def train(data, path):
if os.path.exists(path):
print 'Model path exists, do nothing.'
return
print "Loading features."
integerizer = tools.integerization.CIntegerization()
labels = []
samples = []
for sent in io.getsent(data):
for index in range(len(sent)):
f = feature.extractFeatures(sent, index, integerizer)
x = int(sent[index][2])
assert x == 0 or x == 1
if x == 0: x = -1
labels.append(x)
samples.append(f)
print "Training SVM."
problem = svm.svm_problem(labels, samples)
param = svm.svm_parameter()
param.svm_type = svm.C_SVC
param.kernel_type = svm.LINEAR #
param.C = 1
#param.degree=2
param.eps = 1.0
param.probability = 1
param.cache_size = 1000
param.shrinking = 0
model = svmutil.svm_train(problem, param)
print "Saving model."
os.mkdir(path)
svmutil.svm_save_model(os.path.join(path, "scr"), model)
integerizer.write(os.path.join(path, "int"))
def demo1():
"""
Set of exercises to better understand workings of SVM
"""
pdb.set_trace()
prob = svm.svm_problem([1, -1], [[1, 0, 1], [-1, 0, -1]])
param = svm.svm_parameter()
mod = svm.svm_model(prob, param)
def train(self, features, labels):
labels,names = normaliselabels(labels)
if self.auto_weighting:
nlabels = labels.max() + 1
self.param.nr_weight = int(nlabels)
self.param.weight_label = range(nlabels)
self.param.weight = [(labels != i).mean() for i in xrange(nlabels)]
problem = libsvm.svm_problem(labels.astype(float), features)
model = libsvm.svm_model(problem, self.param)
return libsvmModel(model, names, self.output_probability)
def train(self, features, labels):
labels, names = normaliselabels(labels)
if self.auto_weighting:
nlabels = labels.max() + 1
self.param.nr_weight = int(nlabels)
self.param.weight_label = list(range(nlabels))
self.param.weight = [(labels != i).mean() for i in range(nlabels)]
problem = libsvm.svm_problem(labels.astype(float), features)
model = libsvm.svm_model(problem, self.param)
return libsvmModel(model, names, self.output_probability)
def train(self, labeled_featuresets):
"""
Trains the classifier on the specified training set. Multiple calls to
this method invalidates the previous ones.
The labeled_featuresets parameter must have the format [([feature], label)]
"""
self.__features_ids = {}
self.__last_feature_id = 0
self.__labels_ids = {}
self.__labels = []
y, x = self.__adapt_labeled_featuresets(labeled_featuresets)
prob = svm_problem(y, x)
param = svm_parameter('-c 1000 -q')
self.__model = svm_train(prob, param)
def train(self, labeled_featuresets):
"""
Trains the classifier on the specified training set. Multiple calls to
this method invalidates the previous ones.
The labeled_featuresets parameter must have the format [([feature], label)]
"""
self.__features_ids = {}
self.__last_feature_id = 0
self.__labels_ids = {}
self.__labels = []
y, x = self.__adapt_labeled_featuresets(labeled_featuresets)
prob = svm_problem(y, x)
param = svm_parameter('-c 1000 -q')
self.__model = svm_train(prob, param)
def train(data, path):
if os.path.exists(path):
print 'Model path exists, do nothing.'
return
print "Loading features."
integerizer = tools.integerization.CIntegerization()
labels = []
samples = []
for classid, feature in extractfeat.extractFeat(data, integerizer):
labels.append(classid)
samples.append(feature)
print "Training SVM."
problem = svm.svm_problem(labels, samples)
param = svm.svm_parameter()
param.kernel_type = svm.LINEAR#
param.C=1
#param.degree=2
param.eps=1
param.probability=1
model = svmutil.svm_train(problem, param)
print "Saving model."
os.mkdir(path)
svmutil.svm_save_model(os.path.join(path, "scr"), model)
integerizer.write(os.path.join(path, "int"))
def Training(self, kernel, target, data, IsKernel=False):
problem = svm.svm_problem(target, data, isKernel=IsKernel)
parameter = svm.svm_parameter(kernel)
model = svmutil.svm_train(problem, parameter)
return model
spamreader = csv.reader(csvfile, delimiter=' ', quotechar='|')
for row in spamreader:
label = float(row[0])
Y_test.append(label)
Y_test = np.array(Y_test)
Y_test -= 1
from libsvm.svm import svm_problem, svm_parameter, gen_svm_nodearray
from libsvm.svmutil import *
x = []
for row in X_train:
x.append(row)
y = Y_train
from svm import *
prob = svm_problem(y, x)
xtest = []
for row in X_test:
xtest.append(row)
ytest = Y_test
param = svm_parameter('-t ')
m = svm_train(prob, param) # m is a ctype pointer to an svm_model
p_label, p_acc, p_val = svm_predict(y, x, m)
p_label_test, p_acc_test, p_val_test = svm_predict(ytest, xtest, m)
def f(z):
cc, gamma = z
param = svm_parameter('-t 2 -g ' + str(gamma) + ' -c ' + str(cc))
