ENEM vs ENADE

Libraries

  library(tidyverse)

## ── Attaching packages ───────────────────────────────────────────────────────────────────────────────────────── tidyverse 1.2.1 ──

## ✔ ggplot2 3.1.0       ✔ purrr   0.3.1  
## ✔ tibble  2.0.1       ✔ dplyr   0.8.0.1
## ✔ tidyr   0.8.3       ✔ stringr 1.4.0  
## ✔ readr   1.3.1       ✔ forcats 0.4.0

## Warning: package 'tibble' was built under R version 3.5.2

## Warning: package 'tidyr' was built under R version 3.5.2

## Warning: package 'purrr' was built under R version 3.5.2

## Warning: package 'stringr' was built under R version 3.5.2

## Warning: package 'forcats' was built under R version 3.5.2

## ── Conflicts ──────────────────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

  library(ggplot2)
  library(psych)

## Warning: package 'psych' was built under R version 3.5.2

## 
## Attaching package: 'psych'

## The following objects are masked from 'package:ggplot2':
## 
##     %+%, alpha

  library(plotly)

## 
## Attaching package: 'plotly'

## The following object is masked from 'package:ggplot2':
## 
##     last_plot

## The following object is masked from 'package:stats':
## 
##     filter

## The following object is masked from 'package:graphics':
## 
##     layout

  library(RColorBrewer)

  library(corrplot)

## corrplot 0.84 loaded

  library(sjmisc)

## Warning: package 'sjmisc' was built under R version 3.5.2

## Install package "strengejacke" from GitHub (`devtools::install_github("strengejacke/strengejacke")`) to load all sj-packages at once!

## 
## Attaching package: 'sjmisc'

## The following object is masked from 'package:purrr':
## 
##     is_empty

## The following object is masked from 'package:tidyr':
## 
##     replace_na

## The following object is masked from 'package:tibble':
## 
##     add_case

  library(sjPlot)
  library(sjlabelled)

## Warning: package 'sjlabelled' was built under R version 3.5.2

## 
## Attaching package: 'sjlabelled'

## The following object is masked from 'package:forcats':
## 
##     as_factor

Data

df <- readRDS("enem_enade_bio.rds")

graph_corplot <- function(df, vars1, vars2=NULL) {
 
  col <- colorRampPalette(c("#BB4444", "#EE9988", "#FFFFFF", "#77AADD", "#4477AA"))
  
  if (is.null(vars2)) {
  p.mat <- corr.test(x =df[, vars1], adjust = "none")  %>%  .$p
  corr.test(x =df[, vars1], adjust = "none")  %>% .$r %>% 
  corrplot(method = "color", col = col(50), number.cex = .7,
    addCoef.col = "black", # Add coefficient of correlation
    tl.col = "black", tl.srt = 90, # Text label color and rotation
         # Combine with significance
    p.mat = p.mat, sig.level = 0.05, insig = "blank", 
         # hide correlation coefficient on the principal diagonal 
    diag = TRUE) 
   
  } else {
  p.mat <- corr.test(x =df[, vars1], y = df[ , vars2], adjust = "none")  %>%  .$p
  corr.test(x =df[, vars1], y = df[ , vars2], adjust = "none")  %>% .$r %>% 
  corrplot(method = "color", col = col(50), number.cex = .7,
    addCoef.col = "black", # Add coefficient of correlation
    tl.col = "black", tl.srt = 90, # Text label color and rotation
         # Combine with significance
    p.mat = p.mat, sig.level = 0.05, insig = "blank", 
         # hide correlation coefficient on the principal diagonal 
    diag = TRUE) 
  }
  
}

  names(df)

##  [1] "NU_ANO"          "CO_GRUPO"        "CD_ORGAC"       
##  [4] "CO_REGIAO"       "SG_UF"           "SQ_GRAD"        
##  [7] "IN_GRAD"         "NU_IDADE"        "TP_SEXO"        
## [10] "ANO_FIM_2G"      "ANO_IN_GRA"      "TP_PR_GER"      
## [13] "NT_OBJ_FG"       "NT_DIS_FG"       "NT_FG"          
## [16] "NT_OBJ_CE"       "NT_DIS_CE"       "NT_GER"         
## [19] "Tem_bolsa"       "Privada"         "escol_pais"     
## [22] "Sus_trab"        "branco"          "negrind"        
## [25] "mulato"          "uso_comp"        "bibl_acervo"    
## [28] "cond_fis"        "bibl_serv"       "form_social_BR1"
## [31] "form_social_BR2" "plan_peda"       "exigencia"      
## [34] "co_rs_81c"       "IC_1"            "Monit_1"        
## [37] "Extensao_1"      "IC_incent"       "co_rs_92c"      
## [40] "compet_met"      "compet_soc"      "competencias"   
## [43] "IDD"             "ENEM98_TTO"      "ENEM98_TTR"     
## [46] "ENEM99_TTO"      "ENEM99_TTR"      "ENEM00_TTO"     
## [49] "ENEM00_TTR"      "ENEM01_TTO"      "ENEM01_TTR"     
## [52] "ENEM02_TTO"      "ENEM02_TTR"      "ENEM03_TTO"     
## [55] "ENEM03_TTR"      "ENEM04_TTO"      "ENEM04_TTR"     
## [58] "ENEM05_TTO"      "ENEM05_TTR"

  df$TP_SEXO <- add_labels(df$TP_SEXO, labels = attr(df$TP_SEXO, "value.labels"))
  df %>% select(TP_SEXO) %>% frq

## 
## # TP_SEXO <numeric> 
## # total N=10933  valid N=10933  mean=1.72  sd=0.45
##  
##  val     label  frq raw.prc valid.prc cum.prc
##    1 Masculino 3114   28.48     28.48   28.48
##    2  Feminino 7819   71.52     71.52  100.00
##   NA        NA    0    0.00        NA      NA

   vars1 <- names(df)[c(13, 14, 16, 17, 18, 50, 51, 20, 21, 22, 9 )]
  graph_corplot(df=df, vars1=vars1)

colors <- brewer.pal(7, "Paired")

df %>%
  plot_ly(x=~escol_pais, y=~ENEM01_TTO, z=~NT_GER , 
    type="scatter3d", 
    mode="markers", color=~escol_pais, colors = colors,
    size = 3.5,
    opacity = 1/1.5)

## Warning: Ignoring 9359 observations

df %>%
  plot_ly(x=~escol_pais, y=~ENEM01_TTO, z=~NT_GER , 
    type="scatter3d", 
    mode="markers", color=~escol_pais, colors = colors,
    size = 3.5,  symbol = ~TP_SEXO, symbols = c('circle','x'),
    opacity = 1/1.5)

## Warning: Ignoring 9359 observations