Difference between revisions of "Guinea Pig"
From Cohen Courses
Jump to navigationJump to searchLine 7: | Line 7: | ||
code: | code: | ||
− | + | <pre> | |
− | + | # always start like this | |
− | + | from gp import * | |
+ | import sys | ||
− | + | # supporting routines can go here | |
− | + | def tokens(line): | |
− | + | for tok in line.split(): | |
− | + | yield tok.lower() | |
− | + | #always subclass Planner | |
− | + | class WordCount(Planner): | |
− | + | wc = ReadLines('corpus.txt') | FlattenBy(by=tokens) | Group(by=lambda x:x, reducingWith=ReduceToCount()) | |
− | + | # always end like this | |
− | + | if __name__ == "__main__": | |
− | + | WordCount().main(sys.argv) | |
+ | </pre> |
Revision as of 15:13, 9 May 2014
Quick Start
Running wordcount.py
Set up a directory that contains the file gp.py
and a
second script called wordcount.py
which contains this
code:
# always start like this from gp import * import sys # supporting routines can go here def tokens(line): for tok in line.split(): yield tok.lower() #always subclass Planner class WordCount(Planner): wc = ReadLines('corpus.txt') | FlattenBy(by=tokens) | Group(by=lambda x:x, reducingWith=ReduceToCount()) # always end like this if __name__ == "__main__": WordCount().main(sys.argv)