DATAUNIRIO

#Step 1 cleaning data
#install.packages("stopwords")
library("stopwords")
library(tidyverse)
library(tidytext)

fernando  = 'http://gae.uniriotec.br/7/educaser/fernandopessoa.txt'
text_dataframe = readLines(fernando, encoding = "latin1")
text_dataframe = tolower(text_dataframe)
text_dataframe = tibble(txt = text_dataframe)

DATAUNIRIO

Upgrade RStudio Server (Version:1.1.463 Released:2018-10-29) in Ubuntu

sudo /usr/sbin/rstudio-server stop #stop the current version
# Download
sudo apt-get install gdebi-core
wget https://download2.rstudio.org/rstudio-server-1.1.463-amd64.deb
sudo gdebi rstudio-server-1.1.463-amd64.deb

DATAUNIRIO

url_do_arquivo <- "https://github.com/DATAUNIRIO/Base_de_dados/raw/master/BasesEstados.xlsx"
download.file(url_do_arquivo,"BasesEstados.xlsx",mode="wb") # windows
library(readxl)
BasesEstados <- read_excel("BasesEstados.xlsx")

# Import -----------------------------------------------------------------------
mapa_estados <- geobr::read_state()

DATAUNIRIO

#-----------------------------------------------------------------------------
# Parte 1
#-----------------------------------------------------------------------------
library(reticulate)

reticulate::py_install("requests")
reticulate::py_install("bs4")
reticulate::py_install("os")

DATAUNIRIO

# devtools::install_github("DanChaltiel/crosstable", build_vignettes=TRUE)
# https://danchaltiel.github.io/crosstable/
# https://vincentarelbundock.github.io/modelsummary/articles/datasummary.html


load("C:/Users/Hp/Desktop/Base_de_dados-master/Titanic.RData")
names(Titanic)
library(crosstable)
ct1 <- crosstable(Titanic, c(Sobreviveu), by=Sexo, total="row")
ct2 <- crosstable(Titanic, c(Sobreviveu), by=Sexo, total="column")

DATAUNIRIO

dados_aula_regressao <-read.csv("C:/Users/Hp/Documents/GitHub/Base_de_dados/dados_aula_regressao.csv")
plot(dados_aula_regressao$anos_de_empresa,dados_aula_regressao$salario)

modelo <- lm(salario ~ anos_de_empresa,data=dados_aula_regressao)
summary(modelo)

residuos <-residuals(modelo)

#produce residual vs. fitted plot
plot(fitted(modelo), residuos)

DATAUNIRIO

salario <- rnorm(200,4000,15)
salario <- round(salario,2)
anos_de_empresa<- salario/1000 + rnorm(200,0,5)
anos_de_empresa<- anos_de_empresa + 10
anos_de_empresa<- round(anos_de_empresa)
plot(anos_de_empresa,salario)
min(anos_de_empresa)

modelo <- lm(salario ~ anos_de_empresa)
bptest(modelo)

DATAUNIRIO

# Carrega o pacote
library(deflateBR)

deflate(nominal_values = 1091.01, 
        nominal_dates = as.Date("2015-01-01"), 
        real_date = "01/2022")

# R$ 1653.53
# R$ 1759,56

DATAUNIRIO

# remotes::install_github("thomas-neitmann/ggcharts", upgrade = "never")
library(dplyr)
library(ggcharts)

biomedicalrevenue %>%
  filter(year %in% c(2012, 2015, 2018)) %>%
  bar_chart(x = company, y = revenue, facet = year, top_n = 10)

biomedicalrevenue %>% filter(year == 2018) %>%

DATAUNIRIO

# Importar
library(readxl)
QE <- read_excel("C:/Users/Hp/Desktop/Base_de_dados-master/Questionario_Estresse.xls")
View(QE)

# Transformar
QE$Mora_pais <- ifelse(QE$Mora_pais==1,"Sim","Não")
QE$RJ <- ifelse(QE$RJ==1,"Sim","Não")
QE$Namorado_a <- ifelse(QE$Namorado_a==1,"Sim","Não")