Created
July 16, 2016 04:54
-
-
Save zhoufeng1989/f084ca41ba6189505f5ab4b4d7accf4c to your computer and use it in GitHub Desktop.
This file contains hidden or 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
| import requests | |
| def get_content(url): | |
| response = requests.get(url, stream=True) | |
| for index, line in enumerate(response.iter_lines()): | |
| if index == 0: | |
| continue | |
| yield line | |
| def find_smaller(items, rating): | |
| for index, item in enumerate(items): | |
| if item[2] < rating: | |
| return index | |
| return None | |
| def filter_stream(stream): | |
| for line in stream: | |
| try: | |
| _id, running_time, rating = line.split(",") | |
| t = (int(_id), float(running_time), float(rating)) | |
| yield t | |
| except: | |
| pass | |
| def topN(stream, top=10): | |
| items = [(-1, 0, 0)] * top | |
| for item in filter_stream(stream): | |
| index = find_smaller(items, item[2]) | |
| if index is not None: | |
| items[index] = item | |
| sorted_items = sorted(items, key=lambda item: item[2], reverse=True) | |
| return map(lambda item: (item[0], item[2]), sorted_items) | |
| if __name__ == "__main__": | |
| url = 'https://gist.githubusercontent.com/tyrchen/32c50aadca48aee3da10a77a18479517/raw/7da00efd07b31ba8263611c42ec34fefdf2be2fd/movies.csv' | |
| data = get_content(url) | |
| print topN(data) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment