prova2

2VA

VADeaths

barplot(VADeaths,main = "VADeaths",names.arg = colnames(VADeaths),xlab = "TYPE",ylab = "AGE",col = rainbow(5),beside = T)
legend("topleft", pch = c(15,15,15,15,15),col = rainbow(15),legend = rownames(VADeaths))

ClassificaçãoDoença

p <- c("moderado", "leve", "leve", "severo", "leve", "moderado", 
               "moderado", "moderado", "leve", "leve", "severo", "leve", "moderado", 
               "moderado", "leve", "severo", "moderado", "moderado", "moderado", "leve")
pct <- round(table(p) / sum(table(p)) * 100)
pie(x = table(p),
    labels = paste(pct, "%", ""),
    main = "ClassificaçãoDoença",
    col = rainbow(3))
legend("topleft", legend = names(table(p)),
        fill = rainbow(3))

Twitters

Nuvem

library(wordcloud)

## Loading required package: RColorBrewer

library(httr2)
library(jsonlite)
library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(tm)

## Loading required package: NLP

search_recent_tweets <- function(bearer_token, query, max_results, lang=NULL) { 
  headers <- c(Authorization = sprintf('Bearer %s', bearer_token))
  
  if (max_results < 10) {
    return("max_results deve ser maior ou igual a 10.")
  }
  
  result <- data.frame()
  first_try <- TRUE
  
  while (nrow(result) < max_results) {
    
    if (first_try) {
      params <- list(query = query, tweet.fields = 'lang', max_results=100)
      first_try <- FALSE
    } else {
      params <- list(query = query, tweet.fields = 'lang', max_results=100, pagination_token = tail(tweets, 1)$meta.next_token)
    }
    
    response <- httr::GET(url = 'https://api.twitter.com/2/tweets/search/recent', httr::add_headers(.headers = headers), query = params)
    obj <- httr::content(response, as = "text")
    tweets <- fromJSON(obj, flatten = TRUE) %>% as.data.frame
    if (!("meta.result_count" %in% colnames(tweets))) {
      return(result)
    } 
    
    if (!is.null(lang)) {
      tweets <- tweets%>%filter(data.lang==lang)
    }
    result <- bind_rows(result, tweets)
  }
  
  return(result[1:max_results,])
}
bearer = "AAAAAAAAAAAAAAAAAAAAAErgbQEAAAAA1stDkBEmE6mN5Sy93jUJKcVD2ok%3Dv0QGgUOadaayOXib4H4tjwcTxuZMISzEZXvZYpE8qxaFfaZpCq"
tweets <- search_recent_tweets(bearer_token = bearer,query="#COVID19", max_results= 500, lang = "pt")

tweets_t<-paste(tweets$data.text,collapse= " ")
corpus_t <- Corpus(VectorSource(tweets_t))
corpus_t <-tm_map(corpus_t,tolower)

## Warning in tm_map.SimpleCorpus(corpus_t, tolower): transformation drops
## documents

corpus_t <-tm_map(corpus_t,removePunctuation)

## Warning in tm_map.SimpleCorpus(corpus_t, removePunctuation): transformation
## drops documents

corpus_t <-tm_map(corpus_t,stripWhitespace)

## Warning in tm_map.SimpleCorpus(corpus_t, stripWhitespace): transformation drops
## documents

corpus_t <-tm_map(corpus_t,removeWords,stopwords('portuguese'))

## Warning in tm_map.SimpleCorpus(corpus_t, removeWords, stopwords("portuguese")):
## transformation drops documents

removeURL<-function(x)gsub("http[^[space:]]*", "",x)
corpus_t <-tm_map(corpus_t,removeURL)

## Warning in tm_map.SimpleCorpus(corpus_t, removeURL): transformation drops
## documents

removeNumPunct<-function(x)gsub("[^[:alpha:][:space:]]*", "",x)
corpus_t <-tm_map(corpus_t,content_transformer(removeNumPunct))

## Warning in tm_map.SimpleCorpus(corpus_t, content_transformer(removeNumPunct)):
## transformation drops documents

wordcloud(corpus_t, min.freq= 1, max.words=100,random.order=FALSE, rot.per=0.35, colors=brewer.pal(8, "Dark2"))

Sentimentos

library('syuzhet')
sentiments <- get_nrc_sentiment(tweets_t)

## Warning: `spread_()` was deprecated in tidyr 1.2.0.
## Please use `spread()` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was generated.

barplot(colSums(sentiments), las=2, col= rainbow(10), ylab= "Quantidade", main= "Sentimentos para do #COVID19", font=2)

Teorema

flu <- read.csv("https://www.dropbox.com/s/hmt4vt3xllfrcmd/flu.csv?dl=1", header = T, strip.white = T, na.strings = "", stringsAsFactors = T)
hist(flu$age,col =  rainbow(20), probability = T,
     main = "Histograma sobre a gripe Espanhola")
lines(density(flu$age))

#---
xbar <- rep(NA, 200)
for (i in 1:200){
  minhaAmostra <- sample(flu$age, 35)
  xbar[i] <- mean(minhaAmostra)
}
hist(xbar, col = rainbow(20), probability = T,
     main = "Histograma sobre a gripe Espanhola (Normalizado)")
lines(density(xbar))