def make_query(self):
dataset = self.dataset
unlabeled_entry_ids, unlabeled_pool = zip(
*dataset.get_unlabeled_entries())
labeled_pool, y = zip(*dataset.get_labeled_entries())
if len(np.unique(y)) > 2:
raise ValueError("HintSVM query strategy support binary class "
"active learning only. Found %s classes" % len(np.unique(y)))
hint_pool_idx = self.random_state_.choice(
len(unlabeled_pool), int(len(unlabeled_pool) * self.p))
hint_pool = np.array(unlabeled_pool)[hint_pool_idx]
weight = [1.0 for _ in range(len(labeled_pool))] +\
[(self.ch / self.cl) for _ in range(len(hint_pool))]
y = list(y) + [0 for _ in range(len(hint_pool))]
X = [x for x in labeled_pool] +\
[x for x in hint_pool]
p_val = hintsvm_query(
np.array(X, dtype=np.float64),
np.array(y, dtype=np.float64),
np.array(weight, dtype=np.float64),
np.array(unlabeled_pool, dtype=np.float64),
self.svm_params)
p_val = [abs(float(val[0])) for val in p_val]
idx = int(np.argmax(p_val))
return unlabeled_entry_ids[idx]
def retrieve_score_list(self):
dataset = self.dataset
unlabeled_entry_ids, unlabeled_pool = zip(
*dataset.get_unlabeled_entries())
labeled_pool, y = zip(*dataset.get_labeled_entries())
if len(np.unique(y)) > 2:
raise ValueError("HintSVM query strategy support binary class "
"active learning only. Found %s classes" %
len(np.unique(y)))
hint_pool_idx = self.random_state_.choice(
len(unlabeled_pool), int(len(unlabeled_pool) * self.p))
hint_pool = np.array(unlabeled_pool)[hint_pool_idx]
weight = [1.0 for _ in range(len(labeled_pool))] + \
[(self.ch / self.cl) for _ in range(len(hint_pool))]
if 0 in y:
assert -1 not in y, "we need to switch 0 to -1 in this case"
y = map(lambda v: v if v != 0 else -1, y)
y = list(y) + [0 for _ in range(len(hint_pool))] # cant have zeros !!!
X = [x for x in labeled_pool] + \
[x for x in hint_pool]
p_val = hintsvm_query(np.array(X, dtype=np.float64),
np.array(y, dtype=np.float64),
np.array(weight, dtype=np.float64),
np.array(unlabeled_pool, dtype=np.float64),
self.svm_params)
p_val = [abs(float(val[0])) for val in p_val]
return dict(zip(unlabeled_entry_ids, p_val))
def make_query(self, return_score=False):
"""Return the index of the sample to be queried and labeled and
selection score of each sample. Read-only.
No modification to the internal states.
Returns
-------
ask_id : int
The index of the next unlabeled sample to be queried and labeled.
score : list of (index, score) tuple
Selection score of unlabled entries, the larger the better.
"""
dataset = self.dataset
unlabeled_entry_ids, _ = zip(*dataset.get_unlabeled_entries())
unlabeled_entry_ids, scores = zip(*self._get_scores())
ask_id = np.argmax(scores)
if return_score:
return unlabeled_entry_ids[ask_id], \
list(zip(unlabeled_entry_ids, scores))
else:
return unlabeled_entry_ids[ask_id]
def retrieve_score_list(self):
unlabeled_entry_ids, _ = zip(*self.dataset.get_unlabeled_entries())
labeled_entry_ids = np.array([eid
for eid, x in enumerate(self.dataset.data)
if x[1] != None])
labels = np.array([x[1]
for eid, x in enumerate(self.dataset.data)
if x[1] != None]).reshape(-1, 1)
centers = self.kmeans_.cluster_centers_
P_k_x = self.P_k_x
p_x = self.p_x[list(unlabeled_entry_ids)]
clf = DensityWeightedLogisticRegression(P_k_x[labeled_entry_ids, :],
centers,
self.C)
clf.train(labeled_entry_ids, labels)
P_y_k = clf.predict()
P_y_x = np.zeros(len(unlabeled_entry_ids))
for k, center in enumerate(centers):
P_y_x += P_y_k[k] * P_k_x[unlabeled_entry_ids, k]
# binary case
expected_error = P_y_x
expected_error[P_y_x >= 0.5] = 1. - P_y_x[P_y_x >= 0.5]
scores = expected_error * p_x
return dict(zip(unlabeled_entry_ids, scores))
def make_query(self, return_score=False):
dataset = self.dataset
self.model.train(dataset)
unlabeled_entry_ids, X_pool = zip(*dataset.get_unlabeled_entries())
if isinstance(self.model, ProbabilisticModel):
dvalue = self.model.predict_proba(X_pool)
elif isinstance(self.model, ContinuousModel):
dvalue = self.model.predict_real(X_pool)
if np.shape(dvalue)[1] > 2:
dvalue = -(np.partition(-dvalue, 2, axis=1)[:, :2])
dist = np.abs(dvalue[:, 0] - dvalue[:, 1])
arr1, arr2 = [], []
arr1.append(np.array(dvalue[:, 0]).tolist())
arr2.append(np.array(dvalue[:, 1]).tolist())
div = -np.max(cosine_similarity(arr1, arr2), axis=1)
score = (self.lmbda * dist) + ((1 - self.lmbda) * div)
ask_id = np.argmin(score)
if return_score:
return unlabeled_entry_ids[ask_id], \
list(zip(unlabeled_entry_ids, score))
else:
return unlabeled_entry_ids[ask_id]
def make_query(self, return_score=False):
dataset = self.dataset
self.model.train(dataset)
unlabeled_entry_ids, X_pool = zip(*dataset.get_unlabeled_entries())
if isinstance(self.model, ProbabilisticModel):
dvalue = self.model.predict_proba(X_pool)
elif isinstance(self.model, ContinuousModel):
dvalue = self.model.predict_real(X_pool)
'''if self.method == 'sm':
if np.shape(dvalue)[1] > 2:
dvalue = -(np.partition(-dvalue, 2, axis=1)[:, :2])
score = -np.abs(dvalue[:, 0] - dvalue[:, 1])'''
if self.method == 'mm': # max margin
margin = np.partition(-dvalue, 1, axis=1)
score = -np.abs(margin[:, 0] - margin[:, 1])
'''elif self.method == 'entropy':
score = np.sum(-dvalue * np.log(dvalue), axis=1)'''
ask_id = np.argmax(score)
if return_score:
return unlabeled_entry_ids[ask_id], \
list(zip(unlabeled_entry_ids, score))
else:
return unlabeled_entry_ids[ask_id]
def make_query(self):
dataset = self.dataset
unlabeled_entry_ids, unlabeled_pool = zip(
*dataset.get_unlabeled_entries())
labeled_pool, y = zip(*dataset.get_labeled_entries())
if len(np.unique(y)) > 2:
raise ValueError("HintSVM query strategy support binary class "
"active learning only. Found %s classes" %
len(np.unique(y)))
hint_pool_idx = self.random_state_.choice(
len(unlabeled_pool), int(len(unlabeled_pool) * self.p))
hint_pool = np.array(unlabeled_pool)[hint_pool_idx]
weight = [1.0 for _ in range(len(labeled_pool))] +\
[(self.ch / self.cl) for _ in range(len(hint_pool))]
y = list(y) + [0 for _ in range(len(hint_pool))]
X = [x.tolist() for x in labeled_pool] +\
[x.tolist() for x in hint_pool]
p_val = hintsvm_query(np.array(X), np.array(y), np.array(weight),
np.array([x.tolist() for x in unlabeled_pool]),
self.svm_params)
p_val = [abs(float(val[0])) for val in p_val]
idx = int(np.argmax(p_val))
return unlabeled_entry_ids[idx]
def make_query(self):
dataset = self.dataset
labeled_pool, Y = zip(*dataset.get_labeled_entries())
unlabeled_entry_ids, X_pool = zip(*dataset.get_unlabeled_entries())
labeled_pool = np.array(labeled_pool)
Y = np.array(Y)
X_pool = np.array(X_pool)
br = BinaryRelevance(self.br_base)
br.train(Dataset(labeled_pool, Y))
trnf = br.predict_proba(labeled_pool)
poolf = br.predict_proba(X_pool)
f = poolf * 2 - 1
trnf = np.sort(trnf, axis=1)[:, ::-1]
trnf /= np.tile(trnf.sum(axis=1).reshape(-1, 1), (1, trnf.shape[1]))
if len(np.unique(Y.sum(axis=1))) == 1:
lr = DummyClf()
else:
lr = self.logistic_regression_
lr.train(Dataset(trnf, Y.sum(axis=1)))
idx_poolf = np.argsort(poolf, axis=1)[:, ::-1]
poolf = np.sort(poolf, axis=1)[:, ::-1]
poolf /= np.tile(poolf.sum(axis=1).reshape(-1, 1), (1, poolf.shape[1]))
pred_num_lbl = lr.predict(poolf).astype(int)
yhat = -1 * np.ones((len(X_pool), self.n_labels), dtype=int)
for i, p in enumerate(pred_num_lbl):
yhat[i, idx_poolf[i, :p]] = 1
score = ((1 - yhat * f) / 2).sum(axis=1)
ask_id = self.random_state_.choice(np.where(score == np.max(score))[0])
return unlabeled_entry_ids[ask_id]
def make_query(self):
dataset = self.dataset
unlabeled_entry_ids, unlabeled_pool = zip(
*dataset.get_unlabeled_entries())
labeled_pool, y = zip(*dataset.get_labeled_entries())
cl = self.cl
ch = self.ch
p = self.p
hint_pool_idx = self.random_state_.choice(
len(unlabeled_pool), int(len(unlabeled_pool)*p))
hint_pool = np.array(unlabeled_pool)[hint_pool_idx]
weight = [1.0 for _ in range(len(labeled_pool))] +\
[(ch/cl) for i in range(len(hint_pool))]
y = list(y) + [0 for i in range(len(hint_pool))]
X = [x.tolist() for x in labeled_pool] +\
[x.tolist() for x in hint_pool]
p_val = hintsvm_query(
np.array(X), np.array(y), np.array(weight),
np.array([x.tolist() for x in unlabeled_pool]), self.svm_params)
p_val = [abs(float(val[0])) for val in p_val]
idx = int(np.argmax(p_val))
return unlabeled_entry_ids[idx]
def __init__(self, dataset, classes, active_selecting=True,
subsample_qs=None, random_state=None):
super(HierarchicalSampling, self).__init__(dataset)
X = np.array(next(zip(*self.dataset.get_entries())))
cluster = AgglomerativeClustering()
cluster.fit(X)
childrens = cluster.children_
if subsample_qs is not None:
if not isinstance(subsample_qs, QueryStrategy):
raise TypeError("subsample_qs has to be a QueryStrategy")
self.sub_qs = subsample_qs
else:
self.sub_qs = None
self.active_selecting = active_selecting
self.random_state_ = seed_random_state(random_state)
self.n = len(childrens) + 1
self.m = self.n * 2 - 1
self.num_class = len(classes)
self.classes = list(classes)
self.class_id = dict(zip(self.classes, range(self.num_class)))
self.parent = np.full(self.m, NO_NODE, dtype=int)
self.size = np.zeros(self.m, dtype=int)
self.depth = np.zeros(self.m, dtype=int)
for i, (left_child, right_child) in enumerate(childrens):
parent = i + self.n
self.parent[left_child] = parent
self.parent[right_child] = parent
self.left_child = np.concatenate([np.full(self.n, NO_NODE), childrens[:,0]]).astype(int)
self.right_child = np.concatenate([np.full(self.n, NO_NODE), childrens[:,1]]).astype(int)
for i in range(self.n):
node = i
cur_depth = 0
while node != NO_NODE:
assert node >= 0 and node < self.m
self.size[node] += 1
self.depth[node] = max(self.depth[node], cur_depth)
cur_depth += 1
node = self.parent[node]
self.count = np.zeros((self.m, self.num_class), dtype=int)
self.total = np.zeros(self.m, dtype=int)
self.upper_bound = np.ones((self.m, self.num_class), dtype=float)
self.lower_bound = np.zeros((self.m, self.num_class), dtype=float)
self.admissible = np.zeros((self.m, self.num_class), dtype=bool)
self.best_label = np.full(self.m, NO_LABEL, dtype=int)
self.split = np.zeros(self.m, dtype=bool)
self.cost = self.size.copy()
self.prunings = [self.m-1]
for i, entry in enumerate(self.dataset.data):
if entry[1] != None:
self.update(i, entry[1])
def import_scipy_mat(filename):
from scipy.io import loadmat
data = loadmat(filename)
X = data['X']
y = data['y']
zipper = list(zip(X, y))
np.random.shuffle(zipper)
X, y = zip(*zipper)
X, y = np.array(X), np.array(y).reshape(-1)
return Dataset(X, y)
def import_scipy_mat(filename):
from scipy.io import loadmat
data = loadmat(filename)
X = data['X']
y = data['y']
zipper = list(zip(X, y))
np.random.shuffle(zipper)
X, y = zip(*zipper)
X, y = np.array(X), np.array(y).reshape(-1)
return Dataset(X, y)
def _get_scores(self):
dataset = self.dataset
_, y = dataset.get_entries()
unlabeled_entry_ids, X_pool = dataset.get_unlabeled_entries()
dvalue, score = (None, [random()])
if y.any():
self.model.train(dataset)
if isinstance(self.model, ProbabilisticModel):
dvalue = self.model.predict_proba(X_pool)
elif isinstance(self.model, ContinuousModel):
dvalue = self.model.predict_real(X_pool)
if self.method == 'lc': # least confident
score = -np.max(dvalue, axis=1)
elif self.method == 'sm': # smallest margin
if np.shape(dvalue)[1] > 2:
# Find 2 largest decision values
dvalue = -(np.partition(-dvalue, 2, axis=1)[:, :2])
score = -np.abs(dvalue[:, 0] - dvalue[:, 1])
elif self.method == 'entropy':
score = np.sum(-dvalue * np.log(dvalue), axis=1)
return zip(unlabeled_entry_ids, score)
def make_query(self):
dataset = self.dataset
unlabeled_entry_ids, X_pool = zip(*dataset.get_unlabeled_entries())
if self.disagreement == 'vote':
# Let the trained students vote for unlabeled data
votes = np.zeros((len(X_pool), len(self.students)))
for i, student in enumerate(self.students):
votes[:, i] = student.predict(X_pool)
vote_entropy = self._vote_disagreement(votes)
ask_idx = self.random_state_.choice(
np.where(np.isclose(vote_entropy, np.max(vote_entropy)))[0])
elif self.disagreement == 'kl_divergence':
proba = []
for student in self.students:
proba.append(student.predict_proba(X_pool))
proba = np.array(proba).transpose(1, 0, 2).astype(float)
avg_kl = self._kl_divergence_disagreement(proba)
ask_idx = self.random_state_.choice(
np.where(np.isclose(avg_kl, np.max(avg_kl)))[0])
return unlabeled_entry_ids[ask_idx]
def _labeled_uniform_sample(self, sample_size):
"""sample labeled entries uniformly"""
labeled_entries = self.dataset.get_labeled_entries()
samples = [labeled_entries[
self.random_state_.randint(0, len(labeled_entries))
]for _ in range(sample_size)]
return Dataset(*zip(*samples))
def make_query(self):
dataset = self.dataset
self.model.train(dataset)
unlabeled_entry_ids, X_pool = zip(*dataset.get_unlabeled_entries())
if isinstance(self.model, ProbabilisticModel):
dvalue = self.model.predict_proba(X_pool)
elif isinstance(self.model, ContinuousModel):
dvalue = self.model.predict_real(X_pool)
if self.method == 'lc': # least confident
ask_id = np.argmin(np.max(dvalue, axis=1))
elif self.method == 'sm': # smallest margin
if np.shape(dvalue)[1] > 2:
# Find 2 largest decision values
dvalue = -(np.partition(-dvalue, 2, axis=1)[:, :2])
margin = np.abs(dvalue[:, 0] - dvalue[:, 1])
ask_id = np.argmin(margin)
elif self.method == 'entropy':
entropy = np.sum(-dvalue * np.log(dvalue), axis=1)
ask_id = np.argmax(entropy)
return unlabeled_entry_ids[ask_id]
def make_query(self):
dataset = self.dataset
unlabeled_entry_ids, scores = zip(*self._get_scores())
ask_id = self.random_state_.choice(np.where(scores == np.max(scores))[0])
return unlabeled_entry_ids[ask_id]
def _labeled_uniform_sample(self, sample_size):
"""sample labeled entries uniformly"""
labeled_entries = self.dataset.get_labeled_entries()
samples = [labeled_entries[
self.random_state_.randint(0, len(labeled_entries))
]for _ in range(sample_size)]
return Dataset(*zip(*samples))
def run(trn_ds, tst_ds, lbr, model, qs, quota, j):
E_in, E_out, l = [], [], []
model.train(trn_ds)
E_out.append(1 - model.score(tst_ds))
counter = 0
steps = 15
k = int(j / steps)
if k == 0:
k = 1
for _ in range(0, steps):
counter = counter + 1
l = []
for i in range(0, k):
ask_id = qs.make_query()
l.append(ask_id)
X, _ = zip(*trn_ds.data)
lb = lbr.label(X[ask_id])
trn_ds.update(ask_id, lb)
model.train(trn_ds)
E_out = np.append(E_out, 1 - model.score(tst_ds))
#print '-->', len(E_out)
return E_out, len(E_out), trn_ds, k, j
def make_query(self, n=1, return_score=False):
"""Return the index of the sample to be queried and labeled and
selection score of each sample. Read-only.
No modification to the internal states.
Returns
-------
ask_ids : list
The batch of indexes of the next unlabeled samples to be queried and labeled.
score : list of (index, score) tuple
Selection score of unlabled entries, the larger the better.
"""
dataset = self.dataset
# unlabeled_entry_ids, _ = dataset.get_unlabeled_entries()
unlabeled_entry_ids, scores = zip(*self._get_scores())
# ask_ids = np.argmax(scores)
ask_ids = np.argsort(scores)[-n:][::-1]
# return unlabeled_entry_ids[ask_id]
res = [unlabeled_entry_ids[i] for i in ask_ids]
return res
def make_query(self,
return_score=False,
return_label=False,
n_instances=1):
"""Return the index of the sample to be queried and labeled and
selection score of each sample. Read-only.
No modification to the internal states.
Returns
-------
ask_id : int
The index of the next unlabeled sample to be queried and labeled.
score : list of (index, score) tuple
Selection score of unlabled entries, the larger the better.
"""
dataset = self.dataset
# self.model.train(dataset)
unlabeled_entry_ids, X_pool = zip(*dataset.get_unlabeled_entries())
X_pool = np.array(X_pool)
unlabeled_entry_ids = np.array(unlabeled_entry_ids)
if isinstance(self.model, ProbabilisticModel):
dvalue = self.model.predict_proba(X_pool)
elif isinstance(self.model, ContinuousModel):
dvalue = self.model.predict_real(X_pool)
if self.method == 'lc': # least confident
score = -np.max(dvalue, axis=1)
elif self.method == 'sm': # smallest margin
if np.shape(dvalue)[1] > 2:
# Find 2 largest decision values
dvalue = -(np.partition(-dvalue, 2, axis=1)[:, :2])
score = -np.abs(dvalue[:, 0] - dvalue[:, 1])
elif self.method == 'entropy':
score = np.sum(-dvalue * np.log(dvalue), axis=1)
# ask_id = np.argmax(score)
ask_ids = multi_argmax(score, n_instances=n_instances)
# pre_label = np.argmax(dvalue, axis=1)
# ask_label = pre_label[ask_ids]
if return_score and return_label:
pre_label = np.argmax(dvalue, axis=1)
return unlabeled_entry_ids[ask_ids], score[ask_ids], pre_label[
ask_ids]
elif return_score:
return unlabeled_entry_ids[ask_ids], score[ask_ids]
elif return_label:
pre_label = np.argmax(dvalue, axis=1)
return unlabeled_entry_ids[ask_ids], pre_label[ask_ids]
else:
return unlabeled_entry_ids[ask_ids]
def retrieve_score_list(self):
dataset = self.dataset
unlabeled_entry_ids, X_pool = zip(*dataset.get_unlabeled_entries())
if self.disagreement == 'vote':
# Let the trained students vote for unlabeled data
votes = np.zeros((len(X_pool), len(self.students)))
for i, student in enumerate(self.students):
votes[:, i] = student.predict(X_pool)
score_list = self._vote_disagreement(votes)
elif self.disagreement == 'kl_divergence':
proba = []
for student in self.students:
proba.append(student.predict_proba(X_pool))
proba = np.array(proba).transpose(1, 0, 2).astype(float)
score_list = self._kl_divergence_disagreement(proba)
return dict(zip(unlabeled_entry_ids, score_list))
def make_query(self):
dataset = self.dataset
unlabeled_entry_ids, pool_X = zip(*dataset.get_unlabeled_entries())
# The input class should be 0-n_classes
X, y = zip(*dataset.get_labeled_entries())
pred_embed = np.zeros((len(pool_X), self.embed_dim))
for i in range(self.embed_dim):
self.regressors[i].fit(X, self.class_embed[y, i])
pred_embed[:, i] = self.regressors[i].predict(pool_X)
dist, _ = self.nn_.kneighbors(pred_embed)
dist = dist[:, 0]
ask_idx = self.random_state_.choice(
np.where(np.isclose(dist, np.max(dist)))[0])
return unlabeled_entry_ids[ask_idx]
def make_query(self, n=1):
dataset = self.dataset
unlabeled_entry_ids, _ = zip(*dataset.get_unlabeled_entries())
entry_id = self.random_state_.choice(unlabeled_entry_ids,
size=n,
replace=False)
return list(entry_id) if n > 1 else entry_id[0]
def make_query(self):
dataset = self.dataset
unlabeled_entry_ids, pool_X = zip(*dataset.get_unlabeled_entries())
# The input class should be 0-n_classes
X, y = zip(*dataset.get_labeled_entries())
pred_embed = np.zeros((len(pool_X), self.embed_dim))
for i in range(self.embed_dim):
self.regressors[i].fit(X, self.class_embed[y, i])
pred_embed[:, i] = self.regressors[i].predict(pool_X)
dist, _ = self.nn_.kneighbors(pred_embed)
dist = dist[:, 0]
ask_idx = self.random_state_.choice(
np.where(np.isclose(dist, np.max(dist)))[0])
return unlabeled_entry_ids[ask_idx]
def make_query(self):
dataset = self.dataset
unlabeled_entry_ids, _ = zip(*dataset.get_unlabeled_entries())
unlabeled_entry_ids = shuffle(unlabeled_entry_ids)
return_len = min(len(unlabeled_entry_ids), self.batch_size)
entry_id = unlabeled_entry_ids[:return_len]
# entry_id = [20, 104,106,64,77,37,164,136,127,130]
return entry_id
def __init__(self, *args, **kwargs):
super(ActiveLearningByLearning, self).__init__(*args, **kwargs)
self.query_strategies_ = kwargs.pop("query_strategies", None)
if self.query_strategies_ is None:
raise TypeError("__init__() missing required keyword-only argument: " "'query_strategies'")
elif not self.query_strategies_:
raise ValueError("query_strategies list is empty")
# check if query_strategies share the same dataset with albl
for qs in self.query_strategies_:
if qs.dataset != self.dataset:
raise ValueError("query_strategies should share the same" "dataset instance with albl")
# parameters for Exp4.p
self.delta = kwargs.pop("delta", 0.1)
# query budget
self.T = kwargs.pop("T", None)
if self.T is None:
raise TypeError("__init__() missing required keyword-only argument: 'T'")
self.unlabeled_entry_ids, _ = zip(*self.dataset.get_unlabeled_entries())
self.unlabeled_invert_id_idx = {}
for i, entry in enumerate(self.dataset.get_unlabeled_entries()):
self.unlabeled_invert_id_idx[entry[0]] = i
self.uniform_sampler = kwargs.pop("uniform_sampler", True)
if not isinstance(self.uniform_sampler, bool):
raise ValueError("'uniform_sampler' should be {True, False}")
self.pmin = kwargs.pop("pmin", None)
n_algorithms = len(self.query_strategies_) + self.uniform_sampler
if self.pmin and (self.pmin < (1.0 / n_algorithms) or self.pmin < 0):
raise ValueError("'pmin' should be 0 < pmin < " "1/len(n_active_algorithm)")
self.exp4p_ = Exp4P(
query_strategies=self.query_strategies_,
T=self.T,
delta=self.delta,
pmin=self.pmin,
unlabeled_invert_id_idx=self.unlabeled_invert_id_idx,
uniform_sampler=self.uniform_sampler,
)
self.budget_used = 0
# classifier instance
self.model = kwargs.pop("model", None)
if self.model is None:
raise TypeError("__init__() missing required keyword-only argument: 'model'")
random_state = kwargs.pop("random_state", None)
self.random_state_ = seed_random_state(random_state)
self.query_dist = None
self.W = []
self.queried_hist_ = []
def make_query(self):
dataset = self.dataset
unlabeled_entry_ids, X_pool = zip(*dataset.get_unlabeled_entries())
# Let the trained students vote for unlabeled data
votes = np.zeros((len(X_pool), len(self.students)))
for i, student in enumerate(self.students):
votes[:, i] = student.predict(X_pool)
id_disagreement = [(i, dis) for i, dis in
zip(unlabeled_entry_ids, self.disagreement(votes))]
disagreement = sorted(id_disagreement, key=lambda id_dis: id_dis[1],
reverse=True)
ask_id = self.random_state_.choice(
[e[0] for e in disagreement if e[1] == disagreement[0][1]])
return ask_id
def make_query(self, return_score=False):
"""Return the index of the sample to be queried and labeled and
selection score of each sample. Read-only.
No modification to the internal states.
Returns
-------
ask_id : int
The index of the next unlabeled sample to be queried and labeled.
score : list of (index, score) tuple
Selection score of unlabled entries, the larger the better.
"""
dataset = self.dataset
self.model.train(dataset)
unlabeled_entry_ids, X_pool = zip(*dataset.get_unlabeled_entries())
if isinstance(self.model, ProbabilisticModel):
dvalue = self.model.predict_proba(X_pool)
elif isinstance(self.model, ContinuousModel):
dvalue = self.model.predict_real(X_pool)
if self.method == 'lc': # least confident
score = -np.max(dvalue, axis=1)
elif self.method == 'sm': # smallest margin
if np.shape(dvalue)[1] > 2:
# Find 2 largest decision values
dvalue = -(np.partition(-dvalue, 2, axis=1)[:, :2])
score = -np.abs(dvalue[:, 0] - dvalue[:, 1])
elif self.method == 'entropy':
score = np.sum(-dvalue * np.log(dvalue), axis=1)
ask_id = np.argmax(score)
if return_score:
return unlabeled_entry_ids[ask_id], \
list(zip(unlabeled_entry_ids, score))
else:
return unlabeled_entry_ids[ask_id]
def make_query(self):
dataset = self.dataset
labeled_pool, Y = zip(*dataset.get_labeled_entries())
unlabeled_entry_ids, X_pool = zip(*dataset.get_unlabeled_entries())
major_clf = copy.deepcopy(self.major_learner)
major_clf.train(dataset)
aux_clf = copy.deepcopy(self.auxiliary_learner)
aux_clf.train(dataset)
if self.criterion == 'hlr':
major_pred = major_clf.predict(X_pool)
aux_pred = aux_clf.predict(X_pool)
score = np.abs(major_pred - aux_pred).mean(axis=1)
elif self.criterion in ['mmr', 'shlr']:
major_pred = major_clf.predict(X_pool) * 2 - 1
if 'predict_real' in dir(aux_clf):
aux_pred = aux_clf.predict_real(X_pool)
elif 'predict_proba' in dir(aux_clf):
aux_pred = aux_clf.predict_proba(X_pool) * 2 - 1
else:
raise AttributeError("aux_learner did not support either"
"'predict_real' or 'predict_proba'"
"method")
loss = (major_pred * aux_pred).mean(axis=1)
if self.criterion == 'mmr':
score = (1. - major_pred * aux_pred) / 2.
score = np.sum(score, axis=1)
elif self.criterion == 'shlr':
b = self.b
score = (b - np.clip(major_pred * aux_pred, -b, b)) / 2. / b
score = np.sum(score, axis=1)
else:
raise TypeError(
"supported criterion are ['hlr', 'shlr', 'mmr'], the given "
"one is: " + self.criterion
)
ask_id = self.random_state_.choice(np.where(score == np.max(score))[0])
return unlabeled_entry_ids[ask_id]
def make_query(self):
labeled_entries = self.dataset.get_labeled_entries()
Xlabeled, y = zip(*labeled_entries)
Xlabeled = np.array(Xlabeled)
y = list(y)
unlabeled_entries = self.dataset.get_unlabeled_entries()
unlabeled_entry_ids, X_pool = zip(*unlabeled_entries)
label_count = self.dataset.get_num_of_labels()
clf = copy.copy(self.model)
clf.train(Dataset(Xlabeled, y))
p = Pool(self.n_jobs)
errors = p.map(_E, [(Xlabeled, y, x, clf, label_count, self.sigma, self.model) for x in X_pool])
p.terminate()
return unlabeled_entry_ids[errors.index(min(errors))]
def make_query(self):
dataset = self.dataset
labeled_pool, Y = zip(*dataset.get_labeled_entries())
unlabeled_entry_ids, X_pool = zip(*dataset.get_unlabeled_entries())
major_clf = copy.deepcopy(self.major_learner)
major_clf.train(dataset)
aux_clf = copy.deepcopy(self.auxiliary_learner)
aux_clf.train(dataset)
if self.criterion == 'hlr':
major_pred = major_clf.predict(X_pool)
aux_pred = aux_clf.predict(X_pool)
score = np.abs(major_pred - aux_pred).mean(axis=1)
elif self.criterion in ['mmr', 'shlr']:
major_pred = major_clf.predict(X_pool) * 2 - 1
if 'predict_real' in dir(aux_clf):
aux_pred = aux_clf.predict_real(X_pool)
elif 'predict_proba' in dir(aux_clf):
aux_pred = aux_clf.predict_proba(X_pool) * 2 - 1
else:
raise AttributeError("aux_learner did not support either"
"'predict_real' or 'predict_proba'"
"method")
loss = (major_pred * aux_pred).mean(axis=1)
if self.criterion == 'mmr':
score = (1. - major_pred * aux_pred) / 2.
score = np.sum(score, axis=1)
elif self.criterion == 'shlr':
b = self.b
score = (b - np.clip(major_pred * aux_pred, -b, b)) / 2. / b
score = np.sum(score, axis=1)
else:
raise TypeError(
"supported criterion are ['hlr', 'shlr', 'mmr'], the given "
"one is: " + self.criterion)
ask_id = self.random_state_.choice(np.where(score == np.max(score))[0])
return unlabeled_entry_ids[ask_id]
def make_query(self, n_instances=1):
dataset = self.dataset
unlabeled_entry_ids, _ = zip(*dataset.get_unlabeled_entries())
unlabeled_entry_ids = np.array(unlabeled_entry_ids)
rs = random.sample(range(0, len(unlabeled_entry_ids)), n_instances)
entry_ids = unlabeled_entry_ids[rs]
# entry_id = unlabeled_entry_ids[
# self.random_state_.randint(0, len(unlabeled_entry_ids))]
return entry_ids
def _get_scores(self):
dataset = self.dataset
X, _ = zip(*dataset.data)
scores = self.base_query_strategy._get_scores()
_, X_pool = zip(*dataset.get_unlabeled_entries())
unlabeled_entry_ids, base_scores = zip(*scores)
self.clustering_method.fit(X)
pool_cluster = self.clustering_method.predict(X_pool)
cluster_center = self.clustering_method.cluster_centers_
similarity = []
for i in range(len(X_pool)):
similarity.append(
self.similarity_metric(
X_pool[i].reshape(1, -1),
cluster_center[pool_cluster[i]].reshape(1, -1))[0][0])
similarity = np.asarray(similarity)
scores = base_scores * similarity**self.beta
return zip(unlabeled_entry_ids, scores)
def make_query(self):
dataset = self.dataset
self.model.fit(*(dataset.format_sklearn()))
unlabeled_entry_ids, X_pool = zip(*dataset.get_unlabeled_entries())
mean, var = self.model.predict_mean_var(X_pool)
score = 1.96 * var**.5 - np.abs(mean)
ask_id = np.argmax(score)
return unlabeled_entry_ids[ask_id]
def make_query(self):
labeled_entries = self.dataset.get_labeled_entries()
Xlabeled, y = zip(*labeled_entries)
Xlabeled = np.array(Xlabeled)
y = list(y)
unlabeled_entries = self.dataset.get_unlabeled_entries()
unlabeled_entry_ids, X_pool = zip(*unlabeled_entries)
label_count = self.dataset.get_num_of_labels()
clf = copy.copy(self.model)
clf.train(Dataset(Xlabeled, y))
p = Pool(self.n_jobs)
errors = p.map(
_E, [(Xlabeled, y, x, clf, label_count, self.sigma, self.model)
for x in X_pool])
p.terminate()
return unlabeled_entry_ids[errors.index(min(errors))]
def make_query(self):
dataset = self.dataset
unlabeled_entry_ids, X_pool = zip(*dataset.get_unlabeled_entries())
# Let the trained students vote for unlabeled data
votes = np.zeros((len(X_pool), len(self.students)))
for i, student in enumerate(self.students):
votes[:, i] = student.predict(X_pool)
id_disagreement = [
(i, dis)
for i, dis in zip(unlabeled_entry_ids, self.disagreement(votes))
]
disagreement = sorted(id_disagreement,
key=lambda id_dis: id_dis[1],
reverse=True)
ask_id = self.random_state_.choice(
[e[0] for e in disagreement if e[1] == disagreement[0][1]])
return ask_id
def make_query(self, return_score=False, n_instances=2):
"""Return the index of the sample to be queried and labeled and
selection score of each sample. Read-only.
No modification to the internal states.
Returns
-------
ask_id : int
The index of the next unlabeled sample to be queried and labeled.
score : list of (index, score) tuple
Selection score of unlabled entries, the larger the better.
"""
dataset = self.dataset
unlabeled_entry_ids, _ = zip(*dataset.get_unlabeled_entries())
unlabeled_entry_ids, scores = zip(*self._get_scores())
unlabeled_entry_ids = np.array(unlabeled_entry_ids)
scores = np.array(scores)
# ask_id = np.argmax(scores)
#
# if return_score:
# return unlabeled_entry_ids[ask_id], \
# list(zip(unlabeled_entry_ids, scores))
# else:
# return unlabeled_entry_ids[ask_id]
ask_ids = multi_argmax(scores, n_instances=n_instances)
# pre_label = np.argmax(dvalue, axis=1)
# ask_label = pre_label[ask_ids]
if return_score:
return unlabeled_entry_ids[ask_ids], \
list(zip(unlabeled_entry_ids, scores))
else:
return unlabeled_entry_ids[ask_ids]
def make_query(self):
dataset = self.dataset
X, Y = zip(*dataset.get_labeled_entries())
Y = np.array(Y)
unlabeled_entry_ids, X_pool = zip(*dataset.get_unlabeled_entries())
X_pool = np.array(X_pool)
clfs = []
boundaries = []
for i in range(self.n_labels):
if len(np.unique(Y[:, i])) == 1:
clf = DummyClf()
else:
clf = copy.deepcopy(self.base_clf)
clf.train(Dataset(X, Y[:, i]))
boundaries.append(np.abs(clf.predict_real(X_pool)[:, 1]))
clfs.append(clf)
choices = np.where(np.array(boundaries) == np.min(boundaries))[1]
ask_id = self.random_state_.choice(choices)
return unlabeled_entry_ids[ask_id]
def make_query(self):
dataset = self.dataset
X, Y = zip(*dataset.get_labeled_entries())
Y = np.array(Y)
unlabeled_entry_ids, X_pool = zip(*dataset.get_unlabeled_entries())
X_pool = np.array(X_pool)
clfs = []
boundaries = []
for i in range(self.n_labels):
if len(np.unique(Y[:, i])) == 1:
clf = DummyClf()
else:
clf = copy.deepcopy(self.base_clf)
clf.train(Dataset(X, Y[:, i]))
boundaries.append(np.abs(clf.predict_real(X_pool)[:, 1]))
clfs.append(clf)
choices = np.where(np.array(boundaries) == np.min(boundaries))[1]
ask_id = self.random_state_.choice(choices)
return unlabeled_entry_ids[ask_id]
def format_sklearn(self):
"""
Returns dataset in (X, y) format for use in scikit-learn.
Unlabeled entries are ignored.
Returns
-------
X : numpy array, shape = (n_samples, n_features)
Sample feature set.
y : numpy array, shape = (n_samples)
Sample labels.
"""
X, y = zip(*self.get_labeled_entries())
return np.array(X), np.array(y)
def labeled_uniform_sample(self, sample_size, replace=True):
"""Returns a Dataset object with labeled data only, which is
resampled uniformly with given sample size.
Parameter `replace` decides whether sampling with replacement or not.
Parameters
----------
sample_size
"""
if replace:
samples = [
random.choice(self.get_labeled_entries())
for _ in range(sample_size)
]
else:
samples = random.sample(self.get_labeled_entries(), sample_size)
return Dataset(*zip(*samples))
def make_query(self):
dataset = self.dataset
self.model.train(dataset)
unlabeled_entry_ids, X_pool = zip(*dataset.get_unlabeled_entries())
if self.method == "lc": # least confident
ask_id = np.argmin(np.max(self.model.predict_real(X_pool), axis=1))
elif self.method == "sm": # smallest margin
dvalue = self.model.predict_real(X_pool)
if np.shape(dvalue)[1] > 2:
# Find 2 largest decision values
dvalue = -(np.partition(-dvalue, 2, axis=1)[:, :2])
margin = np.abs(dvalue[:, 0] - dvalue[:, 1])
ask_id = np.argmin(margin)
return unlabeled_entry_ids[ask_id]
def make_query(self):
dataset = self.dataset
try:
unlabeled_entry_ids, _ = zip(*dataset.get_unlabeled_entries())
except ValueError:
# might be no more unlabeled data left
return
while self.budget_used < self.T:
self.calc_query()
ask_idx = self.random_state_.choice(
np.arange(len(self.unlabeled_invert_id_idx)), size=1, p=self.query_dist
)[0]
ask_id = self.unlabeled_entry_ids[ask_idx]
if ask_id in unlabeled_entry_ids:
self.budget_used += 1
return ask_id
else:
self.update(ask_id, dataset.data[ask_id][1])
raise ValueError("Out of query budget")
def __init__(self, X=None, y=None):
if X is None: X = []
if y is None: y = []
self.data = list(zip(X, y))
self.modified = True
self._update_callback = set()
def __init__(self, X=[], y=[]):
self.data = list(zip(X, y))
self.modified = True
self._update_callback = set()
def make_query(self):
dataset = self.dataset
unlabeled_entry_ids, _ = zip(*dataset.get_unlabeled_entries())
entry_id = unlabeled_entry_ids[
self.random_state_.randint(0, len(unlabeled_entry_ids))]
return entry_id