def load2_data_and_labels():
"""
Loads MR polarity data from files, splits the data into words and generates labels.
Returns split sentences and labels.
"""
# Load data from files
positive_examples = list(
open("./rt-polaritydata/rt-polarity.pos", "r").readlines())
positive_examples = [s.strip() for s in positive_examples]
negative_examples = list(
open("./rt-polaritydata/rt-polarity.neg", "r").readlines())
negative_examples = [s.strip() for s in negative_examples]
# Split by words
x_text = positive_examples + negative_examples
x_text = [clean_str(sent) for sent in x_text]
max_document_length = max([len(x.split(" ")) for x in x_text])
x = np.ndarray(shape=(len(x_text), max_document_length,
word_embedding_size),
dtype=np.float32)
for i in range(len(x_text)):
x[i] = util.getSentence_matrix(x_text[i], max_document_length)
# Generate labels
positive_labels = [0 for _ in positive_examples]
negative_labels = [1 for _ in negative_examples]
y = np.concatenate([positive_labels, negative_labels], 0)
return [x, y]
def load_test_data():
semeval_data = SemEval_test_data()
Train_Size = len(semeval_data)
train_data = numpy.ndarray(shape=(Train_Size,MAX_DOCUMENT_LENGTH,word_embedding_size),dtype=numpy.float32)
train_label = numpy.ndarray(shape=(Train_Size,num_classes),dtype=numpy.float32)
i = 0
for one in semeval_data:
sentence = one[0]
train_data[i]=util.getSentence_matrix(sentence,MAX_DOCUMENT_LENGTH)
train_label[i]=getLabelVector(one[3],num_class=num_classes)
i+=1
return train_data,train_label