def test_explain(self):
model = Classifier(**self.default_config())
train_sample = self.dataset.sample(n=self.n_sample)
valid_sample = self.dataset.sample(n=self.n_sample)
model.fit(train_sample.Text, train_sample.Target)
explanations = model.explain(valid_sample.Text)
normal_predictions = model.predict(valid_sample.Text)
explanation_preds = [e["prediction"] for e in explanations]
# check that the process of turning on explain does not change the preds
self.assertEqual(explanation_preds, list(normal_predictions))
self.assertEqual(len(explanation_preds), len(train_sample.Text))
self.assertEqual(type(explanations[0]["token_ends"]), list)
self.assertEqual(type(explanations[0]["token_starts"]), list)
self.assertEqual(type(explanations[0]["explanation"]), dict)
self.assertEqual(len(explanations[0]["token_starts"]), len(explanations[0]["explanation"][0]))
self.assertEqual(len(explanations[0]["token_ends"]), len(explanations[0]["explanation"][0]))
dataset = StanfordSentimentTreebank(nrows=1000).dataframe
model = Classifier(interpolate_pos_embed=False,
n_epochs=1,
batch_size=2,
lr_warmup=0.1,
val_size=0.0,
max_length=64,
prefit_init=False,
base_model=GPTModel)
trainX, testX, trainY, testY = train_test_split(dataset.Text.values,
dataset.Target.values,
test_size=0.3,
random_state=42)
model.fit(trainX, trainY)
samples = model.explain(testX)
words = []
probs = []
clfs = []
for sample, text in zip(samples, testX):
sample_words = []
sample_probs = []
for s, e, p in zip(sample["token_starts"], sample["token_ends"],
sample['explanation'][1]):
sample_words.append(text[s:e])
sample_probs.append(p)
print(list(zip(sample_words, sample_probs)), text)
words.append(sample_words)
probs.append(sample_probs)
clfs.append(sample["prediction"])
