paceaux

import numpy as np
import math

def get_cosine_sim(a, b):
    a = np.array(a)
    b = np.array(b)
    
    aq = np.square(np.abs(a))
    bq =np.square(np.abs(b))

paceaux

import numpy as np



def get_ppmi(term_terms):
    term_terms = np.array(term_terms)
    total = term_terms.sum()
    pxy = term_terms / total
    
    px = pxy.sum(axis=1, keepdims=True)

paceaux

from collections import Counter
import re

def char_ngrams(word, size=1):
    """
    Generates character-level n-grams for a given string with start/end markers.

    Args:
        word (str): The input string to process.
        size (int): The length of the n-gram window. Defaults to 1.

paceaux

/*
* @description Gets the euclidian distance of two vectors
* @param {Array.<number>} v1 - a vector of numbers
* @param {Array.<number>} v2 - a vector of numbers
* @returns {number} A float
*/
function euclidian(v1, v2) {
	const squares = v1.map((el, idx) => {
    const subtr = el - v2[idx];
    return Math.pow(subtr, 2)

paceaux

// Note: Note cryptographically secure. 
function randomString(size = 5) {
    const stringArray = [...Math.random().toString()].slice(2, 2 + size);
    const intArray = stringArray.map(string => parseInt(string, 10));
    let chars = intArray.reduce((acc, c, idx) => {
        const charPos = [65,97];
        let charStart = charPos[c%2];
        const charOffset = Math.ceil(Math.random() * 10)%3;
        charStart = (charOffset * 8) + charStart;
        return String.fromCharCode(c + charStart) + acc;

paceaux

<dl>
  <dt><code>attributes</code></dt>
  <dd>{{dd(attributes)}}</dd>
  <dt><code>label_hidden</code></dt>
  <dd>{{dd(label_hidden)}}</dd>
  <dt><code>title_attributes</code></dt>
  <dd>{{dd(title_attributes)}}</dd>
  <dt><code>label</code></dt>
  <dd>{{dd(label)}}</dd>

paceaux

const wordSeparatorsRegex = /—\.,;:!?‽¡¿⸘()\\[\\]{}<>«»…‘“”"\s/g;

/*
fuck | s|er|ed|ing, motherfucker
shit + s|ton|ing|ting, bullshit
dick + s|head|hole|ed
ass + hole|hat|face 
cock +s
*/
const profanityRegex = /((\b)?(fuck)(\w+)?)|((\b)?shit(\w+)?)|((\b)dick(\w+|\b))|((\b)ass(\w+|\b))|((\b)cocks?\b)|((\b)cunts?\b)|((\b)twats?\b)|(wtf)|(stfu)/gi;

paceaux

<?php 

function getUserIP() {
    if( array_key_exists('HTTP_X_FORWARDED_FOR', $_SERVER) && !empty($_SERVER['HTTP_X_FORWARDED_FOR']) ) {
        if (strpos($_SERVER['HTTP_X_FORWARDED_FOR'], ',')>0) {
            $addr = explode(",",$_SERVER['HTTP_X_FORWARDED_FOR']);
            return trim($addr[0]);
        } else {
            return $_SERVER['HTTP_X_FORWARDED_FOR'];
        }

paceaux

const profanityRegex = /(((\b|\w+)?(fuck|shit|dick|twat|cock|douche|bitch|piss)(\w+|\b))|((\w+|\b)ass?(\b|hole|face|clown))|((\b)cunt(\w+|\b)))/

paceaux

/**
 * @description calculates the levenshtein distance between words
 * @param {string} str a string
 * @param {string} str2 another string
 * @returns {object} with properties 'steps' and 'transitions' 
 */
function levenshtein(str, str2) {
    if (typeof str !== 'string' || typeof str2 !== 'string') return;

    let [shorter, longer] = [str, str2].sort((a, b) => a.length - b.length);