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 ssvm_classifier() :
x_train,y_train,x_test,y_test = load_data1()
print "Data Loaded"
pca = PCA(n_components= 1000)
x_train_reduced = pca.fit_transform(x_train)
x_test_reduced = pca.fit_transform(x_test)
print "PCA finished"
print "Learning the model"
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)
independent_model = MultiLabelClf(inference_method='unary')
independent_ssvm = OneSlackSSVM(independent_model, C=.1, tol=0.01)
independent_ssvm.fit(x_train_reduced, y_train)
print "saving model ..."
with open("data/independent_ssvm.pkl","wb+") as f :
cp.dump(independent_ssvm,f)
#print "Calculatin the cross-validation scores"
#scores = model_selection.cross_val_score(independent_ssvm,x_train_reduced,y_train,cv=3)
print independent_ssvm.score(x_test_reduced,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 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 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 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 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_svm_as_crf_pickling():
iris = load_iris()
X, y = iris.data, iris.target
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, random_state=1)
_, file_name = mkstemp()
pbl = GraphCRF(n_features=4, n_states=3, inference_method="unary")
logger = SaveLogger(file_name)
svm = OneSlackSSVM(pbl, check_constraints=True, C=1, n_jobs=1, logger=logger)
svm.fit(X_train, y_train)
assert_less(0.97, svm.score(X_test, y_test))
assert_less(0.97, logger.load().score(X_test, y_test))
def test_svm_as_crf_pickling():
iris = load_iris()
X, y = iris.data, iris.target
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, random_state=1)
_, file_name = mkstemp()
pbl = GraphCRF(n_features=4, n_states=3, inference_method='unary')
logger = SaveLogger(file_name)
svm = OneSlackSSVM(pbl, check_constraints=True, C=1, n_jobs=1,
logger=logger)
svm.fit(X_train, y_train)
assert_less(.97, svm.score(X_test, y_test))
assert_less(.97, logger.load().score(X_test, y_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=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_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])
from sklearn.utils import shuffle
from pystruct.problems import CrammerSingerSVMProblem
#from pystruct.learners import SubgradientStructuredSVM
#from pystruct.learners import StructuredSVM
from pystruct.learners import OneSlackSSVM
mnist = fetch_mldata("MNIST original")
X, y = mnist.data, mnist.target
X = X / 255.
X_train, y_train = X[:60000], y[:60000]
X_test, y_test = X[60000:], y[60000:]
X_train, y_train = shuffle(X_train, y_train)
pblm = CrammerSingerSVMProblem(n_classes=10, n_features=28**2)
#svm = SubgradientStructuredSVM(pblm, verbose=10, n_jobs=1, plot=True,
#max_iter=10, batch=False, learning_rate=0.0001,
#momentum=0)
#svm = SubgradientStructuredSVM(pblm, verbose=10, n_jobs=1, plot=True,
#max_iter=2, batch=False, momentum=.9,
#learning_rate=0.001, show_loss='true', C=1000)
svm = OneSlackSSVM(pblm, verbose=2, n_jobs=1, plot=True, max_iter=2, C=1000)
#svm = StructuredSVM(pblm, verbose=50, n_jobs=1, plot=True, max_iter=10,
#C=1000)
svm.fit(X_train, y_train)
print(svm.score(X_train, y_train))
print(svm.score(X_test, y_test))
# [Note: if you get an error on the below line, it may be because you need to upgrade scikit-learn]
encoder = OneHotEncoder(n_values=[1, 2, 2, 201, 201],
sparse=False).fit(np.vstack(X))
# Represent features using one-of-K scheme: If a feature can take value in
X_encoded = [
encoder.transform(x) for x in X
] # {0,...,K}, then introduce K binary features such that the value of only
# the i^th binary feature is non-zero when the feature takes value 'i'.
# n_values specifies the number of states each feature can take.
X_small, y_small = X_encoded[:
100], y[:
100] # Pick the first 100 samples from the encoded training set.
# See: http://pystruct.github.io/generated/pystruct.learners.OneSlackSSVM.html
# See: http://pystruct.github.io/generated/pystruct.models.ChainCRF.html
# Rest of documentation can be found here: http://pystruct.github.io/references.html
ssvm = OneSlackSSVM(ChainCRF(n_states=10,
inference_method='max-product',
directed=True),
max_iter=200,
C=1)
# Construct a directed ChainCRF with 10 states for each variable,
# and pass this CRF to OneSlackSSVM constructor to create an object 'ssvm'
ssvm.fit(X_small, y_small) # Learn Structured SVM using X_small and y_small
weights = ssvm.w # Store learnt weights in 'weights'
print ssvm.score(X_small,
y_small) # Evaluate training accuracy on X_small, y_small
print ssvm.predict(
X_small) # Get predicted labels on X_small using the learnt model
"""
================================
Sequence classifcation benchmark
================================
This is a stripped-down version of the "plot_letters.py" example
targetted to benchmark inference and learning algorithms on chains.
"""
import numpy as np
from pystruct.datasets import load_letters
from pystruct.models import ChainCRF
from pystruct.learners import OneSlackSSVM
abc = "abcdefghijklmnopqrstuvwxyz"
letters = load_letters()
X, y, folds = letters['data'], letters['labels'], letters['folds']
# we convert the lists to object arrays, as that makes slicing much more
# convenient
X, y = np.array(X), np.array(y)
X_train, X_test = X[folds == 1], X[folds != 1]
y_train, y_test = y[folds == 1], y[folds != 1]
# Train linear chain CRF
model = ChainCRF()
ssvm = OneSlackSSVM(model=model, C=.1, tol=0.1, verbose=3, max_iter=20)
ssvm.fit(X_train, y_train)
print("Test score with chain CRF: %f" % ssvm.score(X_test, y_test))
sparse=False).fit(np.vstack(X))
# FROM SAMPLE #Represent features using one-of-K scheme: If a feature can take value in
X_encoded = [
encoder.transform(x) for x in X
] # FROM SAMPLE #{0,...,K}, then introduce K binary features such that the value of only
return X_encoded, y, sentences # FROM SAMPLE #the i^th binary feature is non-zero when the feature takes value 'i'.
X_train, Y_train, TrainSent = ReadData("train")
best_C = 0.1
crf = ChainCRF(n_states=10, inference_method="max-product", directed=True)
ssvm = OneSlackSSVM(crf, max_iter=200, C=best_C)
ssvm.fit(X_train[:4500], Y_train[:4500])
error = 1 - ssvm.score(X_train[-500:], Y_train[-500:])
tag = np.array([
'verb', 'noun', 'adjective', 'adverb', 'preposition', 'pronoun',
'determiner', 'number', 'punctuation', 'other'
])
cl = random.sample(range(10), 3)
print('Chosen classes: ', tag[cl])
trans_matrix = np.reshape(ssvm.w[-10 * 10:], (10, 10))
pairs = list(itertools.combinations(cl, 2))
for pair in pairs:
print(tag[pair[0]], "->", tag[pair[1]], trans_matrix[pair[0]][pair[1]])
print(tag[pair[1]], "->", tag[pair[0]], trans_matrix[pair[1]][pair[0]])
features = [
Y_train = Y_train[:4500]
crf = ChainCRF(n_states=10, inference_method='max-product', directed=True)
l1 = [10**i for i in range(-4, 3, 1)]
l1.extend([5 * l for l in l1])
Cs = sorted(l1)
error = {}
best_C = {}
Train_Sizes = [100, 200, 500, 1000, 4500]
for b in Train_Sizes:
score = {}
for C in Cs:
ssvm = OneSlackSSVM(crf, max_iter=200, C=C)
ssvm.fit(X_train[:b], Y_train[:b])
score[C] = ssvm.score(X_val, Y_val)
print('b = ', b, 'C = ', C, ' : ', score[C])
best_C[b] = max(score, key=score.get)
error['train', b] = 1. - score[best_C[b]]
for b in Train_Sizes:
ssvm = OneSlackSSVM(crf, max_iter=200, C=best_C[b])
ssvm.fit(X_train[:b], Y_train[:b])
error['test', b] = 1. - ssvm.score(X_test, Y_test)
plt.xlabel('Size of the training set')
plt.ylabel('Error')
plt.plot(Train_Sizes, [error['train', b] for b in Train_Sizes], label='train')
plt.plot(Train_Sizes, [error['test', b] for b in Train_Sizes], label='test')
plt.legend()
plt.show() #
X_train_bias = np.hstack([X_train, np.ones((X_train.shape[0], 1))])
X_test_bias = np.hstack([X_test, np.ones((X_test.shape[0], 1))])
# n-slack cutting plane ssvm
start = time()
n_slack_svm.fit(X_train_bias, y_train)
time_n_slack_svm = time() - start
acc_n_slack = n_slack_svm.score(X_test_bias, y_test)
print("Score with pystruct n-slack ssvm: %f (took %f seconds)"
% (acc_n_slack, 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
acc_one_slack = one_slack_svm.score(X_test_bias, y_test)
print("Score with pystruct 1-slack ssvm: %f (took %f seconds)"
% (acc_one_slack, time_one_slack_svm))
# online subgradient ssvm
start = time()
subgradient_svm.fit(X_train_bias, y_train)
time_subgradient_svm = time() - start
acc_subgradient = subgradient_svm.score(X_test_bias, y_test)
print("Score with pystruct subgradient ssvm: %f (took %f seconds)"
% (acc_subgradient, time_subgradient_svm))
libsvm = SVC(kernel='linear', C=10)
start = time()
libsvm.fit(X_train, y_train)
print('test index {}'.format(test_index))
print('{} jackets for training, {} for testing'. \
format(len(train_index), len(test_index)))
X_train = X[train_index]
Y_train = Y[train_index]
X_test = X[test_index]
Y_test = Y[test_index]
start = time.time()
""" YOUR S-SVM TRAINING CODE HERE """
ssvm.fit(X_train, Y_train)
end = time.time()
print('CRF learning of 1 fold has taken {} seconds'.format(
(end - start) / 1000.0))
scores_crf[fold] = ssvm.score(X_test, Y_test)
print(np.round(end - start), 'elapsed seconds to train the model')
print("Test score with chain CRF: %f" % scores_crf[fold])
""" Label the testing set and print results """
Y_pred = ssvm.predict(X_test)
wrong_fold_crf = np.sum(np.ravel(Y_test) - np.ravel(Y_pred) != 0)
wrong_segments_crf.append(wrong_fold_crf)
print('{} wrong segments out of {}'. \
format(wrong_fold_crf, len(test_index) * num_segments_per_jacket))
""" figure showing the result of classification of segments for
each jacket in the testing part of present fold """
if plot_labeling:
for ti, pred in zip(test_index, Y_pred):
print(ti)
print(pred)
s = segments[ti]
total_correct = 0
total = 0
precision = {0: [0, 0], 1: [0, 0], 2: [0, 0]}
recall = {0: [0, 0], 1: [0, 0], 2: [0, 0]}
for fold in range(5):
print 'fold ' + str(fold) + "--------------------------"
X = []
Y = []
for i in range(5):
if i == fold:
continue
X.extend(folds[i]['X'])
Y.extend(folds[i]['Y'])
print "Training Size: ", len(X), len(Y)
ssvm.fit(X, Y)
print 'Train Score: ' + str(ssvm.score(X, Y))
# w = Weight(ssvm.w, node_features, edge_features, dictLength)
fold_correct = 0
fold_total = 0
testX = folds[fold]['X']
testY = folds[fold]['Y']
for i in range(len(testX)):
print "Instance: " + str(i)
print folds[fold]['threads'][i].id
Yi = testY[i]
print list(Yi)
infY = crf.inference(testX[i], ssvm.w)
print list(infY)
for py in range(len(Yi)):
recall[Yi[py]][1] += 1
X_train_bias = np.hstack([X_train, np.ones((X_train.shape[0], 1))])
X_test_bias = np.hstack([X_test, np.ones((X_test.shape[0], 1))])
# n-slack cutting plane ssvm
start = time()
n_slack_svm.fit(X_train_bias, y_train)
time_n_slack_svm = time() - start
acc_n_slack = n_slack_svm.score(X_test_bias, y_test)
print("Score with pystruct n-slack ssvm: %f (took %f seconds)" %
(acc_n_slack, 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
acc_one_slack = one_slack_svm.score(X_test_bias, y_test)
print("Score with pystruct 1-slack ssvm: %f (took %f seconds)" %
(acc_one_slack, time_one_slack_svm))
# online subgradient ssvm
start = time()
subgradient_svm.fit(X_train_bias, y_train)
time_subgradient_svm = time() - start
acc_subgradient = subgradient_svm.score(X_test_bias, y_test)
print("Score with pystruct subgradient ssvm: %f (took %f seconds)" %
(acc_subgradient, time_subgradient_svm))
libsvm = SVC(kernel='linear', C=10)
start = time()
libsvm.fit(X_train, y_train)
from sklearn.utils import shuffle
from pystruct.problems import CrammerSingerSVMProblem
#from pystruct.learners import SubgradientStructuredSVM
#from pystruct.learners import StructuredSVM
from pystruct.learners import OneSlackSSVM
mnist = fetch_mldata("MNIST original")
X, y = mnist.data, mnist.target
X = X / 255.
X_train, y_train = X[:60000], y[:60000]
X_test, y_test = X[60000:], y[60000:]
X_train, y_train = shuffle(X_train, y_train)
pblm = CrammerSingerSVMProblem(n_classes=10, n_features=28 ** 2)
#svm = SubgradientStructuredSVM(pblm, verbose=10, n_jobs=1, plot=True,
#max_iter=10, batch=False, learning_rate=0.0001,
#momentum=0)
#svm = SubgradientStructuredSVM(pblm, verbose=10, n_jobs=1, plot=True,
#max_iter=2, batch=False, momentum=.9,
#learning_rate=0.001, show_loss='true', C=1000)
svm = OneSlackSSVM(pblm, verbose=2, n_jobs=1, plot=True, max_iter=2, C=1000)
#svm = StructuredSVM(pblm, verbose=50, n_jobs=1, plot=True, max_iter=10,
#C=1000)
svm.fit(X_train, y_train)
print(svm.score(X_train, y_train))
print(svm.score(X_test, y_test))
from pystruct.models import ChainCRF
from pystruct.learners import OneSlackSSVM
from util import data_generator
for shift in range(5, 7):
print(shift)
x_train, x_test, y_train, y_test = data_generator.baseline_crf(train_percentage=0.6, sft=shift, future=True)
crf = ChainCRF(n_states=2, n_features=x_train.shape[1])
x_train = x_train.values
x_test = x_test.values
y_train = y_train.values.astype(int)
y_test = y_test.values.astype(int)
ssvm = OneSlackSSVM(model=crf, C=.1, max_iter=10)
ssvm.fit([x_train], [y_train])
print(ssvm.score([x_test], [y_test]))
