Avoid creating word_freqs outside and passing it around.

This commit is contained in:
Matías
2014-01-24 21:11:38 -08:00
parent 0ffe4b3fd6
commit e2a8d8f017

View File

@@ -4,49 +4,54 @@ import sys, re, operator, string
#
# The functions
#
def read_file(path_to_file, word_freqs, func):
def read_file(path_to_file, func):
with open(path_to_file) as f:
data = f.read()
func(data, word_freqs, normalize)
func(data, normalize)
def filter_chars(str_data, word_freqs, func):
def filter_chars(str_data, func):
pattern = re.compile('[\W_]+')
func(pattern.sub(' ', str_data), word_freqs, scan)
func(pattern.sub(' ', str_data), scan)
def normalize(str_data, word_freqs, func):
func(str_data.lower(), word_freqs, remove_stop_words)
def normalize(str_data, func):
func(str_data.lower(), remove_stop_words)
def scan(str_data, word_freqs, func):
func(str_data.split(), word_freqs, frequencies)
def scan(str_data, func):
func(str_data.split(), frequencies)
def remove_stop_words(word_list, word_freqs, func):
def remove_stop_words(word_list, func):
with open('../stop_words.txt') as f:
stop_words = f.read().split(',')
# add single-letter words
stop_words.extend(list(string.ascii_lowercase))
func([w for w in word_list if not w in stop_words], word_freqs, sort)
func([w for w in word_list if not w in stop_words], sort)
def frequencies(word_list, word_freqs, func):
def frequencies(word_list, func):
wf = {}
for w in word_list:
if w in wf:
wf[w] += 1
else:
wf[w] = 1
func(wf, word_freqs, no_op)
func(wf, format)
def sort(wf, word_freqs, func):
word_freqs.extend(func(sorted(wf.iteritems(), key=operator.itemgetter(1), reverse=True), None))
def sort(wf, func):
func(sorted(wf.iteritems(), key=operator.itemgetter(1), reverse=True), print_all)
def no_op(a, func):
return a
def no_op(func):
return
def format(word_freqs, func):
text = ""
for (w, c) in word_freqs[0:25]:
text = text + w + ' - ' + str(c) + '\n'
func(text, no_op)
def print_all(text, func):
print text
func(None)
#
# The main function
#
word_freqs = []
read_file(sys.argv[1], word_freqs, filter_chars)
for (w, c) in word_freqs[0:25]:
print w, ' - ', c
read_file(sys.argv[1], filter_chars)