Script para Nuvem

Fundação Getulio Vargas

Fundação Getulio Vargas

bibliotecas

Preparação dos dados

Abrir bases originais:

# abrir base e criar amostras
#dados_finais_2000_2010 <- readRDS("~/RStudio/ENEM/2_Dado tratado/dados_finais_2000_2010.rds")
#df<-slice_sample(dados_finais_2000_2010,prop = 0.01) 
#saveRDS(df, file = "sample_00_10.rds")
#table(dados_finais_2000_2010$NU_ANO)
#table(df$NU_ANO)
#dados_finais_2000_2010 <- readRDS("~/RStudio/ENEM/2_Dado tratado/dados_finais_2012_2014.rds")

#df2<-slice_sample(dados_finais_2000_2010,prop = 0.01) 
#saveRDS(df2, file = "sample_12_14.rds")


#dados_finais_2015_2020 <- readRDS("~/RStudio/ENEM/2_Dado tratado/dados_finais_2015_2020.rds")
#df3<-slice_sample(dados_finais_2015_2020,prop = 0.01) 
#saveRDS(df3, file = "sample_15_20.rds")

#Base de 2000-2010
sample_00_10 <- readRDS("~/RStudio/ENEM/sample_00_10.rds")
#Base de 2011-2015
sample_12_14 <- readRDS("~/RStudio/ENEM/sample_12_14.rds")
#Base de 2015-2016
sample_15_20 <- readRDS("~/RStudio/ENEM/sample_15_20.rds")
#base de Variaveis Ambientais

# unificar base de dados ambiental
Centro <- readRDS("~/RStudio/ENEM/Data-20220615T014950Z-001/Data/Centro.rds")
NE <- readRDS("~/RStudio/ENEM/Data-20220615T014950Z-001/Data/NE.rds")
NO <- readRDS("~/RStudio/ENEM/Data-20220615T014950Z-001/Data/NO.rds")
SE <- readRDS("~/RStudio/ENEM/Data-20220615T014950Z-001/Data/SE.rds")
SUL <- readRDS("~/RStudio/ENEM/Data-20220615T014950Z-001/Data/Sul.rds")
df_Am<-bind_rows(NE, NO, SE,SUL)
rm(NE,NO,SE,SUL,Centro)
head(df_Am)

Preparar Bases:

Selecionar Variaveis de Interesse

  #nota componente X
#  ,#Questão renda
#  ,#Questão
#  ,#Questão
#  ,#Questão
)->sample_00_10

Error: unexpected ')' in ")"

Fundir Bases:

rm(df_enem,df_Am)

Warning in rm(df_enem, df_Am) : object 'df_Am' not found

Analise Exploratória

Sumário dos Dados

Resumo dos Dados

skim(df)

── Data Summary ────────────────────────
                           Values
Name                       df    
Number of rows             915875
Number of columns          25    
Key                        NULL  
_______________________          
Column type frequency:           
  character                2     
  factor                   6     
  logical                  1     
  numeric                  16    
________________________         
Group variables            None  

df[,7:12] <- lapply(df[,7:12], as.numeric)

Warning in lapply(df[, 7:12], as.numeric) : NAs introduced by coercion
Warning in lapply(df[, 7:12], as.numeric) : NAs introduced by coercion
Warning in lapply(df[, 7:12], as.numeric) : NAs introduced by coercion
Warning in lapply(df[, 7:12], as.numeric) : NAs introduced by coercion
Warning in lapply(df[, 7:12], as.numeric) : NAs introduced by coercion
Warning in lapply(df[, 7:12], as.numeric) : NAs introduced by coercion

Analise das uni

#variaveis numéricas
  plot_num(df)

Warning: `guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.

#variaveis Categoricas
freq(df)

Warning in freq_logic(data = data, input = input[i], plot, na.rm, path_out = path_out) :
  Skipping plot for variable 'NU_INSCRICAO' (more than 100 categories)

Warning: `guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.

Warning: `guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.

Warning in freq_logic(data = data, input = input[i], plot, na.rm, path_out = path_out) :
  Skipping plot for variable 'NO_MUNICIPIO_RESIDENCIA' (more than 100 categories)

Warning in freq_logic(data = data, input = input[i], plot, na.rm, path_out = path_out) :
  Skipping plot for variable 'CO_MUNICIPIO_RESIDENCIA' (more than 100 categories)

Warning: `guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.

Warning: `guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.

Warning: `guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> = "none")` instead.

[1] "Variables processed: NU_INSCRICAO, TP_SEXO, SG_UF_RESIDENCIA, NO_MUNICIPIO_RESIDENCIA, CO_MUNICIPIO_RESIDENCIA, NU_NOTA_COMP5, name_state, name_region"

Analise de Correlações

#df1<-slice_sample(df,prop = 0.01)
df1 %>% ggplot(aes(x=NU_ANO,y =NU_NOTA_REDACAO))+#geom_density2d_filled()+
  geom_smooth()+geom_dotplot(size=5,alpha=0.01)

Warning: Ignoring unknown parameters: size
`geom_smooth()` using method = 'gam' and formula 'y ~ s(x, bs = "cs")'
Warning: Removed 1263 rows containing non-finite values (stat_smooth).
Bin width defaults to 1/30 of the range of the data. Pick better value with `binwidth`.

Error in `check_required_aesthetics()`:
! geom_dotplot requires the following missing aesthetics: y
Backtrace:
 1. base `<fn>`(x)
 2. ggplot2:::print.ggplot(x)
 4. ggplot2:::ggplot_build.ggplot(x)
 5. ggplot2 by_layer(function(l, d) l$compute_geom_1(d))
 6. ggplot2 f(l = layers[[i]], d = data[[i]])
 7. l$compute_geom_1(d)
 8. ggplot2 f(..., self = self)
 9. ggplot2:::check_required_aesthetics(...)

a<-"a"
for (i in 7:12) {
  print(i)
  a<-print(colnames(df)[i])
  df1 %>% ggplot(aes(pm25_ugm3,a,col=name_state))+
  geom_point() %>% print()
  
}

[1] 7
[1] "NU_NOTA_REDACAO"
geom_point: na.rm = FALSE
stat_identity: na.rm = FALSE
position_identity 
[1] 8
[1] "NU_NOTA_COMP1"
geom_point: na.rm = FALSE
stat_identity: na.rm = FALSE
position_identity 
[1] 9
[1] "NU_NOTA_COMP2"
geom_point: na.rm = FALSE
stat_identity: na.rm = FALSE
position_identity 
[1] 10
[1] "NU_NOTA_COMP3"
geom_point: na.rm = FALSE
stat_identity: na.rm = FALSE
position_identity 
[1] 11
[1] "NU_NOTA_COMP4"
geom_point: na.rm = FALSE
stat_identity: na.rm = FALSE
position_identity 
[1] 12
[1] "NU_NOTA_COMP5"
geom_point: na.rm = FALSE
stat_identity: na.rm = FALSE
position_identity 

i

[1] 12

#df1 %>% ggplot(aes(pm25_ugm3,NU_NOTA_REDACAO,col=name_state))+
#  geom_point()
  

Regressões

Modelo basico de referencia

#modelo Linear
<-lm(Nota~ poluente,data = )
#Efeitos Mistos
<-lmer(Nota~ poluente + (1+poluente|Estado),data = )
summary()
summary()

extração de Coeficientes

#extração de Coeficientes
ds

#Valor Previsto

%>% ggplot(
  aes(
    predict(),
    col=estado
    )
  ) +
  geom_point()
  

Modelo com controles

#modelo Linear
<-lm(Nota~ poluente,data = )
#Efeitos Mistos
<-lmer(Nota~ poluente + (1+poluente|Estado),data = )
summary()
summary()

extração de Coeficientes

#extração de Coeficientes
ds

#Valor Previsto

%>% ggplot(
  aes(
    predict(),
    col=estado
    )
  ) +
  geom_point()
  

Modelo com controles variando por ano

Modelo com controles variando por modalidade educacional

Modelo com controles variando por modalidade educacional