INTRODUCTION

This report is Project 2 for MKTG3P98

DATA SUMMARY

Set up working directory.

getwd()

## [1] "/Users/charlesmba/Desktop"

setwd("/Users/charlesmba")

Install Packages.

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(ggplot2)

Read the CSV files.

New_Car_Total <- read.csv("/Users/charlesmba/Desktop/New_Car_Total.csv")

Defining a vector of Chrysler models

Chrysler_models <- c( "Chrysler Jeep")

Defining a vector of Ford models

Ford_models <- c( "Ford Expedition", "Ford Explorer")

Defining a vector of Toyota models

toyota_models <- c( "Toyota Corolla", "Toyota Rav4", "Toyota Highlander")

Filtering the dataset for the specified models

selected_models <- c(Ford_models, toyota_models, Chrysler_models)
filtered_data <- New_Car_Total %>%
  filter(Model %in% selected_models)

Separating the data into different regions

regions <- c("European", "Asian", "American", "Middle eastern")
region_data <- lapply(regions, function(region) {
  filtered_data %>% filter(Region == region)
})
names(region_data) <- regions

Extracting MPG data for region and model variables

mpg_data <- lapply(region_data, function(data) {
  data %>%
    select(Region, Model, MPG) %>%
    filter(!is.na(MPG))
})

changing into a dataframe for plotting

mpg_df <- do.call(rbind, mpg_data)

Plotting the data, jitter to prevent overlapping

ggplot(mpg_df, aes(x = Region, y = MPG, color = Model)) +
  geom_point(position = position_jitter(width = 0.2, height = 0), size = 3, alpha = 0.7) +
  labs(title = "MPG Distribution by Region",
       x = "Region",
       y = "MPG") +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

Extracting mean Value Perception data for each region and model.

mean_valu_percp <- lapply(region_data, function(data) {
  if(nrow(data) > 0) {
    data %>%
      group_by(Model) %>%
      summarise(Mean_Valu_Percp_1 = mean(Valu_Percp_1, na.rm = TRUE))
  } else {
    data.frame(Model = character(), Mean_Valu_Percp_1 = numeric())
  }
})

Converting to data frame for plotting

mean_valu_percp_df <- do.call(rbind, lapply(names(mean_valu_percp), function(region) {
  data <- mean_valu_percp[[region]]
  if(nrow(data) > 0) {
    data.frame(Region = region, data)
  } else {
    data.frame(Region = character(), Model = character(), Mean_Valu_Percp_1 = numeric())
  }
}))

Plotting the data

ggplot(mean_valu_percp_df, aes(x = Region, y = Mean_Valu_Percp_1, fill = Model)) +
  geom_bar(stat = "identity", position = position_dodge()) +
  labs(title = "Mean Value Perception by Region and Car Model",
       x = "Region",
       y = "Mean Value Perception (1 to 10)") +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

Filtering the dataset for Chrysler cars only

chrysler_data <- New_Car_Total %>%
  filter(grepl("Chrysler", Model))

Separating data into different regions

regions2 <- c("European", "Asian", "American", "Middle eastern")
region_data2 <- lapply(regions, function(region) {
  chrysler_data %>% filter(Region == region)
})

showing values (check)

names(region_data) <- regions

Extracting payment method column for each region and counting values

pay_meth_counts <- lapply(region_data, function(data) {
  table(factor(data$Pay_Meth, levels = 1:3), useNA = "ifany")
})

Converting count into a data frame for plotting

pay_meth_df <- do.call(rbind, lapply(names(pay_meth_counts), function(region) {
  counts <- pay_meth_counts[[region]]
  data.frame(Region = region, Pay_Meth = as.numeric(names(counts)), Count = as.vector(counts))
}))

Plotting data

ggplot(pay_meth_df, aes(x = Pay_Meth, y = Count, fill = Region)) +
  geom_bar(stat = "identity", position = "dodge") +
  labs(title = "Regional Payment Method Distribution (Chryslers)", 
       x = "Payment Method", 
       y = "Count") +
  theme_minimal()

Extracting Age column for each region and counting values

Age_counts <- lapply(region_data, function(data) {
  table(factor(data$Age, levels = 18:60), useNA = "ifany")
})

Converting count into a data frame for plotting

Age_df <- do.call(rbind, lapply(names(Age_counts), function(region) {
  counts <- Age_counts[[region]]
  data.frame(Region = region, Pay_Meth = as.numeric(names(counts)), Count = as.vector(counts))
}))

Plotting data

ggplot(Age_df, aes(x = Pay_Meth, y = Count, fill = Region)) +
  geom_bar(stat = "identity", position = "dodge") +
  labs(title = "Regional Age Distribution for Chrysler Cars", 
       x = "Age", 
       y = "Count") +
  theme_minimal()

Creating new mean column for Enjoyment

chrysler_data$Enj_mean <- (chrysler_data$Enj_1 + chrysler_data$Enj_2) / 2

Creating new mean column for Future Purchase

chrysler_data$Futu_Pur_mean <- (chrysler_data$Futu_Pur_1 + chrysler_data$Futu_Pur_2) / 2

Creating new mean column for Word of Mouth

chrysler_data$WOM_mean <- (chrysler_data$WOM_1 + chrysler_data$WOM_2) / 2

Creating new mean column for Value Perception

chrysler_data$Valu_Percp_mean <- (chrysler_data$Valu_Percp_1 + chrysler_data$Valu_Percp_2) / 2

Plotting the correlation between Enjoyment and Future Purchase

ggplot(chrysler_data, aes(x = Enj_mean, y = Futu_Pur_mean)) +
  geom_point() +
  geom_smooth(method = "lm", col = "blue") +
  labs(title = "Correlation between Enjoyment and Future Purchase",
       x = "Mean Enjoyment",
       y = "Mean Future Purchase") +
  theme_minimal()

## `geom_smooth()` using formula = 'y ~ x'

Plotting the correlation between Enjoyment and Word of Mouth

ggplot(chrysler_data, aes(x = Enj_mean, y = WOM_mean)) +
  geom_point() +
  geom_smooth(method = "lm", col = "blue") +
  labs(title = "Correlation between Enjoyment and Word of Mouth",
       x = "Mean Enjoyment",
       y = "Mean Word of Mouth") +
  theme_minimal()

## `geom_smooth()` using formula = 'y ~ x'

Plotting the correlation between Future Purchase and Value Perception

ggplot(chrysler_data, aes(x = Futu_Pur_mean, y = Valu_Percp_mean)) +
  geom_point() +
  geom_smooth(method = "lm", col = "blue") +
  labs(title = "Correlation between Future Purchase and Value Perception",
       x = "Mean Future Purchase",
       y = "Mean Value Perception") +
  theme_minimal()

## `geom_smooth()` using formula = 'y ~ x'

Plotting the correlation between Enjoyment and Future Purchase by Region

ggplot(chrysler_data, aes(x = Enj_mean, y = Futu_Pur_mean)) +
  geom_point() +
  geom_smooth(method = "lm", se = FALSE, color = "blue") +
  facet_wrap(~ Region) +
  labs(title = "Correlation between Enjoyment and Future Purchase by Region",
       x = "Mean Enjoyment",
       y = "Mean Future Purchase") +
  theme_minimal()

## `geom_smooth()` using formula = 'y ~ x'

Plotting the correlation between Enjoyment and Word of Mouth by Region

ggplot(chrysler_data, aes(x = Enj_mean, y = WOM_mean)) +
  geom_point() +
  geom_smooth(method = "lm", se = FALSE, color = "blue") +
  facet_wrap(~ Region) +
  labs(title = "Correlation between Enjoyment and Word of Mouth by Region",
       x = "Mean Enjoyment",
       y = "Mean Word of Mouth") +
  theme_minimal()

## `geom_smooth()` using formula = 'y ~ x'

Plotting the correlation between Future Purchase and Value Perception by Region

ggplot(chrysler_data, aes(x = Futu_Pur_mean, y = Valu_Percp_mean)) +
  geom_point() +
  geom_smooth(method = "lm", se = FALSE, color = "blue") +
  facet_wrap(~ Region) +
  labs(title = "Correlation between Future Purchase and Value Perception by Region",
       x = "Mean Future Purchase",
       y = "Mean Value Perception") +
  theme_minimal()

## `geom_smooth()` using formula = 'y ~ x'

Plotting the correlation between Enjoyment and Future Purchase by Insurance Type

ggplot(chrysler_data, aes(x = Enj_mean, y = Futu_Pur_mean, color = Insur_Type)) +
  geom_point() +
  geom_smooth(method = "lm", se = FALSE) +
  labs(title = "Correlation between Enjoyment and Future Purchase by Insurance Type",
       x = "Mean Enjoyment",
       y = "Mean Future Purchase") +
  theme_minimal()

## `geom_smooth()` using formula = 'y ~ x'

Plotting the correlation between Enjoyment and Word of Mouth by Insurance Type

ggplot(chrysler_data, aes(x = Enj_mean, y = WOM_mean, color = Insur_Type)) +
  geom_point() +
  geom_smooth(method = "lm", se = FALSE) +
  labs(title = "Correlation between Enjoyment and Word of Mouth by Insurance Type",
       x = "Mean Enjoyment",
       y = "Mean Word of Mouth") +
  theme_minimal()

## `geom_smooth()` using formula = 'y ~ x'

Plotting the correlation between Future Purchase and Value Perception by Insurance Type

ggplot(chrysler_data, aes(x = Futu_Pur_mean, y = Valu_Percp_mean, color = Insur_Type)) +
  geom_point() +
  geom_smooth(method = "lm", se = FALSE) +
  labs(title = "Correlation between Future Purchase and Value Perception by Insurance Type",
       x = "Mean Future Purchase",
       y = "Mean Value Perception") +
  theme_minimal()

## `geom_smooth()` using formula = 'y ~ x'

Assignment 2

Charles Mba, Arsh Deep Bhamral, Christian Truran,Kiran Dewan

2024-06-18

INTRODUCTION

DATA SUMMARY

Set up working directory.

Install Packages.

Read the CSV files.

Defining a vector of Chrysler models

Defining a vector of Ford models

Defining a vector of Toyota models

Filtering the dataset for the specified models

Separating the data into different regions

Extracting MPG data for region and model variables

changing into a dataframe for plotting

Plotting the data, jitter to prevent overlapping

Extracting mean Value Perception data for each region and model.

Converting to data frame for plotting

Plotting the data

Filtering the dataset for Chrysler cars only

Separating data into different regions

showing values (check)

Extracting payment method column for each region and counting values

Converting count into a data frame for plotting

Plotting data

Extracting Age column for each region and counting values

Converting count into a data frame for plotting

Plotting data

Creating new mean column for Enjoyment

Creating new mean column for Future Purchase

Creating new mean column for Word of Mouth

Creating new mean column for Value Perception

Plotting the correlation between Enjoyment and Future Purchase

Plotting the correlation between Enjoyment and Word of Mouth

Plotting the correlation between Future Purchase and Value Perception

Plotting the correlation between Enjoyment and Future Purchase by Region

Plotting the correlation between Enjoyment and Word of Mouth by Region

Plotting the correlation between Future Purchase and Value Perception by Region

Plotting the correlation between Enjoyment and Future Purchase by Insurance Type

Plotting the correlation between Enjoyment and Word of Mouth by Insurance Type

Plotting the correlation between Future Purchase and Value Perception by Insurance Type