Aula correlação variáveis quanti

carregar

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(corrplot)

## corrplot 0.90 loaded

library(rio)

Passo 0 - Importação de dados

load("C:/Users/mtbor/Downloads/Base_de_dados-master/CARROS.RData")
load("C:/Users/mtbor/Downloads/Base_de_dados-master/df_pokemon.RData")

Passo 1 - visualizar se está tudo bem

head(CARROS)

##                   Kmporlitro Cilindros Preco  HP Amperagem_circ_eletrico  Peso
## Mazda RX4               21.0         6   160 110                    3.90 2.620
## Mazda RX4 Wag           21.0         6   160 110                    3.90 2.875
## Datsun 710              22.8         4   108  93                    3.85 2.320
## Hornet 4 Drive          21.4         6   258 110                    3.08 3.215
## Hornet Sportabout       18.7         8   360 175                    3.15 3.440
## Valiant                 18.1         6   225 105                    2.76 3.460
##                     RPM Tipodecombustivel TipodeMarcha NumdeMarchas
## Mazda RX4         16.46                 0            1            4
## Mazda RX4 Wag     17.02                 0            1            4
## Datsun 710        18.61                 1            1            4
## Hornet 4 Drive    19.44                 1            0            3
## Hornet Sportabout 17.02                 0            0            3
## Valiant           20.22                 1            0            3
##                   NumdeValvulas
## Mazda RX4                     4
## Mazda RX4 Wag                 4
## Datsun 710                    1
## Hornet 4 Drive                1
## Hornet Sportabout             2
## Valiant                       1

head(df)

## # A tibble: 6 x 22
##      id pokemon    species_id height weight base_experience type_1 type_2 attack
##   <dbl> <chr>           <int>  <int>  <int>           <int> <chr>  <chr>   <int>
## 1     1 bulbasaur           1      7     69              64 grass  poison     49
## 2     2 ivysaur             2     10    130             142 grass  poison     62
## 3     3 venusaur            3     20   1000             236 grass  poison     82
## 4     4 charmander          4      6     85              62 fire   <NA>       52
## 5     5 charmeleon          5     11    190             142 fire   <NA>       64
## 6     6 charizard           6     17    905             240 fire   flying     84
## # ... with 13 more variables: defense <int>, hp <int>, special_attack <int>,
## #   special_defense <int>, speed <int>, color_1 <chr>, color_2 <chr>,
## #   color_f <chr>, egg_group_1 <chr>, egg_group_2 <chr>, url_image <chr>,
## #   x <dbl>, y <dbl>

Passo 2 - diagrama de dispersão

DUAS VARIÁVEIS QUANTITATIVAS

par(bg="lightyellow")
plot(CARROS$HP, CARROS$Preco,pch=19,col="blue",main = "Gráfico 1",ylab = "Preço do carro")
abline(lsfit(CARROS$HP,CARROS$Preco),col="red")

par(bg="lightyellow")
plot(CARROS$Peso, CARROS$Preco,pch=19,col="blue",main = "Gráfico 2",ylab = "Preço do carro")
abline(lsfit(CARROS$Peso,CARROS$Preco),col="red")

par(bg="lightyellow")
plot(CARROS$Kmporlitro, CARROS$Preco,pch=19,col="blue",main = "Gráfico 3",ylab = "Preço do carro")
abline(lsfit(CARROS$Kmporlitro,CARROS$Preco),col="red")

Passo 3 - correlação

dados <-data.frame(x=c(2,3,4,5,5,6,7,8),
                   y=c(4,7,9,10,11,11,13,15))
cor(dados$x,dados$y)

## [1] 0.980871

cor(CARROS$Preco,CARROS$HP)

## [1] 0.7909486

cor(CARROS$Preco,CARROS$Peso)

## [1] 0.8879799

cor(CARROS$Preco,CARROS$Kmporlitro)

## [1] -0.8475514

par(bg="lightyellow")
plot(df$hp, df$speed,pch=19,col="blue",main = "Gráfico 4",ylab = "velocidade dos Pokemón")
abline(lsfit(df$hp,df$speed),col="red")

cor(df$hp,df$speed)

## [1] 0.1694177

par(bg="lightyellow")
plot(df$base_experience, df$special_attack,pch=19,col="blue",main = "Gráfico 5")
abline(lsfit(df$base_experience,df$special_attack),col="red")

cor(df$base_experience,df$special_attack)

## [1] 0.6630866

par(bg="lightyellow")
plot(df$special_defense, df$special_attack,pch=19,col="blue",main = "Gráfico 6")
abline(lsfit(df$special_defense,df$special_attack),col="red")

cor(df$special_defense,df$special_attack)

## [1] 0.48673

#————————————————–

names(CARROS)

##  [1] "Kmporlitro"              "Cilindros"              
##  [3] "Preco"                   "HP"                     
##  [5] "Amperagem_circ_eletrico" "Peso"                   
##  [7] "RPM"                     "Tipodecombustivel"      
##  [9] "TipodeMarcha"            "NumdeMarchas"           
## [11] "NumdeValvulas"

CARROS <- CARROS %>% rename(ACE=Amperagem_circ_eletrico)

MC<-CARROS %>% select(Kmporlitro,Preco,HP,
                  ACE,
                  Peso,RPM) %>% cor()
MC

##            Kmporlitro      Preco         HP         ACE       Peso         RPM
## Kmporlitro  1.0000000 -0.8475514 -0.7761684  0.68117191 -0.8676594  0.41868403
## Preco      -0.8475514  1.0000000  0.7909486 -0.71021393  0.8879799 -0.43369788
## HP         -0.7761684  0.7909486  1.0000000 -0.44875912  0.6587479 -0.70822339
## ACE         0.6811719 -0.7102139 -0.4487591  1.00000000 -0.7124406  0.09120476
## Peso       -0.8676594  0.8879799  0.6587479 -0.71244065  1.0000000 -0.17471588
## RPM         0.4186840 -0.4336979 -0.7082234  0.09120476 -0.1747159  1.00000000

corrplot(MC)

corrplot(MC,method="square")

corrplot.mixed(MC)