class Bagging(PoolGenerator):
def __init__(self,
base_classifier=None,
n_classifiers=100,
combination_rule='majority_vote'):
self.base_classifier = base_classifier
self.n_classifiers = n_classifiers
self.ensemble = None
self.combiner = Combiner(rule=combination_rule)
def fit(self, X, y):
self.ensemble = Ensemble()
for _ in range(self.n_classifiers):
# bootstrap
idx = np.random.choice(X.shape[0], X.shape[0], replace=True)
data, target = X[idx, :], y[idx]
classifier = sklearn.base.clone(self.base_classifier)
classifier.fit(data, target)
self.ensemble.add(classifier)
return
def predict(self, X):
out = self.ensemble.output(X)
return self.combiner.combine(out)
class RandomSubspace(PoolGenerator):
def __init__(self, base_classifier=None, n_classifiers=100, combination_rule='majority_vote', max_features=0.5):
self.base_classifier = base_classifier
self.n_classifiers = n_classifiers
self.combiner = Combiner(rule=combination_rule)
self.classifiers = None
self.ensemble = None
self.max_features = max_features
def fit(self, X, y):
self.ensemble = Ensemble()
for i in range(self.n_classifiers):
chosen_features = np.random.choice(X.shape[1], int(np.ceil(X.shape[1]*self.max_features)), replace=False)
transformer = FeatureSubsamplingTransformer(features=chosen_features)
classifier = BrewClassifier(classifier=sklearn.base.clone(self.base_classifier), transformer=transformer)
classifier.fit(X, y)
self.ensemble.add(classifier)
return
def predict(self, X):
out = self.ensemble.output(X)
return self.combiner.combine(out)
class Bagging(PoolGenerator):
def __init__(self, base_classifier=None, n_classifiers=100, combination_rule='majority_vote'):
self.base_classifier = base_classifier
self.n_classifiers = n_classifiers
self.ensemble = None
self.combiner = Combiner(rule=combination_rule)
def fit(self, X, y):
self.ensemble = Ensemble()
for _ in range(self.n_classifiers):
# bootstrap
idx = np.random.choice(X.shape[0], X.shape[0], replace=True)
data, target = X[idx, :], y[idx]
classifier = sklearn.base.clone(self.base_classifier)
classifier.fit(data, target)
self.ensemble.add(classifier)
return
def predict(self, X):
out = self.ensemble.output(X)
return self.combiner.combine(out)
class RandomSubspace(PoolGenerator):
def __init__(self,
base_classifier=None,
n_classifiers=100,
combination_rule='majority_vote',
max_features=0.5):
self.base_classifier = base_classifier
self.n_classifiers = n_classifiers
self.combiner = Combiner(rule=combination_rule)
self.classifiers = None
self.ensemble = None
self.max_features = max_features
def fit(self, X, y):
self.ensemble = Ensemble()
for i in range(self.n_classifiers):
chosen_features = np.random.choice(X.shape[1], int(
np.ceil(X.shape[1] * self.max_features)), replace=False)
transformer = FeatureSubsamplingTransformer(
features=chosen_features)
classifier = BrewClassifier(classifier=sklearn.base.clone(
self.base_classifier), transformer=transformer)
classifier.fit(X, y)
self.ensemble.add(classifier)
return
def predict(self, X):
out = self.ensemble.output(X)
return self.combiner.combine(out)
def test_len_with_one_added(self):
ens = Ensemble()
ens.add(MockClassifier())
assert len(ens) == 1
def test_add_empty_init(self):
ens = Ensemble()
c = MockClassifier()
ens.add(c)
assert ens.classifiers[0] is c
class ICSBagging(PoolGenerator):
def __init__(self, K=10, alpha=0.75, base_classifier=None, n_classifiers=100,
combination_rule='majority_vote', diversity_metric='e', max_samples=1.0,
positive_label=1):
self.K = K
self.alpha = alpha
self.base_classifier = base_classifier
self.n_classifiers = n_classifiers
self.combination_rule = combination_rule
self.positive_label = positive_label
self.classifiers = None
self.ensemble = None
self.combiner = Combiner(rule=combination_rule)
self.diversity_metric = diversity_metric
self.diversity = Diversity(metric=diversity_metric)
self.validation_X = None
self.validation_y = None
def set_validation(self, X, y):
self.validation_X = X
self.validation_y = y
def fitness(self, classifier):
'''
#TODO normalize diversity metric.
'''
self.ensemble.add(classifier)
out = self.ensemble.output(self.validation_X)
y_pred = self.combiner.combine(out)
y_true = self.validation_y
auc = evaluation.auc_score(y_true, y_pred)
div = self.diversity.calculate(self.ensemble,
self.validation_X, self.validation_y)
#diversity = entropy_measure_e(self.ensemble,
# self.validation_X, self.validation_y)
self.ensemble.classifiers.pop()
return self.alpha * auc + (1.0 - self.alpha) * div
def _calc_pos_prob(self):
y_pred = self.combiner.combine(self.ensemble.output(self.validation_X))
mask = self.positive_label == self.validation_y
pos_acc = float(sum(y_pred[mask] == self.validation_y[mask]))/len(self.validation_y[mask])
neg_acc = float(sum(y_pred[~mask] == self.validation_y[~mask]))/len(self.validation_y[~mask])
return 1.0 - (pos_acc / (pos_acc + neg_acc))
def bootstrap_classifiers(self, X, y, K, pos_prob):
mask = self.positive_label == y
negative_label = y[~mask][0]
clfs = []
sets_cX, sets_cy = [], []
for i in range(K):
cX, cy = [], []
for j in range(X.shape[0]):
if np.random.random() < pos_prob:
idx = np.random.random_integers(0, len(X[mask]) - 1)
cX = cX + [X[mask][idx]]
cy = cy + [self.positive_label]
else:
idx = np.random.random_integers(0, len(X[~mask]) - 1)
cX = cX + [X[~mask][idx]]
cy = cy + [negative_label]
if not self.positive_label in cy:
idx_1 = np.random.random_integers(0, len(cX) - 1)
idx_2 = np.random.random_integers(0, len(X[mask])- 1)
cX[idx_1] = X[mask][idx_2]
cy[idx_1] = self.positive_label
elif not negative_label in cy:
idx_1 = np.random.random_integers(0, len(cX) - 1)
idx_2 = np.random.random_integers(0, len(X[~mask])- 1)
cX[idx_1] = X[~mask][idx_2]
cy[idx_1] = negative_label
#print len(cX), len(cy), X.shape[0], len(X), np.bincount(cy)
sets_cX, sets_cy = sets_cX + [cX], sets_cy + [cy]
clf = sklearn.base.clone(self.base_classifier)
clfs = clfs + [clf.fit(cX, cy)]
return clfs
def fit(self, X, y):
#if self.validation_X == None and self.validation_y == None:
self.validation_X = X
self.validation_y = y
self.classes_ = set(y)
self.ensemble = Ensemble()
clfs = self.bootstrap_classifiers(X, y, self.K, 0.5)
self.ensemble.add(np.random.choice(clfs))
for i in range(1, self.n_classifiers):
clfs = self.bootstrap_classifiers(X, y, self.K, self._calc_pos_prob())
self.ensemble.add(max(clfs, key=lambda clf: self.fitness(clf)))
self.validation_X = None
self.validation_y = None
return self
def predict(self, X):
out = self.ensemble.output(X)
return self.combiner.combine(out)
class ICSBaggingNew(PoolGenerator):
def __init__(self, K=10, alpha=0.75, base_classifier=None, n_classifiers=100,
combination_rule='majority_vote', diversity_metric='e', max_samples=1.0,
positive_label=1):
self.K = K
self.alpha = alpha
self.base_classifier = base_classifier
self.n_classifiers = n_classifiers
self.positive_label = positive_label
self.ensemble = None
self.combiner = Combiner(rule=combination_rule)
self.diversity = Diversity(metric=diversity_metric)
self.validation_X = None
self.validation_y = None
def set_validation(self, X, y):
self.validation_X = X
self.validation_y = y
def fitness(self, classifier):
'''
#TODO normalize diversity metric.
'''
self.ensemble.add(classifier)
y_pred = self.predict(self.validation_X)
y_true = self.validation_y
auc = evaluation.auc_score(y_true, y_pred)
div = self.diversity.calculate(self.ensemble, self.validation_X, y_true)
self.ensemble.classifiers.pop() # create interface for this later
return self.alpha * auc + (1.0 - self.alpha) * div
def _calc_pos_prob(self):
y_pred = self.predict(self.validation_X)
y_true = self.validation_y
# obtaining recall scores for each label (assuming the labels are binary)
pos_acc = recall_score(y_true, y_pred, average='binary', pos_label=self.positive_label)
neg_acc = recall_score(y_true, y_pred, average='binary', pos_label=int(not self.positive_label))
return neg_acc / (pos_acc + neg_acc)
def bootstrap_classifiers(self, X, y, K, pos_prob):
pos_idx = (y == self.positive_label)
neg_idx = (y == int(not self.positive_label))
X_pos, y_pos = X[pos_idx,:], y[pos_idx] # positive examples
X_neg, y_neg = X[neg_idx,:], y[neg_idx] # negative examples
classifiers = []
for i in range(K):
X_new = np.zeros(X.shape)
y_new = np.zeros(y.shape)
for j in range(X.shape[0]):
if pos_prob > np.random.random():
# add a randomly chosen positive example
idx = np.random.randint(X_pos.shape[0])
X_new[j,:] = X_pos[idx,:]
y_new[j] = self.positive_label
else:
# add a randomly chosen negative example
idx = np.random.randint(X_neg.shape[0])
X_new[j,:] = X_neg[idx,:]
y_new[j] = int(not self.positive_label)
# if no positive example is present, make sure you insert at least one
if not np.any(y_new == self.positive_label):
idx_new = np.random.randint(X_new.shape[0]) # chosen spot for replacement on new array
idx_pos = np.random.randint(X_pos.shape[0]) # chosen positive example index
X_new[idx_new,:] = X_pos[idx_pos,:]
y_new[idx_new] = self.positive_label
# if no negative example is present, make sure you insert at least one
elif not np.any(y_new == int(not self.positive_label)):
idx_new = np.random.randint(X_new.shape[0]) # chosen spot for replacement on new array
idx_neg = np.random.randint(X_neg.shape[0]) # chosen positive example index
X_new[idx_new,:] = X_neg[idx_neg,:]
y_new[idx_new] = int(not self.positive_label)
# train classifier with the bootstrapped data
clf = sklearn.base.clone(self.base_classifier)
clf.fit(X_new, y_new)
classifiers.append(clf)
return classifiers
def fit(self, X, y):
#if self.validation_X == None and self.validation_y == None:
self.validation_X = X
self.validation_y = y
self.classes_ = set(y)
self.ensemble = Ensemble()
clfs = self.bootstrap_classifiers(X, y, self.K, 0.5)
self.ensemble.add(np.random.choice(clfs))
for i in range(1, self.n_classifiers):
clfs = self.bootstrap_classifiers(X, y, self.K, self._calc_pos_prob())
self.ensemble.add(max(clfs, key=lambda clf: self.fitness(clf)))
self.validation_X = None
self.validation_y = None
return self
def predict(self, X):
out = self.ensemble.output(X)
return self.combiner.combine(out)
def test_add_empty_init(self):
ens = Ensemble()
c = MockClassifier()
ens.add(c)
assert ens.classifiers[0] is c
def test_len_with_mult_added(self):
ens = Ensemble()
ens.add(MockClassifier())
ens.add(MockClassifier())
ens.add(MockClassifier())
assert len(ens) == 3
class SmoteBagging(PoolGenerator):
def __init__(self, base_classifier=None,
n_classifiers=100,
combination_rule='majority_vote', k=2):
#self.b = b
self.k = k
self.n_classifiers = n_classifiers
self.base_classifier = base_classifier
self.ensemble = None
self.combiner = Combiner(rule=combination_rule)
def smote_bootstrap_sample(self, X, y, b, k):
classes = np.unique(y)
count = np.bincount(y) # number of instances of each class
majority_class = count.argmax() # majority clas
majority_count = count.max() # majority class
data = np.empty((0, X.shape[1]))
target = np.empty((0,))
for i in classes:
class_data = X[(y==i),:]
if i == majority_class: # majority class
# regular bootstrap (i.e. 100% sampling rate)
idx = np.random.choice(majority_count, (majority_count,))
data = np.concatenate((data, class_data[idx,:]))
target = np.concatenate((target, i * np.ones((majority_count,))))
#print('original class data = {}'.format(class_data.shape))
#print('sampled class data = {}'.format(class_data[idx,:].shape))
#print()
else: # minority classes
# bootstrap the class data with defined sampling rate
sample_rate = (majority_count / class_data.shape[0]) * (b/100)
idx = np.random.choice(class_data.shape[0], (int(sample_rate * class_data.shape[0]),))
sampled_class_data = class_data[idx,:]
#print('original class data = {}'.format(class_data.shape))
#print('majority_count = {}'.format(majority_count))
#print('class data = {}'.format(class_data.shape))
#print('b = {}'.format(b))
#print('sample rate = {}'.format(sample_rate))
#print('sampled class data = {}'.format(sampled_class_data.shape))
# run smote on bootstrapped data to obtain synthetic samples
# ceil to make sure N_smote is a multiple of 100, and the small value to avoid a zero
N_smote = int( np.ceil((majority_count / sampled_class_data.shape[0]) * (1 - b/100 + 10e-8)) * 100 )
#print(N_smote)
#print('----------')
#print('smote parameters:')
#print('T : {}'.format(sampled_class_data.shape))
#print('N : {}'.format(N_smote))
synthetic = smote(sampled_class_data, N=N_smote, k=self.k)
#print('synthetic data = {})'.format(synthetic.shape))
#print(synthetic)
# add synthetic samples to sampled class data
n_missing = majority_count - sampled_class_data.shape[0]
idx = np.random.choice(synthetic.shape[0], (n_missing,))
new_class_data = np.concatenate((sampled_class_data, synthetic[idx,:]))
#print('new class data = {})'.format(new_class_data.shape))
#print()
data = np.concatenate((data, new_class_data))
target = np.concatenate((target, i * np.ones((new_class_data.shape[0],))))
return data, target
def fit(self, X, y):
self.ensemble = Ensemble()
# this parameter should change between [10, 100] with
# increments of 10, for every classifier in the ensemble
b = 10
for i in range(self.n_classifiers):
#print()
#print('classifier : {}'.format(i))
#print('------------------------')
#print('b = {}'.format(b))
data, target = self.smote_bootstrap_sample(X, y, b=b, k=self.k)
#print('data = {}'.format(data.shape))
#print()
classifier = sklearn.base.clone(self.base_classifier)
classifier.fit(data, target)
self.ensemble.add(classifier)
if b >= 100:
b = 10
else:
b += 10
return
def predict(self, X):
out = self.ensemble.output(X)
return self.combiner.combine(out)
class SmoteBaggingNew(SmoteBagging):
def fit(self, X, y):
self.ensemble = Ensemble()
# this parameter should change between [10, 100] with
# increments of 10, for every classifier in the ensemble
b = 10
for i in range(self.n_classifiers):
# print()
# print('classifier : {}'.format(i))
# print('------------------------')
# print('b = {}'.format(b))
data, target = self.smote_bootstrap_sample(
X, y, b=float(b), k=self.k)
# print('data = {}'.format(data.shape))
# print()
classifier = sklearn.base.clone(self.base_classifier)
classifier.fit(data, target)
self.ensemble.add(classifier)
if b >= 100:
b = 10
else:
b += 10
return
def smote_bootstrap_sample(self, X, y, b, k):
count = np.bincount(y) # number of instances of each class
majority_class = count.argmax() # majority class
majority_count = count.max() # majority class
data = np.empty((0, X.shape[1]))
target = np.empty((0,))
class_data = X[(y == majority_class), :]
idx = np.random.choice(majority_count, (majority_count,))
data = np.concatenate((data, class_data[idx, :]))
target = np.concatenate(
(target, majority_class * np.ones((majority_count,))))
minority_class = count.argmin()
minority_count = count.min()
# print majority_count
N_syn = int((majority_count) * (b / 100))
# print N_syn
N_res = majority_count - N_syn
# print N_res
N_syn, N_res = N_res, N_syn
class_data = X[(y == minority_class), :]
idx = np.random.choice(class_data.shape[0], (N_res,))
sampled_min_data = class_data[idx, :]
# print sampled_min_data.shape
if N_syn > 0:
N_smote = np.ceil(N_syn / minority_count) * 100
N_smote = 100 if N_smote < 100 else int(N_smote - N_smote % 100)
synthetic = smote(X[y == minority_class], N=int(N_smote), k=self.k)
idx = np.random.choice(synthetic.shape[0], (N_syn,))
new_class_data = np.concatenate(
(sampled_min_data, synthetic[idx, :]))
data = np.concatenate((data, new_class_data))
target = np.concatenate(
(target, minority_class * np.ones((new_class_data.shape[0],))))
else:
data = np.concatenate((data, sampled_min_data))
target = np.concatenate(
(target, minority_class * np.ones((sampled_min_data.shape[0],)))) # noqa
return data, target
class SmoteBagging(PoolGenerator):
def __init__(self,
base_classifier=None,
n_classifiers=100,
combination_rule='majority_vote',
k=5):
#self.b = b
self.k = k
self.n_classifiers = n_classifiers
self.base_classifier = base_classifier
self.ensemble = None
self.combiner = Combiner(rule=combination_rule)
def smote_bootstrap_sample(self, X, y, b, k):
classes = np.unique(y)
count = np.bincount(y) # number of instances of each class
majority_class = count.argmax() # majority clas
majority_count = count.max() # majority class
data = np.empty((0, X.shape[1]))
target = np.empty((0, ))
for i in classes:
class_data = X[(y == i), :]
if i == majority_class: # majority class
# regular bootstrap (i.e. 100% sampling rate)
idx = np.random.choice(majority_count, (majority_count, ))
data = np.concatenate((data, class_data[idx, :]))
target = np.concatenate((target, i * np.ones(
(majority_count, ))))
#print('original class data = {}'.format(class_data.shape))
#print('sampled class data = {}'.format(class_data[idx,:].shape))
#print()
else: # minority classes
# bootstrap the class data with defined sampling rate
sample_rate = (majority_count / class_data.shape[0]) * (b /
100)
idx = np.random.choice(
class_data.shape[0],
(int(sample_rate * class_data.shape[0]), ))
sampled_class_data = class_data[idx, :]
#print('original class data = {}'.format(class_data.shape))
#print('majority_count = {}'.format(majority_count))
#print('class data = {}'.format(class_data.shape))
#print('b = {}'.format(b))
#print('sample rate = {}'.format(sample_rate))
#print('sampled class data = {}'.format(sampled_class_data.shape))
# run smote on bootstrapped data to obtain synthetic samples
# ceil to make sure N_smote is a multiple of 100, and the small value to avoid a zero
N_smote = int(
np.ceil((majority_count / sampled_class_data.shape[0]) *
(1 - b / 100 + 10e-8)) * 100)
#print(N_smote)
#print('----------')
#print('smote parameters:')
#print('T : {}'.format(sampled_class_data.shape))
#print('N : {}'.format(N_smote))
synthetic = smote(sampled_class_data, N=N_smote, k=self.k)
#print('synthetic data = {})'.format(synthetic.shape))
#print(synthetic)
# add synthetic samples to sampled class data
n_missing = majority_count - sampled_class_data.shape[0]
idx = np.random.choice(synthetic.shape[0], (n_missing, ))
new_class_data = np.concatenate(
(sampled_class_data, synthetic[idx, :]))
#print('new class data = {})'.format(new_class_data.shape))
#print()
data = np.concatenate((data, new_class_data))
target = np.concatenate((target, i * np.ones(
(new_class_data.shape[0], ))))
return data, target
def fit(self, X, y):
self.ensemble = Ensemble()
# this parameter should change between [10, 100] with
# increments of 10, for every classifier in the ensemble
b = 10
for i in range(self.n_classifiers):
#print()
#print('classifier : {}'.format(i))
#print('------------------------')
#print('b = {}'.format(b))
data, target = self.smote_bootstrap_sample(X,
y,
b=float(b),
k=self.k)
#print('data = {}'.format(data.shape))
#print()
classifier = sklearn.base.clone(self.base_classifier)
classifier.fit(data, target)
self.ensemble.add(classifier)
if b >= 100:
b = 10
else:
b += 10
return
def predict(self, X):
out = self.ensemble.output(X)
return self.combiner.combine(out)
class SmoteBaggingNew(SmoteBagging):
def fit(self, X, y):
self.ensemble = Ensemble()
# this parameter should change between [10, 100] with
# increments of 10, for every classifier in the ensemble
b = 10
for i in range(self.n_classifiers):
#print()
#print('classifier : {}'.format(i))
#print('------------------------')
#print('b = {}'.format(b))
data, target = self.smote_bootstrap_sample(X,
y,
b=float(b),
k=self.k)
#print('data = {}'.format(data.shape))
#print()
classifier = sklearn.base.clone(self.base_classifier)
classifier.fit(data, target)
self.ensemble.add(classifier)
if b >= 100:
b = 10
else:
b += 10
return
def smote_bootstrap_sample(self, X, y, b, k):
classes = np.unique(y)
count = np.bincount(y) # number of instances of each class
majority_class = count.argmax() # majority class
majority_count = count.max() # majority class
data = np.empty((0, X.shape[1]))
target = np.empty((0, ))
class_data = X[(y == majority_class), :]
idx = np.random.choice(majority_count, (majority_count, ))
data = np.concatenate((data, class_data[idx, :]))
target = np.concatenate((target, majority_class * np.ones(
(majority_count, ))))
minority_class = count.argmin()
minority_count = count.min()
# print majority_count
N_syn = int((majority_count) * (b / 100))
# print N_syn
N_res = majority_count - N_syn
# print N_res
N_syn, N_res = N_res, N_syn
class_data = X[(y == minority_class), :]
idx = np.random.choice(class_data.shape[0], (N_res, ))
sampled_min_data = class_data[idx, :]
# print sampled_min_data.shape
if N_syn > 0:
N_smote = np.ceil(N_syn / minority_count) * 100
N_smote = 100 if N_smote < 100 else int(N_smote - N_smote % 100)
synthetic = smote(X[y == minority_class], N=int(N_smote), k=self.k)
idx = np.random.choice(synthetic.shape[0], (N_syn, ))
new_class_data = np.concatenate(
(sampled_min_data, synthetic[idx, :]))
data = np.concatenate((data, new_class_data))
target = np.concatenate((target, minority_class * np.ones(
(new_class_data.shape[0], ))))
else:
data = np.concatenate((data, sampled_min_data))
target = np.concatenate((target, minority_class * np.ones(
(sampled_min_data.shape[0], ))))
return data, target
class ICSBagging(PoolGenerator):
def __init__(self,
K=10,
alpha=0.75,
base_classifier=None,
n_classifiers=100,
combination_rule='majority_vote',
diversity_metric='e',
positive_label=1):
self.K = K
self.alpha = alpha
self.base_classifier = base_classifier
self.n_classifiers = n_classifiers
self.combination_rule = combination_rule
self.positive_label = positive_label
self.classifiers = None
self.ensemble = None
self.combiner = Combiner(rule=combination_rule)
self.diversity_metric = diversity_metric
self.diversity = Diversity(metric=diversity_metric)
self.validation_X = None
self.validation_y = None
def set_validation(self, X, y):
self.validation_X = X
self.validation_y = y
def fitness(self, classifier):
'''
#TODO normalize diversity metric.
'''
self.ensemble.add(classifier)
out = self.ensemble.output(self.validation_X)
y_pred = self.combiner.combine(out)
y_true = self.validation_y
auc = evaluation.auc_score(y_true, y_pred)
div = self.diversity.calculate(self.ensemble, self.validation_X,
self.validation_y)
#diversity = entropy_measure_e(self.ensemble,
# self.validation_X, self.validation_y)
self.ensemble.classifiers.pop()
return self.alpha * auc + (1.0 - self.alpha) * div
def _calc_pos_prob(self):
y_pred = self.combiner.combine(self.ensemble.output(self.validation_X))
mask = self.positive_label == self.validation_y
pos_acc = float(sum(y_pred[mask] == self.validation_y[mask])) / len(
self.validation_y[mask])
neg_acc = float(sum(y_pred[~mask] == self.validation_y[~mask])) / len(
self.validation_y[~mask])
return 1.0 - (pos_acc / (pos_acc + neg_acc))
def bootstrap_classifiers(self, X, y, K, pos_prob):
mask = self.positive_label == y
negative_label = y[~mask][0]
clfs = []
sets_cX, sets_cy = [], []
for i in range(K):
cX, cy = [], []
for j in range(X.shape[0]):
if np.random.random() < pos_prob:
idx = np.random.random_integers(0, len(X[mask]) - 1)
cX = cX + [X[mask][idx]]
cy = cy + [self.positive_label]
else:
idx = np.random.random_integers(0, len(X[~mask]) - 1)
cX = cX + [X[~mask][idx]]
cy = cy + [negative_label]
if not self.positive_label in cy:
idx_1 = np.random.random_integers(0, len(cX) - 1)
idx_2 = np.random.random_integers(0, len(X[mask]) - 1)
cX[idx_1] = X[mask][idx_2]
cy[idx_1] = self.positive_label
elif not negative_label in cy:
idx_1 = np.random.random_integers(0, len(cX) - 1)
idx_2 = np.random.random_integers(0, len(X[~mask]) - 1)
cX[idx_1] = X[~mask][idx_2]
cy[idx_1] = negative_label
#print len(cX), len(cy), X.shape[0], len(X), np.bincount(cy)
sets_cX, sets_cy = sets_cX + [cX], sets_cy + [cy]
clf = sklearn.base.clone(self.base_classifier)
clfs = clfs + [clf.fit(cX, cy)]
return clfs
def fit(self, X, y):
#if self.validation_X == None and self.validation_y == None:
self.validation_X = X
self.validation_y = y
self.classes_ = set(y)
self.ensemble = Ensemble()
clfs = self.bootstrap_classifiers(X, y, self.K, 0.5)
self.ensemble.add(np.random.choice(clfs))
for _ in range(1, self.n_classifiers):
clfs = self.bootstrap_classifiers(X, y, self.K,
self._calc_pos_prob())
self.ensemble.add(max(clfs, key=lambda clf: self.fitness(clf)))
self.validation_X = None
self.validation_y = None
return self
def predict(self, X):
out = self.ensemble.output(X)
return self.combiner.combine(out)
class ICSBaggingNew(PoolGenerator):
def __init__(self,
K=10,
alpha=0.75,
base_classifier=None,
n_classifiers=100,
combination_rule='majority_vote',
diversity_metric='e',
positive_label=1):
self.K = K
self.alpha = alpha
self.base_classifier = base_classifier
self.n_classifiers = n_classifiers
self.positive_label = positive_label
self.ensemble = None
self.combiner = Combiner(rule=combination_rule)
self.diversity = Diversity(metric=diversity_metric)
self.validation_X = None
self.validation_y = None
def set_validation(self, X, y):
self.validation_X = X
self.validation_y = y
def fitness(self, classifier):
'''
#TODO normalize diversity metric.
'''
self.ensemble.add(classifier)
y_pred = self.predict(self.validation_X)
y_true = self.validation_y
auc = evaluation.auc_score(y_true, y_pred)
div = self.diversity.calculate(self.ensemble, self.validation_X,
y_true)
self.ensemble.classifiers.pop() # create interface for this later
return self.alpha * auc + (1.0 - self.alpha) * div
def _calc_pos_prob(self):
y_pred = self.predict(self.validation_X)
y_true = self.validation_y
# obtaining recall scores for each label (assuming the labels are binary)
pos_acc = recall_score(y_true,
y_pred,
average='binary',
pos_label=self.positive_label)
neg_acc = recall_score(y_true,
y_pred,
average='binary',
pos_label=int(not self.positive_label))
return neg_acc / (pos_acc + neg_acc)
def bootstrap_classifiers(self, X, y, K, pos_prob):
pos_idx = (y == self.positive_label)
neg_idx = (y == int(not self.positive_label))
X_pos, y_pos = X[pos_idx, :], y[pos_idx] # positive examples
X_neg, y_neg = X[neg_idx, :], y[neg_idx] # negative examples
classifiers = []
for i in range(K):
X_new = np.zeros(X.shape)
y_new = np.zeros(y.shape)
for j in range(X.shape[0]):
if pos_prob > np.random.random():
# add a randomly chosen positive example
idx = np.random.randint(X_pos.shape[0])
X_new[j, :] = X_pos[idx, :]
y_new[j] = self.positive_label
else:
# add a randomly chosen negative example
idx = np.random.randint(X_neg.shape[0])
X_new[j, :] = X_neg[idx, :]
y_new[j] = int(not self.positive_label)
# if no positive example is present, make sure you insert at least one
if not np.any(y_new == self.positive_label):
idx_new = np.random.randint(
X_new.shape[0]) # chosen spot for replacement on new array
idx_pos = np.random.randint(
X_pos.shape[0]) # chosen positive example index
X_new[idx_new, :] = X_pos[idx_pos, :]
y_new[idx_new] = self.positive_label
# if no negative example is present, make sure you insert at least one
elif not np.any(y_new == int(not self.positive_label)):
idx_new = np.random.randint(
X_new.shape[0]) # chosen spot for replacement on new array
idx_neg = np.random.randint(
X_neg.shape[0]) # chosen positive example index
X_new[idx_new, :] = X_neg[idx_neg, :]
y_new[idx_new] = int(not self.positive_label)
# train classifier with the bootstrapped data
clf = sklearn.base.clone(self.base_classifier)
clf.fit(X_new, y_new)
classifiers.append(clf)
return classifiers
def fit(self, X, y):
#if self.validation_X == None and self.validation_y == None:
self.validation_X = X
self.validation_y = y
self.classes_ = set(y)
self.ensemble = Ensemble()
clfs = self.bootstrap_classifiers(X, y, self.K, 0.5)
self.ensemble.add(np.random.choice(clfs))
for i in range(1, self.n_classifiers):
clfs = self.bootstrap_classifiers(X, y, self.K,
self._calc_pos_prob())
self.ensemble.add(max(clfs, key=lambda clf: self.fitness(clf)))
self.validation_X = None
self.validation_y = None
return self
def predict(self, X):
out = self.ensemble.output(X)
return self.combiner.combine(out)