Counting word frequency in a text with Python: Difference between revisions
(New page: Exercise to produce a "word cloud" based on frequency of words in a text.) |
No edit summary |
||
Line 1: | Line 1: | ||
<source lang="python"> | |||
import string | |||
wd = {} | |||
# for every line, every word in line, add it to the dictionary | |||
for line in open("text.txt"): | |||
for word in line.split(): | |||
word = word.strip(string.punctuation).lower() | |||
# wd[word] = True | |||
wd[word] = wd.get(word, 0) + 1 # for word counting | |||
# get the dictionary keys, and alphabetize | |||
allwords = wd.keys() | |||
allwords.sort() | |||
for word in allwords: | |||
# print w | |||
print word, wd[word] | |||
</source> |
Revision as of 14:52, 17 February 2009
import string
wd = {}
# for every line, every word in line, add it to the dictionary
for line in open("text.txt"):
for word in line.split():
word = word.strip(string.punctuation).lower()
# wd[word] = True
wd[word] = wd.get(word, 0) + 1 # for word counting
# get the dictionary keys, and alphabetize
allwords = wd.keys()
allwords.sort()
for word in allwords:
# print w
print word, wd[word]