bee-san

// get all text from .story-body within p tags on a BBC news web article
let $article = $('.story-body').find('p').text();

bee-san

let $article = $('.story-body').find('p')

bee-san

function TFIDF(documents){
    // calculates TF*IDF
    const TFVals = termFrequency(documents);
    const IDFVals = inverseDocumentFrequency(documents);

    let TFidfDict = {};

    for (const [key, value] of Object.entries(TFVals)){
        if (key in IDFVals){
            TFidfDict[key] = TFVals[key] * IDFVals[key];

bee-san

function TFIDF(documents){
    // calculates TF*IDF
    const TFVals = termFrequency(documents);
    const IDFVals = inverseDocumentFrequency(documents);

    let TFidfDict = {};

    for (const [key, value] of Object.entries(TFVals)){
        if (key in IDFVals){
            TFidfDict[key] = TFVals[key] * IDFVals[key];

bee-san

function TFIDF(documents){
    // calculates TF*IDF
    const TFVals = termFrequency(documents);
    const IDFVals = inverseDocumentFrequency(documents);

    let TFidfDict = {};

    for (const [key, value] of Object.entries(TFVals)){
        if (key in IDFVals){
            TFidfDict[key] = TFVals[key] * IDFVals[key];

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 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);