frequency_words = {}
def sort_words(desc=False):
words = [(word, count) for word, count in frequency_words.items()]
return sorted(words, key=lambda s: s[1], reverse=desc)
def frequency_word_count(words):
for word in words:
if word != '':
if word.lower() in frequency_words:
frequency_words[word.lower()] += 1
else:
frequency_words[word.lower()] = 1
with open('info.txt') as f:
count = 0
for line in f:
print("line {}: {}".format(count + 1, line))
frequency_word_count(line.strip().split(' '))
count += 1
sorted_words = sort_words(desc=True)
print("Most frequent 12 words {}".format(sorted_words[:12]))
'''
run:
line 1: Python is an interpreted
line 2: high-level, general-purpose
line 3: programming language
line 4: python design philosophy emphasizes code readability
line 5: with its notable use of significant whitespace
line 6: python java java c++ c php nodejs c++ c++ c++
Most frequent 12 words [('c++', 4), ('python', 3), ('java', 2), ('is', 1),
('an', 1), ('interpreted', 1), ('high-level,', 1),
('general-purpose', 1), ('programming', 1),
('language', 1), ('design', 1), ('philosophy', 1)]
'''
