def test_multilabel(self):
X, Y = synthetic_multilabel()
self.assertTrue(U.is_multilabel((X, Y)))
MAXLEN = 7
MAXFEATURES = 4
NUM_CLASSES = 4
model = Sequential()
model.add(Embedding(MAXFEATURES + 1, 50, input_length=MAXLEN))
model.add(GlobalAveragePooling1D())
model.add(Dense(NUM_CLASSES, activation='sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy'])
learner = ktrain.get_learner(model,
train_data=(X, Y),
val_data=(X, Y),
batch_size=1)
learner.lr_find()
# use loss instead of accuracy due to: https://github.com/tensorflow/tensorflow/issues/41114
hist = learner.fit(0.001, 200)
learner.view_top_losses(n=5)
learner.validate()
#final_acc = hist.history[VAL_ACC_NAME][-1]
#print('final_accuracy:%s' % (final_acc))
#self.assertGreater(final_acc, 0.97)
final_loss = hist.history['val_loss'][-1]
print('final_loss:%s' % (final_loss))
self.assertLess(final_loss, 0.05)
def __test_ner(self, trn, val, preproc):
self.assertTrue(U.is_iter(trn))
self.assertTrue(U.is_ner(data=trn))
self.assertFalse(U.is_multilabel(trn))
self.assertEqual(U.shape_from_data(trn), (14041, 47))
self.assertFalse(U.ondisk(trn))
self.assertEqual(U.nsamples_from_data(trn), 14041)
self.assertEqual(U.nclasses_from_data(trn), 10)
self.assertEqual(len(U.y_from_data(trn)), 14041)
self.assertFalse(U.bert_data_tuple(trn))
self.assertEqual(
preproc.get_classes(),
[
"<pad>",
"O",
"B-LOC",
"B-PER",
"B-ORG",
"I-PER",
"I-ORG",
"B-MISC",
"I-LOC",
"I-MISC",
],
)
nerseq = preproc.preprocess(["hello world"])
self.assertEqual(len(nerseq), 1)
self.assertEqual(nerseq[0][0][0][0].tolist(), [21010, 100])
def __test_texts_bert(self, trn, val, preproc):
self.assertFalse(U.is_iter(trn))
self.assertEqual(trn[0][0].shape, (4, 10))
self.assertEqual(trn[1].shape, (4, 2))
self.assertEqual(val[0][0].shape, (4, 10))
self.assertEqual(val[1].shape, (4, 2))
self.assertFalse(U.is_multilabel(trn))
self.assertEqual(U.shape_from_data(trn), (4, 10))
self.assertFalse(U.ondisk(trn))
self.assertEqual(U.nsamples_from_data(trn), 4)
self.assertEqual(U.nclasses_from_data(trn), 2)
self.assertEqual(U.y_from_data(trn).shape, (4,2))
self.assertTrue(U.bert_data_tuple(trn))
self.assertEqual(preproc.get_classes(), preproc.get_classes())
self.assertEqual(preproc.preprocess(['hello book'])[0][0][0], 101)
self.assertEqual(preproc.preprocess(['hello book'])[0].shape, (1, 10))
self.assertEqual(preproc.undo(val[0][0][0]), '[CLS] the book is bad . [SEP]')
def __test_texts_standard(self, trn, val, preproc):
self.assertFalse(U.is_iter(trn))
self.assertEqual(trn[0].shape, (4, 10))
self.assertEqual(trn[1].shape, (4, 2))
self.assertEqual(val[0].shape, (4, 10))
self.assertEqual(val[1].shape, (4, 2))
self.assertFalse(U.is_multilabel(trn))
self.assertEqual(U.shape_from_data(trn), (4, 10))
self.assertFalse(U.ondisk(trn))
self.assertEqual(U.nsamples_from_data(trn), 4)
self.assertEqual(U.nclasses_from_data(trn), 2)
self.assertEqual(U.y_from_data(trn).shape, (4,2))
self.assertFalse(U.bert_data_tuple(trn))
self.assertEqual(preproc.get_classes(), preproc.get_classes())
self.assertEqual(preproc.ngram_count(), 3)
self.assertEqual(preproc.preprocess(['hello book'])[0][-1], 1)
self.assertEqual(preproc.preprocess(['hello book']).shape, (1, 10))
self.assertEqual(preproc.undo(val[0][0]), 'the book is bad')
def __test_texts_tfidf(self, trn, val, preproc):
self.assertFalse(U.is_iter(trn))
self.assertEqual(trn[0].shape, (4, 100))
self.assertEqual(trn[1].shape, (4, 2))
self.assertEqual(val[0].shape, (4, 100))
self.assertEqual(val[1].shape, (4, 2))
self.assertFalse(U.is_multilabel(trn))
self.assertEqual(U.shape_from_data(trn), (4, 100))
self.assertFalse(U.ondisk(trn))
self.assertEqual(U.nsamples_from_data(trn), 4)
self.assertEqual(U.nclasses_from_data(trn), 2)
self.assertEqual(U.y_from_data(trn).shape, (4, 2))
self.assertFalse(U.bert_data_tuple(trn))
self.assertEqual(preproc.get_classes(), ['neg', 'pos'])
self.assertEqual(preproc.ngram_count(), 1)
self.assertEqual('%.4f' % (preproc.preprocess(['hello book'])[0][1]),
'0.5878')
self.assertEqual(preproc.preprocess(['hello book']).shape, (1, 100))
self.assertEqual(preproc.undo(val[0][0]), 'book is the bad')
