def test_multinomial_blocks_subgradient_batch():
#testing cutting plane ssvm on easy multinomial dataset
X, Y = generate_blocks_multinomial(n_samples=10, noise=0.6, seed=1)
n_labels = len(np.unique(Y))
crf = GridCRF(n_states=n_labels, inference_method=inference_method)
clf = SubgradientSSVM(model=crf, max_iter=100, batch_size=-1)
clf.fit(X, Y)
Y_pred = clf.predict(X)
assert_array_equal(Y, Y_pred)
clf2 = SubgradientSSVM(model=crf, max_iter=100, batch_size=len(X))
clf2.fit(X, Y)
Y_pred2 = clf2.predict(X)
assert_array_equal(Y, Y_pred2)
def test_multinomial_blocks_subgradient_batch():
#testing cutting plane ssvm on easy multinomial dataset
X, Y = generate_blocks_multinomial(n_samples=10, noise=0.6, seed=1)
n_labels = len(np.unique(Y))
crf = GridCRF(n_states=n_labels, inference_method=inference_method)
clf = SubgradientSSVM(model=crf, max_iter=100, batch_size=-1)
clf.fit(X, Y)
Y_pred = clf.predict(X)
assert_array_equal(Y, Y_pred)
clf2 = SubgradientSSVM(model=crf, max_iter=100, batch_size=len(X))
clf2.fit(X, Y)
Y_pred2 = clf2.predict(X)
assert_array_equal(Y, Y_pred2)
def test_binary_ssvm_attractive_potentials_edgefeaturegraph(inference_method="qpbo"):
X, Y = generate_blocks(n_samples=10)
crf = GridCRF(inference_method=inference_method)
#######
# convert X,Y to EdgeFeatureGraphCRF instances
crf_edge = EdgeFeatureGraphCRF(inference_method=inference_method,
symmetric_edge_features=[0]
)
X_edge = []
Y_edge = []
for i in range(X.shape[0]):
unaries = X[i].reshape((-1, 2))
edges = crf._get_edges(X[i])
edge_feats = np.ones((edges.shape[0], 1))
X_edge.append((unaries, edges, edge_feats))
Y_edge.append((Y[i].reshape((-1,))))
submodular_clf_edge = SubgradientSSVM(model=crf_edge, max_iter=100, C=1,
verbose=1,
zero_constraint=[4,7],
negativity_constraint=[5,6],
)
# fit the model with non-negativity constraint on the off-diagonal potential
submodular_clf_edge.fit(X_edge, Y_edge)
assert submodular_clf_edge.w[5] == submodular_clf_edge.w[6] # symmetry constraint on edge features
# # # bias doesn't matter
# submodular_clf_edge.w += 10*np.ones(submodular_clf_edge.w.shape)
# print len(submodular_clf_edge.w), submodular_clf_edge.w
Y_pred = submodular_clf_edge.predict(X_edge)
assert_array_equal(Y_edge, Y_pred)
# try to fit the model with non-negativity constraint on the off-diagonal potential, this time
# with inverted sign on the edge features
X_edge_neg = [ (x[0], x[1], -x[2]) for x in X_edge ]
submodular_clf_edge = SubgradientSSVM(model=crf_edge, max_iter=100, C=1,
verbose=1,
zero_constraint=[4,7],
negativity_constraint=[5,6],
)
submodular_clf_edge.fit(X_edge_neg, Y_edge)
Y_pred = submodular_clf_edge.predict(X_edge_neg)
assert_array_equal(Y_edge, Y_pred)
def test_binary_blocks_subgradient():
#testing subgradient ssvm on easy binary dataset
X, Y = toy.generate_blocks(n_samples=10)
crf = GridCRF()
clf = SubgradientSSVM(model=crf, max_iter=200, C=100, learning_rate=0.1)
clf.fit(X, Y)
Y_pred = clf.predict(X)
assert_array_equal(Y, Y_pred)
def test_binary_blocks():
#testing subgradient ssvm on easy binary dataset
X, Y = generate_blocks(n_samples=5)
crf = GridCRF(inference_method=inference_method)
clf = SubgradientSSVM(model=crf)
clf.fit(X, Y)
Y_pred = clf.predict(X)
assert_array_equal(Y, Y_pred)
def test_multinomial_checker_subgradient():
X, Y = generate_checker_multinomial(n_samples=10, noise=0.4)
n_labels = len(np.unique(Y))
crf = GridCRF(n_states=n_labels, inference_method=inference_method)
clf = SubgradientSSVM(model=crf, max_iter=50)
clf.fit(X, Y)
Y_pred = clf.predict(X)
assert_array_equal(Y, Y_pred)
def test_binary_blocks():
#testing subgradient ssvm on easy binary dataset
X, Y = generate_blocks(n_samples=5)
crf = GridCRF(inference_method=inference_method)
clf = SubgradientSSVM(model=crf)
clf.fit(X, Y)
Y_pred = clf.predict(X)
assert_array_equal(Y, Y_pred)
def test_multinomial_checker_subgradient():
X, Y = generate_checker_multinomial(n_samples=10, noise=0.4)
n_labels = len(np.unique(Y))
crf = GridCRF(n_states=n_labels, inference_method=inference_method)
clf = SubgradientSSVM(model=crf, max_iter=50)
clf.fit(X, Y)
Y_pred = clf.predict(X)
assert_array_equal(Y, Y_pred)
def test_binary_checker_subgradient():
#testing subgradient ssvm on non-submodular binary dataset
X, Y = toy.generate_checker(n_samples=10)
crf = GridCRF()
clf = SubgradientSSVM(model=crf, max_iter=100, C=100, momentum=.9,
learning_rate=0.1)
clf.fit(X, Y)
Y_pred = clf.predict(X)
assert_array_equal(Y, Y_pred)
def test_binary_blocks():
#testing subgradient ssvm on easy binary dataset
X, Y = generate_blocks(n_samples=5)
crf = GridCRF(inference_method=inference_method)
clf = SubgradientSSVM(model=crf, C=100, learning_rate=1, decay_exponent=1,
momentum=0, decay_t0=10)
clf.fit(X, Y)
Y_pred = clf.predict(X)
assert_array_equal(Y, Y_pred)
def test_multinomial_checker_subgradient():
X, Y = toy.generate_checker_multinomial(n_samples=10, noise=0.0)
n_labels = len(np.unique(Y))
crf = GridCRF(n_states=n_labels)
clf = SubgradientSSVM(model=crf, max_iter=50, C=10,
momentum=.98, learning_rate=0.01)
clf.fit(X, Y)
Y_pred = clf.predict(X)
assert_array_equal(Y, Y_pred)
def test_multinomial_blocks_subgradient():
#testing cutting plane ssvm on easy multinomial dataset
X, Y = generate_blocks_multinomial(n_samples=10, noise=0.3, seed=1)
n_labels = len(np.unique(Y))
crf = GridCRF(n_states=n_labels, inference_method=inference_method)
clf = SubgradientSSVM(model=crf, max_iter=50, C=10, momentum=.98,
learning_rate=0.001)
clf.fit(X, Y)
Y_pred = clf.predict(X)
assert_array_equal(Y, Y_pred)
def test_blobs_2d_subgradient():
# make two gaussian blobs
X, Y = make_blobs(n_samples=80, centers=3, random_state=42)
# we have to add a constant 1 feature by hand :-/
X = np.hstack([X, np.ones((X.shape[0], 1))])
X_train, X_test, Y_train, Y_test = X[:40], X[40:], Y[:40], Y[40:]
pbl = MultiClassClf(n_features=3, n_classes=3)
svm = SubgradientSSVM(pbl, C=1000)
svm.fit(X_train, Y_train)
assert_array_equal(Y_test, np.hstack(svm.predict(X_test)))
def test_blobs_2d_subgradient():
# make two gaussian blobs
X, Y = make_blobs(n_samples=80, centers=3, random_state=42)
# we have to add a constant 1 feature by hand :-/
X = np.hstack([X, np.ones((X.shape[0], 1))])
X_train, X_test, Y_train, Y_test = X[:40], X[40:], Y[:40], Y[40:]
pbl = MultiClassClf(n_features=3, n_classes=3)
svm = SubgradientSSVM(pbl, C=1000)
svm.fit(X_train, Y_train)
assert_array_equal(Y_test, np.hstack(svm.predict(X_test)))
def test_binary_blocks():
#testing subgradient ssvm on easy binary dataset
X, Y = generate_blocks(n_samples=5)
crf = GridCRF(inference_method=inference_method)
clf = SubgradientSSVM(model=crf,
C=100,
learning_rate=1,
decay_exponent=1,
momentum=0,
decay_t0=10)
clf.fit(X, Y)
Y_pred = clf.predict(X)
assert_array_equal(Y, Y_pred)
def test_multinomial_blocks_subgradient():
#testing cutting plane ssvm on easy multinomial dataset
X, Y = generate_blocks_multinomial(n_samples=10, noise=0.3, seed=1)
n_labels = len(np.unique(Y))
crf = GridCRF(n_states=n_labels, inference_method=inference_method)
clf = SubgradientSSVM(model=crf,
max_iter=50,
C=10,
momentum=.98,
learning_rate=0.001)
clf.fit(X, Y)
Y_pred = clf.predict(X)
assert_array_equal(Y, Y_pred)
def test_objective():
# test that LatentSubgradientSSVM does the same as SubgradientSVM,
# in particular that it has the same loss, if there are no latent states.
X, Y = toy.generate_blocks_multinomial(n_samples=10)
n_labels = 3
crfl = LatentGridCRF(n_labels=n_labels, n_states_per_label=1)
clfl = LatentSubgradientSSVM(model=crfl, max_iter=50, C=10.,
learning_rate=0.001, momentum=0.98,
decay_exponent=0)
clfl.w = np.zeros(crfl.size_psi) # this disables random init
clfl.fit(X, Y)
crf = GridCRF(n_states=n_labels)
clf = SubgradientSSVM(model=crf, max_iter=50, C=10.,
learning_rate=0.001, momentum=0.98, decay_exponent=0)
clf.fit(X, Y)
assert_array_almost_equal(clf.w, clfl.w)
assert_array_equal(clf.predict(X), Y)
assert_almost_equal(clf.objective_curve_[-1], clfl.objective_curve_[-1])
def test_objective():
# test that SubgradientLatentSSVM does the same as SubgradientSVM,
# in particular that it has the same loss, if there are no latent states.
X, Y = generate_blocks_multinomial(n_samples=10, noise=.3, seed=1)
inference_method = get_installed(["qpbo", "ad3", "lp"])[0]
n_labels = 3
crfl = LatentGridCRF(n_labels=n_labels, n_states_per_label=1,
inference_method=inference_method)
clfl = SubgradientLatentSSVM(model=crfl, max_iter=20, C=10.,
learning_rate=0.001, momentum=0.98)
crfl.initialize(X, Y)
clfl.w = np.zeros(crfl.size_joint_feature) # this disables random init
clfl.fit(X, Y)
crf = GridCRF(n_states=n_labels, inference_method=inference_method)
clf = SubgradientSSVM(model=crf, max_iter=20, C=10., learning_rate=0.001,
momentum=0.98)
clf.fit(X, Y)
assert_array_almost_equal(clf.w, clfl.w)
assert_almost_equal(clf.objective_curve_[-1], clfl.objective_curve_[-1])
assert_array_equal(clf.predict(X), clfl.predict(X))
assert_array_equal(clf.predict(X), Y)
n_gestures = len(np.unique(gesture_labels))
frame_prior_train, frame_transition_matrix_train = calculate_hmm_params(frame_labels, n_gestures)
gesture_prior_train, gesture_transition_matrix_train = calculate_hmm_params(gesture_labels, n_gestures)
print "Unary (frame) score:", frame_clf_train.score(np.vstack(frame_hists_train), np.hstack(frame_labels))
print "Unary (gesture) score:", gesture_clf_train.score(np.vstack(gesture_hists_train), np.hstack(gesture_labels))
gesture_transition_matrix_train = np.ones([n_gestures,3])/3.
# Markov CRF
markovCRF = MarkovCRF(n_states=n_gestures, clf=frame_clf_train,
prior=frame_prior_train, transition=frame_transition_matrix_train,
inference_method='dai')
markov_svm = SubgradientSSVM(markovCRF, verbose=1, C=1., n_jobs=1)
markov_svm.fit(frame_hists_train, frame_labels)
m_predict = markov_svm.predict(frame_hists_train)
print 'Markov w:', markov_svm.w
print 'Markov CRF score: {}%'.format(100*np.sum([np.sum(np.equal(m_predict[i],x)) for i,x in enumerate(frame_labels)]) / np.sum([np.size(x) for x in frame_labels], dtype=np.float))
# semi-Markov CRF
sm_crf = SemiMarkovCRF(n_states=n_gestures,clf=gesture_clf_train,
prior=gesture_prior_train, transition_matrix=gesture_transition_matrix_train)
sm_svm = SubgradientSSVM(sm_crf, verbose=1, C=1., n_jobs=1)
sm_svm.fit(frame_hists_train, frame_labels)
sm_predict = sm_svm.predict(frame_hists_train)
print 'Semi-Markov w:', sm_svm.w
print 'Semi-Markov CRF score: {}%'.format(100*np.sum([np.sum(sm_predict[i]==x) for i,x in enumerate(frame_labels)]) / np.sum([np.size(x) for x in frame_labels], dtype=np.float))
# Markov semi-Markov CRF
MarkovSemiMarkovCRF = MarkovSemiMarkovCRF(n_states=n_gestures,
markov_prior=frame_prior_train, markov_transition=frame_transition_matrix_train,
print("Score with pystruct n-slack ssvm: %f (took %f seconds)"
% (np.mean(y_pred == y_test), time_n_slack_svm))
## 1-slack cutting plane ssvm
start = time()
one_slack_svm.fit(X_train_bias, y_train)
time_one_slack_svm = time() - start
y_pred = np.hstack(one_slack_svm.predict(X_test_bias))
print("Score with pystruct 1-slack ssvm: %f (took %f seconds)"
% (np.mean(y_pred == y_test), time_one_slack_svm))
#online subgradient ssvm
start = time()
subgradient_svm.fit(X_train_bias, y_train)
time_subgradient_svm = time() - start
y_pred = np.hstack(subgradient_svm.predict(X_test_bias))
print("Score with pystruct subgradient ssvm: %f (took %f seconds)"
% (np.mean(y_pred == y_test), time_subgradient_svm))
# the standard one-vs-rest multi-class would probably be as good and faster
# but solving a different model
libsvm = LinearSVC(multi_class='crammer_singer', C=.1)
start = time()
libsvm.fit(X_train, y_train)
time_libsvm = time() - start
print("Score with sklearn and libsvm: %f (took %f seconds)"
% (libsvm.score(X_test, y_test), time_libsvm))
start = time()
test_conll_os_ssvm = conlleval_fmt(iob_test, test_os_ssvm_preds)
test_conll_os_ssvm_file = open('test_conll_os_ssvm.txt', 'wb')
for sentence in test_conll_os_ssvm:
test_conll_os_ssvm_file.write(bytes(sentence, 'UTF-8'))
test_conll_os_ssvm_file.close()
print(conlleval_results('test_conll_os_ssvm.txt'))
if args.subgrad:
### fit subgradient ssvm
crf = ChainCRF()
sg_ssvm = SubgradientSSVM(crf, max_iter=200,
verbose=args.verbose, n_jobs=-1,
use_memmapping_pool=0, show_loss_every=20, shuffle=True)
sg_ssvm.fit(list(X_train_tsvd), y_train)
test_sg_ssvm_preds = [[id2label[i] for i in sent]
for sent in sg_ssvm.predict(X_test_tsvd)]
test_conll_sg_ssvm = conlleval_fmt(iob_test, test_sg_ssvm_preds)
test_conll_sg_ssvm_file = open('test_conll_sg_ssvm.txt', 'wb')
for sentence in test_conll_sg_ssvm:
test_conll_sg_ssvm_file.write(bytes(sentence, 'UTF-8'))
test_conll_sg_ssvm_file.close()
print(conlleval_results('test_conll_sg_ssvm.txt'))
if args.evals:
print(conlleval_results('test_conll_svc.txt'))
print(conlleval_results('test_conll_crfsuite.txt'))
print(conlleval_results('test_conll_searn.txt'))
print(conlleval_results('test_conll_os_ssvm.txt'))
print(conlleval_results('test_conll_sg_ssvm.txt'))
class EdgeCRFClassifier:
def __init__(self, userId="anonymous"):
self.model = None
self.learner = None
self.featurizer = None
self.userId = userId
def fresh_train(self, x, y, iterations=10):
self.model = EdgeFeatureGraphCRF(inference_method="max-product")
self.learner = SubgradientSSVM(
model=self.model,
max_iter=iterations,
logger=SaveLogger(model_file.format(self.userId + "-learner")))
self.learner.fit(x, y, warm_start=False)
self.save()
def fresh_train_default(self, iterations=10):
default_train = scriptdir + '/../../../data/compression/' \
'googlecomp100.train.lbl'
featurizer = edge_featurize.Featurizer()
x, y = featurizer.fit_transform(default_train)
self.fresh_train(x, y, iterations=iterations)
def update(self, x, y):
"""
Performs an online update of the model
:param x: Input data
:param y: List of Numpy array of label IDs
:return:
"""
self.learner.fit(x, y, warm_start=False)
def predict(self, x):
self.check_featurizer_set()
label_ids = self.learner.predict(x)
labels = []
for sent in label_ids:
labels.append(np.array(self.featurizer.map_inv(sent)))
return labels, label_ids
def set_featurizer(self, featurizer):
self.featurizer = featurizer
def featurize_train(self, train_data, iterations=10):
self.check_featurizer_set()
x, y = self.featurizer.fit_transform(train_data)
self.fresh_train(x, y, iterations)
def featurize_update(self, src, y):
self.check_featurizer_set()
x, _ = self.featurizer.transform(src)
self.update(x, y)
def featurize_predict(self, data):
self.check_featurizer_set()
x, _ = self.featurizer.transform(data)
return self.predict(x)
def save(self, userId=None):
if not userId:
userId = self.userId
with open(model_file.format(userId), 'wb') as pf:
pickle.dump((self.learner, self.model, self.featurizer), pf,
pickle.HIGHEST_PROTOCOL)
def load(self, userId=None):
if not userId:
userId = self.userId
with open(model_file.format(userId), 'rb') as pf:
self.learner, self.model, self.featurizer = pickle.load(pf)
return self
def load_default_init(self):
with open(model_file.format("default"), 'rb') as pf:
self.learner, self.model, self.featurizer = pickle.load(pf)
def check_featurizer_set(self):
if not self.featurizer:
raise RuntimeError("Featurizer not set. Use set_featurizer().")
def text_predict(self, input_txt):
original = []
simplified = []
X, parses = self.featurizer.transform_plain(input_txt)
for x, parse in zip(X, parses):
labels = self.predict([x])[0]
# tokens = parses[0]['form']
tokens = parse['form']
original.append(detokenizer.detokenize([t for t in tokens], True))
# original.append(" ".join([t for t in tokens]))
# print('#\n#\n#')
# print(" ".join(tokens) + "\t===>\t", end='')
graph = nx.DiGraph()
for s, t in x[1]:
# graph.add_edge(tokens[s], tokens[t])
graph.add_edge(s, t)
# print(graph.nodes())
for i, l in enumerate(labels[0]):
if l == 'DEL':
for s, t in graph.edges():
# print(t, s)
if t == i:
# print("DEL", t)
for n in dfs_tree(graph, t).nodes():
# print(n)
graph.remove_node(n)
# print(graph.nodes())
simplified.append(
detokenizer.detokenize(
[tokens[n] for n in sorted(graph.nodes())], True))
# simplified.append(" ".join(
# [tokens[n] for n in sorted(graph.nodes())]))
return original, simplified
