trinker

#' @param packages An optional vector of Campus Labs packages to install.
#' @param pattern An optional grep pattern of campus labs packages to install.
install_cl <- function(packages = NULL, pattern = '.', ...){

    try_install_cran <- function(package){

        if (!require(package, character.only = TRUE, quietly = TRUE)) {
            message(sprintf('The "%s" package is missing; do you want me to install it?', package))
            ans <- menu(c("Yes", "No"))
            if (ans == "2") {

trinker

if (!require("pacman")) install.packages("pacman")
pacman::p_load(udpipe, BTM)
data("brussels_reviews_anno", package = "udpipe")

## Get and load the udpipe model
engmod <- udpipe_download_model(language = "english", udpipe_model_repo = "bnosac/udpipe.models.ud")
ud_engmod <- udpipe_load_model(engmod$file_model)
    
## Annotate the text data and merge back together
nr <- nrow(sentimentr::presidential_debates_2012)

trinker

pacman::p_load(venneuler, tidyverse, ggforce)

## Make some fake data
set.seed(10)
dat <- data.frame(
    Person = paste0('Person_', 1:10),
    setNames(as.data.frame(matrix(rbinom(50, size = 1, prob=c(1/(1:5))), ncol = 5)), paste0('Attribute_', 1:5)),
    stringsAsFactors = FALSE
)

trinker

library(tidyverse)

map <- data_frame(
    ins = c(LETTERS, letters),
    outs = c(rev(LETTERS), rev(letters))
)

map

trinker

min_max <- function(x, ...) {
    m <- min(x, na.rm = TRUE)
    (x - m)/(max(x, na.rm = TRUE) - m)
}

standardization <- function(x, ...) {
    
    if (length(stats::na.omit(unique(x))) > 1) {
        scale(x) 
    } else {

trinker

## Taken from: http://news.mrdwab.com/install_github.R

## source("https://gist.githubusercontent.com/trinker/8a385892fac7d14a1f861f61394a2621/raw/95bdc672c632eff8dcfcd1f19233a0ed3cf85045/install_github.R")
## install_github("trinker/sentimentr") 

#' install_github installs R packages directly from GitHub
#'
#' install_github is a very lightweight function with no dependencies
#' that installs R packages from GitHub.
#'

trinker

fuzzy_map <- function(x, y, distance = 'cosine', cutoff = .40,
                      remove = c('the', 'a', 'an', 'at', 'of', 'in', '-', ' - CL', ' - OS'),
                      substitution = data.frame(
                        pattern = c('univ\\.', '\\bst\\.', '\\bmt\\.', '&'),
                        replacement = c('university', 'saint', 'mount', ' and '),
                        stringsAsFactors = FALSE
                      ),
                      ngrams = 1, # choose 1 or 2 (2 is 2 words)
                      downweight.words = c('suny', 'cuny', 'college', 'university', 'state'),
                      # words that are less important - make smaller to make the words LESS important

trinker

# Portraits

trinker

tell_it_like_it_is <- function(){
	message <- paste0(
	    sprintf(cow, sample(mess, 1)),
        "\n\n\n\n"
	)
	cat(message)
}


cow <- "\n ---------------- \n%s! \n ----------------- \n    \\   ^__^ \n     \\  (oo)\\ ________ \n        (__)\\         )\\ /\\ \n             ||------w|\n             ||      ||"

trinker

## Originally taken from: https://juliasilge.github.io/ibm-ai-day/slides.html#1

if (!require("pacman")) install.packages("pacman")
pacman::p_load(tidyverse, gutenbergr)

## Scrape known books
titles <- c(
    "Twenty Thousand Leagues under the Sea", 
    "The War of the Worlds",
    "Pride and Prejudice",