Finish the last commit
This commit is contained in:
@@ -1,4 +1,5 @@
|
|||||||
#!/usr/bin/env python
|
#!/usr/bin/env python
|
||||||
|
|
||||||
import sys, re, operator, string
|
import sys, re, operator, string
|
||||||
from threading import Thread
|
from threading import Thread
|
||||||
from queue import Queue
|
from queue import Queue
|
||||||
@@ -113,7 +114,7 @@ class WordFrequencyController(ActiveWFObject):
|
|||||||
def _display(self, message):
|
def _display(self, message):
|
||||||
word_freqs = message[0]
|
word_freqs = message[0]
|
||||||
for (w, f) in word_freqs[0:25]:
|
for (w, f) in word_freqs[0:25]:
|
||||||
print(w, ' - ', f)
|
print(w, '-', f)
|
||||||
send(self._storage_manager, ['die'])
|
send(self._storage_manager, ['die'])
|
||||||
self._stopMe = True
|
self._stopMe = True
|
||||||
|
|
||||||
|
|||||||
@@ -1,13 +1,6 @@
|
|||||||
#!/usr/bin/env python
|
#!/usr/bin/env python
|
||||||
import sys, re, operator, string
|
import sys, re, operator, string
|
||||||
from functools import reduce
|
from functools import reduce
|
||||||
|
|
||||||
try:
|
|
||||||
xrange # Python 2
|
|
||||||
except NameError:
|
|
||||||
xrange = range # Python 3
|
|
||||||
|
|
||||||
|
|
||||||
#
|
#
|
||||||
# Functions for map reduce
|
# Functions for map reduce
|
||||||
#
|
#
|
||||||
@@ -17,7 +10,7 @@ def partition(data_str, nlines):
|
|||||||
into chunks of nlines.
|
into chunks of nlines.
|
||||||
"""
|
"""
|
||||||
lines = data_str.split('\n')
|
lines = data_str.split('\n')
|
||||||
for i in xrange(0, len(lines), nlines):
|
for i in range(0, len(lines), nlines):
|
||||||
yield '\n'.join(lines[i:i+nlines])
|
yield '\n'.join(lines[i:i+nlines])
|
||||||
|
|
||||||
def split_words(data_str):
|
def split_words(data_str):
|
||||||
@@ -77,4 +70,4 @@ splits = map(split_words, partition(read_file(sys.argv[1]), 200))
|
|||||||
word_freqs = sort(reduce(count_words, splits))
|
word_freqs = sort(reduce(count_words, splits))
|
||||||
|
|
||||||
for (w, c) in word_freqs[0:25]:
|
for (w, c) in word_freqs[0:25]:
|
||||||
print(w, ' - ', c)
|
print(w, '-', c)
|
||||||
|
|||||||
@@ -1,13 +1,6 @@
|
|||||||
#!/usr/bin/env python
|
#!/usr/bin/env python
|
||||||
import sys, re, operator, string
|
import sys, re, operator, string
|
||||||
from functools import reduce
|
from functools import reduce
|
||||||
|
|
||||||
try:
|
|
||||||
xrange # Python 2
|
|
||||||
except NameError:
|
|
||||||
xrange = range # Python 3
|
|
||||||
|
|
||||||
|
|
||||||
#
|
#
|
||||||
# Functions for map reduce
|
# Functions for map reduce
|
||||||
#
|
#
|
||||||
@@ -17,7 +10,7 @@ def partition(data_str, nlines):
|
|||||||
into chunks of nlines.
|
into chunks of nlines.
|
||||||
"""
|
"""
|
||||||
lines = data_str.split('\n')
|
lines = data_str.split('\n')
|
||||||
for i in xrange(0, len(lines), nlines):
|
for i in range(0, len(lines), nlines):
|
||||||
yield '\n'.join(lines[i:i+nlines])
|
yield '\n'.join(lines[i:i+nlines])
|
||||||
|
|
||||||
def split_words(data_str):
|
def split_words(data_str):
|
||||||
@@ -94,4 +87,4 @@ splits_per_word = regroup(splits)
|
|||||||
word_freqs = sort(map(count_words, splits_per_word.items()))
|
word_freqs = sort(map(count_words, splits_per_word.items()))
|
||||||
|
|
||||||
for (w, c) in word_freqs[0:25]:
|
for (w, c) in word_freqs[0:25]:
|
||||||
print(w, ' - ', c)
|
print(w, '-', c)
|
||||||
|
|||||||
Reference in New Issue
Block a user