emocontext-data.py

def preprocessData(dataFilePath, mode):
    conversations = []
    labels = []
    with io.open(dataFilePath, encoding="utf8") as finput:
        finput.readline()
        for line in finput:
            line = line.strip().split('\t')
            for i in range(1, 4):
                line[i] = tokenize(line[i])
            if mode == "train":
                labels.append(emotion2label[line[4]])
            conv = line[1:4]
            conversations.append(conv)
    if mode == "train":
        return np.array(conversations), np.array(labels)
    else:
        return np.array(conversations)

texts_train, labels_train = preprocessData('./starterkitdata/train.txt', mode="train")
texts_dev, labels_dev = preprocessData('./starterkitdata/dev.txt', mode="train")
texts_test, labels_test = preprocessData('./starterkitdata/test.txt', mode="train")