1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22

import re

def getWordFrequencies(text):
    frequencies = {}
    
    for c in re.split('\W+', text):
        frequencies[c] = (frequencies[c] if frequencies.has_key(c) else 0) + 1
            
    return frequencies


mamaMia = \
"Mamma mia, here I go again\
Mamma mia, here I go again\
My my, how can I resist you?\
Mamma mia, does it show again?\
My my, just how much I've missed you"

result = getWordFrequencies(mamaMia)

for word, freq in result.iteritems():
    print freq, "\t", word

1
2
3
4
5
6
7
8
9

mamaMia = "Mamma mia, here I go again\
 Mamma mia, here I go again\
 My my, how can I resist you?\
 Mamma mia, does it show again?\
 My my, just how much I've missed you"

adict = {}
for w in mamaMia.split(): adict.update( { w : mamaMia.count(w) } ) 
print adict

1
2

// s is the string to check occurances of.
alert(s.split("YourWord").length - 1);

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18

import re
from collections import defaultdict

text = """
Mamma mia, here I go again
Mamma mia, here I go again
My my, how can I resist you?
Mamma mia, does it show again?
My my, just how much I've missed you
""".strip()

histogram = defaultdict(int)
for word in re.split("\W+", text):
	histogram[word.lower()] += 1

template = "%-" + str(max(len(word) for word in histogram.keys())) + "s  %s"
print "\n".join(template % (word, freq) for word, freq in 
				sorted(histogram.items(), key=lambda x:x[1], reverse=True))