Created
April 9, 2019 13:04
-
-
Save prajwal-stha/9749929e48230087c10d6bb4da1233f3 to your computer and use it in GitHub Desktop.
Reducer File
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
#!/usr/bin/python | |
import sys | |
from operator import itemgetter | |
# using a dictionary to map words to their counts | |
current_word = None | |
current_count = 0 | |
word = None | |
# input comes from STDIN | |
for line in sys.stdin: | |
line = line.strip() | |
word, count = line.split('\t', 1) | |
try: | |
count = int(count) | |
except ValueError: | |
continue | |
if current_word == word: | |
current_count += count | |
else: | |
if current_word: | |
print '%s\t%s' % (current_word, current_count) | |
current_count = count | |
current_word = word | |
if current_word == word: | |
print '%s\t%s' % (current_word, current_count) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment