def train():
print('Loading amr data')
paragraphs = generate_paragraphs('amr.txt', k=5)
print('%d total cleaned paragraphs' % len(paragraphs))
print('Training Subgraph Selection Scorer')
train_instances, train_labels = gen_subgraph_data(paragraphs)
subgraph_scorer = SubgraphSelectionScorer()
subgraph_scorer.train(train_instances, train_labels, update_cache=True)
print('Training Order Scorer')
train_instances, train_labels, train_weights = gen_order_data(paragraphs)
order_scorer = OrderScorer()
order_scorer.train(train_instances, train_labels, train_weights)
print('Training Pipeline Scorer')
pipeline_scorer = PipelineScorer()
subgraph_optimizer = SubgraphOptimizer(subgraph_scorer)
order_optimizer = OrderOptimizer(order_scorer)
pipeline_scorer.train(subgraph_optimizer, order_optimizer)
if __name__ == "__main__":
from scorer import OrderScorer
from optimizer import OrderAnnealer as Orderer
train = generate_paragraphs("amr.txt", limit=500, k=5)
examples, labels = add_negative_examples(train, 20)
n = len(examples)
weights = n - np.bincount(labels)
features = np.array([get_features(e.paragraph_graph(), e.sentence_graphs()) for e in examples])
scorer = OrderScorer()
# reg = lm.LogisticRegression()
print("learning")
scorer.train(features, labels, sample_weight=[weights[i] for i in labels])
# reg.fit(features, labels)
print("done")
test = generate_paragraphs("amr_test.txt", limit=50, k=5)
good_tests = []
for t in test:
try:
t.sentence_graphs()
good_tests.append(t)
except ValueError as e:
print(e)
continue
goodness = []
for t in good_tests:
first_order = np.arange(len(t.sentence_graphs()))
np.random.shuffle(first_order)
