def classifier_gmnpsvm_modular (train_fname=traindat,test_fname=testdat,label_fname=label_traindat,width=2.1,C=1,epsilon=1e-5): from modshogun import RealFeatures, MulticlassLabels from modshogun import GaussianKernel, GMNPSVM, CSVFile feats_train=RealFeatures(CSVFile(train_fname)) feats_test=RealFeatures(CSVFile(test_fname)) labels=MulticlassLabels(CSVFile(label_fname)) kernel=GaussianKernel(feats_train, feats_train, width) svm=GMNPSVM(C, kernel, labels) svm.set_epsilon(epsilon) svm.train(feats_train) out=svm.apply(feats_test).get_labels() return out,kernel
def evaluate4svm(labels, feats, params={'c': 1, 'kernal': 'gauss'}, Nsplit=2):
"""
Run Cross-validation to evaluate the SVM.
Parameters
----------
labels: 2d array
Data set labels.
feats: array
Data set feats.
params: dictionary
Search scope parameters.
Nsplit: int, default = 2
The n for n-fold cross validation.
"""
c = params.get('c')
if params.get('kernal' == 'gauss'):
kernal = GaussianKernel()
kernal.set_width(80)
elif params.get('kernal' == 'sigmoid'):
kernal = SigmoidKernel()
else:
kernal = LinearKernel()
split = CrossValidationSplitting(labels, Nsplit)
split.build_subsets()
accuracy = np.zeros(Nsplit)
time_test = np.zeros(accuracy.shape)
for i in range(Nsplit):
idx_train = split.generate_subset_inverse(i)
idx_test = split.generate_subset_indices(i)
feats.add_subset(idx_train)
labels.add_subset(idx_train)
print c, kernal, labels
svm = GMNPSVM(c, kernal, labels)
_ = svm.train(feats)
out = svm.apply(feats_test)
evaluator = MulticlassAccuracy()
accuracy[i] = evaluator.evaluate(out, labels_test)
feats.remove_subset()
labels.remove_subset()
feats.add_subset(idx_test)
labels.add_subset(idx_test)
t_start = time.clock()
time_test[i] = (time.clock() - t_start) / labels.get_num_labels()
feats.remove_subset()
labels.remove_subset()
return accuracy
def classifier_gmnpsvm_modular(train_fname=traindat,
test_fname=testdat,
label_fname=label_traindat,
width=2.1,
C=1,
epsilon=1e-5):
from modshogun import RealFeatures, MulticlassLabels
from modshogun import GaussianKernel, GMNPSVM, CSVFile
feats_train = RealFeatures(CSVFile(train_fname))
feats_test = RealFeatures(CSVFile(test_fname))
labels = MulticlassLabels(CSVFile(label_fname))
kernel = GaussianKernel(feats_train, feats_train, width)
svm = GMNPSVM(C, kernel, labels)
svm.set_epsilon(epsilon)
svm.train(feats_train)
out = svm.apply(feats_test).get_labels()
return out, kernel
class Ai:
def __init__(self):
self.x = None
self.y = None
self.x_test = None
self.y_test = None
self.svm = None
def load_train_data(self, x_fname, y_fname):
Ai.__init__(self)
self.x = np.loadtxt(x_fname)
self.y = np.loadtxt(y_fname) - 1.0
self.x_test = self.x
self.y_test = self.y
def _svm_new(self, kernel_width, c, epsilon):
if self.x == None or self.y == None:
raise Exception("No training data loaded.")
x = RealFeatures(self.x)
y = Labels(self.y)
self.svm = GMNPSVM(c, GaussianKernel(x, x, kernel_width), y)
self.svm.set_epsilon(epsilon)
def write_svm(self):
gz_stream = gz.open(com.TRAIN_SVM_FNAME_GZ, 'wb', 9)
pkl.dump(self.svm, gz_stream)
gz_stream.close()
def read_svm(self):
gz_stream = gz.open(com.TRAIN_SVM_FNAME_GZ, 'rb')
self.svm = pkl.load(gz_stream)
gz_stream.close()
def enable_validation(self, train_frac):
x = self.x
y = self.y
idx = np.arange(len(y))
np.random.shuffle(idx)
train_idx = idx[:np.floor(train_frac * len(y))]
test_idx = idx[np.ceil(train_frac * len(y)):]
self.x = x[:, train_idx]
self.y = y[train_idx]
self.x_test = x[:, test_idx]
self.y_test = y[test_idx]
def train(self, kernel_width, c, epsilon):
self._svm_new(kernel_width, c, epsilon)
x = RealFeatures(self.x)
self.svm.io.enable_progress()
self.svm.train(x)
self.svm.io.disable_progress()
def load_classifier(self):
self.read_svm()
def classify(self, matrix):
cl = self.svm.apply(
RealFeatures(
np.reshape(matrix, newshape=(com.FEATURE_DIM, 1),
order='F'))).get_label(0)
return int(cl + 1.0) % 10
def get_test_error(self):
self.svm.io.enable_progress()
l = self.svm.apply(RealFeatures(self.x_test)).get_labels()
self.svm.io.disable_progress()
return 1.0 - np.mean(l == self.y_test)
def serialization_complex_example (num=5, dist=1, dim=10, C=2.0, width=10):
import os
from numpy import concatenate, zeros, ones
from numpy.random import randn, seed
from modshogun import RealFeatures, MulticlassLabels
from modshogun import GMNPSVM
from modshogun import GaussianKernel
try:
from modshogun import SerializableHdf5File,SerializableAsciiFile, \
SerializableJsonFile,SerializableXmlFile,MSG_DEBUG
except ImportError:
return
from modshogun import NormOne, LogPlusOne
seed(17)
data=concatenate((randn(dim, num), randn(dim, num) + dist,
randn(dim, num) + 2*dist,
randn(dim, num) + 3*dist), axis=1)
lab=concatenate((zeros(num), ones(num), 2*ones(num), 3*ones(num)))
feats=RealFeatures(data)
#feats.io.set_loglevel(MSG_DEBUG)
#feats.io.enable_file_and_line()
kernel=GaussianKernel(feats, feats, width)
labels=MulticlassLabels(lab)
svm = GMNPSVM(C, kernel, labels)
feats.add_preprocessor(NormOne())
feats.add_preprocessor(LogPlusOne())
feats.set_preprocessed(1)
svm.train(feats)
bias_ref = svm.get_svm(0).get_bias()
#svm.print_serializable()
fstream = SerializableHdf5File("blaah.h5", "w")
status = svm.save_serializable(fstream)
check_status(status,'h5')
fstream = SerializableAsciiFile("blaah.asc", "w")
status = svm.save_serializable(fstream)
check_status(status,'asc')
fstream = SerializableJsonFile("blaah.json", "w")
status = svm.save_serializable(fstream)
check_status(status,'json')
fstream = SerializableXmlFile("blaah.xml", "w")
status = svm.save_serializable(fstream)
check_status(status,'xml')
fstream = SerializableHdf5File("blaah.h5", "r")
new_svm=GMNPSVM()
status = new_svm.load_serializable(fstream)
check_status(status,'h5')
new_svm.train()
bias_h5 = new_svm.get_svm(0).get_bias()
fstream = SerializableAsciiFile("blaah.asc", "r")
new_svm=GMNPSVM()
status = new_svm.load_serializable(fstream)
check_status(status,'asc')
new_svm.train()
bias_asc = new_svm.get_svm(0).get_bias()
fstream = SerializableJsonFile("blaah.json", "r")
new_svm=GMNPSVM()
status = new_svm.load_serializable(fstream)
check_status(status,'json')
new_svm.train()
bias_json = new_svm.get_svm(0).get_bias()
fstream = SerializableXmlFile("blaah.xml", "r")
new_svm=GMNPSVM()
status = new_svm.load_serializable(fstream)
check_status(status,'xml')
new_svm.train()
bias_xml = new_svm.get_svm(0).get_bias()
os.unlink("blaah.h5")
os.unlink("blaah.asc")
os.unlink("blaah.json")
os.unlink("blaah.xml")
return svm,new_svm, bias_ref, bias_h5, bias_asc, bias_json, bias_xml
class Ai:
def __init__(self):
self.x = None
self.y = None
self.x_test = None
self.y_test = None
self.svm = None
def load_train_data(self, x_fname, y_fname):
Ai.__init__(self)
self.x = np.loadtxt(x_fname)
self.y = np.loadtxt(y_fname) - 1.0
self.x_test = self.x
self.y_test = self.y
def _svm_new(self, kernel_width, c, epsilon):
if self.x == None or self.y == None:
raise Exception("No training data loaded.")
x = RealFeatures(self.x)
y = MulticlassLabels(self.y)
self.svm = GMNPSVM(c, GaussianKernel(x, x, kernel_width), y)
self.svm.set_epsilon(epsilon)
def write_svm(self):
gz_stream = gz.open(com.TRAIN_SVM_FNAME_GZ, 'wb', 9)
pkl.dump(self.svm, gz_stream)
gz_stream.close()
def read_svm(self):
gz_stream = gz.open(com.TRAIN_SVM_FNAME_GZ, 'rb')
self.svm = pkl.load(gz_stream)
gz_stream.close()
def enable_validation(self, train_frac):
x = self.x
y = self.y
idx = np.arange(len(y))
np.random.shuffle(idx)
train_idx=idx[:np.floor(train_frac*len(y))]
test_idx=idx[np.ceil(train_frac*len(y)):]
self.x = x[:,train_idx]
self.y = y[train_idx]
self.x_test = x[:,test_idx]
self.y_test = y[test_idx]
def train(self, kernel_width, c, epsilon):
self._svm_new(kernel_width, c, epsilon)
x = RealFeatures(self.x)
self.svm.io.enable_progress()
self.svm.train(x)
self.svm.io.disable_progress()
def load_classifier(self): self.read_svm()
def classify(self, matrix):
cl = self.svm.apply(
RealFeatures(
np.reshape(matrix, newshape=(com.FEATURE_DIM, 1),
order='F')
)
).get_label(0)
return int(cl + 1.0) % 10
def get_test_error(self):
self.svm.io.enable_progress()
l = self.svm.apply(RealFeatures(self.x_test)).get_labels()
self.svm.io.disable_progress()
return 1.0 - np.mean(l == self.y_test)