bee-san

function inverseDocumentFrequency(documents){
    // calculates the inverse document frequency of every sentence
    const words_without_stopwords = prettify(documents);
    const sentences = documents.split(".")
    sentences[0] = sentences[0].substring(146);
    const lengthOfDocuments = sentences.length;

    const WordCountDocuments = countWords(words_without_stopwords);
    // calculate TF values of all documents

bee-san

function inverseDocumentFrequency(document){
    // calculates the inverse document frequency of every sentence
    const words_without_stopwords = prettify(document);
    const unique_words_set = uniqueWords(words_without_stopwords);

    const sentences = document.split(".").map(item => item.trim());
    sentences[0] = sentences[0].substring(146);

    const lengthOfDocuments = sentences.length;
    // prettifys each sentence so it doesn't have stopwords

bee-san

function termFrequency(document){
    // calculates term frequency of each sentence
    words_without_stopwords = prettify(document);
    
    // gets rid of trailing spaces
    const sentences = document.split(".").map(item => item.trim());
    sentences[0] = sentences[0].substring(146);

    const TFVals = countWords(words_without_stopwords)
    const unique_words = uniqueWords(words_without_stopwords);

bee-san

function termFrequency(document){
    // calculates term frequency of each sentence
    words_without_stopwords = prettify(document);
    
    // gets rid of trailing spaces
    const sentences = document.split(".").map(item => item.trim());
    sentences[0] = sentences[0].substring(146);

    const TFVals = countWords(words_without_stopwords)
    const unique_words = uniqueWords(words_without_stopwords);

bee-san

function uniqueWords(words){
    const unique_words_set = new Set(words);
    return unique_words = Array.from(unique_words_set);
}

bee-san

function countWords(words){
    // returns a dictionary of {WORD: COUNT} where count is
    // how many times that word appears in "words".
    const unique_words = uniqueWords(words);
    let dict = {};
    // for every single unique word
    for (let i = 0; i <= unique_words.length - 1; i++){
        dict[unique_words[i]] = 0
        // see how many times this unique word appears in all words
        for (let x = 0; x <= words_without_stopwords.length -1; x++){

bee-san

function prettify(document){
    // Turns an array of words into lowercase and removes stopwords
    const stopwords = ["a", "share", "linkthese", "about", "above", "after", "again", "against", "all", "am", "an", "and", "any","", "are","aren't","as","at","be","because","been","before","being","below","between","both","but","by","can't","cannot","could","couldn't","did","didn't","do","does","doesn't","doing","don't","down","during","each","few","for","from","further","had","hadn't","has","hasn't","have","haven't","having","he","he'd","he'll","he's","her","here","here's","hers","herself","him","himself","his","how","how's","i","i'd","i'll","i'm","i've","if","in","into","is","isn't","it","it's","its","itself","let's","me","more","most","mustn't","my","myself","no","nor","not","of","off","on","once","only","or","other","ought","our","ours","ourselves","out","over","own","same","shan't","she","she'd","she'll","she's","should","shouldn't","so","some","such","than","that","that's","the","their","theirs","them","them

bee-san

x = range(-5, 5)
all_less_than_zero = (num * num for num in x if num < 0)

bee-san

# taken from page 87, chapter 3 of Fluent Python by Luciano Ramalho

>>> from unicodedata import name
>>> {chr(i) for i in range(32, 256) if 'SIGN' in name(chr(i), '')}
{'×', '¥', '°', '£', '©', '#', '¬', '%', 'µ', '>', '¤', '±', '¶', '§', '<', '=', '®', '$', '÷', '¢', '+'}

bee-san

# Taken from page 70 chapter 3 of Fluent Python by Luciano Ramalho

DIAL_CODES = [
    (86, 'China'),
    (91, 'India'),
    (1, 'United States'),
    (62, 'Indonesia'),
    (55, 'Brazil'),
    (92, 'Pakistan'),
    (880, 'Bangladesh'),