def test_linear_classifier_weights_on(self, dataset):
# Test get_linear_svm_weights
classifier = self.LEARNER(dataset)
weights = get_linear_svm_weights(classifier, sum=True)
weights = get_linear_svm_weights(classifier, sum=False)
n_class = len(classifier.class_var.values)
def class_pairs(n_class):
for i in range(n_class - 1):
for j in range(i + 1, n_class):
yield i, j
l_map = classifier._get_libsvm_labels_map()
for inst in dataset[:20]:
dec_values = classifier.get_decision_values(inst)
for dec_v, weight, rho, pair in zip(dec_values, weights,
classifier.rho,
class_pairs(n_class)):
t_inst = Orange.data.Instance(classifier.domain, inst)
dec_v1 = example_weighted_sum(t_inst, weight) - rho
self.assertAlmostEqual(dec_v, dec_v1, 4)
def test_linear_regression_weights_on(self, dataset):
predictor = self.LEARNER(dataset)
weights = get_linear_svm_weights(predictor)
for inst in dataset[:20]:
t_inst = Orange.data.Instance(predictor.domain, inst)
prediction = predictor(inst)
w_sum = example_weighted_sum(t_inst, weights)
self.assertAlmostEqual(float(prediction), w_sum - predictor.rho[0], places=4)
def test_linear_regression_weights_on(self, dataset):
predictor = self.LEARNER(dataset)
weights = get_linear_svm_weights(predictor)
for inst in dataset[:20]:
t_inst = Orange.data.Instance(predictor.domain, inst)
prediction = predictor(inst)
w_sum = example_weighted_sum(t_inst, weights)
self.assertAlmostEqual(float(prediction),
w_sum - predictor.rho[0],
places=4)
def test_linear_classifier_weights_on(self, dataset):
# Test get_linear_svm_weights
classifier = self.LEARNER(dataset)
weights = get_linear_svm_weights(classifier, sum=True)
weights = get_linear_svm_weights(classifier, sum=False)
n_class = len(classifier.class_var.values)
def class_pairs(n_class):
for i in range(n_class - 1):
for j in range(i + 1, n_class):
yield i, j
l_map = classifier._get_libsvm_labels_map()
for inst in dataset[:20]:
dec_values = classifier.get_decision_values(inst)
for dec_v, weight, rho, pair in zip(dec_values, weights, classifier.rho, class_pairs(n_class)):
t_inst = Orange.data.Instance(classifier.domain, inst)
dec_v1 = example_weighted_sum(t_inst, weight) - rho
self.assertAlmostEqual(dec_v, dec_v1, 4)
def features_ranking_svm(self, name="ranking", random_state=64):
"""Get ranking of features by REF
random_state: Set seed in svm.SVMLearnerEasy, but it does not work.
"""
ranking_list = []
f_list = [col for col in self.features]
logging_per_run = list()
for i in range(self.n_features):
train_X = self.data_X[f_list]
train_y = self.data_y
if len(train_X.columns) == 0:
break
tuned_learner = svm.SVMLearnerEasy(folds=5,
kernel_type=svm.kernels.Linear,
svm_type=svm.SVMLearner.C_SVC,
random_state=random_state)
org_data_table = df2tb(train_X, train_y)
weights = svm.get_linear_svm_weights(tuned_learner(org_data_table),
sum=False)
internal_scores = defaultdict(float)
for w in weights:
magnitude = np.sqrt(
sum([w_attr**2 for attr, w_attr in w.items()]))
for attr, w_attr in w.items():
internal_scores["%s" % attr] += (w_attr / magnitude)**2
features_score = []
for i in internal_scores:
attr_name = i.split("Orange.feature.Continuous 'N_")[1].split(
"'")[0]
features_score.append((attr_name, internal_scores[i]))
features_score.sort(lambda a, b: cmp(a[1], b[1]))
# Results for low-score feature
logging_per_run.append(features_score)
ranking_list.append(features_score[0][0])
f_list.remove(features_score[0][0])
self.logging.append((name, logging_per_run))
return ranking_list
from Orange import data
from Orange.classification import svm
brown = data.Table("brown-selected")
classifier = svm.SVMLearner(brown,
kernel_type=svm.kernels.Linear,
normalization=False)
weights = svm.get_linear_svm_weights(classifier)
print sorted("%.10f" % w for w in weights.values())
import pylab as plt
plt.hist(weights.values())
