def test_multilabel_with_auxiliary_learner_mmr(self):
trn_ds = Dataset(self.X,
self.y[:5] + [None] * (len(self.y) - 5))
qs = MultilabelWithAuxiliaryLearner(trn_ds,
major_learner=BinaryRelevance(LogisticRegression(solver='liblinear',
multi_class="ovr")),
auxiliary_learner=BinaryRelevance(SVM(gamma="auto")),
criterion='mmr',
random_state=1126)
qseq = run_qs(trn_ds, qs, self.y, self.quota)
assert_array_equal(qseq,
np.array([1258, 1461, 231, 1198, 1498, 1374, 955, 1367, 265, 144]))
def test_multilabel_with_auxiliary_learner_hlr(self):
trn_ds = Dataset(self.X, self.y[:5] + [None] * (len(self.y) - 5))
qs = MultilabelWithAuxiliaryLearner(
trn_ds,
major_learner=BinaryRelevance(LogisticRegression()),
auxiliary_learner=BinaryRelevance(SVM()),
criterion='hlr',
random_state=1126)
qseq = run_qs(trn_ds, qs, self.y, self.quota)
assert_array_equal(
qseq,
np.array([701, 1403, 147, 897, 974, 1266, 870, 703, 292, 1146]))
def test_multilabel_with_auxiliary_learner_shlr(self):
trn_ds = Dataset(self.X,
self.y[:5] + [None] * (len(self.y) - 5))
qs = MultilabelWithAuxiliaryLearner(trn_ds,
major_learner=BinaryRelevance(LogisticRegression(solver='liblinear',
multi_class="ovr")),
auxiliary_learner=BinaryRelevance(SVM(gamma="auto")),
criterion='shlr',
b=1.,
random_state=1126)
qseq = run_qs(trn_ds, qs, self.y, self.quota)
assert_array_equal(qseq,
np.array([1258, 805, 459, 550, 783, 964, 736, 1004, 38, 750]))
def main():
test_size = 0.25 # the percentage of samples in the dataset that will be
# randomly selected and assigned to the test set
result = {'E1': [], 'E2': [], 'E3': [], 'E4': [], 'E5': [], 'E6': []}
for i in range(10): # repeat experiment
trn_ds, tst_ds, fully_labeled_trn_ds = split_train_test(test_size)
trn_ds2 = copy.deepcopy(trn_ds)
trn_ds3 = copy.deepcopy(trn_ds)
trn_ds4 = copy.deepcopy(trn_ds)
trn_ds5 = copy.deepcopy(trn_ds)
trn_ds6 = copy.deepcopy(trn_ds)
lbr = IdealLabeler(fully_labeled_trn_ds)
model = BinaryRelevance(LogisticRegression())
quota = 150 # number of samples to query
qs = MMC(trn_ds, br_base=LogisticRegression())
_, E_out_1 = run(trn_ds, tst_ds, lbr, model, qs, quota)
result['E1'].append(E_out_1)
qs2 = RandomSampling(trn_ds2)
_, E_out_2 = run(trn_ds2, tst_ds, lbr, model, qs2, quota)
result['E2'].append(E_out_2)
qs3 = MultilabelWithAuxiliaryLearner(trn_ds3,
BinaryRelevance(
LogisticRegression()),
BinaryRelevance(SVM()),
criterion='hlr')
_, E_out_3 = run(trn_ds3, tst_ds, lbr, model, qs3, quota)
result['E3'].append(E_out_3)
qs4 = MultilabelWithAuxiliaryLearner(trn_ds4,
BinaryRelevance(
LogisticRegression()),
BinaryRelevance(SVM()),
criterion='shlr')
_, E_out_4 = run(trn_ds4, tst_ds, lbr, model, qs4, quota)
result['E4'].append(E_out_4)
qs5 = MultilabelWithAuxiliaryLearner(trn_ds5,
BinaryRelevance(
LogisticRegression()),
BinaryRelevance(SVM()),
criterion='mmr')
_, E_out_5 = run(trn_ds5, tst_ds, lbr, model, qs5, quota)
result['E5'].append(E_out_5)
qs6 = BinaryMinimization(trn_ds6, LogisticRegression())
_, E_out_6 = run(trn_ds6, tst_ds, lbr, model, qs6, quota)
result['E6'].append(E_out_6)
E_out_1 = np.mean(result['E1'], axis=0)
E_out_2 = np.mean(result['E2'], axis=0)
E_out_3 = np.mean(result['E3'], axis=0)
E_out_4 = np.mean(result['E4'], axis=0)
E_out_5 = np.mean(result['E5'], axis=0)
E_out_6 = np.mean(result['E6'], axis=0)
print("MMC: ", E_out_1[::5].tolist())
print("Random: ", E_out_2[::5].tolist())
print("MultilabelWithAuxiliaryLearner_hlr: ", E_out_3[::5].tolist())
print("MultilabelWithAuxiliaryLearner_shlr: ", E_out_4[::5].tolist())
print("MultilabelWithAuxiliaryLearner_mmr: ", E_out_5[::5].tolist())
print("BinaryMinimization: ", E_out_6[::5].tolist())
query_num = np.arange(1, quota + 1)
fig = plt.figure(figsize=(9, 6))
ax = plt.subplot(111)
ax.plot(query_num, E_out_1, 'g', label='MMC')
ax.plot(query_num, E_out_2, 'k', label='Random')
ax.plot(query_num, E_out_3, 'r', label='AuxiliaryLearner_hlr')
ax.plot(query_num, E_out_4, 'b', label='AuxiliaryLearner_shlr')
ax.plot(query_num, E_out_5, 'c', label='AuxiliaryLearner_mmr')
ax.plot(query_num, E_out_6, 'm', label='BinaryMinimization')
box = ax.get_position()
ax.set_position([box.x0, box.y0, box.width * 0.75, box.height])
plt.legend(loc=2, bbox_to_anchor=(1.05, 1), borderaxespad=0.)
plt.xlabel('Number of Queries')
plt.ylabel('Loss')
plt.title('Experiment Result (Hamming Loss)')
plt.show()
'''
MAIN FUNCTION
'''
result = {'Hamming': [],'F1': []}
model = BinaryRelevance(LogisticRegression())
quota = 20 # number of samples to query
#EXECUTE FROM HERE FOR ITERATIONS
qs1 = MultilabelWithAuxiliaryLearner(
trn_ds,
BinaryRelevance(LogisticRegression()),
BinaryRelevance(SVM()),
criterion='hlr')
run(data_CV_train,trn_ds, qs1, quota)
model.train(trn_ds)
X , y = zip(*tst_ds.get_labeled_entries())
pred = model.predict(X)
output = pd.DataFrame()
output['UE_pred'] = [pred[i][0] for i in range(len(pred))]
output['BR_pred'] = [pred[i][1] for i in range(len(pred))]
output['FR_pred'] = [pred[i][2] for i in range(len(pred))]