almogsi

#ANEW function

ANEW_txt <- read.table("Downloaded_ANEW_txt.txt", header = T, sep = "\t") #you should download ANEW first
ANEW_txt$Word <- as.character(ANEW_txt$Word)
library(stringr)
library(tm)

ANEW <- function(a){
  
  a <- as.character(a)

almogsi

novad <- read.csv("Download_NoVAD_csv.csv") #Change for you local csv file
novad$Word <- as.character(novad$Word)
library(stringr)
library(tm)

NoVAD <- function(a){
  a <- as.character(a)
  sms_corpus <- Corpus(VectorSource(a))
  #translate all letters to lower case
  clean_corpus <- tm_map(sms_corpus, tolower)

almogsi

library(rJava)
library(coreNLP)
initCoreNLP()

#in this case, 'test' is a data frame with a col named 'text'

for (i in 1:dim(test)[1]) {
  cat(paste0(i / dim(test)[1] * 100, '% completed'))
  ann <- annotateString(paste(test$text[i]), format = c("obj"), outputFile = NA, includeXSL = FALSE)
  gd <- getDependency(ann)

almogsi

cat_state <- function(a, abbreviation=F) {
  Swing = c("Wisconsin", "Virginia", "Michigan", "Pennsylvania",
            "New Hampshire", "Colorado", "Nevada", "North Carolina",
            "Florida", "Ohio", "Arizona", "Iowa", "Georgia")
  Swing_abb = state.abb[match(Swing,state.name)]
  Democrat = c("New Mexico", "Minnesota", "Maine", "Oregon",
               "New Jersey", "Delaware", "Connecticut", "Illinois",
               "Washington", "Rhode Island", "New York", "California",
               "Massachusetts", "Hawaii", "Maryland", "Vermont")
  Democrat_abb = state.abb[match(Democrat,state.name)]

almogsi

library(tidyverse)
library(caret)
library(lime)

#fit
lasso_caret<- train(data = mtcars, mpg~., method = "glmnet",
                    tuneGrid = expand.grid(alpha = 1,
                                           lambda = 0))
#LIME
explainer <- lime(mtcars, lasso_caret) #here the train data

almogsi

library(tidyverse)
library(quanteda)
library(spacyr)

get_passive <- function(text, ratio = F){
  d <- spacy_parse(text, dependency = T)
  
  aux_pass <- d %>% 
    mutate(doc_id = as.numeric(str_remove_all(doc_id, "text"))) %>% 
    group_by(doc_id) %>%