def test_constraint_removal():
digits = load_digits()
X, y = digits.data, digits.target
y = 2 * (y % 2) - 1 # even vs odd as +1 vs -1
X = X / 16.
pbl = BinaryClf(n_features=X.shape[1])
clf_no_removal = OneSlackSSVM(model=pbl, max_iter=500, C=1,
inactive_window=0, tol=0.01)
clf_no_removal.fit(X, y)
clf = OneSlackSSVM(model=pbl, max_iter=500, C=1, tol=0.01,
inactive_threshold=1e-8)
clf.fit(X, y)
# check that we learned something
assert_greater(clf.score(X, y), .92)
# results are mostly equal
# if we decrease tol, they will get more similar
assert_less(np.mean(clf.predict(X) != clf_no_removal.predict(X)), 0.02)
# without removal, have as many constraints as iterations
assert_equal(len(clf_no_removal.objective_curve_),
len(clf_no_removal.constraints_))
# with removal, there are less constraints than iterations
assert_less(len(clf.constraints_),
len(clf.objective_curve_))
def test_standard_svm_blobs_2d_class_weight():
# no edges, reduce to crammer-singer svm
X, Y = make_blobs(n_samples=210, centers=3, random_state=1, cluster_std=3,
shuffle=False)
X = np.hstack([X, np.ones((X.shape[0], 1))])
X, Y = X[:170], Y[:170]
X_graphs = [(x[np.newaxis, :], np.empty((0, 2), dtype=np.int)) for x in X]
pbl = GraphCRF(n_features=3, n_states=3, inference_method='unary')
svm = OneSlackSSVM(pbl, check_constraints=False, C=1000)
svm.fit(X_graphs, Y[:, np.newaxis])
weights = 1. / np.bincount(Y)
weights *= len(weights) / np.sum(weights)
pbl_class_weight = GraphCRF(n_features=3, n_states=3, class_weight=weights,
inference_method='unary')
svm_class_weight = OneSlackSSVM(pbl_class_weight, C=10,
check_constraints=False,
break_on_bad=False)
svm_class_weight.fit(X_graphs, Y[:, np.newaxis])
assert_greater(f1_score(Y, np.hstack(svm_class_weight.predict(X_graphs))),
f1_score(Y, np.hstack(svm.predict(X_graphs))))
def test_standard_svm_blobs_2d_class_weight():
# no edges, reduce to crammer-singer svm
X, Y = make_blobs(n_samples=210,
centers=3,
random_state=1,
cluster_std=3,
shuffle=False)
X = np.hstack([X, np.ones((X.shape[0], 1))])
X, Y = X[:170], Y[:170]
X_graphs = [(x[np.newaxis, :], np.empty((0, 2), dtype=np.int)) for x in X]
pbl = GraphCRF(n_features=3, n_states=3, inference_method='unary')
svm = OneSlackSSVM(pbl, check_constraints=False, C=1000)
svm.fit(X_graphs, Y[:, np.newaxis])
weights = 1. / np.bincount(Y)
weights *= len(weights) / np.sum(weights)
pbl_class_weight = GraphCRF(n_features=3,
n_states=3,
class_weight=weights,
inference_method='unary')
svm_class_weight = OneSlackSSVM(pbl_class_weight,
C=10,
check_constraints=False,
break_on_bad=False)
svm_class_weight.fit(X_graphs, Y[:, np.newaxis])
assert_greater(f1_score(Y, np.hstack(svm_class_weight.predict(X_graphs))),
f1_score(Y, np.hstack(svm.predict(X_graphs))))
def test_constraint_removal():
digits = load_digits()
X, y = digits.data, digits.target
y = 2 * (y % 2) - 1 # even vs odd as +1 vs -1
X = X / 16.
pbl = BinarySVMModel(n_features=X.shape[1])
clf_no_removal = OneSlackSSVM(model=pbl, max_iter=500, verbose=1, C=10,
inactive_window=0, tol=0.01)
clf_no_removal.fit(X, y)
clf = OneSlackSSVM(model=pbl, max_iter=500, verbose=1, C=10, tol=0.01,
inactive_threshold=1e-8)
clf.fit(X, y)
# results are mostly equal
# if we decrease tol, they will get more similar
assert_less(np.mean(clf.predict(X) != clf_no_removal.predict(X)), 0.02)
# without removal, have as many constraints as iterations
# +1 for true y constraint
assert_equal(len(clf_no_removal.objective_curve_) + 1,
len(clf_no_removal.constraints_))
# with removal, there are less constraints than iterations
assert_less(len(clf.constraints_),
len(clf.objective_curve_))
def main():
print("Please be patient. Will take 5-20 minutes.")
snakes = load_snakes()
X_train, Y_train = snakes['X_train'], snakes['Y_train']
X_train = [one_hot_colors(x) for x in X_train]
Y_train_flat = [y_.ravel() for y_ in Y_train]
X_train_directions, X_train_edge_features = prepare_data(X_train)
# first, train on X with directions only:
crf = EdgeFeatureGraphCRF(inference_method='qpbo')
ssvm = OneSlackSSVM(crf, inference_cache=50, C=.1, tol=.1, switch_to='ad3',
n_jobs=-1)
ssvm.fit(X_train_directions, Y_train_flat)
# Evaluate using confusion matrix.
# Clearly the middel of the snake is the hardest part.
X_test, Y_test = snakes['X_test'], snakes['Y_test']
X_test = [one_hot_colors(x) for x in X_test]
Y_test_flat = [y_.ravel() for y_ in Y_test]
X_test_directions, X_test_edge_features = prepare_data(X_test)
Y_pred = ssvm.predict(X_test_directions)
print("Results using only directional features for edges")
print("Test accuracy: %.3f"
% accuracy_score(np.hstack(Y_test_flat), np.hstack(Y_pred)))
print(confusion_matrix(np.hstack(Y_test_flat), np.hstack(Y_pred)))
# now, use more informative edge features:
crf = EdgeFeatureGraphCRF(inference_method='qpbo')
ssvm = OneSlackSSVM(crf, inference_cache=50, C=.1, tol=.1, switch_to='ad3',
n_jobs=-1)
ssvm.fit(X_train_edge_features, Y_train_flat)
Y_pred2 = ssvm.predict(X_test_edge_features)
print("Results using also input features for edges")
print("Test accuracy: %.3f"
% accuracy_score(np.hstack(Y_test_flat), np.hstack(Y_pred2)))
print(confusion_matrix(np.hstack(Y_test_flat), np.hstack(Y_pred2)))
# plot stuff
fig, axes = plt.subplots(2, 2)
axes[0, 0].imshow(snakes['X_test'][0], interpolation='nearest')
axes[0, 0].set_title('Input')
y = Y_test[0].astype(np.int)
bg = 2 * (y != 0) # enhance contrast
axes[0, 1].matshow(y + bg, cmap=plt.cm.Greys)
axes[0, 1].set_title("Ground Truth")
axes[1, 0].matshow(Y_pred[0].reshape(y.shape) + bg, cmap=plt.cm.Greys)
axes[1, 0].set_title("Prediction w/o edge features")
axes[1, 1].matshow(Y_pred2[0].reshape(y.shape) + bg, cmap=plt.cm.Greys)
axes[1, 1].set_title("Prediction with edge features")
for a in axes.ravel():
a.set_xticks(())
a.set_yticks(())
plt.show()
from IPython.core.debugger import Tracer
Tracer()()
def test_one_slack_constraint_caching():
# testing cutting plane ssvm on easy multinomial dataset
X, Y = generate_blocks_multinomial(n_samples=10, noise=0.5, seed=0,
size_x=9)
n_labels = len(np.unique(Y))
exact_inference = get_installed([('ad3', {'branch_and_bound': True}), "lp"])[0]
crf = GridCRF(n_states=n_labels, inference_method=exact_inference)
clf = OneSlackSSVM(model=crf, max_iter=150, C=1,
check_constraints=True, break_on_bad=True,
inference_cache=50, inactive_window=0)
clf.fit(X, Y)
Y_pred = clf.predict(X)
assert_array_equal(Y, Y_pred)
assert_equal(len(clf.inference_cache_), len(X))
# there should be 13 constraints, which are less than the 94 iterations
# that are done
# check that we didn't change the behavior of how we construct the cache
constraints_per_sample = [len(cache) for cache in clf.inference_cache_]
if exact_inference == "lp":
assert_equal(len(clf.inference_cache_[0]), 18)
assert_equal(np.max(constraints_per_sample), 18)
assert_equal(np.min(constraints_per_sample), 18)
else:
assert_equal(len(clf.inference_cache_[0]), 13)
assert_equal(np.max(constraints_per_sample), 20)
assert_equal(np.min(constraints_per_sample), 11)
def test_one_slack_constraint_caching():
#testing cutting plane ssvm on easy multinomial dataset
X, Y = generate_blocks_multinomial(n_samples=10,
noise=0.5,
seed=0,
size_x=9)
n_labels = len(np.unique(Y))
crf = GridCRF(n_states=n_labels, inference_method='lp')
clf = OneSlackSSVM(model=crf,
max_iter=150,
C=1,
check_constraints=True,
break_on_bad=True,
inference_cache=50,
inactive_window=0,
verbose=10)
clf.fit(X, Y)
Y_pred = clf.predict(X)
assert_array_equal(Y, Y_pred)
assert_equal(len(clf.inference_cache_), len(X))
# there should be 11 constraints, which are less than the 94 iterations
# that are done
assert_equal(len(clf.inference_cache_[0]), 11)
# check that we didn't change the behavior of how we construct the cache
constraints_per_sample = [len(cache) for cache in clf.inference_cache_]
assert_equal(np.max(constraints_per_sample), 19)
assert_equal(np.min(constraints_per_sample), 11)
def msrc():
models_basedir = 'models/msrc/'
crf = EdgeCRF(n_states=24, n_features=2028, n_edge_features=4,
inference_method='gco')
clf = OneSlackSSVM(crf, max_iter=10000, C=0.01, verbose=2,
tol=0.1, n_jobs=4,
inference_cache=100)
X, Y = load_msrc('train')
Y = remove_areas(Y)
start = time()
clf.fit(X, Y)
stop = time()
np.savetxt(models_basedir + 'msrc_full.csv', clf.w)
with open(models_basedir + 'msrc_full' + '.pickle', 'w') as f:
cPickle.dump(clf, f)
X, Y = load_msrc('test')
Y = remove_areas(Y)
Y_pred = clf.predict(X)
print 'Error on test set: %f' % compute_error(Y, Y_pred)
print 'Score on test set: %f' % clf.score(X, Y)
print 'Norm of weight vector: |w|=%f' % np.linalg.norm(clf.w)
print 'Elapsed time: %f s' % (stop - start)
return clf
def syntetic_test():
# test model on different train set size & on different train sets
results = np.zeros((18, 5))
full_labeled = np.array([2, 4, 10, 25, 100])
train_size = 400
for dataset in xrange(1, 19):
X, Y = load_syntetic(dataset)
for j, nfull in enumerate(full_labeled):
crf = EdgeCRF(n_states=10, n_features=10, n_edge_features=2,
inference_method='qpbo')
clf = OneSlackSSVM(crf, max_iter=10000, C=0.01, verbose=0,
tol=0.1, n_jobs=4, inference_cache=100)
x_train = X[:nfull]
y_train = Y[:nfull]
x_test = X[(train_size + 1):]
y_test = Y[(train_size + 1):]
try:
clf.fit(x_train, y_train)
y_pred = clf.predict(x_test)
results[dataset - 1, j] = compute_error(y_test, y_pred)
print 'dataset=%d, nfull=%d, error=%f' % (dataset, nfull,
results[dataset - 1, j])
except ValueError:
print 'dataset=%d, nfull=%d: Failed' % (dataset, nfull)
np.savetxt('results/syntetic/full_labeled.txt', results)
def test_binary_blocks_one_slack_graph():
#testing cutting plane ssvm on easy binary dataset
# generate graphs explicitly for each example
X, Y = generate_blocks(n_samples=3)
crf = GraphCRF(inference_method=inference_method)
clf = OneSlackSSVM(model=crf, max_iter=100, C=1,
check_constraints=True, break_on_bad=True,
n_jobs=1, tol=.1)
x1, x2, x3 = X
y1, y2, y3 = Y
n_states = len(np.unique(Y))
# delete some rows to make it more fun
x1, y1 = x1[:, :-1], y1[:, :-1]
x2, y2 = x2[:-1], y2[:-1]
# generate graphs
X_ = [x1, x2, x3]
G = [make_grid_edges(x) for x in X_]
# reshape / flatten x and y
X_ = [x.reshape(-1, n_states) for x in X_]
Y = [y.ravel() for y in [y1, y2, y3]]
X = list(zip(X_, G))
clf.fit(X, Y)
Y_pred = clf.predict(X)
for y, y_pred in zip(Y, Y_pred):
assert_array_equal(y, y_pred)
def msrc():
models_basedir = 'models/msrc/'
crf = EdgeCRF(n_states=24, n_features=2028, n_edge_features=4,
inference_method='gco')
clf = OneSlackSSVM(crf, max_iter=10000, C=0.01, verbose=2,
tol=0.1, n_jobs=4,
inference_cache=100)
X, Y = load_msrc('train')
Y = remove_areas(Y)
start = time()
clf.fit(X, Y)
stop = time()
np.savetxt(models_basedir + 'msrc_full.csv', clf.w)
with open(models_basedir + 'msrc_full' + '.pickle', 'w') as f:
pickle.dump(clf, f)
X, Y = load_msrc('test')
Y = remove_areas(Y)
Y_pred = clf.predict(X)
print('Error on test set: %f' % compute_error(Y, Y_pred))
print('Score on test set: %f' % clf.score(X, Y))
print('Norm of weight vector: |w|=%f' % np.linalg.norm(clf.w))
print('Elapsed time: %f s' % (stop - start))
return clf
def test_one_slack_constraint_caching():
# testing cutting plane ssvm on easy multinomial dataset
X, Y = generate_blocks_multinomial(n_samples=10, noise=0.5, seed=0,
size_x=9)
n_labels = len(np.unique(Y))
exact_inference = get_installed([('ad3', {'branch_and_bound': True}), "lp"])[0]
crf = GridCRF(n_states=n_labels, inference_method=exact_inference)
clf = OneSlackSSVM(model=crf, max_iter=150, C=1,
check_constraints=True, break_on_bad=True,
inference_cache=50, inactive_window=0)
clf.fit(X, Y)
Y_pred = clf.predict(X)
assert_array_equal(Y, Y_pred)
assert_equal(len(clf.inference_cache_), len(X))
# there should be 13 constraints, which are less than the 94 iterations
# that are done
# check that we didn't change the behavior of how we construct the cache
constraints_per_sample = [len(cache) for cache in clf.inference_cache_]
if exact_inference == "lp":
assert_equal(len(clf.inference_cache_[0]), 18)
assert_equal(np.max(constraints_per_sample), 18)
assert_equal(np.min(constraints_per_sample), 18)
else:
assert_equal(len(clf.inference_cache_[0]), 13)
assert_equal(np.max(constraints_per_sample), 20)
assert_equal(np.min(constraints_per_sample), 11)
def test_binary_blocks_one_slack_graph():
#testing cutting plane ssvm on easy binary dataset
# generate graphs explicitly for each example
for inference_method in ["dai", "lp"]:
print("testing %s" % inference_method)
X, Y = toy.generate_blocks(n_samples=3)
crf = GraphCRF(inference_method=inference_method)
clf = OneSlackSSVM(problem=crf, max_iter=100, C=100, verbose=100,
check_constraints=True, break_on_bad=True,
n_jobs=1)
x1, x2, x3 = X
y1, y2, y3 = Y
n_states = len(np.unique(Y))
# delete some rows to make it more fun
x1, y1 = x1[:, :-1], y1[:, :-1]
x2, y2 = x2[:-1], y2[:-1]
# generate graphs
X_ = [x1, x2, x3]
G = [make_grid_edges(x) for x in X_]
# reshape / flatten x and y
X_ = [x.reshape(-1, n_states) for x in X_]
Y = [y.ravel() for y in [y1, y2, y3]]
X = zip(X_, G)
clf.fit(X, Y)
Y_pred = clf.predict(X)
for y, y_pred in zip(Y, Y_pred):
assert_array_equal(y, y_pred)
def train(x_train, y_train, x_test, y_test):
x_train = np.asarray(x_train, dtype=np.float)
y_train = np.asarray(y_train, dtype=np.int64)
# x_test = np.asarray(x_test, dtype=np.float)
# y_test = np.asarray(y_test, dtype=np.int64)
x_test = x_train
y_test = y_train
from pystruct.learners import NSlackSSVM, OneSlackSSVM, SubgradientSSVM, LatentSSVM, SubgradientLatentSSVM, PrimalDSStructuredSVM
from pystruct.models import MultiLabelClf, MultiClassClf
clf = OneSlackSSVM(MultiLabelClf(),
C=1,
show_loss_every=1,
verbose=1,
max_iter=1000)
# print(x_train, y_train)
# input()
clf.fit(x_train, y_train)
result = clf.predict(x_test)
print('Result: \n', result)
print('True label:\n', y_test)
clf.score(x_test, y_test)
print('\n')
count = 0
for i in range(len(result)):
# print(np.sum(np.square(y_test[i]-result[i])))
if np.sum(np.square(y_test[i] - result[i])) != 0:
print('True label: ', y_test[i], 'Predict: ', result[i])
count += 1
print(count)
translate_vector(x_test, y_test)
def syntetic():
# train model on a single set
models_basedir = 'models/syntetic/'
crf = EdgeCRF(n_states=10, n_features=10, n_edge_features=2,
inference_method='gco')
clf = OneSlackSSVM(crf, max_iter=10000, C=0.01, verbose=2,
tol=0.1, n_jobs=4, inference_cache=100)
X, Y = load_syntetic(1)
x_train, x_test, y_train, y_test = train_test_split(X, Y,
train_size=100,
random_state=179)
start = time()
clf.fit(x_train, y_train)
stop = time()
np.savetxt(models_basedir + 'syntetic_full.csv', clf.w)
with open(models_basedir + 'syntetic_full' + '.pickle', 'w') as f:
cPickle.dump(clf, f)
y_pred = clf.predict(x_test)
print 'Error on test set: %f' % compute_error(y_test, y_pred)
print 'Score on test set: %f' % clf.score(x_test, y_test)
print 'Score on train set: %f' % clf.score(x_train, y_train)
print 'Norm of weight vector: |w|=%f' % np.linalg.norm(clf.w)
print 'Elapsed time: %f s' % (stop - start)
return clf
def syntetic_test():
# test model on different train set size & on different train sets
results = np.zeros((18, 5))
full_labeled = np.array([2, 4, 10, 25, 100])
train_size = 400
for dataset in range(1, 19):
X, Y = load_syntetic(dataset)
for j, nfull in enumerate(full_labeled):
crf = EdgeCRF(n_states=10, n_features=10, n_edge_features=2,
inference_method='qpbo')
clf = OneSlackSSVM(crf, max_iter=10000, C=0.01, verbose=0,
tol=0.1, n_jobs=4, inference_cache=100)
x_train = X[:nfull]
y_train = Y[:nfull]
x_test = X[(train_size + 1):]
y_test = Y[(train_size + 1):]
try:
clf.fit(x_train, y_train)
y_pred = clf.predict(x_test)
results[dataset - 1, j] = compute_error(y_test, y_pred)
print('dataset=%d, nfull=%d, error=%f' % (dataset, nfull,
results[dataset - 1, j]))
except ValueError:
print('dataset=%d, nfull=%d: Failed' % (dataset, nfull))
np.savetxt('results/syntetic/full_labeled.txt', results)
def CRF_pred(eeg1,
eeg2,
emg,
y,
eeg1test,
eeg2test,
emgtest,
C=0.9,
weight_shift=0,
max_iter=1000,
fs=128):
# For the ith iteration, select as trainin the sub_indices other than those at index i for train_index
eeg1_train = eeg1.values
eeg2_train = eeg2.values
emg_train = emg.values
y_train = y.values
# The test subject is the one at index i
eeg1_test = eeg1test.values
eeg2_test = eeg2test.values
emg_test = emgtest.values
# CRF Model Preprocessing
eeg1_ = process_EEG(eeg1_train)
eeg2_ = process_EEG(eeg2_train)
emg_ = process_EMG(emg_train)
xtrain_ = np.concatenate((eeg1_, eeg2_, emg_), axis=1)
ytrain_classes = np.reshape(y_train, (y_train.shape[0], ))
ytrain_ = y_train
eeg1_ = process_EEG(eeg1_test)
eeg2_ = process_EEG(eeg2_test)
emg_ = process_EMG(emg_test)
xtest_ = np.concatenate((eeg1_, eeg2_, emg_), axis=1)
xtrain_crf = np.reshape(
xtrain_,
(3, -1, xtrain_.shape[1])) # Reshape so that it works with CRF
ytrain_crf = np.reshape(ytrain_,
(3, -1)) - 1 # Reshape so that it works with CRF
# CRF Model fitting:
classes = np.unique(ytrain_)
weights_crf = compute_class_weight("balanced", list(classes),
list(ytrain_classes))
weights_crf[0] = weights_crf[0] + (2.5 * weight_shift)
weights_crf[1] = weights_crf[1] + (1.5 * weight_shift)
model = ChainCRF(class_weight=weights_crf)
ssvm = OneSlackSSVM(model=model, C=C, max_iter=max_iter)
ssvm.fit(xtrain_crf, ytrain_crf)
# Test on the third guy
xtest_crf = np.reshape(xtest_, (2, -1, xtest_.shape[1]))
y_pred_crf = ssvm.predict(xtest_crf)
y_pred_crf = np.asarray(y_pred_crf).reshape(-1) + 1
return y_pred_crf
def losocv_CRF_prepro(xtrain, y, C=0.5, weight_shift=0, max_iter=1000, fs=128):
"""Leave one subject out cross validation for the CRF model becasuse it requires
special datahandling. Input should be a Pandas Dataframe."""
epochs = 21600
num_sub = 3
# Indices of the subjects
sub_indices = [
np.arange(0, epochs),
np.arange(epochs, epochs * 2),
np.arange(epochs * 2, epochs * 3)
]
res = []
for i in range(len(sub_indices)):
# For the ith iteration, select as trainin the sub_indices other than those at index i for train_index
train_index = np.concatenate(
[sub_indices[(i + 1) % num_sub], sub_indices[(i + 2) % num_sub]])
xtrain_ = xtrain[train_index]
y_train = y.values[train_index]
ytrain_ = y_train
# The test subject is the one at index i
test_index = sub_indices[i]
xtest_ = xtrain[test_index]
y_test = y.values[test_index]
ytest_ = y_test
# CRF Model Preprocessing
ytrain_classes = np.reshape(y_train, (y_train.shape[0], ))
xtrain_crf = np.reshape(
xtrain_,
(2, -1, xtrain_.shape[1])) # Reshape so that it works with CRF
ytrain_crf = np.reshape(
ytrain_, (2, -1)) - 1 # Reshape so that it works with CRF
# CRF Model fitting:
classes = np.unique(ytrain_)
weights_crf = compute_class_weight("balanced", list(classes),
list(ytrain_classes))
weights_crf[0] = weights_crf[0] + (2.5 * weight_shift)
weights_crf[1] = weights_crf[1] + (1.5 * weight_shift)
model = ChainCRF(class_weight=weights_crf)
ssvm = OneSlackSSVM(model=model, C=C, max_iter=max_iter)
ssvm.fit(xtrain_crf, ytrain_crf)
# Test on the third guy
xtest_crf = np.reshape(xtest_, (1, -1, xtest_.shape[1]))
ytest_crf = np.reshape(ytest_, (1, -1)) - 1
y_pred_crf = ssvm.predict(xtest_crf)
y_pred_crf = np.asarray(y_pred_crf).reshape(-1) + 1
resy = sklearn.metrics.balanced_accuracy_score(ytest_, y_pred_crf)
print("Iteration, result:", i, resy)
res.append(resy)
return res
def test(nfiles):
X = []
Y = []
X_tst = []
Y_tst = []
ntrain = nfiles
ntest = 5*nfiles
print("Training/testing with %d/%d files." % (ntrain,ntest))
start = time.clock()
filename = '../maps/MAPS_AkPnCGdD_2/AkPnCGdD/MUS'
#filename = '../maps/MAPS_AkPnCGdD_1/AkPnCGdD/ISOL/NO'
files = dirs.get_files_with_extension(filename, '.mid')
train_files = files[:ntrain]
print("\t" + str(train_files))
#test_files = files[ntrain:ntest+ntrain]
# for legit testing
test_files = files[-ntest:]
map(per_file, train_files,
it.repeat(X, ntrain), it.repeat(Y, ntrain))
map(per_file, test_files,
it.repeat(X_tst, ntest), it.repeat(Y_tst, ntest))
end = time.clock()
print("\tRead time: %f" % (end - start))
print("\tnWindows train: " + str([X[i].shape[0] for i in range(len(X))]))
start = time.clock()
crf = ChainCRF(n_states=2)
clf = OneSlackSSVM(model=crf, C=100, n_jobs=-1,
inference_cache=100, tol=.1)
clf.fit(np.array(X), np.array(Y))
end = time.clock()
print("\tTrain time: %f" % (end - start))
start = time.clock()
Y_pred = clf.predict(X_tst)
comp = []
for i in range(len(Y_tst)):
for j in range(len(Y_tst[i])):
comp.append((Y_tst[i][j], Y_pred[i][j]))
print Y_tst[i][j],
print
for j in range(len(Y_tst[i])):
print Y_pred[i][j],
print
print
print("\tTrue positives: %d" % comp.count((1,1)))
print("\tTrue negatives: %d" % comp.count((0,0)))
print("\tFalse positives: %d" % comp.count((0,1)))
print("\tFalse negatives: %d" % comp.count((1,0)))
end = time.clock()
print("\tTest time: %f" % (end - start))
def model_test(k, head, tail):
"""
CRF训练和预测
"""
each_fold_time = time.time() #开始计时
#divide train set and test set
train_id = dataId[head:tail]
test_id = dataId[:head] + dataId[tail:]
X_train = X_arr[train_id, :]
Y_train = Y_arr[train_id]
X_test = X_arr[test_id, :]
Y_test = Y_arr[test_id]
campTest = Camp_arr[test_id]
#ends divide train set and test set
if len(X_train) > 0:
#实例化CRF
EFGCRF = EdgeFeatureGraphCRF(inference_method='qpbo',
class_weight=CLASS_WEIGHT)
if LEARNER == "OneSlackSSVM":
#利用OneSlackSSVM训练模型参数
ssvm = OneSlackSSVM(EFGCRF,
C=.1,
tol=.1,
max_iter=100,
switch_to='ad3')
elif LEARNER == "FrankWolfeSSVM":
#利用FrankWolfeSSVM训练模型参数
ssvm = FrankWolfeSSVM(EFGCRF, C=.1, tol=.1, max_iter=100)
else:
#没有选择分类器退出
pass
ssvm.fit(X_train, Y_train)
Y_pred = ssvm.predict(X_test)
df_result = statistic_result(Y_pred, Y_test, campTest)
V_precision = precision_score(df_result["label"], df_result["pred"])
V_recall = recall_score(df_result["label"], df_result["pred"])
V_f1 = f1_score(df_result["label"], df_result["pred"])
camps_pred, camps_lbl = statistic_campaign_result(Y_pred, Y_test)
C_precision = precision_score(camps_lbl, camps_pred)
C_recall = recall_score(camps_lbl, camps_pred)
C_f1 = f1_score(camps_lbl, camps_pred)
result_Queue.put(
[V_precision, V_recall, V_f1, C_precision, C_recall, C_f1])
else:
print("TRAIN SET is NULL")
print("the {}th fold using time: {:.4f} min".format(
k + 1, (time.time() - each_fold_time) / 60))
del X_train, Y_train, X_test, Y_test, Y_pred, campTest
def test_multinomial_blocks_one_slack():
#testing cutting plane ssvm on easy multinomial dataset
X, Y = generate_blocks_multinomial(n_samples=10, noise=0.5, seed=0)
n_labels = len(np.unique(Y))
crf = GridCRF(n_states=n_labels, inference_method=inference_method)
clf = OneSlackSSVM(model=crf, max_iter=150, C=1,
check_constraints=True, break_on_bad=True, tol=.1,
inference_cache=50)
clf.fit(X, Y)
Y_pred = clf.predict(X)
assert_array_equal(Y, Y_pred)
def test_one_slack_attractive_potentials():
# test that submodular SSVM can learn the block dataset
X, Y = generate_blocks(n_samples=10)
crf = GridCRF(inference_method=inference_method)
submodular_clf = OneSlackSSVM(
model=crf, max_iter=200, C=1, check_constraints=True, negativity_constraint=[5], inference_cache=50
)
submodular_clf.fit(X, Y)
Y_pred = submodular_clf.predict(X)
assert_array_equal(Y, Y_pred)
assert_true(submodular_clf.w[5] < 0)
def test_equal_class_weights():
# test that equal class weight is the same as no class weight
X, Y = make_blobs(n_samples=80, centers=3, random_state=42)
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 = OneSlackSSVM(pbl, C=10)
svm.fit(X_train, Y_train)
predict_no_class_weight = svm.predict(X_test)
pbl_class_weight = MultiClassClf(n_features=3, n_classes=3,
class_weight=np.ones(3))
svm_class_weight = OneSlackSSVM(pbl_class_weight, C=10)
svm_class_weight.fit(X_train, Y_train)
predict_class_weight = svm_class_weight.predict(X_test)
assert_array_equal(predict_no_class_weight, predict_class_weight)
assert_array_almost_equal(svm.w, svm_class_weight.w)
def test_class_weights():
X, Y = make_blobs(n_samples=210, centers=3, random_state=1, cluster_std=3,
shuffle=False)
X = np.hstack([X, np.ones((X.shape[0], 1))])
X, Y = X[:170], Y[:170]
pbl = MultiClassClf(n_features=3, n_classes=3)
svm = OneSlackSSVM(pbl, C=10)
svm.fit(X, Y)
weights = 1. / np.bincount(Y)
weights *= len(weights) / np.sum(weights)
pbl_class_weight = MultiClassClf(n_features=3, n_classes=3,
class_weight=weights)
svm_class_weight = OneSlackSSVM(pbl_class_weight, C=10)
svm_class_weight.fit(X, Y)
assert_greater(f1_score(Y, svm_class_weight.predict(X)),
f1_score(Y, svm.predict(X)))
def test_one_slack_attractive_potentials():
# test that submodular SSVM can learn the block dataset
X, Y = toy.generate_blocks(n_samples=10)
crf = GridCRF()
submodular_clf = OneSlackSSVM(model=crf, max_iter=200, C=100, verbose=1,
check_constraints=True,
positive_constraint=[5], n_jobs=-1)
submodular_clf.fit(X, Y)
Y_pred = submodular_clf.predict(X)
assert_array_equal(Y, Y_pred)
assert_true(submodular_clf.w[5] < 0) # don't ask me about signs
def test_multinomial_blocks_one_slack():
#testing cutting plane ssvm on easy multinomial dataset
X, Y = generate_blocks_multinomial(n_samples=10, noise=0.5, seed=0)
n_labels = len(np.unique(Y))
crf = GridCRF(n_states=n_labels, inference_method=inference_method)
clf = OneSlackSSVM(model=crf, max_iter=150, C=1,
check_constraints=True, break_on_bad=True, tol=.1,
inference_cache=50)
clf.fit(X, Y)
Y_pred = clf.predict(X)
assert_array_equal(Y, Y_pred)
def test_class_weights():
# test that equal class weight is the same as no class weight
X, Y = make_blobs(n_samples=210, centers=3, random_state=1, cluster_std=3,
shuffle=False)
X = np.hstack([X, np.ones((X.shape[0], 1))])
X, Y = X[:170], Y[:170]
pbl = CrammerSingerSVMModel(n_features=3, n_classes=3)
svm = OneSlackSSVM(pbl, verbose=10, C=10)
svm.fit(X, Y)
weights = 1. / np.bincount(Y)
weights *= len(weights) / np.sum(weights)
pbl_class_weight = CrammerSingerSVMModel(n_features=3, n_classes=3,
class_weight=weights)
svm_class_weight = OneSlackSSVM(pbl_class_weight, verbose=10, C=10)
svm_class_weight.fit(X, Y)
assert_greater(f1_score(Y, svm_class_weight.predict(X)),
f1_score(Y, svm.predict(X)))
def test_one_slack_repellent_potentials():
# test non-submodular problem with and without submodularity constraint
# dataset is checkerboard
X, Y = generate_checker()
crf = GridCRF(inference_method=inference_method)
clf = OneSlackSSVM(model=crf, max_iter=10, C=0.01, check_constraints=True)
clf.fit(X, Y)
Y_pred = clf.predict(X)
# standard crf can predict perfectly
assert_array_equal(Y, Y_pred)
submodular_clf = OneSlackSSVM(
model=crf, max_iter=10, C=0.01, check_constraints=True, negativity_constraint=[4, 5, 6]
)
submodular_clf.fit(X, Y)
Y_pred = submodular_clf.predict(X)
assert_less(submodular_clf.score(X, Y), 0.99)
# submodular crf can not do better than unaries
for i, x in enumerate(X):
y_pred_unaries = crf.inference(x, np.array([1, 0, 0, 1, 0, 0, 0]))
assert_array_equal(y_pred_unaries, Y_pred[i])
def test_equal_class_weights():
# test that equal class weight is the same as no class weight
X, Y = make_blobs(n_samples=80, centers=3, random_state=42)
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 = OneSlackSSVM(pbl, C=10)
svm.fit(X_train, Y_train)
predict_no_class_weight = svm.predict(X_test)
pbl_class_weight = MultiClassClf(n_features=3,
n_classes=3,
class_weight=np.ones(3))
svm_class_weight = OneSlackSSVM(pbl_class_weight, C=10)
svm_class_weight.fit(X_train, Y_train)
predict_class_weight = svm_class_weight.predict(X_test)
assert_array_equal(predict_no_class_weight, predict_class_weight)
assert_array_almost_equal(svm.w, svm_class_weight.w)
def test_one_slack_attractive_potentials():
# test that submodular SSVM can learn the block dataset
X, Y = generate_blocks(n_samples=10)
crf = GridCRF(inference_method=inference_method)
submodular_clf = OneSlackSSVM(model=crf, max_iter=200, C=1,
check_constraints=True,
negativity_constraint=[5],
inference_cache=50)
submodular_clf.fit(X, Y)
Y_pred = submodular_clf.predict(X)
assert_array_equal(Y, Y_pred)
assert_true(submodular_clf.w[5] < 0)
def test_multinomial_blocks_one_slack():
#testing cutting plane ssvm on easy multinomial dataset
X, Y = toy.generate_blocks_multinomial(n_samples=10, noise=0.3,
seed=0)
n_labels = len(np.unique(Y))
for inference_method in ['lp']:
crf = GridCRF(n_states=n_labels, inference_method=inference_method)
clf = OneSlackSSVM(problem=crf, max_iter=50, C=100, verbose=100,
check_constraints=True, break_on_bad=True)
clf.fit(X, Y)
Y_pred = clf.predict(X)
assert_array_equal(Y, Y_pred)
def test_blobs_2d_one_slack():
# 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 = OneSlackSSVM(pbl, check_constraints=True, C=1000)
svm.fit(X_train, Y_train)
assert_array_equal(Y_test, np.hstack(svm.predict(X_test)))
def test_one_slack_repellent_potentials():
# test non-submodular problem with and without submodularity constraint
# dataset is checkerboard
X, Y = generate_checker()
crf = GridCRF(inference_method=inference_method)
clf = OneSlackSSVM(model=crf, max_iter=10, C=.01,
check_constraints=True)
clf.fit(X, Y)
Y_pred = clf.predict(X)
# standard crf can predict perfectly
assert_array_equal(Y, Y_pred)
submodular_clf = OneSlackSSVM(model=crf, max_iter=10, C=.01,
check_constraints=True,
negativity_constraint=[4, 5, 6])
submodular_clf.fit(X, Y)
Y_pred = submodular_clf.predict(X)
assert_less(submodular_clf.score(X, Y), .99)
# submodular crf can not do better than unaries
for i, x in enumerate(X):
y_pred_unaries = crf.inference(x, np.array([1, 0, 0, 1, 0, 0, 0]))
assert_array_equal(y_pred_unaries, Y_pred[i])
def test_blobs_2d_one_slack():
# make two gaussian blobs
X, Y = make_blobs(n_samples=80, centers=2, random_state=1)
Y = 2 * Y - 1
# 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 = BinarySVMModel(n_features=3)
svm = OneSlackSSVM(pbl, verbose=30, C=1000)
svm.fit(X_train, Y_train)
assert_array_equal(Y_test, np.hstack(svm.predict(X_test)))
def test_one_slack_repellent_potentials():
# test non-submodular learning with and without positivity constraint
# dataset is checkerboard
X, Y = toy.generate_checker()
for inference_method in ["lp", "qpbo", "ad3"]:
crf = GridCRF(inference_method=inference_method)
clf = OneSlackSSVM(model=crf, max_iter=10, C=100, verbose=0,
check_constraints=True, n_jobs=-1)
clf.fit(X, Y)
Y_pred = clf.predict(X)
# standard crf can predict perfectly
assert_array_equal(Y, Y_pred)
submodular_clf = OneSlackSSVM(model=crf, max_iter=10, C=100,
verbose=0, check_constraints=True,
positive_constraint=[4, 5, 6], n_jobs=-1)
submodular_clf.fit(X, Y)
Y_pred = submodular_clf.predict(X)
# submodular crf can not do better than unaries
for i, x in enumerate(X):
y_pred_unaries = crf.inference(x, np.array([1, 0, 0, 1, 0, 0, 0]))
assert_array_equal(y_pred_unaries, Y_pred[i])
def test_blobs_2d_one_slack():
# 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 = OneSlackSSVM(pbl, check_constraints=True, C=1000)
svm.fit(X_train, Y_train)
assert_array_equal(Y_test, np.hstack(svm.predict(X_test)))
def test_class_weights():
X, Y = make_blobs(n_samples=210,
centers=3,
random_state=1,
cluster_std=3,
shuffle=False)
X = np.hstack([X, np.ones((X.shape[0], 1))])
X, Y = X[:170], Y[:170]
pbl = MultiClassClf(n_features=3, n_classes=3)
svm = OneSlackSSVM(pbl, C=10)
svm.fit(X, Y)
weights = 1. / np.bincount(Y)
weights *= len(weights) / np.sum(weights)
pbl_class_weight = MultiClassClf(n_features=3,
n_classes=3,
class_weight=weights)
svm_class_weight = OneSlackSSVM(pbl_class_weight, C=10)
svm_class_weight.fit(X, Y)
assert_greater(f1_score(Y, svm_class_weight.predict(X), average='macro'),
f1_score(Y, svm.predict(X), average='macro'))
def fit_crf(self):
for C in self.C_range:
print("Testing C value: {}".format(C))
model = EdgeFeatureGraphCRF(inference_method="ad3")
ssvm = OneSlackSSVM(model,
inference_cache=50,
C=C,
tol=self.tol,
max_iter=self.max_iter,
n_jobs=4,
verbose=False)
ssvm.fit(self.X_train, self.y_train)
predictions = [x for x in ssvm.predict(self.X_dev)]
self.evaluate_predictions(predictions, self.y_dev)
# Fit against the whole dataset except test
# Is this approach correct?
model = EdgeFeatureGraphCRF(inference_method="ad3")
ssvm = OneSlackSSVM(model,
inference_cache=50,
C=0.03,
tol=self.tol,
max_iter=self.max_iter,
n_jobs=4,
verbose=False)
X_train_dev = np.concatenate([self.X_train, self.X_dev])
y_train_dev = np.concatenate([self.y_train, self.y_dev])
ssvm.fit(X_train_dev, y_train_dev)
if self.eval_against_test:
predictions = [x for x in ssvm.predict(self.X_test)]
print("Test set evaluation")
self.evaluate_predictions(predictions, self.y_test)
self.model = ssvm
return ssvm
def test_standard_svm_blobs_2d():
# no edges, reduce to crammer-singer svm
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:]
X_train_graphs = [(x[np.newaxis, :], np.empty((0, 2), dtype=np.int)) for x in X_train]
X_test_graphs = [(x[np.newaxis, :], np.empty((0, 2), dtype=np.int)) for x in X_test]
pbl = GraphCRF(n_features=3, n_states=3)
svm = OneSlackSSVM(pbl, verbose=10, check_constraints=True, C=1000)
svm.fit(X_train_graphs, Y_train[:, np.newaxis])
assert_array_equal(Y_test, np.hstack(svm.predict(X_test_graphs)))
def msrc_test():
# test model on different train set sizes
basedir = '../data/msrc/trainmasks/'
models_basedir = 'models/msrc/'
quality = []
Xtest, Ytest = load_msrc('test')
Ytest = remove_areas(Ytest)
Xtrain, Ytrain = load_msrc('train')
Ytrain = remove_areas(Ytrain)
for n_train in [20, 40, 80, 160, 276]:
crf = EdgeCRF(n_states=24, n_features=2028, n_edge_features=4,
inference_method='gco')
clf = OneSlackSSVM(crf, max_iter=1000, C=0.01, verbose=0,
tol=0.1, n_jobs=4, inference_cache=100)
if n_train != 276:
train_mask = np.genfromtxt(basedir + 'trainMaskX%d.txt' % n_train)
train_mask = train_mask[:277].astype(np.bool)
else:
train_mask = np.ones(276).astype(np.bool)
curX = []
curY = []
for (s, x, y) in zip(train_mask, Xtrain, Ytrain):
if s:
curX.append(x)
curY.append(y)
start = time()
clf.fit(curX, curY)
stop = time()
np.savetxt(models_basedir + 'test_model_%d.csv' % n_train, clf.w)
with open(models_basedir + 'test_model_%d' % n_train + '.pickle', 'w') as f:
pickle.dump(clf, f)
Ypred = clf.predict(Xtest)
q = 1 - compute_error(Ytest, Ypred)
print('n_train=%d, quality=%f, time=%f' % (n_train, q, stop - start))
quality.append(q)
np.savetxt('results/msrc/msrc_full.txt', quality)
def msrc_test():
# test model on different train set sizes
basedir = '../data/msrc/trainmasks/'
models_basedir = 'models/msrc/'
quality = []
Xtest, Ytest = load_msrc('test')
Ytest = remove_areas(Ytest)
Xtrain, Ytrain = load_msrc('train')
Ytrain = remove_areas(Ytrain)
for n_train in [20, 40, 80, 160, 276]:
crf = EdgeCRF(n_states=24, n_features=2028, n_edge_features=4,
inference_method='gco')
clf = OneSlackSSVM(crf, max_iter=1000, C=0.01, verbose=0,
tol=0.1, n_jobs=4, inference_cache=100)
if n_train != 276:
train_mask = np.genfromtxt(basedir + 'trainMaskX%d.txt' % n_train)
train_mask = train_mask[:277].astype(np.bool)
else:
train_mask = np.ones(276).astype(np.bool)
curX = []
curY = []
for (s, x, y) in zip(train_mask, Xtrain, Ytrain):
if s:
curX.append(x)
curY.append(y)
start = time()
clf.fit(curX, curY)
stop = time()
np.savetxt(models_basedir + 'test_model_%d.csv' % n_train, clf.w)
with open(models_basedir + 'test_model_%d' % n_train + '.pickle', 'w') as f:
cPickle.dump(clf, f)
Ypred = clf.predict(Xtest)
q = 1 - compute_error(Ytest, Ypred)
print 'n_train=%d, quality=%f, time=%f' % (n_train, q, stop - start)
quality.append(q)
np.savetxt('results/msrc/msrc_full.txt', quality)
def conditional_random_fields(X, y):
"""
"""
X_ = [(np.atleast_2d(x), np.empty((0, 2), dtype=np.int)) for x in X]
Y = y.reshape(-1, 1)
X_train, X_test, y_train, y_test = train_test_split(X_, Y)
pbl = GraphCRF()
svm = OneSlackSSVM(pbl)
svm.fit(X_train, y_train)
y_pred = np.vstack(svm.predict(X_test))
print("Score with pystruct crf svm: %f "
% (np.mean(y_pred == y_test)))
print classification_report(y_test, y_pred)
plot_confusion_matrix(y_test, y_pred)
class PystructSequenceLearner(SequenceLearner):
def __init__(self):
# the model
self.model = ChainCRF(directed=True)
# the learner
self.learner = OneSlackSSVM(model=self.model,
C=.1,
inference_cache=50,
tol=0.1,
n_jobs=1)
# self.learner = StructuredPerceptron(model=self.model, average=True)
def fit(self, X, y):
# Train linear chain CRF
self.learner.fit(X, y)
def predict(self, X):
return self.learner.predict(X)
def test_standard_svm_blobs_2d():
# no edges, reduce to crammer-singer svm
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:]
X_train_graphs = [(x[np.newaxis, :], np.empty((0, 2), dtype=np.int))
for x in X_train]
X_test_graphs = [(x[np.newaxis, :], np.empty((0, 2), dtype=np.int))
for x in X_test]
pbl = GraphCRF(n_features=3, n_states=3, inference_method='unary')
svm = OneSlackSSVM(pbl, check_constraints=True, C=1000)
svm.fit(X_train_graphs, Y_train[:, np.newaxis])
assert_array_equal(Y_test, np.hstack(svm.predict(X_test_graphs)))
def test_one_slack_constraint_caching():
#testing cutting plane ssvm on easy multinomial dataset
X, Y = toy.generate_blocks_multinomial(n_samples=10, noise=0.5,
seed=0, size_x=9)
n_labels = len(np.unique(Y))
crf = GridCRF(n_states=n_labels)
clf = OneSlackSSVM(model=crf, max_iter=150, C=1,
check_constraints=True, break_on_bad=True,
inference_cache=50, inactive_window=0)
clf.fit(X, Y)
Y_pred = clf.predict(X)
assert_array_equal(Y, Y_pred)
assert_equal(len(clf.inference_cache_), len(X))
# there should be 21 constraints, which are less than the 94 iterations
# that are done
assert_equal(len(clf.inference_cache_[0]), 21)
# check that we didn't change the behavior of how we construct the cache
constraints_per_sample = [len(cache) for cache in clf.inference_cache_]
assert_equal(np.max(constraints_per_sample), 21)
assert_equal(np.min(constraints_per_sample), 21)
def test_one_slack_constraint_caching():
#testing cutting plane ssvm on easy multinomial dataset
X, Y = toy.generate_blocks_multinomial(n_samples=10, noise=0.3,
seed=0)
n_labels = len(np.unique(Y))
crf = GridCRF(n_states=n_labels, inference_method='lp')
clf = OneSlackSSVM(problem=crf, max_iter=50, C=100, verbose=100,
check_constraints=True, break_on_bad=True,
inference_cache=50)
clf.fit(X, Y)
Y_pred = clf.predict(X)
assert_array_equal(Y, Y_pred)
assert_equal(len(clf.inference_cache_), len(X))
# there should be 9 constraints, which are less than the 16 iterations
# that are done
assert_equal(len(clf.inference_cache_[0]), 9)
# check that we didn't change the behavior of how we construct the cache
constraints_per_sample = [len(cache) for cache in clf.inference_cache_]
assert_equal(np.max(constraints_per_sample), 10)
assert_equal(np.min(constraints_per_sample), 8)
def CRF_pred_prepro(xtrain,
y,
xtest,
C=0.9,
weight_shift=0,
max_iter=1000,
fs=128):
y_train = y.values
# CRF Model Preprocessing
xtrain_ = xtrain
ytrain_classes = np.reshape(y_train, (y_train.shape[0], ))
ytrain_ = y_train
xtest_ = xtest
xtrain_crf = np.reshape(
xtrain_,
(3, -1, xtrain_.shape[1])) # Reshape so that it works with CRF
ytrain_crf = np.reshape(ytrain_,
(3, -1)) - 1 # Reshape so that it works with CRF
# CRF Model fitting:
classes = np.unique(ytrain_)
weights_crf = compute_class_weight("balanced", list(classes),
list(ytrain_classes))
weights_crf[0] = weights_crf[0] + (2.5 * weight_shift)
weights_crf[1] = weights_crf[1] + (1.5 * weight_shift)
model = ChainCRF(class_weight=weights_crf)
ssvm = OneSlackSSVM(model=model, C=C, max_iter=max_iter)
ssvm.fit(xtrain_crf, ytrain_crf)
# Test on the third guy
xtest_crf = np.reshape(xtest_, (2, -1, xtest_.shape[1]))
y_pred_crf = ssvm.predict(xtest_crf)
y_pred_crf = np.asarray(y_pred_crf).reshape(-1) + 1
return y_pred_crf
fw_bc_svm = FrankWolfeSSVM(model, C=.1, max_iter=50)
fw_batch_svm = FrankWolfeSSVM(model, C=.1, max_iter=50, batch_mode=True)
# n-slack cutting plane ssvm
start = time()
n_slack_svm.fit(X_train_bias, y_train)
time_n_slack_svm = time() - start
y_pred = np.hstack(n_slack_svm.predict(X_test_bias))
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)
## string labels to label ids
label2id = {l:i for i,l in enumerate(set(y_train_flat))}
id2label = {l:i for i,l in label2id.items()}
y_train = [np.array([label2id[tok[2]] for tok in sentence])
for sentence in iob_train]
if args.oneslack:
### fit oneslack ssvm
crf = ChainCRF()
os_ssvm = OneSlackSSVM(crf, verbose=args.verbose, n_jobs=-1,
use_memmapping_pool=0,
show_loss_every=20,
tol=0.01, cache_tol=0.1)
os_ssvm.fit(list(X_train_tsvd), y_train)
test_os_ssvm_preds = [[id2label[i] for i in sent]
for sent in os_ssvm.predict(X_test_tsvd)]
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]
def main():
print("Please be patient. Will take 5-20 minutes.")
snakes = load_snakes()
X_train, Y_train = snakes['X_train'], snakes['Y_train']
X_train = [one_hot_colors(x) for x in X_train]
Y_train_flat = [y_.ravel() for y_ in Y_train]
X_train_directions, X_train_edge_features = prepare_data(X_train)
if 'ogm' in get_installed():
inference = ('ogm', {'alg': 'fm'})
else:
inference = 'qpbo'
# first, train on X with directions only:
crf = EdgeFeatureGraphCRF(inference_method=inference)
ssvm = OneSlackSSVM(crf,
inference_cache=50,
C=.1,
tol=.1,
max_iter=100,
n_jobs=1)
ssvm.fit(X_train_directions, Y_train_flat)
# Evaluate using confusion matrix.
# Clearly the middel of the snake is the hardest part.
X_test, Y_test = snakes['X_test'], snakes['Y_test']
X_test = [one_hot_colors(x) for x in X_test]
Y_test_flat = [y_.ravel() for y_ in Y_test]
X_test_directions, X_test_edge_features = prepare_data(X_test)
Y_pred = ssvm.predict(X_test_directions)
print("Results using only directional features for edges")
print("Test accuracy: %.3f" %
accuracy_score(np.hstack(Y_test_flat), np.hstack(Y_pred)))
print(confusion_matrix(np.hstack(Y_test_flat), np.hstack(Y_pred)))
# now, use more informative edge features:
crf = EdgeFeatureGraphCRF(inference_method=inference)
ssvm = OneSlackSSVM(crf,
inference_cache=50,
C=.1,
tol=.1,
switch_to='ad3',
n_jobs=1)
ssvm.fit(X_train_edge_features, Y_train_flat)
Y_pred2 = ssvm.predict(X_test_edge_features)
print("Results using also input features for edges")
print("Test accuracy: %.3f" %
accuracy_score(np.hstack(Y_test_flat), np.hstack(Y_pred2)))
print(confusion_matrix(np.hstack(Y_test_flat), np.hstack(Y_pred2)))
# plot stuff
fig, axes = plt.subplots(2, 2)
axes[0, 0].imshow(snakes['X_test'][0], interpolation='nearest')
axes[0, 0].set_title('Input')
y = Y_test[0].astype(np.int)
bg = 2 * (y != 0) # enhance contrast
axes[0, 1].matshow(y + bg, cmap=plt.cm.Greys)
axes[0, 1].set_title("Ground Truth")
axes[1, 0].matshow(Y_pred[0].reshape(y.shape) + bg, cmap=plt.cm.Greys)
axes[1, 0].set_title("Prediction w/o edge features")
axes[1, 1].matshow(Y_pred2[0].reshape(y.shape) + bg, cmap=plt.cm.Greys)
axes[1, 1].set_title("Prediction with edge features")
for a in axes.ravel():
a.set_xticks(())
a.set_yticks(())
plt.show()
from IPython.core.debugger import Tracer
Tracer()()
inference = ('ogm', {'alg': 'fm'})
else:
inference = 'qpbo'
# first, train on X with directions only:
crf = EdgeFeatureGraphCRF(inference_method=inference)
ssvm = OneSlackSSVM(crf, inference_cache=50, C=.1, tol=.1, max_iter=100,
n_jobs=1)
ssvm.fit(X_train_directions, Y_train_flat)
# Evaluate using confusion matrix.
# Clearly the middel of the snake is the hardest part.
X_test, Y_test = snakes['X_test'], snakes['Y_test']
X_test = [one_hot_colors(x) for x in X_test]
Y_test_flat = [y_.ravel() for y_ in Y_test]
X_test_directions, X_test_edge_features = prepare_data(X_test)
Y_pred = ssvm.predict(X_test_directions)
print("Results using only directional features for edges")
print("Test accuracy: %.3f"
% accuracy_score(np.hstack(Y_test_flat), np.hstack(Y_pred)))
print(confusion_matrix(np.hstack(Y_test_flat), np.hstack(Y_pred)))
# now, use more informative edge features:
crf = EdgeFeatureGraphCRF(inference_method=inference)
ssvm = OneSlackSSVM(crf, inference_cache=50, C=.1, tol=.1, switch_to='ad3',
n_jobs=1)
ssvm.fit(X_train_edge_features, Y_train_flat)
Y_pred2 = ssvm.predict(X_test_edge_features)
print("Results using also input features for edges")
print("Test accuracy: %.3f"
% accuracy_score(np.hstack(Y_test_flat), np.hstack(Y_pred2)))
print(confusion_matrix(np.hstack(Y_test_flat), np.hstack(Y_pred2)))
yeast = fetch_mldata("yeast")
X = yeast.data
X = np.hstack([X, np.ones((X.shape[0], 1))])
y = yeast.target.toarray().astype(np.int).T
X_train, X_test = X[:1500], X[1500:]
y_train, y_test = y[:1500], y[1500:]
else:
scene = load_scene()
X_train, X_test = scene['X_train'], scene['X_test']
y_train, y_test = scene['y_train'], scene['y_test']
n_labels = y_train.shape[1]
full = np.vstack([x for x in itertools.combinations(range(n_labels), 2)])
tree = chow_liu_tree(y_train)
#tree_model = MultiLabelClf(edges=tree, inference_method=('ogm', {'alg': 'dyn'}))
tree_model = MultiLabelClf(edges=tree, inference_method='max-product')
tree_ssvm = OneSlackSSVM(tree_model, inference_cache=50, C=.1, tol=0.01)
print("fitting tree model...")
tree_ssvm.fit(X_train, y_train)
print("Training loss tree model: %f"
% hamming_loss(y_train, np.vstack(tree_ssvm.predict(X_train))))
print("Test loss tree model: %f"
% hamming_loss(y_test, np.vstack(tree_ssvm.predict(X_test))))
for num in new_index_list:
new_array = Xtest_scaler[num[0]:num[1], :]
Xtest_scale.append(new_array)
Xtest_scale = np.array(Xtest_scale)
print Xtest_scale.shape
print 'Test set scaled'
ssvm.fit(Xtrain_scale, y_train)
print 'Model fit'
# Storing model weights for plot of transition probabilities
if type(transition_states) == str:
transition_states = ssvm.w[-49:].reshape(7, 7)
else:
transition_states = transition_states + ssvm.w[-49:].reshape(7, 7)
predicted = ssvm.predict(Xtest_scale)
print 'Predictions made'
# Metrics
fold_cm = confusion_matrix(np.hstack(y_test), np.hstack(predicted))
if type(total_confusion_matrix) == str:
total_confusion_matrix = fold_cm
else:
total_confusion_matrix = total_confusion_matrix + fold_cm
report = classification_report(np.hstack(y_test), np.hstack(predicted))
for line in report.split('\n'):
print line
print 'Metrics written'
# Code for plotting matrix depicting transition probabilities
# for the CRF model averaged across 10 folds of CV.
class SSVM:
"""Structured SVM wrapper"""
def __init__(self,
inference_train,
inference_pred,
dat_obj,
C=1.0,
share_params=True,
multi_label=True,
poi_info=None,
debug=False):
assert (C > 0)
self.C = C
self.inference_train = inference_train
self.inference_pred = inference_pred
self.share_params = share_params
self.multi_label = multi_label
self.dat_obj = dat_obj
self.debug = debug
self.trained = False
if poi_info is None:
self.poi_info = None
else:
self.poi_info = poi_info
self.scaler_node = MinMaxScaler(feature_range=(-1, 1), copy=False)
self.scaler_edge = MinMaxScaler(feature_range=(-1, 1), copy=False)
def train(self, trajid_list, n_jobs=4):
if self.poi_info is None:
self.poi_info = self.dat_obj.calc_poi_info(trajid_list)
# build POI_ID <--> POI__INDEX mapping for POIs used to train CRF
# which means only POIs in traj such that len(traj) >= 2 are included
poi_set = {
p
for tid in trajid_list for p in self.dat_obj.traj_dict[tid]
if len(self.dat_obj.traj_dict[tid]) >= 2
}
self.poi_list = sorted(poi_set)
self.poi_id_dict, self.poi_id_rdict = dict(), dict()
for idx, poi in enumerate(self.poi_list):
self.poi_id_dict[poi] = idx
self.poi_id_rdict[idx] = poi
# generate training data
train_traj_list = [
self.dat_obj.traj_dict[k] for k in trajid_list
if len(self.dat_obj.traj_dict[k]) >= 2
]
node_features_list = Parallel(n_jobs=n_jobs)(
delayed(calc_node_features)(tr[0], len(tr), self.poi_list,
self.poi_info, self.dat_obj)
for tr in train_traj_list)
edge_features = calc_edge_features(trajid_list, self.poi_list,
self.poi_info, self.dat_obj)
# feature scaling: node features
# should each example be flattened to one vector before scaling?
self.fdim_node = node_features_list[0].shape
X_node_all = np.vstack(node_features_list)
X_node_all = self.scaler_node.fit_transform(X_node_all)
X_node_all = X_node_all.reshape(-1, self.fdim_node[0],
self.fdim_node[1])
# feature scaling: edge features
fdim_edge = edge_features.shape
edge_features = self.scaler_edge.fit_transform(
edge_features.reshape(fdim_edge[0] * fdim_edge[1], -1))
self.edge_features = edge_features.reshape(fdim_edge)
assert (len(train_traj_list) == X_node_all.shape[0])
X_train = [(X_node_all[k, :, :], self.edge_features.copy(),
(self.poi_id_dict[train_traj_list[k][0]],
len(train_traj_list[k])))
for k in range(len(train_traj_list))]
y_train = [
np.array([self.poi_id_dict[k] for k in tr])
for tr in train_traj_list
]
assert (len(X_train) == len(y_train))
# train
sm = MyModel(inference_train=self.inference_train,
inference_pred=self.inference_pred,
share_params=self.share_params,
multi_label=self.multi_label)
if self.debug is True:
print('C:', self.C)
verbose = 1 if self.debug is True else 0
self.osssvm = OneSlackSSVM(model=sm,
C=self.C,
n_jobs=n_jobs,
verbose=verbose)
try:
self.osssvm.fit(X_train, y_train, initialize=True)
self.trained = True
print('SSVM training finished.')
# except ValueError:
except:
self.trained = False
sys.stderr.write('SSVM training FAILED.\n')
# raise
return self.trained
def predict(self, startPOI, nPOI):
assert (self.trained is True)
if startPOI not in self.poi_list:
return None
X_node_test = calc_node_features(startPOI, nPOI, self.poi_list,
self.poi_info, self.dat_obj)
# feature scaling
# should each example be flattened to one vector before scaling?
# X_node_test = X_node_test.reshape(1, -1) # flatten test example to a vector
X_node_test = self.scaler_node.transform(X_node_test)
# X_node_test = X_node_test.reshape(self.fdim)
X_test = [(X_node_test, self.edge_features,
(self.poi_id_dict[startPOI], nPOI))]
y_hat_list = self.osssvm.predict(X_test)[0]
# print(y_hat_list)
return [
np.array([self.poi_id_rdict[x] for x in y_hat])
for y_hat in y_hat_list
]
crf = EdgeFeatureGraphCRF(inference_method=inference)
ssvm = OneSlackSSVM(crf,
inference_cache=50,
C=.1,
tol=.1,
max_iter=100,
n_jobs=1)
ssvm.fit(X_train_directions, Y_train_flat)
# Evaluate using confusion matrix.
# Clearly the middel of the snake is the hardest part.
X_test, Y_test = snakes['X_test'], snakes['Y_test']
X_test = [one_hot_colors(x) for x in X_test]
Y_test_flat = [y_.ravel() for y_ in Y_test]
X_test_directions, X_test_edge_features = prepare_data(X_test)
Y_pred = ssvm.predict(X_test_directions)
print("Results using only directional features for edges")
print("Test accuracy: %.3f" %
accuracy_score(np.hstack(Y_test_flat), np.hstack(Y_pred)))
print(confusion_matrix(np.hstack(Y_test_flat), np.hstack(Y_pred)))
# now, use more informative edge features:
crf = EdgeFeatureGraphCRF(inference_method=inference)
ssvm = OneSlackSSVM(crf,
inference_cache=50,
C=.1,
tol=.1,
switch_to='ad3',
n_jobs=1)
ssvm.fit(X_train_edge_features, Y_train_flat)
Y_pred2 = ssvm.predict(X_test_edge_features)
#inference = 'qpbo'
#I'm interested in AD3 inference.
inference = 'ad3'
# first, train on X with directions only:
crf = EdgeFeatureGraphCRF(inference_method=inference)
ssvm = OneSlackSSVM(crf, inference_cache=50, C=.1, tol=.1, max_iter=100,
n_jobs=1)
t0 = time.time()
ssvm.fit(X_train_directions, Y_train_flat)
print("Model EdgeFeatureGraphCRF fitted. %.1fs"%(time.time()-t0))
Y_GT = np.hstack(Y_test_flat)
print("- Results using only directional features for edges. %.1fs"%(time.time()-t0))
t0 = time.time()
Y_pred = ssvm.predict(X_test_directions)
REPORT(Y_GT, Y_pred, time.time()-t0)
print "- Result with binarized graph"
t0 = time.time()
Y_pred = ssvm.predict(X_test_directions, [True]*len(X_test_directions))
REPORT(Y_GT, Y_pred, time.time()-t0)
#Predict under constraints
def buildConstraints(X, bOne=True):
"""
We iterate over each graph, and make sure that for each, we constrain to have a single instances of classes 1 to 9
(or atmost one)
The constraints must be a list of tuples like ( <operator>, <unaries>, <states>, <negated> )
print("val end export")
Xtrain = np.loadtxt(vfnumpypath + "Xtrain.txt")
Ytrain = np.loadtxt(vfnumpypath + "Ytrain.txt", dtype="int")
print("train end export")
#independent Model
independent_model = MultiLabelClf(inference_method='unary')
independent_ssvm = OneSlackSSVM(independent_model, C=.1, tol=0.01)
print("fitting independent model...")
independent_ssvm.fit(Xtrain, Ytrain)
#print np.vstack(independent_ssvm.predict(Xval))[1,:]
print("Test exact matching ratio: %f" % check_exactmatchratio(
Yval, np.vstack(independent_ssvm.predict(Xval)), datatotest))
print(
f1_score(Yval[3, :],
np.vstack(independent_ssvm.predict(Xtrain))[3, :],
average='macro'))
'''
print("Training loss independent model: %f"
% hamming_loss(Ytrain, np.vstack(independent_ssvm.predict(Xtrain))))
print("Test loss independent model: %f"
% hamming_loss(Yval, np.vstack(independent_ssvm.predict(Xval))))
print Yval.shape
print Yval[1,:]
'''
print("Training SSVM")
inference = 'qpbo'
# first, train on X with directions only:
crf = EdgeFeatureGraphCRF(inference_method=inference)
ssvm = OneSlackSSVM(crf,
inference_cache=50,
C=1.,
tol=.1,
max_iter=500,
n_jobs=4)
Y_flat = [y_.ravel() for y_ in Y]
Y_flat = np.asarray(
[Y_flat[i][j] for i in range(len(Y_flat)) for j in range(len(Y_flat[i]))])
ssvm.fit(X, Y)
Z_bin = ssvm.predict(X)
Z_flat = np.asarray(
[Z_bin[i][j] for i in range(len(Z_bin)) for j in range(len(Z_bin[i]))])
f1_score = metrics.f1_score(Y_flat, Z_flat, average='weighted')
conf_mat = metrics.confusion_matrix(Y_flat, Z_flat)
TPR = conf_mat[0][0] / (conf_mat[0][0] + conf_mat[0][1])
FPR = conf_mat[1][0] / (conf_mat[1][0] + conf_mat[1][1])
print('Results with classifier: ' + ssvm.__class__.__name__)
print('TPR/FPR = ' + str(TPR) + '/' + str(FPR))
print('F1-score = ' + str(f1_score))
my_classifier = ssvm
# Run prediction on the img_idx-th image
img_idx = 0
the_img = imgs[img_idx]
the_gt = gt_imgs[img_idx]
