# Returns 5 most frequent words in a text
def important_words(an_index, stop_words):
    mydict = index_text(an_index)   # takes the result from index_text function
    all_words = []                  # Create an empty list to put in all words from an_index in
    
    # Tar bort stop_words från text
    for item in stop_words:
        if item in an_index:
            del an_index[item]
    
    # Combine all the words into a single list
    for key in mydict:
        all_words.extend(mydict[key])    
        
        # Count occurrences of each word
    word_counter = {}                    # This dictionary stores words as keys and their respective numbers as values
    for word in all_words:
        if word not in stop_words:       # If the word is a stop-word, it's ignored and not included in word_counter
            if word in word_counter:    
                word_counter[word] += 1  # If the word has already been inserted into the dictionary, it adds to the count by 1
            else:
                word_counter[word] = 1   # If the word isn't already in word_counter, it will be added
                
    sorted_words = sorted(word_counter.items(), key=lambda x: x[1], reverse=True)   # Sorts tuple, x[1] takes the second elements of the tuple (the values).
    # The order of the tuple is reversed, starting with the largest values to the smallest.
    top_words = [word[0] for word in sorted_words[:5]]
    return top_words   # Returns the five most frequent words in the text

text = """This is a text object.
   This object has many words. I will now count
   the words and return most frequent ones, in
   ascending order."""

word_list = [word for word in text.split()]

word_list.sort()

for word in word_list:
    print(word)

text = "i will now count the words and return the most frequent words in ascending order".split()
an_index = list(range(len(text)))

def index_text(index):
    return {text[i]: i for i in index}

    for item in stop_words:
        if item in an_index:
            del an_index[item]

    # Combine all the words into a single list
    for key in mydict:
        all_words.extend(mydict[key])    

            if word in word_counter:    
                word_counter[word] += 1  # If the word has already been inserted into the dictionary, it adds to the count by 1
            else:
                word_counter[word] = 1   # If the word isn't already in word_counter, it will be added

def important_words(an_index, stop_words):
    mydict = index_text(an_index)  # assumes this returns a dictionary {index: [words]}
    all_words = []  # To collect all words from the index

    # Remove stop words from the text
    for key in mydict:
        filtered_words = [word for word in mydict[key] if word not in stop_words]
        all_words.extend(filtered_words)  # Add the filtered words to the list

    # Count occurrences of each word
    word_counter = {}
    for word in all_words:
        word_counter[word] = word_counter.get(word, 0) + 1  # Count the word

    # Sort words by frequency in descending order
    sorted_words = sorted(word_counter.items(), key=lambda x: x[1], reverse=True)
    
    # Get the top 5 frequent words
    top_words = [word[0] for word in sorted_words[:5]]
    return top_words

path2text = '/home/pedro/temp/Frankenstein_Letter_1.txt'

with open(path2text) as f:
    words = f.read()
    # make everything capital letters or The and the will be 2 different words
    words = words.upper()

# find punctuation and numbers
unwanted = []
for w in words:
    if not w.isalpha():
        if not w in unwanted:
            unwanted.append(w)

# unwanted  looks like: ['_', ' ', '.', ',', '\n', '1', '7', '—', '?', ';', '’', '-', '!', ':', "'"]
len(unwanted) # 15

words_list = words.split()
len(words_list) # 1221
for i in range(len(words_list)):
    for u in unwanted:
        if u in words_list[i]:
            words_list[i] = words_list[i].replace(u, '')
    
words_set = set(words_list)
len(words_set) # 586

# a dictionary to hold the count of each word        
words_dict = {w:0 for w in words_set}

# loop through words_list and increase the count for each dictionary key
for word in words_list:
    words_dict[word] +=1

# make a list of (word, count) tuples
tups = [(key, words_dict[key]) for key in words_dict.keys()]
# sort tups by tup[1], the count reversed so the highest count comes first
tups.sort(key=lambda tup: tup[1], reverse=True)
# show the results
for i in range(5):
    print(tups[i])

Output:
('THE', 67)
('I', 46)
('AND', 44)
('MY', 42)
('OF', 36)

import re

# allow for other characters than a-zA-Z   
e = re.compile(r'\b[A-Za-züäÜÄÖöï]+\b')
words_list = e.findall(words)
# carry on from here as above, but no need to lose numbers and punctuation