Python Inverted Index

Question

Problem:

I need to create a Dictionary of inverted indexes where I should tokenize the string, remove the stopwords and extract the word root (stemmer) all using the nltk package. The output of the program must be a dictionary of dictionaries containing the word radicals extracted along with the amounts of times they appear in the sentence.

Doubt:

The stemmer I perform on the sentence returns me only the only appearance of the tokenized word, however I need it to appear every time it is in the sentence.

Example of the current output (need to show 'cas' every time the word 'home' is found):

Another issue:

How to concatenate all dictionaries into a single?

Exit from the program:

Code:

import nltk
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
from nltk.tokenize import RegexpTokenizer

def readBaseFile(fileName):
    with open(fileName, 'r') as fileRead:
        lines = fileRead.read().splitlines()

    fileRead.close()
    
    return lines


def countFrequency(my_list, fileNumber):
    freq = {}

    for key in my_list:
        if (key not in freq):
            freq[key] = {fileNumber:1}
        else:
            freq[key] = {fileNumber:freq[key]+1}

    print(freq)

    return freq

def readLinesInSubfile(linesInBaseFile, fileNumber):
    tokenizeWord = tokenizer.tokenize(linesInBaseFile[0])
    print(tokenizeWord)

    tokenizeWord = {stemmer.stem(word) for word in tokenizeWord if not word in stopwords}

    print(tokenizeWord)

    return countFrequency(tokenizeWord, fileNumber)

def subfilesOfBaseFile(linesInBaseFile, fileNumber):
    linesInSubfiles = {}

    for files in range(len(linesInBaseFile)):
        linesInSubfiles = readBaseFile('base1/'+linesInBaseFile[files])

        dictionary = readLinesInSubfile(linesInSubfiles, fileNumber)

        fileNumber = fileNumber + 1

    return dictionary

stopwords = nltk.corpus.stopwords.words("portuguese")
stemmer = nltk.stem.RSLPStemmer()
tokenizer = nltk.RegexpTokenizer(r"\w+")
def main():
    fileToRead = "base1/base.txt"
    fileNumber = 1

    linesInBaseFile = readBaseFile(fileToRead)
    print(linesInBaseFile)

    subfilesOfBaseFile(linesInBaseFile, fileNumber)

if __name__ == "__main__":
    main()