Carregar a base
load("C:/Users/roberta.bastos/Desktop/Base_de_dados-master/CARROS.RData")
Análise exploratória
O boxplot 1
boxplot(CARROS$Preco ~ CARROS$Tipodecombustivel,horizontal = T,
col=c("red","blue"),main="O boxplot 1",
xlab = "Preço do carro",
ylab = "Tipo de combustívrel")
O boxplot 2
boxplot(CARROS$Kmporlitro ~ CARROS$Tipodecombustivel,horizontal = T,
col=c("red","blue"),main="O boxplot 2",
xlab = "km/l do carro",
ylab = "Tipo de combustívrel")
O boxplot 3
boxplot(CARROS$HP ~ CARROS$TipodeMarcha,horizontal = T,
col=c("green","yellow"),main="O boxplot 3",
xlab = "HP do carro",
ylab = "Tipo de marcha")
Duas variáveis quantitativas
library(psych)
describeBy(Preco ~Tipodecombustivel, data = CARROS)
##
## Descriptive statistics by group
## Tipodecombustivel: Alc
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 14 132.46 56.89 120.55 127.11 61.82 71.1 258 186.9 0.8 -0.49 15.21
## ------------------------------------------------------------
## Tipodecombustivel: Gas
## vars n mean sd median trimmed mad min max range skew kurtosis
## X1 1 18 307.15 106.77 311 308.52 72.65 120.3 472 351.7 -0.26 -1.06
## se
## X1 25.16
describeBy(Kmporlitro ~Tipodecombustivel, data = CARROS)
##
## Descriptive statistics by group
## Tipodecombustivel: Alc
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 14 24.56 5.38 22.8 24.34 6 17.8 33.9 16.1 0.41 -1.4 1.44
## ------------------------------------------------------------
## Tipodecombustivel: Gas
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 18 16.62 3.86 15.65 16.42 2.97 10.4 26 15.6 0.48 -0.05 0.91
describeBy(HP ~Tipodecombustivel, data = CARROS)
##
## Descriptive statistics by group
## Tipodecombustivel: Alc
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 14 91.36 24.42 96 92 32.62 52 123 71 -0.24 -1.61 6.53
## ------------------------------------------------------------
## Tipodecombustivel: Gas
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 18 189.72 60.28 180 186.81 48.18 91 335 244 0.45 -0.15 14.21
describeBy(Preco ~TipodeMarcha, data = CARROS)
##
## Descriptive statistics by group
## TipodeMarcha: Auto
## vars n mean sd median trimmed mad min max range skew kurtosis
## X1 1 19 290.38 110.17 275.8 289.71 124.83 120.1 472 351.9 0.05 -1.26
## se
## X1 25.28
## ------------------------------------------------------------
## TipodeMarcha: Manual
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 13 143.53 87.2 120.3 131.25 58.86 71.1 351 279.9 1.33 0.4 24.19
describeBy(Kmporlitro ~TipodeMarcha, data = CARROS)
##
## Descriptive statistics by group
## TipodeMarcha: Auto
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 19 17.15 3.83 17.3 17.12 3.11 10.4 24.4 14 0.01 -0.8 0.88
## ------------------------------------------------------------
## TipodeMarcha: Manual
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 13 24.39 6.17 22.8 24.38 6.67 15 33.9 18.9 0.05 -1.46 1.71
describeBy(HP ~TipodeMarcha, data = CARROS)
##
## Descriptive statistics by group
## TipodeMarcha: Auto
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 19 160.26 53.91 175 161.06 77.1 62 245 183 -0.01 -1.21 12.37
## ------------------------------------------------------------
## TipodeMarcha: Manual
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 13 126.85 84.06 109 114.73 63.75 52 335 283 1.36 0.56 23.31
Análise por tipo de combinação
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
CARROS %>% group_by(TipodeMarcha) %>%
select(Preco) %>%
summarise(media=mean(Preco))
## Adding missing grouping variables: `TipodeMarcha`
## # A tibble: 2 x 2
## TipodeMarcha media
## * <chr> <dbl>
## 1 Auto 290.
## 2 Manual 144.
CARROS %>% group_by(TipodeMarcha)%>%
select(Preco) %>%
summarise(media=mean(Preco))
## Adding missing grouping variables: `TipodeMarcha`
## # A tibble: 2 x 2
## TipodeMarcha media
## * <chr> <dbl>
## 1 Auto 290.
## 2 Manual 144.
CARROS %>% group_by(TipodeMarcha) %>%
select(Preco,Kmporlitro) %>%
summarise(media_preco=mean(Preco),media_kml=mean(Kmporlitro))
## Adding missing grouping variables: `TipodeMarcha`
## # A tibble: 2 x 3
## TipodeMarcha media_preco media_kml
## * <chr> <dbl> <dbl>
## 1 Auto 290. 17.1
## 2 Manual 144. 24.4
Tabela_resumo<-CARROS %>% group_by(TipodeMarcha) %>%
select(Preco,Kmporlitro) %>%
summarise(media_preco=mean(Preco),media_kml=mean(Kmporlitro))
## Adding missing grouping variables: `TipodeMarcha`
CARROS %>%
group_by(TipodeMarcha) %>%
select(Tipodecombustivel) %>%
table()
## Adding missing grouping variables: `TipodeMarcha`
## Tipodecombustivel
## TipodeMarcha Alc Gas
## Auto 7 12
## Manual 7 6
CARROS %>%
filter(Tipodecombustivel=="Gas") %>%
group_by(TipodeMarcha) %>%
select(HP) %>%
summarise(media=mean(HP),n=n())
## Adding missing grouping variables: `TipodeMarcha`
## # A tibble: 2 x 3
## TipodeMarcha media n
## * <chr> <dbl> <int>
## 1 Auto 194. 12
## 2 Manual 181. 6
Tabela_resumo
## # A tibble: 2 x 3
## TipodeMarcha media_preco media_kml
## * <chr> <dbl> <dbl>
## 1 Auto 290. 17.1
## 2 Manual 144. 24.4
Variações de boxplots
graf2<-boxplot(CARROS$Kmporlitro ~ CARROS$Tipodecombustivel,horizontal = T,
col=c("red","blue"),main="O boxplot 2",
xlab = "km/l do carro",
ylab = "Tipo de combustívrel")
graf3<-boxplot(CARROS$HP ~ CARROS$TipodeMarcha,horizontal = T,
col=c("green","yellow"),main="O boxplot 3",
xlab = "HP do carro",
ylab = "Tipo de marcha")
par(mfrow=c(2,1))
graf2
## $stats
## [,1] [,2]
## [1,] 17.8 10.40
## [2,] 21.4 14.70
## [3,] 22.8 15.65
## [4,] 30.4 19.20
## [5,] 33.9 21.00
##
## $n
## [1] 14 18
##
## $conf
## [,1] [,2]
## [1,] 18.99955 13.97416
## [2,] 26.60045 17.32584
##
## $out
## [1] 26
##
## $group
## [1] 2
##
## $names
## [1] "Alc" "Gas"
graf3
## $stats
## [,1] [,2]
## [1,] 62.0 52
## [2,] 116.5 66
## [3,] 175.0 109
## [4,] 192.5 113
## [5,] 245.0 175
##
## $n
## [1] 19 13
##
## $conf
## [,1] [,2]
## [1,] 147.4518 88.40398
## [2,] 202.5482 129.59602
##
## $out
## [1] 264 335
##
## $group
## [1] 2 2
##
## $names
## [1] "Auto" "Manual"
Gráficos de dispersão - Duas variáveis quantitativas
plot(CARROS$HP,CARROS$Preco)
abline(lsfit(CARROS$HP,CARROS$Preco),col="darkred")
cor(CARROS$HP,CARROS$Preco)
## [1] 0.7909486
plot(CARROS$HP,CARROS$Kmporlitro,pch=19,col="red",
xlab = "HP",
ylab = "Km/l",
main = "diagrama de dispersão")
abline(lsfit(CARROS$HP,CARROS$Kmporlitro),
col="blue")
cor(CARROS$Kmporlitro,CARROS$HP)
## [1] -0.7761684
plot(CARROS$Amperagem_circ_eletrico,CARROS$RPM,pch=19,col="red",
xlab = "Amperagem circ eletrico",
ylab = "RPM",
main = "diagrama de dispersão")
abline(lsfit(CARROS$Amperagem_circ_eletrico,CARROS$RPM),
col="blue")
cor(CARROS$Amperagem_circ_eletrico,CARROS$RPM)
## [1] 0.09120476
Matriz de correlação das variáveis quantitativas
names(CARROS)
## [1] "Kmporlitro" "Cilindros"
## [3] "Preco" "HP"
## [5] "Amperagem_circ_eletrico" "Peso"
## [7] "RPM" "Tipodecombustivel"
## [9] "TipodeMarcha" "NumdeMarchas"
## [11] "NumdeValvulas"
variaveis_quanti<-c("Kmporlitro","Preco","HP","Peso","RPM")
CARROS[,variaveis_quanti]
## Kmporlitro Preco HP Peso RPM
## Mazda RX4 21.0 160.0 110 2.620 16.46
## Mazda RX4 Wag 21.0 160.0 110 2.875 17.02
## Datsun 710 22.8 108.0 93 2.320 18.61
## Hornet 4 Drive 21.4 258.0 110 3.215 19.44
## Hornet Sportabout 18.7 360.0 175 3.440 17.02
## Valiant 18.1 225.0 105 3.460 20.22
## Duster 360 14.3 360.0 245 3.570 15.84
## Merc 240D 24.4 146.7 62 3.190 20.00
## Merc 230 22.8 140.8 95 3.150 22.90
## Merc 280 19.2 167.6 123 3.440 18.30
## Merc 280C 17.8 167.6 123 3.440 18.90
## Merc 450SE 16.4 275.8 180 4.070 17.40
## Merc 450SL 17.3 275.8 180 3.730 17.60
## Merc 450SLC 15.2 275.8 180 3.780 18.00
## Cadillac Fleetwood 10.4 472.0 205 5.250 17.98
## Lincoln Continental 10.4 460.0 215 5.424 17.82
## Chrysler Imperial 14.7 440.0 230 5.345 17.42
## Fiat 128 32.4 78.7 66 2.200 19.47
## Honda Civic 30.4 75.7 52 1.615 18.52
## Toyota Corolla 33.9 71.1 65 1.835 19.90
## Toyota Corona 21.5 120.1 97 2.465 20.01
## Dodge Challenger 15.5 318.0 150 3.520 16.87
## AMC Javelin 15.2 304.0 150 3.435 17.30
## Camaro Z28 13.3 350.0 245 3.840 15.41
## Pontiac Firebird 19.2 400.0 175 3.845 17.05
## Fiat X1-9 27.3 79.0 66 1.935 18.90
## Porsche 914-2 26.0 120.3 91 2.140 16.70
## Lotus Europa 30.4 95.1 113 1.513 16.90
## Ford Pantera L 15.8 351.0 264 3.170 14.50
## Ferrari Dino 19.7 145.0 175 2.770 15.50
## Maserati Bora 15.0 301.0 335 3.570 14.60
## Volvo 142E 21.4 121.0 109 2.780 18.60
cor(CARROS[,variaveis_quanti])
## Kmporlitro Preco HP Peso RPM
## Kmporlitro 1.0000000 -0.8475514 -0.7761684 -0.8676594 0.4186840
## Preco -0.8475514 1.0000000 0.7909486 0.8879799 -0.4336979
## HP -0.7761684 0.7909486 1.0000000 0.6587479 -0.7082234
## Peso -0.8676594 0.8879799 0.6587479 1.0000000 -0.1747159
## RPM 0.4186840 -0.4336979 -0.7082234 -0.1747159 1.0000000
library(corrplot)
## corrplot 0.84 loaded
correlacao_carros<-cor(CARROS[,variaveis_quanti])
correlacao_carros
## Kmporlitro Preco HP Peso RPM
## Kmporlitro 1.0000000 -0.8475514 -0.7761684 -0.8676594 0.4186840
## Preco -0.8475514 1.0000000 0.7909486 0.8879799 -0.4336979
## HP -0.7761684 0.7909486 1.0000000 0.6587479 -0.7082234
## Peso -0.8676594 0.8879799 0.6587479 1.0000000 -0.1747159
## RPM 0.4186840 -0.4336979 -0.7082234 -0.1747159 1.0000000
par(mfrow=c(1,1))
corrplot(correlacao_carros)
corrplot(correlacao_carros,method = "square")
corrplot(correlacao_carros,method = "pie")
corrplot.mixed(correlacao_carros)
colnames(CARROS)[5]<-"ACE"