Deleted unneeded comments and checks
This commit is contained in:
@@ -26,4 +26,4 @@ Possible names:
|
||||
|
||||
- No commitment
|
||||
- Plugins
|
||||
- Why one when we can have many?
|
||||
- Dependency injection
|
||||
|
||||
@@ -1,13 +1,6 @@
|
||||
import operator
|
||||
|
||||
def top25(word_list):
|
||||
"""
|
||||
Takes a list of words and returns a dictionary associating
|
||||
words with frequencies of occurrence
|
||||
"""
|
||||
if type(word_list) is not list or word_list == []:
|
||||
return {}
|
||||
|
||||
word_freqs = {}
|
||||
for w in word_list:
|
||||
if w in word_freqs:
|
||||
|
||||
@@ -1,10 +1,6 @@
|
||||
import operator, collections
|
||||
|
||||
def top25(word_list):
|
||||
"""
|
||||
Takes a list of words and returns a dictionary associating
|
||||
words with frequencies of occurrence
|
||||
"""
|
||||
counts = collections.Counter(w for w in word_list)
|
||||
return counts.most_common(25)
|
||||
|
||||
|
||||
@@ -1,31 +1,13 @@
|
||||
import sys, re, string
|
||||
|
||||
def extract_words(path_to_file):
|
||||
"""
|
||||
Takes a path to a file and returns the non-stop
|
||||
words, after properly removing nonalphanumeric chars
|
||||
and normalizing for lower case
|
||||
"""
|
||||
if type(path_to_file) is not str or not path_to_file:
|
||||
return []
|
||||
|
||||
try:
|
||||
with open(path_to_file) as f:
|
||||
str_data = f.read()
|
||||
except IOError as e:
|
||||
print "I/O error({0}) when opening {1}: {2}".format(e.errno, path_to_file, e.strerror)
|
||||
return []
|
||||
|
||||
with open(path_to_file) as f:
|
||||
str_data = f.read()
|
||||
pattern = re.compile('[\W_]+')
|
||||
word_list = pattern.sub(' ', str_data).lower().split()
|
||||
|
||||
try:
|
||||
with open('../stop_words.txt') as f:
|
||||
stop_words = f.read().split(',')
|
||||
except IOError as e:
|
||||
print "I/O error({0}) when opening ../stops_words.txt: {1}".format(e.errno, e.strerror)
|
||||
return []
|
||||
|
||||
with open('../stop_words.txt') as f:
|
||||
stop_words = f.read().split(',')
|
||||
stop_words.extend(list(string.ascii_lowercase))
|
||||
return [w for w in word_list if not w in stop_words]
|
||||
|
||||
|
||||
@@ -1,11 +1,6 @@
|
||||
import sys, re, string
|
||||
|
||||
def extract_words(path_to_file):
|
||||
"""
|
||||
Takes a path to a file and returns the non-stop
|
||||
words, after properly removing nonalphanumeric chars
|
||||
and normalizing for lower case
|
||||
"""
|
||||
words = re.findall('[a-z]{2,}', open(path_to_file).read().lower())
|
||||
stopwords = set(open('../stop_words.txt').read().split(','))
|
||||
return [w for w in words if w not in stopwords]
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
import sys, ConfigParser, imp
|
||||
|
||||
def load_plugins():
|
||||
@@ -11,13 +10,9 @@ def load_plugins():
|
||||
tfwords = imp.load_compiled('tfwords', words_plugin)
|
||||
tffreqs = imp.load_compiled('tffreqs', frequencies_plugin)
|
||||
|
||||
#
|
||||
# The main function
|
||||
#
|
||||
|
||||
load_plugins()
|
||||
word_freqs = tffreqs.top25(tfwords.extract_words(sys.argv[1]))
|
||||
|
||||
for tf in word_freqs:
|
||||
print tf[0], ' - ', tf[1]
|
||||
for (w, c) in word_freqs:
|
||||
print w, ' - ', c
|
||||
|
||||
|
||||
Reference in New Issue
Block a user