library(rio)
peru=import("dataPeru.xlsx")

#HACER EL PORCENTAJE DE LAS FILAS QUE NOS PIDEN

library(dplyr)
## 
## Adjuntando el paquete: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
peru <- peru %>%
  mutate(valores_percentsu = (contribuyentesSunat / sum(contribuyentesSunat)) * 100)
peru <- peru %>%
  mutate(valores_percentpea = (peaOcupada / sum(peaOcupada)) * 100)
modelo1=formula(buenEstado ~ valores_percentsu + valores_percentpea)
regre1=lm(modelo1,data = peru)
summary(regre1)
## 
## Call:
## lm(formula = modelo1, data = peru)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -10.589  -3.966  -1.347   1.907  21.518 
## 
## Coefficients:
##                    Estimate Std. Error t value Pr(>|t|)    
## (Intercept)          18.646      2.694   6.922 5.98e-07 ***
## valores_percentsu     1.955      2.255   0.867    0.395    
## valores_percentpea   -1.963      2.758  -0.712    0.484    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 7.925 on 22 degrees of freedom
## Multiple R-squared:  0.1561, Adjusted R-squared:  0.07939 
## F-statistic: 2.035 on 2 and 22 DF,  p-value: 0.1546

#RESPUESTA2

modelo2=formula(peaOcupada~ buenEstado + contribuyentesSunat)
regre2=lm(modelo2,data = peru)
summary(regre2)
## 
## Call:
## lm(formula = modelo2, data = peru)
## 
## Residuals:
##    Min     1Q Median     3Q    Max 
## -91867 -58573 -11166  46174 155851 
## 
## Coefficients:
##                       Estimate Std. Error t value Pr(>|t|)    
## (Intercept)          1.155e+05  3.787e+04   3.049  0.00588 ** 
## buenEstado          -1.412e+03  1.983e+03  -0.712  0.48395    
## contribuyentesSunat  9.206e-01  1.741e-02  52.872  < 2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 74540 on 22 degrees of freedom
## Multiple R-squared:  0.9932, Adjusted R-squared:  0.9926 
## F-statistic:  1603 on 2 and 22 DF,  p-value: < 2.2e-16

#DATAFRAME

modelo1=formula(buenEstado ~ v2x_partip + v2xdl_delib)