lib/exercises-in-programming-style
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Minor improvements to candy factory

Browse Source
This commit is contained in:
Crista Lopes
2013-11-18 16:10:32 -08:00
parent 189fbe305b
commit 5264099a59
1 changed files with 7 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
06-candy-factory/tf-06.py
View File

@@ -1,5 +1,4 @@
#!/usr/bin/env python #!/usr/bin/env python
import sys, re, operator, string import sys, re, operator, string
# #
@@ -10,24 +9,17 @@ def read_file(path_to_file):
Takes a path to a file and returns the entire Takes a path to a file and returns the entire
contents of the file as a string contents of the file as a string
""" """
f = open(path_to_file) with open(path_to_file) as f:
data = f.read() data = f.read()
f.close()
return data return data
def filter_chars(str_data): def filter_chars_and_normalize(str_data):
""" """
Takes a string and returns a copy with all nonalphanumeric Takes a string and returns a copy with all nonalphanumeric
chars replaced by white space chars replaced by white space
""" """
pattern = re.compile('[\W_]+') pattern = re.compile('[\W_]+')
return pattern.sub(' ', str_data) return pattern.sub(' ', str_data).lower()
def normalize(str_data):
"""
Takes a string and returns a copy with all chars in lower case
"""
return str_data.lower()
def scan(str_data): def scan(str_data):
""" """
@@ -41,9 +33,8 @@ def remove_stop_words(word_list):
Takes a list of words and returns a copy with all stop Takes a list of words and returns a copy with all stop
words removed words removed
""" """
f = open('../stop_words.txt') with open('../stop_words.txt') as f:
stop_words = f.read().split(',') stop_words = f.read().split(',')
f.close()
# add single-letter words # add single-letter words
stop_words.extend(list(string.ascii_lowercase)) stop_words.extend(list(string.ascii_lowercase))
return [w for w in word_list if not w in stop_words] return [w for w in word_list if not w in stop_words]
@@ -69,11 +60,10 @@ def sort(word_freq):
""" """
return sorted(word_freq.iteritems(), key=operator.itemgetter(1), reverse=True) return sorted(word_freq.iteritems(), key=operator.itemgetter(1), reverse=True)
# #
# The main function # The main function
# #
word_freqs = sort(frequencies(remove_stop_words(scan(normalize(filter_chars(read_file(sys.argv[1]))))))) word_freqs = sort(frequencies(remove_stop_words(scan(filter_chars_and_normalize(read_file(sys.argv[1]))))))
for tf in word_freqs[0:25]: for tf in word_freqs[0:25]:
print tf[0], ' - ', tf[1] print tf[0], ' - ', tf[1]