def __init__(self,
word_embedding,
synonyms_filepath=io_utils.get_synonyms_filepath(),
train_indices=io_utils.train_indices(),
test_indices=io_utils.test_indices(),
words_per_news=25,
bag_size=1,
bags_per_minibatch=50,
callback=None):
super(CNNModel, self).__init__(io=io_utils.NetworkIOProvider(),
word_embedding=word_embedding,
synonyms_filepath=synonyms_filepath,
train_indices=train_indices,
test_indices=test_indices,
bag_size=bag_size,
words_per_news=words_per_news,
bags_per_minibatch=bags_per_minibatch,
callback=callback)
def get_data_indices(self, data_type):
if data_type == DataType.Test:
return io_utils.test_indices()
if data_type == DataType.Train:
return io_utils.train_indices()
news_filepath = root + "art{}.txt".format(n)
opin_filepath = root + "art{}.opin.txt".format(n)
neutral_filepath = root + "art{}.neut.txt".format(n)
print neutral_filepath
entities = EntityCollection.from_file(entity_filepath)
news = News.from_file(news_filepath, entities)
opinions = OpinionCollection.from_file(opin_filepath,
io_utils.get_synonyms_filepath())
neutral_opins = make_neutrals(news, synonyms, opinions)
neutral_opins.save(neutral_filepath)
#
# Test
#
root = io_utils.test_root()
for n in io_utils.test_indices():
entity_filepath = path.join(root, "art{}.ann".format(n))
news_filepath = path.join(root, "art{}.txt".format(n))
neutral_filepath = path.join(root, "art{}.neut.txt".format(n))
print neutral_filepath
entities = EntityCollection.from_file(entity_filepath)
news = News.from_file(news_filepath, entities)
neutral_opins = make_neutrals(news, synonyms)
neutral_opins.save(neutral_filepath)
pcnn_filepath = path.join(output_root, '{}.csv'.format(pcnn_name))
cnn_callback = PandasLoggerCallback(epochs=config.Epochs,
test_on_epochs=config.test_on_epochs,
csv_filepath=cnn_filepath,
model_name=cnn_name)
pcnn_callback = PandasLoggerCallback(epochs=config.Epochs,
test_on_epochs=config.test_on_epochs,
csv_filepath=pcnn_filepath,
model_name=pcnn_name)
return [(CNNModel, cnn_callback),
(PCNNModel, pcnn_callback)]
if __name__ == "__main__":
gpu_memory_fraction = 0.35
config = CNNConfig()
models = compose_all_models(config)
for _ in config.iterate_over_grid():
for tf_model, callback in models:
eval_model(config=config,
callback=callback,
model_type=tf_model,
train_indices=io_utils.train_indices(),
test_indices=io_utils.test_indices(),
gpu_memory_fraction=gpu_memory_fraction)