def __init__(self,y,x):
assert len(y) == len(x)
self.prob = prob = svmc.new_svm_problem()
self.size = size = len(y)
self.y_array = y_array = svmc.new_double(size)
for i in range(size):
svmc.double_setitem(y_array,i,y[i])
self.x_matrix = x_matrix = svmc.svm_node_matrix(size)
self.data = []
self.maxlen = 0;
for i in range(size):
data = _convert_to_svm_node_array(x[i])
self.data.append(data);
svmc.svm_node_matrix_set(x_matrix,i,data)
if type(x[i]) == dict:
if (len(x[i]) > 0):
self.maxlen = max(self.maxlen,max(x[i].keys()))
else:
self.maxlen = max(self.maxlen,len(x[i]))
svmc.svm_problem_l_set(prob,size)
svmc.svm_problem_y_set(prob,y_array)
svmc.svm_problem_x_set(prob,x_matrix)
def cross_validation(prob, param, fold):
if param.gamma == 0:
param.gamma = 1.0/prob.maxlen
dblarr = svmc.new_double(prob.size)
svmc.svm_cross_validation(prob.prob, param.param, fold, dblarr)
ret = _double_array_to_list(dblarr, prob.size)
svmc.delete_double(dblarr)
return ret
def _double_array(seq):
size = len(seq)
array = svmc.new_double(size)
i = 0
for item in seq:
svmc.double_setitem(array,i,item)
i = i + 1
return array
def predict_values_raw(self,x):
#convert x into svm_node, allocate a double array for return
n = self.nr_class*(self.nr_class-1)/2
data = _convert_to_svm_node_array(x)
dblarr = svmc.new_double(n)
svmc.svm_predict_values(self.model, data, dblarr)
ret = _double_array_to_list(dblarr, n)
svmc.delete_double(dblarr)
svmc.svm_node_array_destroy(data)
return ret
def predict_probability(self,x):
#c code will do nothing on wrong type, so we have to check ourself
if self.svm_type == NU_SVR or self.svm_type == EPSILON_SVR:
raise TypeError, "call get_svr_probability or get_svr_pdf for probability output of regression"
elif self.svm_type == ONE_CLASS:
raise TypeError, "probability not supported yet for one-class problem"
#only C_SVC,NU_SVC goes in
if not self.probability:
raise TypeError, "model does not support probabiliy estimates"
#convert x into svm_node, alloc a double array to receive probabilities
data = _convert_to_svm_node_array(x)
dblarr = svmc.new_double(self.nr_class)
pred = svmc.svm_predict_probability(self.model, data, dblarr)
pv = _double_array_to_list(dblarr, self.nr_class)
svmc.delete_double(dblarr)
svmc.svm_node_array_destroy(data)
p = {}
for i in range(len(self.labels)):
p[self.labels[i]] = pv[i]
return pred, p