Created
August 1, 2019 12:30
-
-
Save sismetanin/2ada2f8d8c2e3fc7177dd9c285a3ddef to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment