def test():
print('Loading amr data')
paragraphs = generate_paragraphs('amr_test.txt', k=5)
print('%d total cleaned paragraphs' % len(paragraphs))
paragraphs = paragraphs
print('Testing Subgraph Selection Scorer')
test_instances, test_labels = gen_subgraph_data(paragraphs, k=1)
subgraph_scorer = SubgraphSelectionScorer()
subgraph_scorer.load()
subgraph_scorer.test(test_instances, test_labels)
print('Testing Order Scorer')
test_instances, test_labels, test_weights = gen_order_data(paragraphs)
order_scorer = OrderScorer()
order_scorer.load()
order_scorer.test(test_instances, test_labels)
print('Testing Pipeline Scorer')
pipeline_scorer = PipelineScorer()
pipeline_scorer.load()
baseline_graphs = pipeline_scorer.test(paragraphs, subgraph_strategy='baseline', order_strategy='baseline', processes=3)
greedy_graphs = pipeline_scorer.test(paragraphs, subgraph_strategy='greedy', order_strategy='greedy', processes=3)
anneal_graphs = pipeline_scorer.test(paragraphs, subgraph_strategy='greedy', order_strategy='anneal', processes=3)
pickle.dump(baseline_graphs, open('baseline_graphs.pickle', 'wb'))
pickle.dump(greedy_graphs, open('greedy_graphs.pickle', 'wb'))
pickle.dump(anneal_graphs, open('anneal_graphs.pickle', 'wb'))
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)
features.append(len(partition.root_partitioning) ** 2)
# mean, min, max, std_dev of #of fragments per partition
features += summary_statistics([len(s) for s in partition.root_partitioning])
# mean, min, max, std_dev of subgraph similarity for every pair of subgraphs (including a subgraph with itself)
features += summary_statistics([subgraph_similarity(partition.get_subgraph(s1), partition.get_subgraph(s2)) for s1, s2 in list(itertools.combinations(partition.root_partitioning, 2)) + [(s,s) for s in partition.root_partitioning]])
# mean, min, max, std_dev of verb overlap for every pair of subgraphs (including a subgraph with itself)
features += summary_statistics([len(partition.get_subgraph(s1).get_verbs() & partition.get_subgraph(s2).get_verbs()) for s1, s2 in list(itertools.combinations(partition.root_partitioning, 2)) + [(s,s) for s in partition.root_partitioning]])
return features
if __name__ == '__main__':
train_instances, train_labels, test_instances, test_labels, test = generate_train_test(use_cache=True)
scorer = SubgraphSelectionScorer()
scorer.train(train_instances, train_labels)
scorer.test(test_instances, test_labels)
for t in test:
try:
optimizer = SubgraphOptimizer(scorer)
final_state = optimizer.optimize(t)
except ValueError:
continue
print(final_state)
'''
final_partition = final_state.partition
dummy_ordering = list(final_partition.root_partitioning)