libsvm-python
heart_scale.py
from svmutil import *
d1='/home/barnix/cpp/tinycdb/svmlib.py/'
# Read data in LIBSVM format
y,x = svm_read_problem(d1+'heart_scale')
m = svm_train(y[:200], x[:200], '-c 4')
p_label, p_acc, p_val = svm_predict(y[200:], x[200:], m)
svm.py
#!/usr/bin/env python
from ctypes import *
from ctypes.util import find_library
import sys
# For unix the prefix 'lib' is not considered.
if find_library('svm'):
libsvm = CDLL(find_library('svm'))
elif find_library('libsvm'):
libsvm = CDLL(find_library('libsvm'))
else:
if sys.platform == 'win32':
libsvm = CDLL('../windows/libsvm.dll')
else:
libsvm = CDLL('/home/barnix/cpp/tinycdb/svmlib_so/bin/Debug/libsvmlib_so.so')
# Construct constants
SVM_TYPE = ['C_SVC', 'NU_SVC', 'ONE_CLASS', 'EPSILON_SVR', 'NU_SVR' ]
KERNEL_TYPE = ['LINEAR', 'POLY', 'RBF', 'SIGMOID', 'PRECOMPUTED']
for i, s in enumerate(SVM_TYPE): exec("%s = %d" % (s , i))
for i, s in enumerate(KERNEL_TYPE): exec("%s = %d" % (s , i))
PRINT_STRING_FUN = CFUNCTYPE(None, c_char_p)
def print_null(s):
return
def genFields(names, types):
return list(zip(names, types))
def fillprototype(f, restype, argtypes):
f.restype = restype
f.argtypes = argtypes
class svm_node(Structure):
_names = ["index", "value"]
_types = [c_int, c_double]
_fields_ = genFields(_names, _types)
def gen_svm_nodearray(xi, feature_max=None, issparse=None):
if isinstance(xi, dict):
index_range = xi.keys()
elif isinstance(xi, (list, tuple)):
index_range = range(len(xi))
else:
raise TypeError('xi should be a dictionary, list or tuple')
if feature_max:
assert(isinstance(feature_max, int))
index_range = filter(lambda j: j <= feature_max, index_range)
if issparse:
index_range = filter(lambda j:xi[j] != 0, index_range)
index_range = sorted(index_range)
ret = (svm_node * (len(index_range)+1))()
ret[-1].index = -1
for idx, j in enumerate(index_range):
ret[idx].index = j
ret[idx].value = xi[j]
max_idx = 0
if index_range:
max_idx = index_range[-1]
return ret, max_idx
class svm_problem(Structure):
_names = ["l", "y", "x"]
_types = [c_int, POINTER(c_double), POINTER(POINTER(svm_node))]
_fields_ = genFields(_names, _types)
def __init__(self, y, x):
if len(y) != len(x):
raise ValueError("len(y) != len(x)")
self.l = l = len(y)
max_idx = 0
x_space = self.x_space = []
for i, xi in enumerate(x):
tmp_xi, tmp_idx = gen_svm_nodearray(xi)
x_space += [tmp_xi]
max_idx = max(max_idx, tmp_idx)
self.n = max_idx
self.y = (c_double * l)()
for i, yi in enumerate(y): self.y[i] = yi
self.x = (POINTER(svm_node) * l)()
for i, xi in enumerate(self.x_space): self.x[i] = xi
class svm_parameter(Structure):
_names = ["svm_type", "kernel_type", "degree", "gamma", "coef0",
"cache_size", "eps", "C", "nr_weight", "weight_label", "weight",
"nu", "p", "shrinking", "probability"]
_types = [c_int, c_int, c_int, c_double, c_double,
c_double, c_double, c_double, c_int, POINTER(c_int), POINTER(c_double),
c_double, c_double, c_int, c_int]
_fields_ = genFields(_names, _types)
def __init__(self, options = None):
if options == None:
options = ''
self.parse_options(options)
def show(self):
attrs = svm_parameter._names + self.__dict__.keys()
values = map(lambda attr: getattr(self, attr), attrs)
for attr, val in zip(attrs, values):
print(' %s: %s' % (attr, val))
def set_to_default_values(self):
self.svm_type = C_SVC;
self.kernel_type = RBF
self.degree = 3
self.gamma = 0
self.coef0 = 0
self.nu = 0.5
self.cache_size = 100
self.C = 1
self.eps = 0.001
self.p = 0.1
self.shrinking = 1
self.probability = 0
self.nr_weight = 0
self.weight_label = (c_int*0)()
self.weight = (c_double*0)()
self.cross_validation = False
self.nr_fold = 0
self.print_func = None
def parse_options(self, options):
argv = options.split()
self.set_to_default_values()
self.print_func = cast(None, PRINT_STRING_FUN)
weight_label = []
weight = []
i = 0
while i < len(argv):
if argv[i] == "-s":
i = i + 1
self.svm_type = int(argv[i])
elif argv[i] == "-t":
i = i + 1
self.kernel_type = int(argv[i])
elif argv[i] == "-d":
i = i + 1
self.degree = int(argv[i])
elif argv[i] == "-g":
i = i + 1
self.gamma = float(argv[i])
elif argv[i] == "-r":
i = i + 1
self.coef0 = float(argv[i])
elif argv[i] == "-n":
i = i + 1
self.nu = float(argv[i])
elif argv[i] == "-m":
i = i + 1
self.cache_size = float(argv[i])
elif argv[i] == "-c":
i = i + 1
self.C = float(argv[i])
elif argv[i] == "-e":
i = i + 1
self.eps = float(argv[i])
elif argv[i] == "-p":
i = i + 1
self.p = float(argv[i])
elif argv[i] == "-h":
i = i + 1
self.shrinking = int(argv[i])
elif argv[i] == "-b":
i = i + 1
self.probability = int(argv[i])
elif argv[i] == "-q":
self.print_func = PRINT_STRING_FUN(print_null)
elif argv[i] == "-v":
i = i + 1
self.cross_validation = 1
self.nr_fold = int(argv[i])
if self.nr_fold < 2:
raise ValueError("n-fold cross validation: n must >= 2")
elif argv[i].startswith("-w"):
i = i + 1
self.nr_weight += 1
nr_weight = self.nr_weight
weight_label += [int(argv[i-1][2:])]
weight += [float(argv[i])]
else:
raise ValueError("Wrong options")
i += 1
libsvm.svm_set_print_string_function(self.print_func)
self.weight_label = (c_int*self.nr_weight)()
self.weight = (c_double*self.nr_weight)()
for i in range(self.nr_weight):
self.weight[i] = weight[i]
self.weight_label[i] = weight_label[i]
class svm_model(Structure):
def __init__(self):
self.__createfrom__ = 'python'
def __del__(self):
# free memory created by C to avoid memory leak
if hasattr(self, '__createfrom__') and self.__createfrom__ == 'C':
libsvm.svm_free_and_destroy_model(pointer(self))
def get_svm_type(self):
return libsvm.svm_get_svm_type(self)
def get_nr_class(self):
return libsvm.svm_get_nr_class(self)
def get_svr_probability(self):
return libsvm.svm_get_svr_probability(self)
def get_labels(self):
nr_class = self.get_nr_class()
labels = (c_int * nr_class)()
libsvm.svm_get_labels(self, labels)
return labels[:nr_class]
def is_probability_model(self):
return (libsvm.svm_check_probability_model(self) == 1)
def toPyModel(model_ptr):
"""
toPyModel(model_ptr) -> svm_model
Convert a ctypes POINTER(svm_model) to a Python svm_model
"""
if bool(model_ptr) == False:
raise ValueError("Null pointer")
m = model_ptr.contents
m.__createfrom__ = 'C'
return m
fillprototype(libsvm.svm_train, POINTER(svm_model), [POINTER(svm_problem), POINTER(svm_parameter)])
fillprototype(libsvm.svm_cross_validation, None, [POINTER(svm_problem), POINTER(svm_parameter), c_int, POINTER(c_double)])
fillprototype(libsvm.svm_save_model, c_int, [c_char_p, POINTER(svm_model)])
fillprototype(libsvm.svm_load_model, POINTER(svm_model), [c_char_p])
fillprototype(libsvm.svm_get_svm_type, c_int, [POINTER(svm_model)])
fillprototype(libsvm.svm_get_nr_class, c_int, [POINTER(svm_model)])
fillprototype(libsvm.svm_get_labels, None, [POINTER(svm_model), POINTER(c_int)])
fillprototype(libsvm.svm_get_svr_probability, c_double, [POINTER(svm_model)])
fillprototype(libsvm.svm_predict_values, c_double, [POINTER(svm_model), POINTER(svm_node), POINTER(c_double)])
fillprototype(libsvm.svm_predict, c_double, [POINTER(svm_model), POINTER(svm_node)])
fillprototype(libsvm.svm_predict_probability, c_double, [POINTER(svm_model), POINTER(svm_node), POINTER(c_double)])
fillprototype(libsvm.svm_free_model_content, None, [POINTER(svm_model)])
fillprototype(libsvm.svm_free_and_destroy_model, None, [POINTER(POINTER(svm_model))])
fillprototype(libsvm.svm_destroy_param, None, [POINTER(svm_parameter)])
fillprototype(libsvm.svm_check_parameter, c_char_p, [POINTER(svm_problem), POINTER(svm_parameter)])
fillprototype(libsvm.svm_check_probability_model, c_int, [POINTER(svm_model)])
fillprototype(libsvm.svm_set_print_string_function, None, [PRINT_STRING_FUN])
svmutil.py
#!/usr/bin/env python
from svm import *
def svm_read_problem(data_file_name):
"""
svm_read_problem(data_file_name) -> [y, x]
Read LIBSVM-format data from data_file_name and return labels y
and data instances x.
"""
prob_y = []
prob_x = []
for line in open(data_file_name):
line = line.split(None, 1)
# In case an instance with all zero features
if len(line) == 1: line += ['']
label, features = line
xi = {}
for e in features.split():
ind, val = e.split(":")
xi[int(ind)] = float(val)
prob_y += [float(label)]
prob_x += [xi]
return (prob_y, prob_x)
def svm_load_model(model_file_name):
"""
svm_load_model(model_file_name) -> model
Load a LIBSVM model from model_file_name and return.
"""
model = libsvm.svm_load_model(model_file_name)
if not model:
print("can't open model file %s" % model_file_name)
return None
model = toPyModel(model)
return model
def svm_save_model(model_file_name, model):
"""
svm_save_model(model_file_name, model) -> None
Save a LIBSVM model to the file model_file_name.
"""
libsvm.svm_save_model(model_file_name, model)
def evaluations(ty, pv):
"""
evaluations(ty, pv) -> (ACC, MSE, SCC)
Calculate accuracy, mean squared error and squared correlation coefficient
using the true values (ty) and predicted values (pv).
"""
if len(ty) != len(pv):
raise ValueError("len(ty) must equal to len(pv)")
total_correct = total_error = 0
sumv = sumy = sumvv = sumyy = sumvy = 0
for v, y in zip(pv, ty):
if y == v:
total_correct += 1
total_error += (v-y)*(v-y)
sumv += v
sumy += y
sumvv += v*v
sumyy += y*y
sumvy += v*y
l = len(ty)
ACC = 100.0*total_correct/l
MSE = total_error/l
try:
SCC = ((l*sumvy-sumv*sumy)*(l*sumvy-sumv*sumy))/((l*sumvv-sumv*sumv)*(l*sumyy-sumy*sumy))
except:
SCC = float('nan')
return (ACC, MSE, SCC)
def svm_train(arg1, arg2=None, arg3=None):
"""
svm_train(y, x [, 'options']) -> model | ACC | MSE
svm_train(prob, [, 'options']) -> model | ACC | MSE
svm_train(prob, param) -> model | ACC| MSE
Train an SVM model from data (y, x) or an svm_problem prob using
'options' or an svm_parameter param.
If '-v' is specified in 'options' (i.e., cross validation)
either accuracy (ACC) or mean-squared error (MSE) is returned.
'options':
-s svm_type : set type of SVM (default 0)
0 -- C-SVC
1 -- nu-SVC
2 -- one-class SVM
3 -- epsilon-SVR
4 -- nu-SVR
-t kernel_type : set type of kernel function (default 2)
0 -- linear: u'*v
1 -- polynomial: (gamma*u'*v + coef0)^degree
2 -- radial basis function: exp(-gamma*|u-v|^2)
3 -- sigmoid: tanh(gamma*u'*v + coef0)
4 -- precomputed kernel (kernel values in training_set_file)
-d degree : set degree in kernel function (default 3)
-g gamma : set gamma in kernel function (default 1/num_features)
-r coef0 : set coef0 in kernel function (default 0)
-c cost : set the parameter C of C-SVC, epsilon-SVR, and nu-SVR (default 1)
-n nu : set the parameter nu of nu-SVC, one-class SVM, and nu-SVR (default 0.5)
-p epsilon : set the epsilon in loss function of epsilon-SVR (default 0.1)
-m cachesize : set cache memory size in MB (default 100)
-e epsilon : set tolerance of termination criterion (default 0.001)
-h shrinking : whether to use the shrinking heuristics, 0 or 1 (default 1)
-b probability_estimates : whether to train a SVC or SVR model for probability estimates, 0 or 1 (default 0)
-wi weight : set the parameter C of class i to weight*C, for C-SVC (default 1)
-v n: n-fold cross validation mode
-q : quiet mode (no outputs)
"""
prob, param = None, None
if isinstance(arg1, (list, tuple)):
assert isinstance(arg2, (list, tuple))
y, x, options = arg1, arg2, arg3
prob = svm_problem(y, x)
param = svm_parameter(options)
elif isinstance(arg1, svm_problem):
prob = arg1
if isinstance(arg2, svm_parameter):
param = arg2
else:
param = svm_parameter(arg2)
if prob == None or param == None:
raise TypeError("Wrong types for the arguments")
if param.kernel_type == PRECOMPUTED:
for xi in prob.x_space:
idx, val = xi[0].index, xi[0].value
if xi[0].index != 0:
raise ValueError('Wrong input format: first column must be 0:sample_serial_number')
if val <= 0 or val > prob.n:
raise ValueError('Wrong input format: sample_serial_number out of range')
if param.gamma == 0 and prob.n > 0:
param.gamma = 1.0 / prob.n
libsvm.svm_set_print_string_function(param.print_func)
err_msg = libsvm.svm_check_parameter(prob, param)
if err_msg:
raise ValueError('Error: %s' % err_msg)
if param.cross_validation:
l, nr_fold = prob.l, param.nr_fold
target = (c_double * l)()
libsvm.svm_cross_validation(prob, param, nr_fold, target)
ACC, MSE, SCC = evaluations(prob.y[:l], target[:l])
if param.svm_type in [EPSILON_SVR, NU_SVR]:
print("Cross Validation Mean squared error = %g" % MSE)
print("Cross Validation Squared correlation coefficient = %g" % SCC)
return MSE
else:
print("Cross Validation Accuracy = %g%%" % ACC)
return ACC
else:
m = libsvm.svm_train(prob, param)
m = toPyModel(m)
# If prob is destroyed, data including SVs pointed by m can remain.
m.x_space = prob.x_space
return m
def svm_predict(y, x, m, options=""):
"""
svm_predict(y, x, m [, "options"]) -> (p_labels, p_acc, p_vals)
Predict data (y, x) with the SVM model m.
"options":
-b probability_estimates: whether to predict probability estimates,
0 or 1 (default 0); for one-class SVM only 0 is supported.
The return tuple contains
p_labels: a list of predicted labels
p_acc: a tuple including accuracy (for classification), mean-squared
error, and squared correlation coefficient (for regression).
p_vals: a list of decision values or probability estimates (if '-b 1'
is specified). If k is the number of classes, for decision values,
each element includes results of predicting k(k-1)/2 binary-class
SVMs. For probabilities, each element contains k values indicating
the probability that the testing instance is in each class.
Note that the order of classes here is the same as 'model.label'
field in the model structure.
"""
predict_probability = 0
argv = options.split()
i = 0
while i < len(argv):
if argv[i] == '-b':
i += 1
predict_probability = int(argv[i])
else:
raise ValueError("Wrong options")
i+=1
svm_type = m.get_svm_type()
is_prob_model = m.is_probability_model()
nr_class = m.get_nr_class()
pred_labels = []
pred_values = []
if predict_probability:
if not is_prob_model:
raise ValueError("Model does not support probabiliy estimates")
if svm_type in [NU_SVR, EPSILON_SVR]:
print("Prob. model for test data: target value = predicted value + z,\n"
"z: Laplace distribution e^(-|z|/sigma)/(2sigma),sigma=%g" % m.get_svr_probability());
nr_class = 0
prob_estimates = (c_double * nr_class)()
for xi in x:
xi, idx = gen_svm_nodearray(xi)
label = libsvm.svm_predict_probability(m, xi, prob_estimates)
values = prob_estimates[:nr_class]
pred_labels += [label]
pred_values += [values]
else:
if is_prob_model:
print("Model supports probability estimates, but disabled in predicton.")
if svm_type in (ONE_CLASS, EPSILON_SVR, NU_SVC):
nr_classifier = 1
else:
nr_classifier = nr_class*(nr_class-1)//2
dec_values = (c_double * nr_classifier)()
for xi in x:
xi, idx = gen_svm_nodearray(xi)
label = libsvm.svm_predict_values(m, xi, dec_values)
values = dec_values[:nr_classifier]
pred_labels += [label]
pred_values += [values]
ACC, MSE, SCC = evaluations(y, pred_labels)
l = len(y)
if svm_type in [EPSILON_SVR, NU_SVR]:
print("Mean squared error = %g (regression)" % MSE)
print("Squared correlation coefficient = %g (regression)" % SCC)
else:
print("Accuracy = %g%% (%d/%d) (classification)" % (ACC, int(l*ACC/100), l))
return pred_labels, (ACC, MSE, SCC), pred_values