#setting the working directory
getwd()
## [1] "/Users/agzl/Desktop/Project 1"
setwd("~/Desktop/Project 1")
car1<- read.csv2("Car_Survey_1.csv")
str(car1)
## 'data.frame': 1180 obs. of 23 variables:
## $ Resp : chr "Res1" "Res2" "Res3" "Res4" ...
## $ Att_1 : int 6 7 7 4 6 6 1 6 3 6 ...
## $ Att_2 : int 6 5 7 1 6 6 1 5 2 6 ...
## $ Enj_1 : int 6 5 7 1 6 6 1 5 3 4 ...
## $ Enj_2 : int 6 2 5 1 5 5 1 3 2 4 ...
## $ Perform_1 : int 5 2 5 1 5 5 2 5 2 4 ...
## $ Perform_2 : int 6 6 5 1 2 5 2 5 3 4 ...
## $ Perform_3 : int 3 7 3 1 1 7 2 2 1 1 ...
## $ WOM_1 : int 3 5 6 7 7 5 2 4 6 5 ...
## $ WOM_2 : int 3 5 6 7 7 5 3 6 6 6 ...
## $ Futu_Pur_1 : int 3 6 7 3 7 7 5 4 7 6 ...
## $ Futu_Pur_2 : int 3 6 7 3 6 7 2 4 7 6 ...
## $ Valu_Percp_1: int 5 6 5 6 6 7 2 4 6 6 ...
## $ Valu_Percp_2: int 2 7 7 5 5 7 2 4 6 6 ...
## $ Pur_Proces_1: int 6 7 7 5 6 7 2 4 6 6 ...
## $ Pur_Proces_2: int 4 6 7 4 7 7 6 4 6 6 ...
## $ Residence : int 2 2 1 2 1 2 2 1 2 1 ...
## $ Pay_Meth : int 2 2 2 2 2 2 2 2 2 2 ...
## $ Insur_Type : chr "Collision" "Collision" "Collision" "Collision" ...
## $ Gender : chr "Male" "Male" "Male" "Male" ...
## $ Age : int 18 18 19 19 19 19 19 21 21 21 ...
## $ Education : int 2 2 2 2 2 2 2 2 2 2 ...
## $ X : logi NA NA NA NA NA NA ...
head(car1, n=5)
## Resp Att_1 Att_2 Enj_1 Enj_2 Perform_1 Perform_2 Perform_3 WOM_1 WOM_2
## 1 Res1 6 6 6 6 5 6 3 3 3
## 2 Res2 7 5 5 2 2 6 7 5 5
## 3 Res3 7 7 7 5 5 5 3 6 6
## 4 Res4 4 1 1 1 1 1 1 7 7
## 5 Res5 6 6 6 5 5 2 1 7 7
## Futu_Pur_1 Futu_Pur_2 Valu_Percp_1 Valu_Percp_2 Pur_Proces_1 Pur_Proces_2
## 1 3 3 5 2 6 4
## 2 6 6 6 7 7 6
## 3 7 7 5 7 7 7
## 4 3 3 6 5 5 4
## 5 7 6 6 5 6 7
## Residence Pay_Meth Insur_Type Gender Age Education X
## 1 2 2 Collision Male 18 2 NA
## 2 2 2 Collision Male 18 2 NA
## 3 1 2 Collision Male 19 2 NA
## 4 2 2 Collision Male 19 2 NA
## 5 1 2 Collision Female 19 2 NA
car2<- read.csv("Car_Survey_2.csv")
str(car2)
## 'data.frame': 1049 obs. of 9 variables:
## $ Respondents: chr "Res1" "Res2" "Res3" "Res4" ...
## $ Region : chr "European" "European" "European" "European" ...
## $ Model : chr "Ford Expedition" "Ford Expedition" "Ford Expedition" "Ford Expedition" ...
## $ MPG : int 15 15 15 15 15 15 15 15 15 15 ...
## $ Cyl : int 8 8 8 8 8 8 8 8 8 8 ...
## $ acc1 : num 5.5 5.5 5.5 5.5 5.5 5.5 5.5 5.5 5.5 5.5 ...
## $ C_cost. : num 16 16 16 16 16 16 16 16 16 16 ...
## $ H_Cost : num 14 14 14 14 14 14 14 14 14 14 ...
## $ Post.Satis : int 4 3 5 5 5 3 3 6 3 5 ...
head(car2, n=5)
## Respondents Region Model MPG Cyl acc1 C_cost. H_Cost Post.Satis
## 1 Res1 European Ford Expedition 15 8 5.5 16 14 4
## 2 Res2 European Ford Expedition 15 8 5.5 16 14 3
## 3 Res3 European Ford Expedition 15 8 5.5 16 14 5
## 4 Res4 European Ford Expedition 15 8 5.5 16 14 5
## 5 Res5 European Ford Expedition 15 8 5.5 16 14 5
names(car2)[ 1 ]<-c("Resp")
head(car2,n=1)
## Resp Region Model MPG Cyl acc1 C_cost. H_Cost Post.Satis
## 1 Res1 European Ford Expedition 15 8 5.5 16 14 4
library(ggplot2)
## DATA MANIPULATION ##
#merging the two datasets
cartotal<-merge(car1,car2,by="Resp")
str(cartotal)
## 'data.frame': 1049 obs. of 31 variables:
## $ Resp : chr "Res1" "Res10" "Res100" "Res1000" ...
## $ Att_1 : int 6 6 6 6 6 3 2 7 2 6 ...
## $ Att_2 : int 6 6 7 6 6 1 2 7 1 6 ...
## $ Enj_1 : int 6 4 7 7 7 4 1 7 2 6 ...
## $ Enj_2 : int 6 4 3 6 6 3 2 6 1 5 ...
## $ Perform_1 : int 5 4 5 6 6 5 2 5 2 5 ...
## $ Perform_2 : int 6 4 6 6 6 6 2 6 2 5 ...
## $ Perform_3 : int 3 1 6 6 6 6 1 5 2 5 ...
## $ WOM_1 : int 3 5 3 6 4 2 6 6 7 3 ...
## $ WOM_2 : int 3 6 5 6 4 6 7 6 7 3 ...
## $ Futu_Pur_1 : int 3 6 6 6 4 6 6 6 7 6 ...
## $ Futu_Pur_2 : int 3 6 6 6 6 6 5 7 7 6 ...
## $ Valu_Percp_1: int 5 6 7 4 5 5 4 6 4 5 ...
## $ Valu_Percp_2: int 2 6 6 6 6 4 4 5 6 6 ...
## $ Pur_Proces_1: int 6 6 5 6 6 5 4 5 6 6 ...
## $ Pur_Proces_2: int 4 6 5 3 7 5 5 5 7 5 ...
## $ Residence : int 2 1 2 2 1 1 1 2 1 2 ...
## $ Pay_Meth : int 2 2 1 3 3 3 3 3 3 3 ...
## $ Insur_Type : chr "Collision" "Collision" "Collision" "Liability" ...
## $ Gender : chr "Male" "Male" "Female" "Female" ...
## $ Age : int 18 21 32 24 24 25 26 26 27 27 ...
## $ Education : int 2 2 1 2 2 2 2 2 2 2 ...
## $ X : logi NA NA NA NA NA NA ...
## $ Region : chr "European" "European" "American" "Asian" ...
## $ Model : chr "Ford Expedition" "Ford Expedition" "Toyota Rav4" "Toyota Corolla" ...
## $ MPG : int 15 15 24 26 26 26 26 26 26 26 ...
## $ Cyl : int 8 8 4 4 4 4 4 4 4 4 ...
## $ acc1 : num 5.5 5.5 8.2 8 8 8 8 8 8 8 ...
## $ C_cost. : num 16 16 10 7 7 7 7 7 7 7 ...
## $ H_Cost : num 14 14 8 6 6 6 6 6 6 6 ...
## $ Post.Satis : int 4 5 4 6 5 6 5 6 7 6 ...
write.csv(cartotal,'cartotal',row.names=FALSE)
#checking for NA values
summary(cartotal)
## Resp Att_1 Att_2 Enj_1
## Length:1049 Min. :1.000 Min. :1.000 Min. :1.000
## Class :character 1st Qu.:4.000 1st Qu.:4.000 1st Qu.:4.000
## Mode :character Median :6.000 Median :6.000 Median :6.000
## Mean :4.882 Mean :5.287 Mean :5.378
## 3rd Qu.:6.000 3rd Qu.:6.000 3rd Qu.:7.000
## Max. :7.000 Max. :7.000 Max. :7.000
## NA's :4 NA's :4
## Enj_2 Perform_1 Perform_2 Perform_3
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:3.000 1st Qu.:4.000 1st Qu.:4.000 1st Qu.:3.000
## Median :5.000 Median :5.000 Median :5.000 Median :5.000
## Mean :4.575 Mean :4.947 Mean :4.831 Mean :4.217
## 3rd Qu.:6.000 3rd Qu.:6.000 3rd Qu.:6.000 3rd Qu.:6.000
## Max. :7.000 Max. :7.000 Max. :7.000 Max. :7.000
## NA's :4 NA's :2 NA's :4 NA's :1
## WOM_1 WOM_2 Futu_Pur_1 Futu_Pur_2 Valu_Percp_1
## Min. :1.000 Min. :1.00 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:4.000 1st Qu.:4.00 1st Qu.:4.000 1st Qu.:5.000 1st Qu.:5.000
## Median :6.000 Median :6.00 Median :6.000 Median :6.000 Median :6.000
## Mean :5.286 Mean :5.35 Mean :5.321 Mean :5.371 Mean :5.411
## 3rd Qu.:7.000 3rd Qu.:6.00 3rd Qu.:6.000 3rd Qu.:6.000 3rd Qu.:6.000
## Max. :7.000 Max. :7.00 Max. :9.000 Max. :7.000 Max. :7.000
## NA's :1 NA's :3 NA's :5 NA's :2 NA's :4
## Valu_Percp_2 Pur_Proces_1 Pur_Proces_2 Residence
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:4.000 1st Qu.:5.000 1st Qu.:4.000 1st Qu.:1.000
## Median :5.000 Median :6.000 Median :5.000 Median :1.000
## Mean :5.114 Mean :5.256 Mean :4.923 Mean :1.474
## 3rd Qu.:6.000 3rd Qu.:6.000 3rd Qu.:6.000 3rd Qu.:2.000
## Max. :7.000 Max. :7.000 Max. :7.000 Max. :5.000
## NA's :1 NA's :3 NA's :4 NA's :5
## Pay_Meth Insur_Type Gender Age
## Min. :1.000 Length:1049 Length:1049 Min. :18.00
## 1st Qu.:1.000 Class :character Class :character 1st Qu.:23.00
## Median :2.000 Mode :character Mode :character Median :34.00
## Mean :2.153 Mean :35.22
## 3rd Qu.:3.000 3rd Qu.:48.00
## Max. :3.000 Max. :60.00
##
## Education X Region Model
## Min. :1.000 Mode:logical Length:1049 Length:1049
## 1st Qu.:2.000 NA's:1049 Class :character Class :character
## Median :2.000 Mode :character Mode :character
## Mean :1.989
## 3rd Qu.:2.000
## Max. :3.000
##
## MPG Cyl acc1 C_cost. H_Cost
## Min. :14.00 Min. :4.0 Min. :3.600 Min. : 7.00 Min. : 6.000
## 1st Qu.:17.00 1st Qu.:4.0 1st Qu.:5.100 1st Qu.:10.00 1st Qu.: 8.000
## Median :19.00 Median :6.0 Median :6.500 Median :12.00 Median :10.000
## Mean :19.58 Mean :5.8 Mean :6.202 Mean :11.35 Mean : 9.634
## 3rd Qu.:22.00 3rd Qu.:6.0 3rd Qu.:7.500 3rd Qu.:13.00 3rd Qu.:11.000
## Max. :26.00 Max. :8.0 Max. :8.500 Max. :16.00 Max. :14.000
##
## Post.Satis
## Min. :2.00
## 1st Qu.:5.00
## Median :6.00
## Mean :5.28
## 3rd Qu.:6.00
## Max. :7.00
##
#replacing the NA values with the mean value of the column
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
cartotal<-cartotal %>%
mutate(across(everything(),~ifelse(is.na(.),mean(.,na.rm=TRUE), . )))
summary(cartotal)
## Resp Att_1 Att_2 Enj_1
## Length:1049 Min. :1.000 Min. :1.000 Min. :1.000
## Class :character 1st Qu.:4.000 1st Qu.:4.000 1st Qu.:5.000
## Mode :character Median :5.000 Median :6.000 Median :6.000
## Mean :4.882 Mean :5.287 Mean :5.378
## 3rd Qu.:6.000 3rd Qu.:6.000 3rd Qu.:7.000
## Max. :7.000 Max. :7.000 Max. :7.000
##
## Enj_2 Perform_1 Perform_2 Perform_3
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:3.000 1st Qu.:4.000 1st Qu.:4.000 1st Qu.:3.000
## Median :5.000 Median :5.000 Median :5.000 Median :5.000
## Mean :4.575 Mean :4.947 Mean :4.831 Mean :4.217
## 3rd Qu.:6.000 3rd Qu.:6.000 3rd Qu.:6.000 3rd Qu.:6.000
## Max. :7.000 Max. :7.000 Max. :7.000 Max. :7.000
##
## WOM_1 WOM_2 Futu_Pur_1 Futu_Pur_2 Valu_Percp_1
## Min. :1.000 Min. :1.00 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:4.000 1st Qu.:4.00 1st Qu.:5.000 1st Qu.:5.000 1st Qu.:5.000
## Median :6.000 Median :6.00 Median :6.000 Median :6.000 Median :6.000
## Mean :5.286 Mean :5.35 Mean :5.321 Mean :5.371 Mean :5.411
## 3rd Qu.:7.000 3rd Qu.:6.00 3rd Qu.:6.000 3rd Qu.:6.000 3rd Qu.:6.000
## Max. :7.000 Max. :7.00 Max. :9.000 Max. :7.000 Max. :7.000
##
## Valu_Percp_2 Pur_Proces_1 Pur_Proces_2 Residence
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:4.000 1st Qu.:5.000 1st Qu.:4.000 1st Qu.:1.000
## Median :5.000 Median :6.000 Median :5.000 Median :1.000
## Mean :5.114 Mean :5.256 Mean :4.923 Mean :1.474
## 3rd Qu.:6.000 3rd Qu.:6.000 3rd Qu.:6.000 3rd Qu.:2.000
## Max. :7.000 Max. :7.000 Max. :7.000 Max. :5.000
##
## Pay_Meth Insur_Type Gender Age
## Min. :1.000 Length:1049 Length:1049 Min. :18.00
## 1st Qu.:1.000 Class :character Class :character 1st Qu.:23.00
## Median :2.000 Mode :character Mode :character Median :34.00
## Mean :2.153 Mean :35.22
## 3rd Qu.:3.000 3rd Qu.:48.00
## Max. :3.000 Max. :60.00
##
## Education X Region Model
## Min. :1.000 Min. : NA Length:1049 Length:1049
## 1st Qu.:2.000 1st Qu.: NA Class :character Class :character
## Median :2.000 Median : NA Mode :character Mode :character
## Mean :1.989 Mean :NaN
## 3rd Qu.:2.000 3rd Qu.: NA
## Max. :3.000 Max. : NA
## NA's :1049
## MPG Cyl acc1 C_cost. H_Cost
## Min. :14.00 Min. :4.0 Min. :3.600 Min. : 7.00 Min. : 6.000
## 1st Qu.:17.00 1st Qu.:4.0 1st Qu.:5.100 1st Qu.:10.00 1st Qu.: 8.000
## Median :19.00 Median :6.0 Median :6.500 Median :12.00 Median :10.000
## Mean :19.58 Mean :5.8 Mean :6.202 Mean :11.35 Mean : 9.634
## 3rd Qu.:22.00 3rd Qu.:6.0 3rd Qu.:7.500 3rd Qu.:13.00 3rd Qu.:11.000
## Max. :26.00 Max. :8.0 Max. :8.500 Max. :16.00 Max. :14.000
##
## Post.Satis
## Min. :2.00
## 1st Qu.:5.00
## Median :6.00
## Mean :5.28
## 3rd Qu.:6.00
## Max. :7.00
##
#Define model and region as categorical variables
cartotal$Model<-as.factor(cartotal$Model)
cartotal$Region<-as.factor(cartotal$Region)
#split the model column into brand and models
library(tidyr)
cars_separated<-cartotal %>% separate(Model, into = c("Brand","Model"),
sep=" ", extra="merge")
#Add the split columns to your dataset cartotal
cartotal<-cars_separated
View(cartotal)
#Demographic groups by age variable (convert age into 3 groups)
cartotal$Agegrp<-cut(cartotal$Age, breaks=c(0,30,50,Inf),
labels = c("Young adults","Adults","Mature Adults"),
right=FALSE)
names(cartotal)
## [1] "Resp" "Att_1" "Att_2" "Enj_1" "Enj_2"
## [6] "Perform_1" "Perform_2" "Perform_3" "WOM_1" "WOM_2"
## [11] "Futu_Pur_1" "Futu_Pur_2" "Valu_Percp_1" "Valu_Percp_2" "Pur_Proces_1"
## [16] "Pur_Proces_2" "Residence" "Pay_Meth" "Insur_Type" "Gender"
## [21] "Age" "Education" "X" "Region" "Brand"
## [26] "Model" "MPG" "Cyl" "acc1" "C_cost."
## [31] "H_Cost" "Post.Satis" "Agegrp"
head(cartotal,n=5)
## Resp Att_1 Att_2 Enj_1 Enj_2 Perform_1 Perform_2 Perform_3 WOM_1 WOM_2
## 1 Res1 6 6 6 6 5 6 3 3 3
## 2 Res10 6 6 4 4 4 4 1 5 6
## 3 Res100 6 7 7 3 5 6 6 3 5
## 4 Res1000 6 6 7 6 6 6 6 6 6
## 5 Res1001 6 6 7 6 6 6 6 4 4
## Futu_Pur_1 Futu_Pur_2 Valu_Percp_1 Valu_Percp_2 Pur_Proces_1 Pur_Proces_2
## 1 3 3 5 2 6 4
## 2 6 6 6 6 6 6
## 3 6 6 7 6 5 5
## 4 6 6 4 6 6 3
## 5 4 6 5 6 6 7
## Residence Pay_Meth Insur_Type Gender Age Education X Region Brand
## 1 2 2 Collision Male 18 2 NaN European Ford
## 2 1 2 Collision Male 21 2 NaN European Ford
## 3 2 1 Collision Female 32 1 NaN American Toyota
## 4 2 3 Liability Female 24 2 NaN Asian Toyota
## 5 1 3 Liability Female 24 2 NaN Asian Toyota
## Model MPG Cyl acc1 C_cost. H_Cost Post.Satis Agegrp
## 1 Expedition 15 8 5.5 16 14 4 Young adults
## 2 Expedition 15 8 5.5 16 14 5 Young adults
## 3 Rav4 24 4 8.2 10 8 4 Adults
## 4 Corolla 26 4 8.0 7 6 6 Young adults
## 5 Corolla 26 4 8.0 7 6 5 Young adults
# Creating mean values for variables
# For future purchase intention
cartotal$Futu_Pur_Mean=(cartotal$Futu_Pur_1+
cartotal$Futu_Pur_2)/2
# For purchase process
cartotal$Pur_Proces_Mean=(cartotal$Pur_Proces_1+
cartotal$Pur_Proces_2)/2
View(cartotal)
## CREATING NEW VARIABLES ##
#Creating a loyalty score (car purchase process & future purchase intentions)
cartotal$Loyalty=(cartotal$Futu_Pur_Mean+
cartotal$Pur_Proces_Mean)/2
## DATA VISUALIZATION ##
# MARKET SHARE
#Create a graph of cars by brands across region, compared to main competitors (data visualization)
# Filter the dataset to include only the main competitors
cartotal_competitors <- cartotal%>%
filter(Brand=="Toyota" |Brand=="Kia"|Brand=="Honda"|Brand=="Ford")
# Create the graph
ggplot(cartotal_competitors, aes(x = Region, fill = Brand)) +
theme_bw() +
geom_bar() +
labs(y = "Number of cars",
title = "Market share of Toyota and its main concurrents")
# POPULARITY OF MODELS ACCORDING TO AGE GROUPS
toyota_sales <- cartotal %>%
filter(Brand == "Toyota") %>%
group_by(Agegrp, Model) %>%
summarise(count = n(), .groups = "drop")
ggplot(toyota_sales, aes(x = Agegrp, y = Model, size = count, color = count)) +
geom_point() +
scale_size(range = c(3,10)) +
theme_bw() +
labs(title = "Most Sold Toyota Models by Age Group",
x = "Age Group",
y = "Toyota Model",
size = "Number of Sales",
color = "Number of Sales")
#create a grpah (data visualization - future purchase intentions across regions)
Futu_Pur_Table<-aggregate(Futu_Pur_Mean~Brand+Region, cartotal_competitors, mean)
ggplot(Futu_Pur_Table, aes(x=Region, y=Futu_Pur_Mean, group=Brand))+
geom_line(aes(color=Brand))+
geom_point(aes(color=Brand))+
labs(y="Likeliness of a future purchase",
title="Future purchase intentions by Brand and Region")
#create a grpah (data visualization - future purchase intentions across regions)
Futu_Pur_Table<-aggregate(Futu_Pur_Mean~Brand+Region, cartotal_competitors, mean)
ggplot(Futu_Pur_Table, aes(x=Region, y=Futu_Pur_Mean, group=Brand))+
geom_line(aes(color=Brand))+
geom_point(aes(color=Brand))+
labs(y="Likeliness of a future purchase",
title="Future purchase intentions by Brand and Region")
#create a grpah (data visualization - future purchase intentions across regions)
Pur_Proces_Table<-aggregate(Pur_Proces_Mean~Brand+Region, cartotal_competitors, mean)
ggplot(Pur_Proces_Table, aes(x=Region, y=Pur_Proces_Mean, group=Brand))+
geom_line(aes(color=Brand))+
geom_point(aes(color=Brand))+
labs(y="Puchase process",
title="Purchase process perception by Brand and Region")
#LOYALTY ACCORDING TO BRANDS/REGIONS
loyalty_table<-aggregate(Loyalty~Brand+Region, cartotal_competitors, mean)
print(loyalty_table)
## Brand Region Loyalty
## 1 Ford American 5.164488
## 2 Honda American 5.063433
## 3 Kia American 5.700000
## 4 Toyota American 5.042137
## 5 Ford Asian 5.125000
## 6 Honda Asian 5.203691
## 7 Toyota Asian 5.230832
## 8 Ford European 5.629310
## 9 Honda European 5.301724
## 10 Kia European 4.763158
## 11 Toyota European 4.950000
## 12 Ford Middle Eastern 5.647059
## 13 Honda Middle Eastern 5.529412
## 14 Toyota Middle Eastern 5.375000
ggplot(loyalty_table, aes(x=Region, y=Loyalty, group=Brand))+
geom_line(aes(color=Brand))+
geom_point(aes(color=Brand))+
labs(y="Loyalty score",
title="Loyalty score by brands and regions")
