Aula 05 - Dois tipos de Análise
Nathalia Colares
08/02/2021
PASSO 1 - cARREGAR BANCO DE DADOS
load("C:/Users/victo/Desktop/Base_de_dados-master/CARROS.RData")PASSO 2 - TRANSFORMAR VARIÁVEIS
CARROS$Tipodecombustivel<-ifelse(CARROS$Tipodecombustivel==0, "Gas", "Alc")
CARROS$TipodeMarcha<-ifelse(CARROS$TipodeMarcha==0, "Auto", "Manual")
summary(CARROS)## Kmporlitro Cilindros Preco HP
## Min. :10.40 Min. :4.000 Min. : 71.1 Min. : 52.0
## 1st Qu.:15.43 1st Qu.:4.000 1st Qu.:120.8 1st Qu.: 96.5
## Median :19.20 Median :6.000 Median :196.3 Median :123.0
## Mean :20.09 Mean :6.188 Mean :230.7 Mean :146.7
## 3rd Qu.:22.80 3rd Qu.:8.000 3rd Qu.:326.0 3rd Qu.:180.0
## Max. :33.90 Max. :8.000 Max. :472.0 Max. :335.0
## Amperagem_circ_eletrico Peso RPM Tipodecombustivel
## Min. :2.760 Min. :1.513 Min. :14.50 Length:32
## 1st Qu.:3.080 1st Qu.:2.581 1st Qu.:16.89 Class :character
## Median :3.695 Median :3.325 Median :17.71 Mode :character
## Mean :3.597 Mean :3.217 Mean :17.85
## 3rd Qu.:3.920 3rd Qu.:3.610 3rd Qu.:18.90
## Max. :4.930 Max. :5.424 Max. :22.90
## TipodeMarcha NumdeMarchas NumdeValvulas
## Length:32 Min. :3.000 Min. :1.000
## Class :character 1st Qu.:3.000 1st Qu.:2.000
## Mode :character Median :4.000 Median :2.000
## Mean :3.688 Mean :2.812
## 3rd Qu.:4.000 3rd Qu.:4.000
## Max. :5.000 Max. :8.000#PASSO 3 - ANÁLISE EXPLORATÓRIA DE DADOS -AED #KM/L, HP, PREÇO DO CARRO - QUANTITATIVAS
boxplot(CARROS$Preco ~ CARROS$Tipodecombustivel,
horizontal = T,
col=c("red","blue"),
main="O boxplot",
xlab = "Preço do Carro",
ylab = "Tipo de combustível")
graf2<-boxplot(CARROS$Kmporlitro ~ CARROS$Tipodecombustivel,
horizontal = T,
col=c("red","blue"),
main="O boxplot 2",
xlab = "Km/l do carro",
ylab = "Tipo de combustível")
graf3<-boxplot(CARROS$HP ~ CARROS$TipodeMarcha,
horizontal = T,
col=c("green","yellow"),
main="O boxplot 3",
xlab = "HP",
ylab = "Tipo de marcha")
par(mfrow=c(1,2))
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
##
## $names
## [1] "Auto" "Manual"#PASSO 4 - INSTALAR PACOTE PSYCH #PARA RESUMO DE DADOS
library(psych)
describeBy(Preco ~ Tipodecombustivel, data=CARROS)##
## Descriptive statistics by group
## Tipodecombustivel: Alc
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 14 132.46 56.89 120.55 127.11 61.82 71.1 258 186.9 0.8 -0.49 15.21
## ------------------------------------------------------------
## Tipodecombustivel: Gas
## vars n mean sd median trimmed mad min max range skew kurtosis
## X1 1 18 307.15 106.77 311 308.52 72.65 120.3 472 351.7 -0.26 -1.06
## se
## X1 25.16describeBy(HP ~ TipodeMarcha, data=CARROS)##
## Descriptive statistics by group
## TipodeMarcha: Auto
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 19 160.26 53.91 175 161.06 77.1 62 245 183 -0.01 -1.21 12.37
## ------------------------------------------------------------
## TipodeMarcha: Manual
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 13 126.85 84.06 109 114.73 63.75 52 335 283 1.36 0.56 23.31library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionCARROS %>%
group_by(TipodeMarcha) %>%
select(Tipodecombustivel) %>%
table()## Adding missing grouping variables: `TipodeMarcha`## Tipodecombustivel
## TipodeMarcha Alc Gas
## Auto 7 12
## Manual 7 6CARROS %>%
filter(Tipodecombustivel=="Gas") %>%
group_by(TipodeMarcha) %>%
select(HP) %>%
summarise(media=mean(HP),n=n())## Adding missing grouping variables: `TipodeMarcha`## # A tibble: 2 x 3
## TipodeMarcha media n
## * <chr> <dbl> <int>
## 1 Auto 194. 12
## 2 Manual 181. 6#associacao linear relacao posistiva
plot(CARROS$HP,CARROS$Preco,pch=19)
abline(lsfit(CARROS$HP,CARROS$Preco),col="darkred")
cor(CARROS$HP,CARROS$Preco) #positiva forte, prox de 1## [1] 0.7909486#associacao linear relacao negativa
plot(CARROS$HP,CARROS$Kmporlitrom, pch=19)
abline(lsfit(CARROS$HP,CARROS$Kmporlitro),col="blue")
cor(CARROS$HP,CARROS$Kmporlitro) #negativa forte, prox de 1## [1] -0.7761684somente 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", "Amperagem_circ_eletrico", "Peso", "RPM")
CARROS[,variaveis_quanti]## Kmporlitro Preco HP Amperagem_circ_eletrico Peso RPM
## Mazda RX4 21.0 160.0 110 3.90 2.620 16.46
## Mazda RX4 Wag 21.0 160.0 110 3.90 2.875 17.02
## Datsun 710 22.8 108.0 93 3.85 2.320 18.61
## Hornet 4 Drive 21.4 258.0 110 3.08 3.215 19.44
## Hornet Sportabout 18.7 360.0 175 3.15 3.440 17.02
## Valiant 18.1 225.0 105 2.76 3.460 20.22
## Duster 360 14.3 360.0 245 3.21 3.570 15.84
## Merc 240D 24.4 146.7 62 3.69 3.190 20.00
## Merc 230 22.8 140.8 95 3.92 3.150 22.90
## Merc 280 19.2 167.6 123 3.92 3.440 18.30
## Merc 280C 17.8 167.6 123 3.92 3.440 18.90
## Merc 450SE 16.4 275.8 180 3.07 4.070 17.40
## Merc 450SL 17.3 275.8 180 3.07 3.730 17.60
## Merc 450SLC 15.2 275.8 180 3.07 3.780 18.00
## Cadillac Fleetwood 10.4 472.0 205 2.93 5.250 17.98
## Lincoln Continental 10.4 460.0 215 3.00 5.424 17.82
## Chrysler Imperial 14.7 440.0 230 3.23 5.345 17.42
## Fiat 128 32.4 78.7 66 4.08 2.200 19.47
## Honda Civic 30.4 75.7 52 4.93 1.615 18.52
## Toyota Corolla 33.9 71.1 65 4.22 1.835 19.90
## Toyota Corona 21.5 120.1 97 3.70 2.465 20.01
## Dodge Challenger 15.5 318.0 150 2.76 3.520 16.87
## AMC Javelin 15.2 304.0 150 3.15 3.435 17.30
## Camaro Z28 13.3 350.0 245 3.73 3.840 15.41
## Pontiac Firebird 19.2 400.0 175 3.08 3.845 17.05
## Fiat X1-9 27.3 79.0 66 4.08 1.935 18.90
## Porsche 914-2 26.0 120.3 91 4.43 2.140 16.70
## Lotus Europa 30.4 95.1 113 3.77 1.513 16.90
## Ford Pantera L 15.8 351.0 264 4.22 3.170 14.50
## Ferrari Dino 19.7 145.0 175 3.62 2.770 15.50
## Maserati Bora 15.0 301.0 335 3.54 3.570 14.60
## Volvo 142E 21.4 121.0 109 4.11 2.780 18.60cor(CARROS[,variaveis_quanti])## Kmporlitro Preco HP
## Kmporlitro 1.0000000 -0.8475514 -0.7761684
## Preco -0.8475514 1.0000000 0.7909486
## HP -0.7761684 0.7909486 1.0000000
## Amperagem_circ_eletrico 0.6811719 -0.7102139 -0.4487591
## Peso -0.8676594 0.8879799 0.6587479
## RPM 0.4186840 -0.4336979 -0.7082234
## Amperagem_circ_eletrico Peso RPM
## Kmporlitro 0.68117191 -0.8676594 0.41868403
## Preco -0.71021393 0.8879799 -0.43369788
## HP -0.44875912 0.6587479 -0.70822339
## Amperagem_circ_eletrico 1.00000000 -0.7124406 0.09120476
## Peso -0.71244065 1.0000000 -0.17471588
## RPM 0.09120476 -0.1747159 1.00000000plot(CARROS$Amperagem_circ_eletrico, CARROS$RPM)
abline(lsfit(CARROS$Amperagem_circ_eletrico,CARROS$RPM),col="blue")
cor(CARROS$Amperagem_circ_eletrico,CARROS$RPM)## [1] 0.09120476#muito próxima de zero.#visualizar matriz
library(corrplot)## corrplot 0.84 loadedcorrelacao_carros<-cor(CARROS[,variaveis_quanti])
correlacao_carros## Kmporlitro Preco HP
## Kmporlitro 1.0000000 -0.8475514 -0.7761684
## Preco -0.8475514 1.0000000 0.7909486
## HP -0.7761684 0.7909486 1.0000000
## Amperagem_circ_eletrico 0.6811719 -0.7102139 -0.4487591
## Peso -0.8676594 0.8879799 0.6587479
## RPM 0.4186840 -0.4336979 -0.7082234
## Amperagem_circ_eletrico Peso RPM
## Kmporlitro 0.68117191 -0.8676594 0.41868403
## Preco -0.71021393 0.8879799 -0.43369788
## HP -0.44875912 0.6587479 -0.70822339
## Amperagem_circ_eletrico 1.00000000 -0.7124406 0.09120476
## Peso -0.71244065 1.0000000 -0.17471588
## RPM 0.09120476 -0.1747159 1.00000000corrplot(correlacao_carros)
corrplot.mixed(correlacao_carros)
Conclusão
Dois tipos de análise:
- Quali vs Quanti
- Quanti vs Quanti