Created
November 10, 2022 21:39
-
-
Save konverner/552b8b4720ebe56e5768b5174ddf9d97 to your computer and use it in GitHub Desktop.
dataloader from directory
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
class DataLoader: | |
def __init__(self, dir): | |
self.dir = dir | |
self.filenames = [filename for filename in os.listdir(dir)] | |
self.index = -1 | |
self.size = len(self.filenames) | |
def __iter__(self): | |
return self | |
def __next__(self): | |
self.index += 1 | |
if self.index < self.size: | |
with open(self.dir + self.filenames[self.index], 'r') as f: | |
tokenized_text = f.read().split() | |
return tokenized_text | |
self.index = -1 | |
raise StopIteration |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment