# Stanford Sentiment Treebank Experiment
# You should run python prepare.py in the data/stanford direction firstly
total_data_file = 'data/stanford/total.data'
total_sentences = LineSentence(total_data_file, repeat=5)

train_data_file = 'data/stanford/train2.data'
train_label_file = 'data/stanford/train2.label'
train_sentences = LineSentence(train_data_file)
train_labels = numpy.fromfile(train_label_file, sep='\n', dtype=numpy.int32)

dev_data_file = 'data/stanford/dev2.data'
dev_label_file = 'data/stanford/dev2.label'
dev_sentences = LineSentence(dev_data_file)
dev_labels = numpy.fromfile(dev_label_file, sep='\n', dtype=numpy.int32)

test_data_file = 'data/stanford/test2.data'
test_label_file = 'data/stanford/test2.label'
test_sentences = LineSentence(test_data_file)
test_labels = numpy.fromfile(test_label_file, sep='\n', dtype=numpy.int32)

# n_filters=[6,14] in the paper
# n_filters=[4,6] in LeNet
# But you can go deeper
model = DCNNDeep(sentences=train_sentences, output_layer_size=2, wordvec_dim=48, 
                 alpha=0.012, entropy_descent_m=0.995, dropout_rate_in_hiddens=0.5, 
                 dropout_rate_in_input=0.2, min_count=2, full_con_layer_size=5, 
                 filter_width=[7,5,3], k_top=4, n_filters=[6,14,6], alpha_m=0.999995, 
                 min_alpha=0.00001, pre_train_word_vec=True, pre_train_sentences=total_sentences)
model.train(train_sentences=train_sentences, train_labels=train_labels, patience=5, 
            validate_freq=2000, max_entropy_allowed=0.38, validate_sentences=dev_sentences, 
            validate_labels=dev_labels, chunksize=5)
print 'test accuracy: %f' %model.accuracy(test_sentences, test_labels)