.weighted_ink_data[i],
self.labels[i],
temp_n_clusters[i]+1),
distmat=distmats[i],
verbose=verbose)
prototypes = _train_prototypes(self.weighted_ink_data[i],
partition,
self.labels[i])
if verbose: print "candidate for %s has length %d"%(
self.labels[i], len(prototypes))
candidates.append(prototypes)
for it in range(n_iter):
if verbose: print "Iteration %d"%it
# find the most beneficial class to increse prototype by 1
min_error = 1.0
min_idx = None
best_classifier = None
for i in range(len(self.labels)):
if len(candidates[i]) < temp_n_clusters[i]+1:
# degenerated case. dont need to test
error = 1.0
elif temp_n_clusters[i]+1 > self.maxclust:
# maxclust reached
error = 1.0
else:
test_classifier = ClassifierDTW()
prototypes = curr_classifier.trained_prototypes
# filter out all prototypes with the label
prototypes = [p
for p in prototypes
if p.label != self.labels[i]]
prototypes += candidates[i]
test_classifier.trained_prototypes = prototypes
(accuracy,_,_) = test_classifier.test(test_data,
dview=dview)
error = 1.0 - accuracy / 100.0
if verbose: print "> %f"%error
if (error < min_error):
min_error = error
min_idx = i
best_classifier = test_classifier
# Stop if no update found or error reduction is small
if (min_idx is None) or (error_rates[-1] - min_error < threshold):
if verbose: print "no improvement. done."
break
# choose the min_idx
temp_n_clusters[min_idx] += 1
error_rates.append(min_error)
added_labels.append(self.labels[min_idx])
n_clusters.append(temp_n_clusters.copy())
curr_classifier = best_classifier
if verbose:
print error_rates
print n_clusters
print "choosing %s"%self.labels[min_idx]
# replace the candidate if needed
if (temp_n_clusters[min_idx]+1 <= self.maxclust):
partition,_ = _partition_subset(
(self.weighted_ink_data[min_idx],
self.labels[min_idx],
temp_n_clusters[min_idx]+1),
distmat=distmats[min_idx],
verbose=verbose)
prototypes = _train_prototypes(
self.weighted_ink_data[min_idx],
partition,
self.labels[min_idx])
if verbose:
print "candidate for %s has length %d"%(
self.labels[min_idx], len(prototypes))
candidates[min_idx] = prototypes
self.n_clusters = n_clusters[-1]
return (error_rates, added_labels)
