class UncertaintySampler(object):
def __init__(self, X, y, labs, n=2):
y = [yy if yy >= 0 else None for yy in y]
self.dataset = Dataset(X, y)
self.labs = labs
self.uc = UncertaintySampling(self.dataset,
method='lc',
model=LinearSVC())
self.n = n
def get_next(self):
print >> sys.stderr, 'get_next: start'
out = self.uc.make_query(n=self.n)
print >> sys.stderr, 'get_next: done'
return out
def set_label(self, idx, label):
print >> sys.stderr, 'set_label: start'
out = self.dataset.update(idx, label)
print >> sys.stderr, 'set_label: done'
return out
def get_data(self):
X, y = zip(*self.dataset.get_entries())
X, y = np.vstack(X), np.array(
[yy if yy is not None else -1 for yy in y])
return X, y
def n_hits(self):
labels = np.array(zip(*self.dataset.get_entries())[1])
return (labels == 1).sum()
def n_labeled(self):
return self.dataset.len_labeled()
def is_labeled(self, idx):
return idx in np.where(zip(*self.dataset.get_entries())[1])[0]
def save(self, outpath):
""" !! This should be updated to save in same format as simple_las """
X, y = self.get_data()
f = h5py.File(
'%s-%s-%s.h5' %
(outpath, 'uncertainty', datetime.now().strftime('%Y%m%d_%H%M%S')))
f['X'] = X
f['y'] = y
f['labs'] = self.labs
f.close()
def run_featureselection(trn_dss,
tst_ds,
y_train,
model,
method_,
qs,
X_test,
y_test,
all_cols,
save_name,
save,
type_,
part=20):
"""
Batch active learning algorithm with feature selection
"""
E_in, E_out = [], []
f1score = []
features_ls = []
label_holder, asked_id = [], []
tn, fp, fn, tp = [], [], [], []
k = trn_dss.len_labeled()
k_beg = trn_dss.len_labeled()
quota = len(trn_dss.data)
iter_ = 0
while (k < quota):
clear_output(wait=True)
# Standard usage of libact objects
# make_query returns the index of the sample that the active learning algorithm would like to query
lbls, asks = [], []
if (part < trn_dss.len_unlabeled()):
part1 = part
else:
part1 = trn_dss.len_unlabeled()
# -------------------> Feature Selection
# select features with feature selection
X_train_feature = [i[0] for i in trn_dss.get_labeled_entries()]
y_train_feature = [i[1] for i in trn_dss.get_labeled_entries()]
col_index, features_f = feature_selection(X_train_feature,
y_train_feature,
all_cols,
f_class=True)
features_ls.append(features_f)
# update the X_train dataset and y_train with the current selection of variables
X_train_updated = [i[0][col_index] for i in trn_dss.data]
y_train_updated = [i[1] for i in trn_dss.data]
trn_dss_updated = Dataset(X_train_updated, y_train_updated)
# update X_test
X_test_feature = [i[col_index] for i in X_test]
if (type_ == 'random'):
qs = RandomSampling(trn_dss_updated, method=method_, model=model)
model1 = model
elif (type_ == 'unc'):
qs = UncertaintySampling(trn_dss_updated,
method=method_,
model=model)
model1 = model
elif (type_ == 'qbc'):
qs = QueryByCommittee(trn_dss_updated, models=model)
model1 = method_
elif (type_ == 'dens'):
qs = DWUS(trn_dss_updated, model=model)
model1 = model
for i in range(0, part1):
# ask id only asks for particular id, not all, everytime
ask_id = qs.make_query()
asks.append(ask_id)
# lbl label returns the label of a given sample
lb = y_train[ask_id]
lbls.append(lb)
# update updates the unlabeled sample with queried sample
trn_dss.update(ask_id, lb)
trn_dss_updated.update(ask_id, lb)
label_holder.append(lbls)
asked_id.append(asks)
# trains only on the labeled examples and chosen values
model1.train(trn_dss_updated)
# predict it
pred_y = model1.predict(X_test_feature)
# save the results
f1score.append(f1_score(y_test, pred_y))
tn.append(confusion_matrix(y_test, pred_y)[0][0])
fp.append(confusion_matrix(y_test, pred_y)[0][1])
fn.append(confusion_matrix(y_test, pred_y)[1][0])
tp.append(confusion_matrix(y_test, pred_y)[1][1])
# score returns the mean accuracy of the results
#E_in = np.append(E_in, 1 - model.score(trn_dss)) #train
#E_out = np.append(E_out, 1 - model.score(tst_ds)) #test
k = trn_dss_updated.len_labeled()
print(k)
print(quota)
print('iteration:', iter_)
print(len(f1score))
print('train dataset labeled:', trn_dss.len_labeled())
print('train dataset shape:', trn_dss.format_sklearn()[0].shape)
print('train dataset sum:', trn_dss.format_sklearn()[1].sum())
print('Current f1 score:', f1_score(y_test, pred_y))
print('Current progress:', np.round(k / quota * 100, 2), '%')
print('Chosen_features:', features_f)
# number of iterations
iter_ = iter_ + 1
q = [i for i in range(k_beg, quota, part)]
iter_ = [i for i in range(0, len(f1score))]
if (save == True):
#q= [i for i in range(k_beg,quota,part)]
#iter_=[i for i in range(0,len(f1score))]
saved_file = pd.DataFrame({
'iter': iter_,
'quota': q,
'f1_score': f1score,
'tn': tn,
'fp': fp,
'fn': fn,
'tp': tp,
'id_index': asked_id,
'label': label_holder,
'features': features_ls
})
saved_file.to_csv(save_name)
return q, iter_, f1score, tn, fp, fn, tp, k, trn_dss.data, label_holder, asked_id, features_ls