COSC - Project 02

%run -i word_count.py

print(process_word('Test!'))
print(process_word('WHAT?:?:?'))
print(process_word(':_(:;hEl\'lo,)123'))

print(process_line('This is a test string". It\'s fifty-eight characters long!'))

words = (process_file("tale_of_two_cities.txt"))
print("There are {} words contained in the file.".format(len(words)))

print(words[:20])

unique = find_unique(words)
print('There are {} unique words contained in the file.' .format(len(unique)))

words_list = ['random'] * 210
words_list = words_list + ['letters'] * 25 + ['love'] * 479 + ['meditation'] * 999 + ['extras'] * 1234 + ['travel'] * 679 + ['explore'] * 358

words_freq_dict = find_frequency(words_list)   #here you need to use words.

words_100_1000 = []

for word, count in words_freq_dict.items():
    if count >= 100 and count < 1000:
        words_100_1000.append(word)

final_list_four_strings = words_100_1000[:4]

for word in final_list_four_strings:
    print(f'The word "{word}" appears {words_freq_dict[word]} times in the file.')

most_common(words_freq_dict,20)   

stop = (process_file('stopwords.txt'))
print('There are {} words in our list of stop words.'.format(len(stop)))

print(stop[:50])

words_ns = remove_stop(words,stop)
unique_ns = remove_stop(words,stop)
print('There are {} non-stop words contained in the file.'.format(len(words_ns)))
print('There are {} unique non-stop words contained in the file'.format(len(unique_ns)))

print(stop[:50])

words_ns = find_frequency(words)
most_common(words_ns,20)

count_by_length(words)

words = (process_file("tale_of_two_cities.txt"))
sorted(words, key=len, reverse=True)

count_by_first(words)