I am trying to find the count of words that occured in a file. I have a text file (TEST.txt
) the content of the file is as follows:
ashwin prog
from collections import Counter;
cnt = Counter ();
for line in open ('TEST.txt', 'r'):
for word in line.split ():
cnt [word] += 1
print cnt
Using a Defaultdict:
from collections import defaultdict
def read_file(fname):
words_dict = defaultdict(int)
fp = open(fname, 'r')
lines = fp.readlines()
words = []
for line in lines:
words += line.split(' ')
for word in words:
words_dict[word] += 1
return words_dict
FILE_NAME = 'file.txt'
wordCounter = {}
with open(FILE_NAME,'r') as fh:
for line in fh:
# Replacing punctuation characters. Making the string to lower.
# The split will spit the line into a list.
word_list = line.replace(',','').replace('\'','').replace('.','').lower().split()
for word in word_list:
# Adding the word into the wordCounter dictionary.
if word not in wordCounter:
wordCounter[word] = 1
else:
# if the word is already in the dictionary update its count.
wordCounter[word] = wordCounter[word] + 1
print('{:15}{:3}'.format('Word','Count'))
print('-' * 18)
# printing the words and its occurrence.
for (word,occurance) in wordCounter.items():
print('{:15}{:3}'.format(word,occurance))
Use the update
method of Counter. Example:
from collections import Counter
data = '''\
ashwin programmer india
amith programmer india'''
c = Counter()
for line in data.splitlines():
c.update(line.split())
print(c)
Output:
Counter({'india': 2, 'programmer': 2, 'amith': 1, 'ashwin': 1})
f = open('input.txt', 'r')
data=f.read().lower()
list1=data.split()
d={}
for i in set(list1):
d[i]=0
for i in list1:
for j in d.keys():
if i==j:
d[i]=d[i]+1
print(d)
You're iterating over every line and calling Counter each time. You want Counter to run over the entire file. Try:
from collections import Counter
with open("TEST.txt", "r") as f:
# Used file context read and save into contents
contents = f.read().split()
print Counter(contents)