plt.bar([a for a, b in wrong_np_num_l], [b for a, b in wrong_np_num_l])
plt.title('Wrong NP Num', fontsize=10)
plt.subplot(2, 3, 4)
plt.bar([a for a, b in np_dis_l], [b for a, b in np_dis_l])
plt.title('NP Dis', fontsize=10)
plt.subplot(2, 3, 5)
plt.bar([a for a, b in correct_np_dis_l], [b for a, b in correct_np_dis_l])
plt.title('Correct NP Dis', fontsize=10)
plt.subplot(2, 3, 6)
plt.bar([a for a, b in wrong_np_dis_l], [b for a, b in wrong_np_dis_l])
plt.title('Wrong NP Dis', fontsize=10)
plt.savefig('results/data_analysis.png')
if __name__ == '__main__':
# build data from raw OntoNotes data
print 'Processing'
generate_vector_data()
generate_input_data()
# split training data into dev and train, saved in ./data/train_data
print 'Dividing'
train_generator = DataGenerator("train", args.batch_size)
train_generator.devide()
save_f = file("./data/train_data", 'wb')
cPickle.dump(train_generator, save_f, protocol=cPickle.HIGHEST_PROTOCOL)
save_f.close()
print 'Analysing'
analysis_data(train_generator)
