def main(graph_type="dependency", epochs=25):
root = os.path.join(os.path.dirname(__file__), "../../")
dataset = MultiNLIDataset(root)
if graph_type == "dependency":
graph_builder = DependencyGraph(lang="en")
elif graph_type == "similarity":
graph_builder = SimilarityGraph(lang="en")
else:
graph_builder = StaticGraph(lang="en")
trainer = Trainer(graph_builder, root, log_dir="classifier")
trainer.build()
sequence_length = 25
vocab_size = len(trainer.preprocessor.vocabulary.get())
def preprocessor(x):
_x = trainer.preprocess(x, sequence_length)
values = (_x["text"], _x["graph"])
return values
model = GraphBasedClassifier(vocab_size, sequence_length, lstm=None)
model.build(trainer.num_classes, preprocessor)
metrics = trainer.train(model.model, epochs=epochs)
test_data = dataset.test_data()
y_pred = model.predict(test_data["text"])
print(
classification_report(test_data["label"],
y_pred,
target_names=dataset.labels()))
def main():
root = os.path.join(os.path.dirname(__file__), "../../")
dataset = MultiNLIDataset(root)
trainer = BaselineTrainer(root, log_dir="classifier_baseline")
trainer.build()
sequence_length = 25
vocab_size = len(trainer.preprocessor.vocabulary.get())
def preprocessor(x):
_x = trainer.preprocess(x, sequence_length)
return _x["text"]
model = MergeClassifier(vocab_size)
model.build(trainer.num_classes, preprocessor)
metrics = trainer.train(model.model,
epochs=25,
sequence_length=sequence_length,
representation="GloVe.6B.100d")
test_data = dataset.test_data()
y_pred = model.predict(test_data["text"])
print(
classification_report(test_data["label"],
y_pred,
target_names=dataset.labels()))
def main():
root = os.path.join(os.path.dirname(__file__), "../../")
dataset = MultiNLIDataset(root)
classifier = TfidfClassifier()
train_data = dataset.train_data()
scores = classifier.fit(train_data["text"], train_data["label"])
test_data = dataset.test_data()
y_pred = classifier.predict(test_data["text"])
print(classification_report(test_data["label"], y_pred,
target_names=dataset.labels()))
def num_classes(self):
return len(MultiNLIDataset.labels())