---
title: "Ejercicios Clase 8"
author: ""
header-includes:
   - \usepackage{bbm}
date: "06/11/2023"
output: pdf_document
---



```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```


```{r message=FALSE, warning=FALSE, include=FALSE}
library(quanteda) #librerías
library(knitr)
library(quanteda.textplots)
library(quanteda.textstats)

base_final_grande <- read.delim("C:/Users/Usuario/Documents/IntroRTextoLIM/Clase8/Material/base_genero_final.txt",sep="\t",header = T,encoding = "latin1")


```



```{r tokens, message=FALSE, warning=FALSE, include=FALSE}


dfm <- dfm(tokens(base_final_grande$text, remove_punct = TRUE,remove_numbers = TRUE),
              tolower = TRUE,
              remove_punct = TRUE, 
              remove_numbers = TRUE,
           remove = c(stopwords("spanish"))) %>%
  dfm_remove(min_nchar=3) %>%
  dfm_trim(min_termfreq = 50, min_docfreq = 2)

```


# Introducción

El presente **documento** contiene algunos resultados del procesamiento de menciones parlamentarias realizadas en el marco del curso de *Introducción a la programación y análisis de texto con R*. 


```{r echo=FALSE, message=FALSE, warning=FALSE}
palabras=topfeatures(dfm,10)

knitr::kable(palabras, caption = "Palabras más mencionadas", col.names = c("N"))

```






```{r message=FALSE, warning=FALSE, include=FALSE}
#hago un corpus nuevo y aplico kwic

kw_ddhhsspp <- kwic(tolower(base_final_grande$text), pattern = phrase(c("derechos humanos", "salud pública")))

dfm_2 <- dfm(tokens(kw_ddhhsspp$pre, remove_punct = TRUE,remove_numbers = TRUE),
              tolower = TRUE,
              remove_punct = TRUE,
              remove_numbers = TRUE,
           remove = c(stopwords("spanish"))) %>%
  dfm_remove(min_nchar=3)%>%
  dfm_group(groups = kw_ddhhsspp$keyword)


```


\newpage


# Nubes de palabras

## General 

A continuación hago una nube de palabras general y por grupos.


```{r echo=FALSE, fig.cap="Nube", message=FALSE, warning=FALSE, out.width="80%"}

textplot_wordcloud(dfm_2, min.count = 4,max_words = 100,random.order = TRUE,
                   rot.per = .50, colors = RColorBrewer::brewer.pal(8,"Dark2"))

```


##Grupos


```{r echo=FALSE, message=FALSE, warning=FALSE,out.width = "100%",fig.cap="Nube de palabras por grupos"}

textplot_wordcloud(dfm_2, min.count = 1,max_words = 100,random.order = TRUE,
                   rot.per = .50, colors = RColorBrewer::brewer.pal(8,"Dark2"),comparison = TRUE)

```