if __name__ == '__main__':
# Create parser
p = Parser()
# Create training dataset
ds = p.create_dataset("en-ud-train-projective.conllu", train=True)
model_file = 'model.pkl'
# model_file = 'model_t800.pkl'
# Train LR model
if os.path.exists(model_file):
# if model exists, load from file
print("Loading existing model...")
lr = pickle.load(open(model_file, 'rb'))
else:
# train model using minibatch GD
lr = LogisticRegression()
lr.fit(*ds.to_arrays())
pickle.dump(lr, open(model_file, 'wb'))
# Create test dataset
test_ds = p.create_dataset("en-ud-dev.conllu")
# Copy feature maps to ensure that test datapoints are encoded in the same way
test_ds.copy_feature_maps(ds)
# Compute move-level accuracy
lr.classify_datapoints(*test_ds.to_arrays())
# Compute UAS and sentence-level accuracy
t = TreeConstructor(p)
t.evaluate(lr, 'en-ud-dev.conllu', ds)
