def self_training2(X, y, X_unLabeled, param, th):
model = svmutil.svm_train(svmutil.svm_problem(x=X.tolist(), y=y.tolist()), param)
obj = model.get_objective_value()[0]
itr_num = 0
while True:
predicted_labels = np.array(svmutil.svm_predict(x=X_unLabeled.tolist(),
y=[1]*len(X_unLabeled),
m=model,
options="-q")[0])
model = svmutil.svm_train(svmutil.svm_problem(x=np.append(X, X_unLabeled, axis=0).tolist(),
y=np.append(y, predicted_labels).tolist()), param)
obj_new = model.get_objective_value()[0]
itr_num += 1
if abs(obj_new - obj) < th:
break
else:
obj = obj_new
y_unlabeled = ma.array(data=np.array(svmutil.svm_predict(x=X_unLabeled.tolist(),
y=[1]*len(X_unLabeled),
m=model,
options="-q")[0]),
mask=[True]*len(X_unLabeled))
return model, y_unlabeled, obj_new, itr_num
def get_SVM_trained_classifer(self, training_datafile,
classifier_dumpfile):
# read all tweets and labels
tweet_items = common.get_filtered_training_data(training_datafile)
tweets = []
for (words, sentiment) in tweet_items:
words_filtered = [
e.lower() for e in words.split() if (common.is_ascii(e))
]
tweets.append((words_filtered, sentiment))
results = helper.get_SVM_feature_vector_and_labels(
self.feature_list, tweets)
self.feature_vectors = results['feature_vector']
self.labels = results['labels']
problem = svm_problem(self.labels, self.feature_vectors)
# '-q' option suppress console output
param = svm_parameter('-q')
param.kernel_type = LINEAR
# param.show()
classifier = svm_train(problem, param)
svm_save_model(classifier_dumpfile, classifier)
return classifier
def test_convert_nusvmc(self):
iris = load_iris()
X = iris.data[:, :2]
y = iris.target
y[y == 2] = 1
prob = svmutil.svm_problem(y, X.tolist())
param = svmutil.svm_parameter()
param.svm_type = NuSVC
param.kernel_type = svmutil.RBF
param.eps = 1
param.probability = 1
if noprint:
param.print_func = noprint
libsvm_model = svmutil.svm_train(prob, param)
node = convert(libsvm_model, "LibSvmNuSvmc",
[('input', FloatTensorType(shape=['None', 'None']))])
self.assertTrue(node is not None)
dump_data_and_model(
X[:5].astype(numpy.float32),
SkAPIClProba2(libsvm_model),
node,
basename="LibSvmNuSvmc-Dec2",
allow_failure=
"StrictVersion(onnxruntime.__version__) <= StrictVersion('0.1.3')")
def setUpClass(self):
"""
Set up the unit test by loading the dataset and training a model.
"""
if not _HAS_SKLEARN:
return
if not _HAS_LIBSVM:
return
scikit_data = load_boston()
prob = svmutil.svm_problem(
scikit_data["target"] > scikit_data["target"].mean(),
scikit_data["data"].tolist(),
)
param = svmutil.svm_parameter()
param.svm_type = svmutil.C_SVC
param.kernel_type = svmutil.LINEAR
param.eps = 1
libsvm_model = svmutil.svm_train(prob, param)
libsvm_spec = libsvm_converter.convert(
libsvm_model, scikit_data.feature_names, "target"
).get_spec()
# Save the data and the model
self.scikit_data = scikit_data
self.libsvm_spec = libsvm_spec
def test_multi_class_without_probability(self):
# Generate some random data.
# This unit test should not rely on scikit learn for test data.
x, y = [], []
for _ in range(50):
x.append(
[random.gauss(200, 30), random.gauss(-100, 22), random.gauss(100, 42)]
)
y.append(random.choice([1, 2, 10, 12]))
y[0], y[1], y[2], y[3] = 1, 2, 10, 12
column_names = ["x1", "x2", "x3"]
prob = svmutil.svm_problem(y, x)
df = pd.DataFrame(x, columns=column_names)
for param1 in self.non_kernel_parameters:
for param2 in self.kernel_parameters:
param_str = " ".join([self.base_param, param1, param2])
param = svmutil.svm_parameter(param_str)
model = svm_train(prob, param)
# Get predictions with probabilities as dictionaries
(df["prediction"], _, _) = svm_predict(y, x, model, " -q")
spec = libsvm.convert(model, column_names, "target")
metrics = evaluate_classifier(spec, df, verbose=False)
self.assertEqual(metrics["num_errors"], 0)
def setUpClass(self):
"""
Set up the unit test by loading the dataset and training a model.
"""
if not _HAS_LIBSVM:
# setUpClass is still called even if class is skipped.
return
# Generate some random data.
# This unit test should not rely on scikit learn for test data.
self.x, self.y = [], []
random.seed(42)
for _ in range(50):
self.x.append([random.gauss(200, 30), random.gauss(-100, 22)])
self.y.append(random.choice([1, 2]))
self.y[0] = 1 # Make sure 1 is always the first label it sees
self.y[1] = 2
self.column_names = ["x1", "x2"]
self.prob = svmutil.svm_problem(self.y, self.x)
param = svmutil.svm_parameter()
param.svm_type = svmutil.NU_SVC
param.kernel_type = svmutil.LINEAR
param.eps = 1
param.probability = 1
# Save the data and the model
self.libsvm_model = svmutil.svm_train(self.prob, param)
self.df = pd.DataFrame(self.x, columns=self.column_names)
def test_convert_svmc_raw(self):
iris = load_iris()
X = iris.data[:, :2]
y = iris.target
y[y == 2] = 1
prob = svmutil.svm_problem(y, X.tolist())
param = svmutil.svm_parameter()
param.svm_type = SVC
param.kernel_type = svmutil.RBF
param.eps = 1
param.probability = 0
if noprint:
param.print_func = noprint
libsvm_model = svmutil.svm_train(prob, param)
# known svm runtime dimension error in ONNX Runtime
node = convert(libsvm_model, "LibSvmSvmcRaw",
[('input', FloatTensorType(shape=['None', 'None']))])
self.assertTrue(node is not None)
dump_data_and_model(
X[:5].astype(numpy.float32),
SkAPICl(libsvm_model),
node,
basename="LibSvmSvmcRaw",
allow_failure=
"StrictVersion(onnxruntime.__version__) < StrictVersion('0.5.0')")
def test_convert_svmc_linear_raw_multi(self):
iris = load_iris()
X = iris.data[:, :2]
y = iris.target
y[-5:] = 3
prob = svmutil.svm_problem(y, X.tolist())
param = svmutil.svm_parameter()
param.svm_type = SVC
param.kernel_type = svmutil.LINEAR
param.eps = 1
param.probability = 0
if noprint:
param.print_func = noprint
libsvm_model = svmutil.svm_train(prob, param)
node = convert(libsvm_model, "LibSvmNuSvmcMultiRaw",
[('input', FloatTensorType(shape=['None', 2]))])
self.assertTrue(node is not None)
X2 = numpy.vstack([X[:2], X[60:62], X[110:112],
X[147:149]]) # 5x0, 5x1
dump_data_and_model(
X2.astype(numpy.float32),
SkAPICl(libsvm_model),
node,
basename="LibSvmSvmcRaw-Dec3",
verbose=False,
allow_failure=
"StrictVersion(onnxruntime.__version__) <= StrictVersion('0.1.3')")
def test_convert_svmc(self):
iris = load_iris()
X = iris.data[:, :2]
y = iris.target
y[y == 2] = 1
prob = svmutil.svm_problem(y, X.tolist())
param = svmutil.svm_parameter()
param.svm_type = SVC
param.kernel_type = svmutil.RBF
param.eps = 1
param.probability = 1
if noprint:
param.print_func = noprint
libsvm_model = svmutil.svm_train(prob, param)
node = convert(libsvm_model, "LibSvmSvmc",
[('input', FloatTensorType())])
self.assertTrue(node is not None)
dump_data_and_model(X[:5].astype(numpy.float32),
SkAPIClProba2(libsvm_model),
node,
basename="LibSvmSvmc-Dec2")
def generate_svm_model(rows, param, kmers=[1,2,3]):
y, x = libsvm_generate_matrix(rows, kmers, dense=True)
prob = svmutil.svm_problem(y, x)
# s = 3 -- epsilon-SVR
param_str = "-s 3 -b 1 -q " # epsilon-SVR, prob estimate true, quiet mode
param_str += " ".join(["-{} {}".format(k,v) for k,v in param.items()])
params = svmutil.svm_parameter(param_str)
model = svmutil.svm_train(prob, params)
return model
def _stop_training(self):
super(LibSVMClassifier, self)._stop_training()
self.normalizer = _LabelNormalizer(self.labels)
labels = self.normalizer.normalize(self.labels.tolist())
features = self.data
# Call svm training method.
prob = libsvmutil.svm_problem(labels, features.tolist())
# Train
self.model = libsvmutil.svm_train(prob, self.parameter)
def train(self, input_data_path, params="-t 0 -c 4 -b 1", is_eval=True):
with commons.PhaseLogger("LIBSVM.train.read_problem"):
Y, X = svmutil.svm_read_problem(input_data_path + "/Train.txt")
prob = svmutil.svm_problem(Y, X)
#Y, X = svmutil.svm_read_problem(input_data_path + "\\Train.txt")
self._params = svmutil.svm_parameter(params)
with commons.PhaseLogger("LIBSVM.train.svm_train"):
self._model = svmutil.svm_train(prob, self._params)
self._init = True
if is_eval is True:
p_labels, p_acc, p_vals = svmutil.svm_predict(Y, X, self._model)
acc, mse, _ = p_acc
logging.info("[%s]: train with Acc[%.4f] Mse[%.4f]" %
(self._get_class_name(), acc, mse))
def setUpClass(self):
"""
Set up the unit test by loading the dataset and training a model.
"""
if not _HAS_SKLEARN:
return
if not _HAS_LIBSVM:
return
scikit_data = load_boston()
prob = svmutil.svm_problem(scikit_data["target"],
scikit_data["data"].tolist())
param = svmutil.svm_parameter()
param.svm_type = svmutil.NU_SVR
param.kernel_type = svmutil.LINEAR
param.eps = 1
self.libsvm_model = svmutil.svm_train(prob, param)
def predict(tr_data_arr, tr_label_arr, pred_data_arr, pred_label_arr):
data_arr = data_format(tr_data_arr)
prob = svm_problem(tr_label_arr, data_arr)
# 以下参数c和g通过交叉验证得到
param = svm_parameter('-c 2048.0 -g 0.001953125')
svm_model = svm_train(prob, param)
pred_data_arr = data_format(pred_data_arr)
pred_data_len = len(pred_label_arr)
wrong = 0
for idx, data in enumerate(pred_data_arr):
p_label, p_acc, p_val = svm_predict(
[pred_label_arr[idx]], [data], svm_model)
if int(p_label[0]) != int(pred_label_arr[idx]):
wrong += 1
accuracy = (pred_data_len - wrong) * 100.0 / pred_data_len
return pred_data_len, wrong, accuracy
def process(training_file, test_file, check, draw):
# Load training data.
with open(training_file) as f:
class_1 = pickle.load(f)
class_2 = pickle.load(f)
labels = pickle.load(f)
# Convert data to lists for libsvm.
class_1 = map(list, class_1)
class_2 = map(list, class_2)
labels = list(labels)
samples = class_1 + class_2
problem = svmutil.svm_problem(labels, samples)
# Don't print to stdout, use radial basis functions.
param = svmutil.svm_parameter('-q -t 2')
model = svmutil.svm_train(problem, param)
# Load test data.
with open(test_file) as f:
class_1 = pickle.load(f)
class_2 = pickle.load(f)
labels = pickle.load(f)
class_1 = map(list, class_1)
class_2 = map(list, class_2)
labels = list(labels)
if check:
# Sadly, this prints to stdout too :-/
svmutil.svm_predict(labels, class_1 + class_2,
model) # Prints accuracy.
if draw:
def classify(x, y, model=model):
return array(
svmutil.svm_predict([0] * len(x), map(list, zip(x, y)),
model)[0])
imtools.plot_2d_boundary(
[-6, 6, -6, 6], [array(class_1), array(class_2)], classify,
[1, -1])
show()
def process(training_file, test_file, check, draw):
# Load training data.
with open(training_file) as f:
class_1 = pickle.load(f)
class_2 = pickle.load(f)
labels = pickle.load(f)
# Convert data to lists for libsvm.
class_1 = map(list, class_1)
class_2 = map(list, class_2)
labels = list(labels)
samples = class_1 + class_2
problem = svmutil.svm_problem(labels, samples)
# Don't print to stdout, use radial basis functions.
param = svmutil.svm_parameter('-q -t 2')
model = svmutil.svm_train(problem, param)
# Load test data.
with open(test_file) as f:
class_1 = pickle.load(f)
class_2 = pickle.load(f)
labels = pickle.load(f)
class_1 = map(list, class_1)
class_2 = map(list, class_2)
labels = list(labels)
if check:
# Sadly, this prints to stdout too :-/
svmutil.svm_predict(labels, class_1 + class_2, model) # Prints accuracy.
if draw:
def classify(x, y, model=model):
return array(svmutil.svm_predict([0] * len(x), map(list, zip(x, y)),
model)[0])
imtools.plot_2d_boundary(
[-6, 6, -6, 6], [array(class_1), array(class_2)], classify, [1, -1])
show()
def test_convert_svmr_linear(self):
iris = load_iris()
X = iris.data[:, :2]
y = iris.target
prob = svmutil.svm_problem(y, X.tolist())
param = svmutil.svm_parameter()
param.svm_type = SVR
param.kernel_type = svmutil.LINEAR
param.eps = 1
if noprint:
param.print_func = noprint
libsvm_model = svmutil.svm_train(prob, param)
node = convert(libsvm_model, "LibSvmSvmrLinear",
[('input', FloatTensorType())])
self.assertTrue(node is not None)
dump_data_and_model(X[:5].astype(numpy.float32),
SkAPIReg(libsvm_model),
node,
basename="LibSvmSvmrLinear-Dec3")
def run_kfold(param_dict, rows, numfold, kmers=[1,2,3]):
"""
Run k KFold
Args:
param_dict: dictionary mapping param string to its value
rows: input rows
numfold: k for cross validation
kmers: list of kmers, default [1,2,3]
Return:
dictionary of model performance (SCC, MSE) if benchmark is True, else
return predictions for each fold
"""
kf = KFold(numfold, shuffle=True)
splitted = kf.split(rows)
param_str = "-s 3 -b 1 -q " # epsilon-SVR, prob estimate true, quiet mode
param_str += " ".join(["-{} {}".format(k,v) for k,v in param_dict.items()])
params = svmutil.svm_parameter(param_str)
foldidx = 1
fold_results = []
for train_idx, test_idx in splitted:
train_list = [rows[i] for i in train_idx]
test_list = [rows[i] for i in test_idx]
y_train, x_train = libsvm_generate_matrix(train_list, kmers)
y_test, x_test = libsvm_generate_matrix(test_list, kmers)
train_prob = svmutil.svm_problem(y_train, x_train)
model = svmutil.svm_train(train_prob, params)
#svmutil.svm_save_model('model_name.model', m)
# y is only needed when we need the model performance
svmpred = svmutil.svm_predict(y_test, x_test, model, options="-q")
fold_results.append({"test":test_list, "svmpred":svmpred})
return fold_results
import os
from libsvm import svmutil
import ocr
OCR_PATH = '/Users/thakis/Downloads/data/sudoku_images/ocr_data/'
features, labels = ocr.load_ocr_data(os.path.join(OCR_PATH, 'training'))
test_features, test_labels = \
ocr.load_ocr_data(os.path.join(OCR_PATH, 'testing'))
features = map(list, features)
test_features = map(list, test_features)
problem = svmutil.svm_problem(labels, features)
param = svmutil.svm_parameter('-q -t 0')
model = svmutil.svm_train(problem, param)
print 'Training data fit:'
svmutil.svm_predict(labels, features, model)
print 'Testing data fit:'
svmutil.svm_predict(test_labels, test_features, model)
tic.k('start')
SUDOKU_PATH = '/Users/thakis/Downloads/data/sudoku_images/sudokus/'
imname = os.path.join(SUDOKU_PATH, 'sudoku18.jpg')
vername = os.path.join(SUDOKU_PATH, 'sudoku18.sud')
im = numpy.array(Image.open(imname).convert('L'))
x = sudoku.find_sudoku_edges(im, axis=0)
y = sudoku.find_sudoku_edges(im, axis=1)
tic.k('found edges')
# Extract cells, run OCR.
OCR_PATH = '/Users/thakis/Downloads/data/sudoku_images/ocr_data/'
features, labels = ocr.load_ocr_data(os.path.join(OCR_PATH, 'training'))
problem = svmutil.svm_problem(labels, map(list, features))
param = svmutil.svm_parameter('-q -t 0')
model = svmutil.svm_train(problem, param)
tic.k('built OCR model')
crops = []
for col in range(9):
for row in range(9):
crop = im[y[col]:y[col + 1], x[row]:x[row + 1]]
crops.append(ocr.compute_feature(crop))
tic.k('extracted cells')
res = svmutil.svm_predict(numpy.loadtxt(vername), map(list, crops), model)[0]
tic.k('recognized cells')
res = numpy.array(res).reshape(9, 9)
eigenfaces = pca.components_.reshape((n_components, h, w))
print("Projecting the input data on the eigenfaces orthonormal basis")
X_train_pca = pca.transform(X_train)
X_test_pca = pca.transform(X_test)
#
################################################################################
## Train a SVM classification model
#
print("Fitting the classifier to the training set")
param_grid = {'C': [1e3, 5e3, 1e4, 5e4, 1e5],
'gamma': [0.0001, 0.0005, 0.001, 0.005, 0.01, 0.1], }
prob = svm_problem(y_train,X_train_pca)
param = svm_parameter("-q")
param.kernel='rbf'
#param_grid = {'C': [1e3, 5e3, 1e4, 5e4, 1e5],
# 'gamma': [0.0001, 0.0005, 0.001, 0.005, 0.01, 0.1], }
param.C=32
param.gamma=0.0001
print("Pass")
#parameters = GridSearchCV( param_grid)
model= svm_train(prob,param)
#clf = clf.fit(X_train_pca, y_train)
#print("Best estimator found by grid search:")
#print(m.best_estimator_)
y_pred, pred_acc, pred_val = svm_predict(y_test,X_test_pca,model)
res = bc.classify(test_features)[0]
acc = numpy.sum(1.0 * (res == test_labels)) / len(test_labels)
print 'Bayes Accuracy:', acc
print_confusion(res, test_labels, classnames)
# FIXME: Bayes accuracy gets very bad if the input dimensions aren't reduced
# enough. Probably some float underflow due to things not using log
# probabilities?
# Test SVM.
features = map(list, features)
test_features = map(list, test_features)
str_int_map = {} # libSVM needs int labels.
for i, c in enumerate(classnames):
str_int_map[c], str_int_map[i] = i, c
def convert_labels(labels, str_int_map):
return [str_int_map[l] for l in labels]
problem = svmutil.svm_problem(convert_labels(labels, str_int_map), features)
# Use a linear kernel, radial basis functions have horrible results (~20% acc)
param = svmutil.svm_parameter('-q -t 0')
model = svmutil.svm_train(problem, param)
res = svmutil.svm_predict(
convert_labels(test_labels, str_int_map), test_features, model)[0]
res = convert_labels(res, str_int_map)
acc = numpy.sum(1.0 * (res == test_labels)) / len(test_labels)
print 'SVM Accuracy:', acc
print_confusion(res, test_labels, classnames)
acc = numpy.sum(1.0 * (res == test_labels)) / len(test_labels)
print 'Bayes Accuracy:', acc
print_confusion(res, test_labels, classnames)
# FIXME: Bayes accuracy gets very bad if the input dimensions aren't reduced
# enough. Probably some float underflow due to things not using log
# probabilities?
# Test SVM.
features = map(list, features)
test_features = map(list, test_features)
str_int_map = {} # libSVM needs int labels.
for i, c in enumerate(classnames):
str_int_map[c], str_int_map[i] = i, c
def convert_labels(labels, str_int_map):
return [str_int_map[l] for l in labels]
problem = svmutil.svm_problem(convert_labels(labels, str_int_map), features)
# Use a linear kernel, radial basis functions have horrible results (~20% acc)
param = svmutil.svm_parameter('-q -t 0')
model = svmutil.svm_train(problem, param)
res = svmutil.svm_predict(convert_labels(test_labels, str_int_map),
test_features, model)[0]
res = convert_labels(res, str_int_map)
acc = numpy.sum(1.0 * (res == test_labels)) / len(test_labels)
print 'SVM Accuracy:', acc
print_confusion(res, test_labels, classnames)
def train(y, x):
train_len = int(1.0 * len(y))
prob = svmutil.svm_problem(y[:train_len], x[:train_len])
param = svmutil.svm_parameter('-t 2 -c 4 -b 1 -e 1e-12')
m = svmutil.svm_train(prob, param)
return m
neg_loc = np.where(label < 0)
pos_x1 = x1[pos_loc]
pos_x2 = x2[pos_loc]
neg_x1 = x1[neg_loc]
neg_x2 = x2[neg_loc]
plt.plot(pos_x1, pos_x2, 'b^')
plt.plot(neg_x1, neg_x2, 'ro')
plt.xlim(0, 1)
plt.ylim(0, 1)
ax = plt.gca()
ax.set_aspect(1)
plt.show()
y = list(label)
x = svm_data_format(x1, x2)
prob = svm.svm_problem(y, x)
# param = svm.svm_parameter('-t 0 -c 1')
# param = svm.svm_parameter('-t 1 -d 2')
param = svm.svm_parameter('-t 2')
model = svm.svm_train(prob, param)
svm.svm_save_model('test.model', model)
# test
# y0 = [-1]
# x0 = [{1: 1, 2: 0}]
# p_label, p_acc, p_val = svm.svm_predict(y0, x0, model)
# print('p_label = ', p_label)
# print('p_acc = ', p_acc)
# print('p_val = ', p_val)
import os
from libsvm import svmutil
import ocr
OCR_PATH = '/Users/thakis/Downloads/data/sudoku_images/ocr_data/'
features, labels = ocr.load_ocr_data(os.path.join(OCR_PATH, 'training'))
test_features, test_labels = \
ocr.load_ocr_data(os.path.join(OCR_PATH, 'testing'))
features = map(list, features)
test_features = map(list, test_features)
problem = svmutil.svm_problem(labels, features)
param = svmutil.svm_parameter('-q -t 0')
model = svmutil.svm_train(problem, param)
print 'Training data fit:'
svmutil.svm_predict(labels, features, model)
print 'Testing data fit:'
svmutil.svm_predict(test_labels, test_features, model)